From 4ec9a87e4645336ef8f63feab4c2c2ff6474ff3c Mon Sep 17 00:00:00 2001
From: -LAN- <laipz8200@outlook.com>
Date: Thu, 25 Jul 2024 00:32:39 +0800
Subject: [PATCH 01/60] 
 fix(api/core/workflow/nodes/iteration/iteration_node.py): Extend output in
 iteration if output is a array. (#6647)

Signed-off-by: -LAN- <laipz8200@outlook.com>
---
 api/core/workflow/nodes/iteration/iteration_node.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/api/core/workflow/nodes/iteration/iteration_node.py b/api/core/workflow/nodes/iteration/iteration_node.py
index fcd853a4bd..54dfe8b7f4 100644
--- a/api/core/workflow/nodes/iteration/iteration_node.py
+++ b/api/core/workflow/nodes/iteration/iteration_node.py
@@ -106,7 +106,11 @@ class IterationNode(BaseIterationNode):
         variable_pool.remove([self.node_id] + output_selector[1:])
         state.current_output = output
         if output is not None:
-            state.outputs.append(output)
+            # NOTE: This is a temporary patch to process double nested list (for example, DALL-E output in iteration).
+            if isinstance(output, list):
+                state.outputs.extend(output)
+            else:
+                state.outputs.append(output)
 
     @classmethod
     def _extract_variable_selector_to_variable_mapping(cls, node_data: IterationNodeData) -> dict[str, list[str]]:

From 91fd8521c3f5f9d9d8bbbe791f4c0c9facc0a267 Mon Sep 17 00:00:00 2001
From: Jyong <76649700+JohnJyong@users.noreply.github.com>
Date: Thu, 25 Jul 2024 10:07:55 +0800
Subject: [PATCH 02/60] fix reranking model field error (#6654)

---
 api/core/workflow/nodes/knowledge_retrieval/entities.py       | 4 ++--
 .../nodes/knowledge_retrieval/knowledge_retrieval_node.py     | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/api/core/workflow/nodes/knowledge_retrieval/entities.py b/api/core/workflow/nodes/knowledge_retrieval/entities.py
index 5a9a4a9009..5758b895f3 100644
--- a/api/core/workflow/nodes/knowledge_retrieval/entities.py
+++ b/api/core/workflow/nodes/knowledge_retrieval/entities.py
@@ -46,8 +46,8 @@ class MultipleRetrievalConfig(BaseModel):
     score_threshold: Optional[float] = None
     reranking_mode: str = 'reranking_model'
     reranking_enable: bool = True
-    reranking_model: RerankingModelConfig
-    weights: WeightedScoreConfig
+    reranking_model: Optional[RerankingModelConfig] = None
+    weights: Optional[WeightedScoreConfig] = None
 
 
 class ModelConfig(BaseModel):
diff --git a/api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py b/api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py
index 5f8966f880..7a2b3c8512 100644
--- a/api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py
+++ b/api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py
@@ -140,8 +140,8 @@ class KnowledgeRetrievalNode(BaseNode):
         elif node_data.retrieval_mode == DatasetRetrieveConfigEntity.RetrieveStrategy.MULTIPLE.value:
             if node_data.multiple_retrieval_config.reranking_mode == 'reranking_model':
                 reranking_model = {
-                    'reranking_provider_name': node_data.multiple_retrieval_config.reranking_model['provider'],
-                    'reranking_model_name': node_data.multiple_retrieval_config.reranking_model['name']
+                    'reranking_provider_name': node_data.multiple_retrieval_config.reranking_model.provider,
+                    'reranking_model_name': node_data.multiple_retrieval_config.reranking_model.model
                 }
                 weights = None
             elif node_data.multiple_retrieval_config.reranking_mode == 'weighted_score':

From a876baf0a9cc46f03e8e67af4dfebb2398309683 Mon Sep 17 00:00:00 2001
From: majian <46617237@qq.com>
Date: Thu, 25 Jul 2024 11:15:54 +0800
Subject: [PATCH 03/60] Resolve variable type parameter error (#6646)

---
 api/core/workflow/nodes/tool/tool_node.py | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/api/core/workflow/nodes/tool/tool_node.py b/api/core/workflow/nodes/tool/tool_node.py
index 1bd126f842..238477117d 100644
--- a/api/core/workflow/nodes/tool/tool_node.py
+++ b/api/core/workflow/nodes/tool/tool_node.py
@@ -125,11 +125,15 @@ class ToolNode(BaseNode):
                 ]
             else:
                 tool_input = node_data.tool_parameters[parameter_name]
-                segment_group = parser.convert_template(
-                    template=str(tool_input.value),
-                    variable_pool=variable_pool,
-                )
-                result[parameter_name] = segment_group.log if for_log else segment_group.text
+                if tool_input.type == 'variable':
+                    parameter_value = variable_pool.get(tool_input.value).value
+                else:
+                    segment_group = parser.convert_template(
+                        template=str(tool_input.value),
+                        variable_pool=variable_pool,
+                    )
+                    parameter_value = segment_group.log if for_log else segment_group.text
+                result[parameter_name] = parameter_value
 
         return result
 

From 349ec0db7749fd6154cd4212cd3560287300a980 Mon Sep 17 00:00:00 2001
From: yanghx <30469680+yanghx-git@users.noreply.github.com>
Date: Thu, 25 Jul 2024 11:20:20 +0800
Subject: [PATCH 04/60] fix tencent_cos_storage image-preview error is not a
 byte (#6652)

---
 api/extensions/storage/tencent_storage.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/api/extensions/storage/tencent_storage.py b/api/extensions/storage/tencent_storage.py
index 6d9fb80f5e..e2c1ca55e3 100644
--- a/api/extensions/storage/tencent_storage.py
+++ b/api/extensions/storage/tencent_storage.py
@@ -32,8 +32,7 @@ class TencentStorage(BaseStorage):
     def load_stream(self, filename: str) -> Generator:
         def generate(filename: str = filename) -> Generator:
             response = self.client.get_object(Bucket=self.bucket_name, Key=filename)
-            while chunk := response['Body'].get_stream(chunk_size=4096):
-                yield chunk
+            yield from response['Body'].get_stream(chunk_size=4096)
 
         return generate()
 

From 9815aab7a371fcaa34e1daa644ff8d1308a96e92 Mon Sep 17 00:00:00 2001
From: longzhihun <38651850@qq.com>
Date: Thu, 25 Jul 2024 11:20:37 +0800
Subject: [PATCH 05/60] [seanguo] feat: add llama 3.1 support in bedrock
 (#6645)

---
 .../bedrock/llm/_position.yaml                |  2 ++
 .../model_providers/bedrock/llm/llm.py        | 24 ++++++++++++------
 .../llm/meta.llama3-1-70b-instruct-v1:0.yaml  | 25 +++++++++++++++++++
 .../llm/meta.llama3-1-8b-instruct-v1:0.yaml   | 25 +++++++++++++++++++
 4 files changed, 69 insertions(+), 7 deletions(-)
 create mode 100644 api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-70b-instruct-v1:0.yaml
 create mode 100644 api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-8b-instruct-v1:0.yaml

diff --git a/api/core/model_runtime/model_providers/bedrock/llm/_position.yaml b/api/core/model_runtime/model_providers/bedrock/llm/_position.yaml
index 3a79a929ba..6789a79987 100644
--- a/api/core/model_runtime/model_providers/bedrock/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/llm/_position.yaml
@@ -10,6 +10,8 @@
 - cohere.command-text-v14
 - cohere.command-r-plus-v1.0
 - cohere.command-r-v1.0
+- meta.llama3-1-8b-instruct-v1:0
+- meta.llama3-1-70b-instruct-v1:0
 - meta.llama3-8b-instruct-v1:0
 - meta.llama3-70b-instruct-v1:0
 - meta.llama2-13b-chat-v1
diff --git a/api/core/model_runtime/model_providers/bedrock/llm/llm.py b/api/core/model_runtime/model_providers/bedrock/llm/llm.py
index 882d0b6352..e9906c8294 100644
--- a/api/core/model_runtime/model_providers/bedrock/llm/llm.py
+++ b/api/core/model_runtime/model_providers/bedrock/llm/llm.py
@@ -208,14 +208,25 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
 
         if model_info['support_tool_use'] and tools:
             parameters['toolConfig'] = self._convert_converse_tool_config(tools=tools)
+        try:
+            if stream:
+                response = bedrock_client.converse_stream(**parameters)
+                return self._handle_converse_stream_response(model_info['model'], credentials, response, prompt_messages)
+            else:
+                response = bedrock_client.converse(**parameters)
+                return self._handle_converse_response(model_info['model'], credentials, response, prompt_messages)
+        except ClientError as ex:
+            error_code = ex.response['Error']['Code']
+            full_error_msg = f"{error_code}: {ex.response['Error']['Message']}"
+            raise self._map_client_to_invoke_error(error_code, full_error_msg)
+        except (EndpointConnectionError, NoRegionError, ServiceNotInRegionError) as ex:
+            raise InvokeConnectionError(str(ex))
 
-        if stream:
-            response = bedrock_client.converse_stream(**parameters)
-            return self._handle_converse_stream_response(model_info['model'], credentials, response, prompt_messages)
-        else:
-            response = bedrock_client.converse(**parameters)
-            return self._handle_converse_response(model_info['model'], credentials, response, prompt_messages)
+        except UnknownServiceError as ex:
+            raise InvokeServerUnavailableError(str(ex))
 
+        except Exception as ex:
+            raise InvokeError(str(ex))
     def _handle_converse_response(self, model: str, credentials: dict, response: dict,
                                 prompt_messages: list[PromptMessage]) -> LLMResult:
         """
@@ -558,7 +569,6 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
         except ClientError as ex:
             error_code = ex.response['Error']['Code']
             full_error_msg = f"{error_code}: {ex.response['Error']['Message']}"
-
             raise CredentialsValidateFailedError(str(self._map_client_to_invoke_error(error_code, full_error_msg)))
 
         except Exception as ex:
diff --git a/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-70b-instruct-v1:0.yaml b/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-70b-instruct-v1:0.yaml
new file mode 100644
index 0000000000..10bfa7b1d5
--- /dev/null
+++ b/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-70b-instruct-v1:0.yaml
@@ -0,0 +1,25 @@
+model: meta.llama3-1-70b-instruct-v1:0
+label:
+  en_US: Llama 3.1 Instruct 70B
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.5
+  - name: top_p
+    use_template: top_p
+    default: 0.9
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.00265'
+  output: '0.0035'
+  unit: '0.001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-8b-instruct-v1:0.yaml b/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-8b-instruct-v1:0.yaml
new file mode 100644
index 0000000000..81cd53243f
--- /dev/null
+++ b/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-8b-instruct-v1:0.yaml
@@ -0,0 +1,25 @@
+model: meta.llama3-1-8b-instruct-v1:0
+label:
+  en_US: Llama 3.1 Instruct 8B
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.5
+  - name: top_p
+    use_template: top_p
+    default: 0.9
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.0003'
+  output: '0.0006'
+  unit: '0.001'
+  currency: USD

From 585444c50c99fd2629680f7d01ef06a270431bd9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=9D=9E=E6=B3=95=E6=93=8D=E4=BD=9C?= <hjlarry@163.com>
Date: Thu, 25 Jul 2024 11:21:51 +0800
Subject: [PATCH 06/60] chore: fix type annotations (#6600)

---
 .../app/configuration/config-var/index.tsx         |  2 +-
 .../prompt-mode/advanced-mode-waring.tsx           |  2 --
 .../notion-page-selector-modal/index.tsx           |  8 ++++----
 web/app/components/base/select/index.tsx           |  2 +-
 web/app/components/explore/category.tsx            |  2 +-
 .../model-provider-page/declarations.ts            |  1 +
 web/app/components/header/dataset-nav/index.tsx    |  7 ++++---
 .../components/header/nav/nav-selector/index.tsx   |  4 ++--
 web/app/components/tools/provider/card.tsx         |  2 +-
 web/app/components/tools/provider/detail.tsx       |  2 +-
 web/app/components/tools/workflow-tool/index.tsx   |  2 +-
 .../workflow/block-selector/index-bar.tsx          | 14 ++++++++++----
 12 files changed, 27 insertions(+), 21 deletions(-)

diff --git a/web/app/components/app/configuration/config-var/index.tsx b/web/app/components/app/configuration/config-var/index.tsx
index a4f8b6839f..9ef624ed97 100644
--- a/web/app/components/app/configuration/config-var/index.tsx
+++ b/web/app/components/app/configuration/config-var/index.tsx
@@ -96,7 +96,7 @@ const ConfigVar: FC<IConfigVarProps> = ({ promptVariables, readonly, onPromptVar
         ...rest,
         type: type === InputVarType.textInput ? 'string' : type,
         key: variable,
-        name: label,
+        name: label as string,
       }
 
       if (payload.type === InputVarType.textInput)
diff --git a/web/app/components/app/configuration/prompt-mode/advanced-mode-waring.tsx b/web/app/components/app/configuration/prompt-mode/advanced-mode-waring.tsx
index 759a15213d..6fb58ba9a1 100644
--- a/web/app/components/app/configuration/prompt-mode/advanced-mode-waring.tsx
+++ b/web/app/components/app/configuration/prompt-mode/advanced-mode-waring.tsx
@@ -4,7 +4,6 @@ import React from 'react'
 import { useTranslation } from 'react-i18next'
 import { useContext } from 'use-context-selector'
 import I18n from '@/context/i18n'
-import { FlipBackward } from '@/app/components/base/icons/src/vender/line/arrows'
 import { LanguagesSupported } from '@/i18n/language'
 type Props = {
   onReturnToSimpleMode: () => void
@@ -38,7 +37,6 @@ const AdvancedModeWarning: FC<Props> = ({
             onClick={onReturnToSimpleMode}
             className='shrink-0 flex items-center h-6 px-2 bg-indigo-600 shadow-xs border border-gray-200 rounded-lg text-white text-xs font-semibold cursor-pointer space-x-1'
           >
-            <FlipBackward className='w-3 h-3 text-white' />
             <div className='text-xs font-semibold uppercase'>{t('appDebug.promptMode.switchBack')}</div>
           </div>
           <div
diff --git a/web/app/components/base/notion-page-selector/notion-page-selector-modal/index.tsx b/web/app/components/base/notion-page-selector/notion-page-selector-modal/index.tsx
index b120ef94b2..e7fba57056 100644
--- a/web/app/components/base/notion-page-selector/notion-page-selector-modal/index.tsx
+++ b/web/app/components/base/notion-page-selector/notion-page-selector-modal/index.tsx
@@ -2,15 +2,15 @@ import { useState } from 'react'
 import { useTranslation } from 'react-i18next'
 import { XMarkIcon } from '@heroicons/react/24/outline'
 import NotionPageSelector from '../base'
-import type { NotionPageSelectorValue } from '../base'
 import s from './index.module.css'
+import type { NotionPage } from '@/models/common'
 import cn from '@/utils/classnames'
 import Modal from '@/app/components/base/modal'
 
 type NotionPageSelectorModalProps = {
   isShow: boolean
   onClose: () => void
-  onSave: (selectedPages: NotionPageSelectorValue[]) => void
+  onSave: (selectedPages: NotionPage[]) => void
   datasetId: string
 }
 const NotionPageSelectorModal = ({
@@ -20,12 +20,12 @@ const NotionPageSelectorModal = ({
   datasetId,
 }: NotionPageSelectorModalProps) => {
   const { t } = useTranslation()
-  const [selectedPages, setSelectedPages] = useState<NotionPageSelectorValue[]>([])
+  const [selectedPages, setSelectedPages] = useState<NotionPage[]>([])
 
   const handleClose = () => {
     onClose()
   }
-  const handleSelectPage = (newSelectedPages: NotionPageSelectorValue[]) => {
+  const handleSelectPage = (newSelectedPages: NotionPage[]) => {
     setSelectedPages(newSelectedPages)
   }
   const handleSave = () => {
diff --git a/web/app/components/base/select/index.tsx b/web/app/components/base/select/index.tsx
index 24da8855fa..dee983690b 100644
--- a/web/app/components/base/select/index.tsx
+++ b/web/app/components/base/select/index.tsx
@@ -191,7 +191,7 @@ const SimpleSelect: FC<ISelectProps> = ({
                   onClick={(e) => {
                     e.stopPropagation()
                     setSelectedItem(null)
-                    onSelect({ value: null })
+                    onSelect({ name: '', value: '' })
                   }}
                   className="h-5 w-5 text-gray-400 cursor-pointer"
                   aria-hidden="false"
diff --git a/web/app/components/explore/category.tsx b/web/app/components/explore/category.tsx
index 2b6cfbd9be..cf655c5333 100644
--- a/web/app/components/explore/category.tsx
+++ b/web/app/components/explore/category.tsx
@@ -28,7 +28,7 @@ const Category: FC<ICategoryProps> = ({
   allCategoriesEn,
 }) => {
   const { t } = useTranslation()
-  const isAllCategories = !list.includes(value)
+  const isAllCategories = !list.includes(value as AppCategory)
 
   const itemClassName = (isSelected: boolean) => cn(
     'flex items-center px-3 py-[7px] h-[32px] rounded-lg border-[0.5px] border-transparent text-gray-700 font-medium leading-[18px] cursor-pointer hover:bg-gray-200',
diff --git a/web/app/components/header/account-setting/model-provider-page/declarations.ts b/web/app/components/header/account-setting/model-provider-page/declarations.ts
index abc81262b9..1547032163 100644
--- a/web/app/components/header/account-setting/model-provider-page/declarations.ts
+++ b/web/app/components/header/account-setting/model-provider-page/declarations.ts
@@ -12,6 +12,7 @@ export enum FormTypeEnum {
   secretInput = 'secret-input',
   select = 'select',
   radio = 'radio',
+  boolean = 'boolean',
   files = 'files',
 }
 
diff --git a/web/app/components/header/dataset-nav/index.tsx b/web/app/components/header/dataset-nav/index.tsx
index f415658eee..abf76608a8 100644
--- a/web/app/components/header/dataset-nav/index.tsx
+++ b/web/app/components/header/dataset-nav/index.tsx
@@ -11,6 +11,7 @@ import useSWR from 'swr'
 import useSWRInfinite from 'swr/infinite'
 import { flatten } from 'lodash-es'
 import Nav from '../nav'
+import type { NavItem } from '../nav/nav-selector'
 import { fetchDatasetDetail, fetchDatasets } from '@/service/datasets'
 import type { DataSetListResponse } from '@/models/datasets'
 
@@ -31,7 +32,7 @@ const DatasetNav = () => {
         datasetId,
       }
       : null,
-    apiParams => fetchDatasetDetail(apiParams.datasetId))
+    apiParams => fetchDatasetDetail(apiParams.datasetId as string))
   const { data: datasetsData, setSize } = useSWRInfinite(datasetId ? getKey : () => null, fetchDatasets, { revalidateFirstPage: false, revalidateAll: true })
   const datasetItems = flatten(datasetsData?.map(datasetData => datasetData.data))
 
@@ -46,14 +47,14 @@ const DatasetNav = () => {
       text={t('common.menus.datasets')}
       activeSegment='datasets'
       link='/datasets'
-      curNav={currentDataset}
+      curNav={currentDataset as Omit<NavItem, 'link'>}
       navs={datasetItems.map(dataset => ({
         id: dataset.id,
         name: dataset.name,
         link: `/datasets/${dataset.id}/documents`,
         icon: dataset.icon,
         icon_background: dataset.icon_background,
-      }))}
+      })) as NavItem[]}
       createText={t('common.menus.newDataset')}
       onCreate={() => router.push('/datasets/create')}
       onLoadmore={handleLoadmore}
diff --git a/web/app/components/header/nav/nav-selector/index.tsx b/web/app/components/header/nav/nav-selector/index.tsx
index 51192c6580..26f538d72d 100644
--- a/web/app/components/header/nav/nav-selector/index.tsx
+++ b/web/app/components/header/nav/nav-selector/index.tsx
@@ -23,13 +23,13 @@ export type NavItem = {
   link: string
   icon: string
   icon_background: string
-  mode: string
+  mode?: string
 }
 export type INavSelectorProps = {
   navs: NavItem[]
   curNav?: Omit<NavItem, 'link'>
   createText: string
-  isApp: boolean
+  isApp?: boolean
   onCreate: (state: string) => void
   onLoadmore?: () => void
 }
diff --git a/web/app/components/tools/provider/card.tsx b/web/app/components/tools/provider/card.tsx
index 7f87d65e3a..6a688186cf 100644
--- a/web/app/components/tools/provider/card.tsx
+++ b/web/app/components/tools/provider/card.tsx
@@ -36,7 +36,7 @@ const ProviderCard = ({
   }, [collection.labels, labelList, language])
 
   return (
-    <div className={cn('group flex col-span-1 bg-white border-2 border-solid border-transparent rounded-xl shadow-sm min-h-[160px] flex flex-col transition-all duration-200 ease-in-out cursor-pointer hover:shadow-lg', active && '!border-primary-400')} onClick={onSelect}>
+    <div className={cn('group col-span-1 bg-white border-2 border-solid border-transparent rounded-xl shadow-sm min-h-[160px] flex flex-col transition-all duration-200 ease-in-out cursor-pointer hover:shadow-lg', active && '!border-primary-400')} onClick={onSelect}>
       <div className='flex pt-[14px] px-[14px] pb-3 h-[66px] items-center gap-3 grow-0 shrink-0'>
         <div className='relative shrink-0'>
           {typeof collection.icon === 'string' && (
diff --git a/web/app/components/tools/provider/detail.tsx b/web/app/components/tools/provider/detail.tsx
index ee02e4966d..546b9cd9a1 100644
--- a/web/app/components/tools/provider/detail.tsx
+++ b/web/app/components/tools/provider/detail.tsx
@@ -85,7 +85,7 @@ const ProviderDetail = ({
   const [customCollection, setCustomCollection] = useState<CustomCollectionBackend | WorkflowToolProviderResponse | null>(null)
   const [isShowEditCollectionToolModal, setIsShowEditCustomCollectionModal] = useState(false)
   const [showConfirmDelete, setShowConfirmDelete] = useState(false)
-  const [deleteAction, setDeleteAction] = useState(null)
+  const [deleteAction, setDeleteAction] = useState('')
   const doUpdateCustomToolCollection = async (data: CustomCollectionBackend) => {
     await updateCustomCollection(data)
     onRefreshData()
diff --git a/web/app/components/tools/workflow-tool/index.tsx b/web/app/components/tools/workflow-tool/index.tsx
index 436b2c55ab..0f9fe4c4c1 100644
--- a/web/app/components/tools/workflow-tool/index.tsx
+++ b/web/app/components/tools/workflow-tool/index.tsx
@@ -173,7 +173,7 @@ const WorkflowToolAsModal: FC<Props> = ({
               <div>
                 <div className='py-2 leading-5 text-sm font-medium text-gray-900'>{t('tools.createTool.description')}</div>
                 <textarea
-                  className='w-full h-10 px-3 py-2 text-sm font-normal bg-gray-100 rounded-lg border border-transparent outline-none appearance-none caret-primary-600 placeholder:text-gray-400 hover:bg-gray-50 hover:border hover:border-gray-300 focus:bg-gray-50 focus:border focus:border-gray-300 focus:shadow-xs h-[80px] resize-none'
+                  className='w-full px-3 py-2 text-sm font-normal bg-gray-100 rounded-lg border border-transparent outline-none appearance-none caret-primary-600 placeholder:text-gray-400 hover:bg-gray-50 hover:border hover:border-gray-300 focus:bg-gray-50 focus:border focus:border-gray-300 focus:shadow-xs h-[80px] resize-none'
                   placeholder={t('tools.createTool.descriptionPlaceholder') || ''}
                   value={description}
                   onChange={e => setDescription(e.target.value)}
diff --git a/web/app/components/workflow/block-selector/index-bar.tsx b/web/app/components/workflow/block-selector/index-bar.tsx
index f485384969..6eab51246d 100644
--- a/web/app/components/workflow/block-selector/index-bar.tsx
+++ b/web/app/components/workflow/block-selector/index-bar.tsx
@@ -1,6 +1,7 @@
 import { pinyin } from 'pinyin-pro'
+import type { FC, RefObject } from 'react'
 
-export const groupItems = (items, getFirstChar) => {
+export const groupItems = (items: Array<any>, getFirstChar: (item: string) => string) => {
   const groups = items.reduce((acc, item) => {
     const firstChar = getFirstChar(item)
     if (!firstChar || firstChar.length === 0)
@@ -34,9 +35,14 @@ export const groupItems = (items, getFirstChar) => {
   return { letters, groups }
 }
 
-const IndexBar = ({ letters, itemRefs }) => {
-  const handleIndexClick = (letter) => {
-    const element = itemRefs.current[letter]
+type IndexBarProps = {
+  letters: string[]
+  itemRefs: RefObject<{ [key: string]: HTMLElement | null }>
+}
+
+const IndexBar: FC<IndexBarProps> = ({ letters, itemRefs }) => {
+  const handleIndexClick = (letter: string) => {
+    const element = itemRefs.current?.[letter]
     if (element)
       element.scrollIntoView({ behavior: 'smooth' })
   }

From ca696fe94c67cb3b855fb3f632673ec7dfe773ce Mon Sep 17 00:00:00 2001
From: Giga Group <88305215+maybemaynot@users.noreply.github.com>
Date: Thu, 25 Jul 2024 11:27:58 +0800
Subject: [PATCH 07/60] Add support of tool-call for model provider "hunyuan"
 (#6656)

Co-authored-by: sun <sun@centen.cn>
---
 .../model_providers/hunyuan/llm/llm.py        | 128 ++++++++++++++++--
 1 file changed, 119 insertions(+), 9 deletions(-)

diff --git a/api/core/model_runtime/model_providers/hunyuan/llm/llm.py b/api/core/model_runtime/model_providers/hunyuan/llm/llm.py
index 2b6d8e0047..8859dd72bd 100644
--- a/api/core/model_runtime/model_providers/hunyuan/llm/llm.py
+++ b/api/core/model_runtime/model_providers/hunyuan/llm/llm.py
@@ -14,6 +14,7 @@ from core.model_runtime.entities.message_entities import (
     PromptMessage,
     PromptMessageTool,
     SystemPromptMessage,
+    ToolPromptMessage,
     UserPromptMessage,
 )
 from core.model_runtime.errors.invoke import InvokeError
@@ -44,6 +45,17 @@ class HunyuanLargeLanguageModel(LargeLanguageModel):
             "Stream": stream,
             **custom_parameters,
         }
+        # add Tools and ToolChoice
+        if (tools and len(tools) > 0):
+            params['ToolChoice'] = "auto"
+            params['Tools'] = [{
+                "Type": "function", 
+                "Function": {
+                    "Name": tool.name, 
+                    "Description": tool.description,
+                    "Parameters": json.dumps(tool.parameters)
+                }
+            } for tool in tools]
 
         request.from_json_string(json.dumps(params))
         response = client.ChatCompletions(request)
@@ -89,9 +101,43 @@ class HunyuanLargeLanguageModel(LargeLanguageModel):
 
     def _convert_prompt_messages_to_dicts(self, prompt_messages: list[PromptMessage]) -> list[dict]:
         """Convert a list of PromptMessage objects to a list of dictionaries with 'Role' and 'Content' keys."""
-        return [{"Role": message.role.value, "Content": message.content} for message in prompt_messages]
+        dict_list = []
+        for message in prompt_messages:
+            if isinstance(message, AssistantPromptMessage):
+                tool_calls = message.tool_calls
+                if (tool_calls and len(tool_calls) > 0):
+                    dict_tool_calls = [
+                        {
+                            "Id": tool_call.id,
+                            "Type": tool_call.type,
+                            "Function": {
+                                "Name": tool_call.function.name,
+                                "Arguments": tool_call.function.arguments if (tool_call.function.arguments == "") else "{}"
+                            }
+                        } for tool_call in tool_calls]
+                    
+                    dict_list.append({ 
+                        "Role": message.role.value,
+                        # fix set content = "" while tool_call request
+                        # fix [hunyuan] None, [TencentCloudSDKException] code:InvalidParameter message:Messages Content and Contents not allowed empty at the same time.
+                        "Content": " ", # message.content if (message.content is not None) else "", 
+                        "ToolCalls":  dict_tool_calls
+                    })
+                else:
+                    dict_list.append({ "Role": message.role.value, "Content": message.content })
+            elif isinstance(message, ToolPromptMessage):
+                tool_execute_result = { "result": message.content }
+                content =json.dumps(tool_execute_result, ensure_ascii=False)
+                dict_list.append({ "Role": message.role.value, "Content": content, "ToolCallId": message.tool_call_id  })
+            else:
+                dict_list.append({ "Role": message.role.value, "Content": message.content })
+        return dict_list
 
     def _handle_stream_chat_response(self, model, credentials, prompt_messages, resp):
+
+        tool_call = None
+        tool_calls = []
+
         for index, event in enumerate(resp):
             logging.debug("_handle_stream_chat_response, event: %s", event)
 
@@ -109,20 +155,54 @@ class HunyuanLargeLanguageModel(LargeLanguageModel):
             usage = data.get('Usage', {})
             prompt_tokens = usage.get('PromptTokens', 0)
             completion_tokens = usage.get('CompletionTokens', 0)
-            usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)
+
+            response_tool_calls = delta.get('ToolCalls')
+            if (response_tool_calls is not None):
+                new_tool_calls = self._extract_response_tool_calls(response_tool_calls)
+                if (len(new_tool_calls) > 0):
+                    new_tool_call = new_tool_calls[0]
+                    if (tool_call is None): tool_call = new_tool_call
+                    elif (tool_call.id != new_tool_call.id):
+                        tool_calls.append(tool_call)
+                        tool_call = new_tool_call
+                    else:
+                        tool_call.function.name += new_tool_call.function.name
+                        tool_call.function.arguments += new_tool_call.function.arguments
+                if (tool_call is not None and len(tool_call.function.name) > 0 and len(tool_call.function.arguments) > 0):
+                    tool_calls.append(tool_call)
+                    tool_call = None
 
             assistant_prompt_message = AssistantPromptMessage(
                 content=message_content,
                 tool_calls=[]
             )
+            # rewrite content = "" while tool_call to avoid show content on web page
+            if (len(tool_calls) > 0): assistant_prompt_message.content = ""
+            
+            # add tool_calls to assistant_prompt_message
+            if (finish_reason == 'tool_calls'):
+                assistant_prompt_message.tool_calls = tool_calls
+                tool_call = None
+                tool_calls = []
 
-            delta_chunk = LLMResultChunkDelta(
-                index=index,
-                role=delta.get('Role', 'assistant'),
-                message=assistant_prompt_message,
-                usage=usage,
-                finish_reason=finish_reason,
-            )
+            if (len(finish_reason) > 0):
+                usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)
+
+                delta_chunk = LLMResultChunkDelta(
+                    index=index,
+                    role=delta.get('Role', 'assistant'),
+                    message=assistant_prompt_message,
+                    usage=usage,
+                    finish_reason=finish_reason,
+                )
+                tool_call = None
+                tool_calls = []
+
+            else:
+                delta_chunk = LLMResultChunkDelta(
+                    index=index,
+                    message=assistant_prompt_message,
+                )
 
             yield LLMResultChunk(
                 model=model,
@@ -177,12 +257,15 @@ class HunyuanLargeLanguageModel(LargeLanguageModel):
         """
         human_prompt = "\n\nHuman:"
         ai_prompt = "\n\nAssistant:"
+        tool_prompt = "\n\nTool:"
         content = message.content
 
         if isinstance(message, UserPromptMessage):
             message_text = f"{human_prompt} {content}"
         elif isinstance(message, AssistantPromptMessage):
             message_text = f"{ai_prompt} {content}"
+        elif isinstance(message, ToolPromptMessage):
+            message_text = f"{tool_prompt} {content}"
         elif isinstance(message, SystemPromptMessage):
             message_text = content
         else:
@@ -203,3 +286,30 @@ class HunyuanLargeLanguageModel(LargeLanguageModel):
         return {
             InvokeError: [TencentCloudSDKException],
         }
+    
+    def _extract_response_tool_calls(self,
+                                     response_tool_calls: list[dict]) \
+            -> list[AssistantPromptMessage.ToolCall]:
+        """
+        Extract tool calls from response
+
+        :param response_tool_calls: response tool calls
+        :return: list of tool calls
+        """
+        tool_calls = []
+        if response_tool_calls:
+            for response_tool_call in response_tool_calls:
+                response_function = response_tool_call.get('Function', {})
+                function = AssistantPromptMessage.ToolCall.ToolCallFunction(
+                    name=response_function.get('Name', ''),
+                    arguments=response_function.get('Arguments', '')
+                )
+
+                tool_call = AssistantPromptMessage.ToolCall(
+                    id=response_tool_call.get('Id', 0),
+                    type='function',
+                    function=function
+                )
+                tool_calls.append(tool_call)
+
+        return tool_calls
\ No newline at end of file

From 55c2b61921348733691b8381bdd52d4182b37578 Mon Sep 17 00:00:00 2001
From: -LAN- <laipz8200@outlook.com>
Date: Thu, 25 Jul 2024 11:30:52 +0800
Subject: [PATCH 08/60] fix(api/fields/workflow_fields.py): Add check in
 environment variables (#6621)

---
 api/fields/workflow_fields.py | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/api/fields/workflow_fields.py b/api/fields/workflow_fields.py
index c98c332021..ff33a97ff2 100644
--- a/api/fields/workflow_fields.py
+++ b/api/fields/workflow_fields.py
@@ -1,10 +1,12 @@
 from flask_restful import fields
 
-from core.app.segments import SecretVariable, Variable
+from core.app.segments import SecretVariable, SegmentType, Variable
 from core.helper import encrypter
 from fields.member_fields import simple_account_fields
 from libs.helper import TimestampField
 
+ENVIRONMENT_VARIABLE_SUPPORTED_TYPES = (SegmentType.STRING, SegmentType.NUMBER, SegmentType.SECRET)
+
 
 class EnvironmentVariableField(fields.Raw):
     def format(self, value):
@@ -16,14 +18,18 @@ class EnvironmentVariableField(fields.Raw):
                 'value': encrypter.obfuscated_token(value.value),
                 'value_type': value.value_type.value,
             }
-        elif isinstance(value, Variable):
+        if isinstance(value, Variable):
             return {
                 'id': value.id,
                 'name': value.name,
                 'value': value.value,
                 'value_type': value.value_type.value,
             }
-        return value
+        if isinstance(value, dict):
+            value_type = value.get('value_type')
+            if value_type not in ENVIRONMENT_VARIABLE_SUPPORTED_TYPES:
+                raise ValueError(f'Unsupported environment variable value type: {value_type}')
+            return value
 
 
 environment_variable_fields = {

From ebcc07e3e99c22c77f22dc5d4a001c51d9ce52f9 Mon Sep 17 00:00:00 2001
From: xielong <xielong.me@gmail.com>
Date: Thu, 25 Jul 2024 13:10:39 +0800
Subject: [PATCH 09/60] feat: support max_retries in jina requests (#6585)

---
 api/.env.example                              |  1 +
 api/core/helper/ssrf_proxy.py                 | 62 +++++++++++++------
 .../builtin/jina/tools/jina_reader.py         |  2 +
 .../builtin/jina/tools/jina_reader.yaml       | 14 +++++
 .../builtin/jina/tools/jina_search.py         |  4 +-
 .../builtin/jina/tools/jina_search.yaml       | 14 +++++
 api/tests/unit_tests/core/helper/__init__.py  |  0
 .../unit_tests/core/helper/test_ssrf_proxy.py | 52 ++++++++++++++++
 8 files changed, 129 insertions(+), 20 deletions(-)
 create mode 100644 api/tests/unit_tests/core/helper/__init__.py
 create mode 100644 api/tests/unit_tests/core/helper/test_ssrf_proxy.py

diff --git a/api/.env.example b/api/.env.example
index 474798cef7..80ef185e51 100644
--- a/api/.env.example
+++ b/api/.env.example
@@ -216,6 +216,7 @@ UNSTRUCTURED_API_KEY=
 
 SSRF_PROXY_HTTP_URL=
 SSRF_PROXY_HTTPS_URL=
+SSRF_DEFAULT_MAX_RETRIES=3
 
 BATCH_UPLOAD_LIMIT=10
 KEYWORD_DATA_SOURCE_TYPE=database
diff --git a/api/core/helper/ssrf_proxy.py b/api/core/helper/ssrf_proxy.py
index 019b27f28a..63cf548ae4 100644
--- a/api/core/helper/ssrf_proxy.py
+++ b/api/core/helper/ssrf_proxy.py
@@ -1,13 +1,16 @@
 """
 Proxy requests to avoid SSRF
 """
+import logging
 import os
+import time
 
 import httpx
 
 SSRF_PROXY_ALL_URL = os.getenv('SSRF_PROXY_ALL_URL', '')
 SSRF_PROXY_HTTP_URL = os.getenv('SSRF_PROXY_HTTP_URL', '')
 SSRF_PROXY_HTTPS_URL = os.getenv('SSRF_PROXY_HTTPS_URL', '')
+SSRF_DEFAULT_MAX_RETRIES = int(os.getenv('SSRF_DEFAULT_MAX_RETRIES', '3'))
 
 proxies = {
     'http://': SSRF_PROXY_HTTP_URL,
@@ -15,34 +18,55 @@ proxies = {
 } if SSRF_PROXY_HTTP_URL and SSRF_PROXY_HTTPS_URL else None
 
 
-def make_request(method, url, **kwargs):
-    if SSRF_PROXY_ALL_URL:
-        return httpx.request(method=method, url=url, proxy=SSRF_PROXY_ALL_URL, **kwargs)
-    elif proxies:
-        return httpx.request(method=method, url=url, proxies=proxies, **kwargs)
-    else:
-        return httpx.request(method=method, url=url, **kwargs)
+BACKOFF_FACTOR = 0.5
+STATUS_FORCELIST = [429, 500, 502, 503, 504]
 
 
-def get(url, **kwargs):
-    return make_request('GET', url, **kwargs)
+def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
+    retries = 0
+    while retries <= max_retries:
+        try:
+            if SSRF_PROXY_ALL_URL:
+                response = httpx.request(method=method, url=url, proxy=SSRF_PROXY_ALL_URL, **kwargs)
+            elif proxies:
+                response = httpx.request(method=method, url=url, proxies=proxies, **kwargs)
+            else:
+                response = httpx.request(method=method, url=url, **kwargs)
+
+            if response.status_code not in STATUS_FORCELIST:
+                return response
+            else:
+                logging.warning(f"Received status code {response.status_code} for URL {url} which is in the force list")
+
+        except httpx.RequestError as e:
+            logging.warning(f"Request to URL {url} failed on attempt {retries + 1}: {e}")
+
+        retries += 1
+        if retries <= max_retries:
+            time.sleep(BACKOFF_FACTOR * (2 ** (retries - 1)))
+
+    raise Exception(f"Reached maximum retries ({max_retries}) for URL {url}")
 
 
-def post(url, **kwargs):
-    return make_request('POST', url, **kwargs)
+def get(url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
+    return make_request('GET', url, max_retries=max_retries, **kwargs)
 
 
-def put(url, **kwargs):
-    return make_request('PUT', url, **kwargs)
+def post(url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
+    return make_request('POST', url, max_retries=max_retries, **kwargs)
 
 
-def patch(url, **kwargs):
-    return make_request('PATCH', url, **kwargs)
+def put(url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
+    return make_request('PUT', url, max_retries=max_retries, **kwargs)
 
 
-def delete(url, **kwargs):
-    return make_request('DELETE', url, **kwargs)
+def patch(url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
+    return make_request('PATCH', url, max_retries=max_retries, **kwargs)
 
 
-def head(url, **kwargs):
-    return make_request('HEAD', url, **kwargs)
+def delete(url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
+    return make_request('DELETE', url, max_retries=max_retries, **kwargs)
+
+
+def head(url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
+    return make_request('HEAD', url, max_retries=max_retries, **kwargs)
diff --git a/api/core/tools/provider/builtin/jina/tools/jina_reader.py b/api/core/tools/provider/builtin/jina/tools/jina_reader.py
index 8409129833..cee46cee23 100644
--- a/api/core/tools/provider/builtin/jina/tools/jina_reader.py
+++ b/api/core/tools/provider/builtin/jina/tools/jina_reader.py
@@ -60,11 +60,13 @@ class JinaReaderTool(BuiltinTool):
         if tool_parameters.get('no_cache', False):
             headers['X-No-Cache'] = 'true'
 
+        max_retries = tool_parameters.get('max_retries', 3)
         response = ssrf_proxy.get(
             str(URL(self._jina_reader_endpoint + url)),
             headers=headers,
             params=request_params,
             timeout=(10, 60),
+            max_retries=max_retries
         )
 
         if tool_parameters.get('summary', False):
diff --git a/api/core/tools/provider/builtin/jina/tools/jina_reader.yaml b/api/core/tools/provider/builtin/jina/tools/jina_reader.yaml
index 072e7f0528..58ad6d8694 100644
--- a/api/core/tools/provider/builtin/jina/tools/jina_reader.yaml
+++ b/api/core/tools/provider/builtin/jina/tools/jina_reader.yaml
@@ -150,3 +150,17 @@ parameters:
       pt_BR: Habilitar resumo para a saída
     llm_description: enable summary
     form: form
+  - name: max_retries
+    type: number
+    required: false
+    default: 3
+    label:
+      en_US: Retry
+      zh_Hans: 重试
+      pt_BR: Repetir
+    human_description:
+      en_US: Number of times to retry the request if it fails
+      zh_Hans: 请求失败时重试的次数
+      pt_BR: Número de vezes para repetir a solicitação se falhar
+    llm_description: Number of times to retry the request if it fails
+    form: form
diff --git a/api/core/tools/provider/builtin/jina/tools/jina_search.py b/api/core/tools/provider/builtin/jina/tools/jina_search.py
index e6bc08147f..d4a81cd096 100644
--- a/api/core/tools/provider/builtin/jina/tools/jina_search.py
+++ b/api/core/tools/provider/builtin/jina/tools/jina_search.py
@@ -40,10 +40,12 @@ class JinaSearchTool(BuiltinTool):
         if tool_parameters.get('no_cache', False):
             headers['X-No-Cache'] = 'true'
 
+        max_retries = tool_parameters.get('max_retries', 3)
         response = ssrf_proxy.get(
             str(URL(self._jina_search_endpoint + query)),
             headers=headers,
-            timeout=(10, 60)
+            timeout=(10, 60),
+            max_retries=max_retries
         )
 
         return self.create_text_message(response.text)
diff --git a/api/core/tools/provider/builtin/jina/tools/jina_search.yaml b/api/core/tools/provider/builtin/jina/tools/jina_search.yaml
index da0a300c6c..2bc70e1be1 100644
--- a/api/core/tools/provider/builtin/jina/tools/jina_search.yaml
+++ b/api/core/tools/provider/builtin/jina/tools/jina_search.yaml
@@ -91,3 +91,17 @@ parameters:
       pt_BR: Ignorar o cache
     llm_description: bypass the cache
     form: form
+  - name: max_retries
+    type: number
+    required: false
+    default: 3
+    label:
+      en_US: Retry
+      zh_Hans: 重试
+      pt_BR: Repetir
+    human_description:
+      en_US: Number of times to retry the request if it fails
+      zh_Hans: 请求失败时重试的次数
+      pt_BR: Número de vezes para repetir a solicitação se falhar
+    llm_description: Number of times to retry the request if it fails
+    form: form
diff --git a/api/tests/unit_tests/core/helper/__init__.py b/api/tests/unit_tests/core/helper/__init__.py
new file mode 100644
index 0000000000..e69de29bb2
diff --git a/api/tests/unit_tests/core/helper/test_ssrf_proxy.py b/api/tests/unit_tests/core/helper/test_ssrf_proxy.py
new file mode 100644
index 0000000000..d917bb1003
--- /dev/null
+++ b/api/tests/unit_tests/core/helper/test_ssrf_proxy.py
@@ -0,0 +1,52 @@
+import random
+from unittest.mock import MagicMock, patch
+
+from core.helper.ssrf_proxy import SSRF_DEFAULT_MAX_RETRIES, STATUS_FORCELIST, make_request
+
+
+@patch('httpx.request')
+def test_successful_request(mock_request):
+    mock_response = MagicMock()
+    mock_response.status_code = 200
+    mock_request.return_value = mock_response
+
+    response = make_request('GET', 'http://example.com')
+    assert response.status_code == 200
+
+
+@patch('httpx.request')
+def test_retry_exceed_max_retries(mock_request):
+    mock_response = MagicMock()
+    mock_response.status_code = 500
+
+    side_effects = [mock_response] * SSRF_DEFAULT_MAX_RETRIES
+    mock_request.side_effect = side_effects
+
+    try:
+        make_request('GET', 'http://example.com', max_retries=SSRF_DEFAULT_MAX_RETRIES - 1)
+        raise AssertionError("Expected Exception not raised")
+    except Exception as e:
+        assert str(e) == f"Reached maximum retries ({SSRF_DEFAULT_MAX_RETRIES - 1}) for URL http://example.com"
+
+
+@patch('httpx.request')
+def test_retry_logic_success(mock_request):
+    side_effects = []
+
+    for _ in range(SSRF_DEFAULT_MAX_RETRIES):
+        status_code = random.choice(STATUS_FORCELIST)
+        mock_response = MagicMock()
+        mock_response.status_code = status_code
+        side_effects.append(mock_response)
+
+    mock_response_200 = MagicMock()
+    mock_response_200.status_code = 200
+    side_effects.append(mock_response_200)
+
+    mock_request.side_effect = side_effects
+
+    response = make_request('GET', 'http://example.com', max_retries=SSRF_DEFAULT_MAX_RETRIES)
+
+    assert response.status_code == 200
+    assert mock_request.call_count == SSRF_DEFAULT_MAX_RETRIES + 1
+    assert mock_request.call_args_list[0][1].get('method') == 'GET'

From 0b4c26578ee2146d00d0545144a19fa3a8f24efb Mon Sep 17 00:00:00 2001
From: Seayon <153660639@qq.com>
Date: Thu, 25 Jul 2024 16:48:00 +0800
Subject: [PATCH 10/60] Enhance database URI security and add URL encoding
 (#6668)

---
 api/configs/middleware/__init__.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/api/configs/middleware/__init__.py b/api/configs/middleware/__init__.py
index a32b70bdc7..07688e9aeb 100644
--- a/api/configs/middleware/__init__.py
+++ b/api/configs/middleware/__init__.py
@@ -1,4 +1,5 @@
 from typing import Any, Optional
+from urllib.parse import quote_plus
 
 from pydantic import Field, NonNegativeInt, PositiveInt, computed_field
 from pydantic_settings import BaseSettings
@@ -104,7 +105,7 @@ class DatabaseConfig:
         ).strip("&")
         db_extras = f"?{db_extras}" if db_extras else ""
         return (f"{self.SQLALCHEMY_DATABASE_URI_SCHEME}://"
-                f"{self.DB_USERNAME}:{self.DB_PASSWORD}@{self.DB_HOST}:{self.DB_PORT}/{self.DB_DATABASE}"
+                f"{quote_plus(self.DB_USERNAME)}:{quote_plus(self.DB_PASSWORD)}@{self.DB_HOST}:{self.DB_PORT}/{self.DB_DATABASE}" 
                 f"{db_extras}")
 
     SQLALCHEMY_POOL_SIZE: NonNegativeInt = Field(

From 75e6576c6750f556ae9db75f2e796e01863b7c7e Mon Sep 17 00:00:00 2001
From: -LAN- <laipz8200@outlook.com>
Date: Thu, 25 Jul 2024 17:06:38 +0800
Subject: [PATCH 11/60] refactor(api/core/app/segments): implement `to_object`
 in ObjectVariable and ArrayVariable. (#6671)

Signed-off-by: -LAN- <laipz8200@outlook.com>
---
 api/core/app/segments/segments.py  | 6 ------
 api/core/app/segments/variables.py | 6 ++++++
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/api/core/app/segments/segments.py b/api/core/app/segments/segments.py
index e6bf6cc3a3..afd383880f 100644
--- a/api/core/app/segments/segments.py
+++ b/api/core/app/segments/segments.py
@@ -34,12 +34,6 @@ class Segment(BaseModel):
         return str(self.value)
 
     def to_object(self) -> Any:
-        if isinstance(self.value, Segment):
-            return self.value.to_object()
-        if isinstance(self.value, list):
-            return [v.to_object() for v in self.value]
-        if isinstance(self.value, dict):
-            return {k: v.to_object() for k, v in self.value.items()}
         return self.value
 
 
diff --git a/api/core/app/segments/variables.py b/api/core/app/segments/variables.py
index b020914d84..5edaccc4d6 100644
--- a/api/core/app/segments/variables.py
+++ b/api/core/app/segments/variables.py
@@ -56,6 +56,9 @@ class ObjectVariable(Variable):
         # TODO: Use markdown code block
         return json.dumps(self.model_dump()['value'], ensure_ascii=False, indent=2)
 
+    def to_object(self):
+        return {k: v.to_object() for k, v in self.value.items()}
+
 
 class ArrayVariable(Variable):
     value_type: SegmentType = SegmentType.ARRAY
@@ -65,6 +68,9 @@ class ArrayVariable(Variable):
     def markdown(self) -> str:
         return '\n'.join(['- ' + item.markdown for item in self.value])
 
+    def to_object(self):
+        return [v.to_object() for v in self.value]
+
 
 class FileVariable(Variable):
     value_type: SegmentType = SegmentType.FILE

From 16b4f560cdbe8866cf3d1c612b0529a32661b45b Mon Sep 17 00:00:00 2001
From: tmuife <43266626@qq.com>
Date: Thu, 25 Jul 2024 17:07:14 +0800
Subject: [PATCH 12/60] fix bugs(when using Oracle23ai as Vector DB) (#6658)

---
 api/core/rag/datasource/vdb/oracle/oraclevector.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/api/core/rag/datasource/vdb/oracle/oraclevector.py b/api/core/rag/datasource/vdb/oracle/oraclevector.py
index f65f57da60..4bd09b331d 100644
--- a/api/core/rag/datasource/vdb/oracle/oraclevector.py
+++ b/api/core/rag/datasource/vdb/oracle/oraclevector.py
@@ -55,7 +55,7 @@ CREATE TABLE IF NOT EXISTS {table_name} (
 )
 """
 SQL_CREATE_INDEX = """
-CREATE INDEX idx_docs_{table_name} ON {table_name}(text) 
+CREATE INDEX IF NOT EXISTS idx_docs_{table_name} ON {table_name}(text) 
 INDEXTYPE IS CTXSYS.CONTEXT PARAMETERS 
 ('FILTER CTXSYS.NULL_FILTER SECTION GROUP CTXSYS.HTML_SECTION_GROUP LEXER sys.my_chinese_vgram_lexer')
 """
@@ -248,7 +248,7 @@ class OracleVector(BaseVector):
 
     def delete(self) -> None:
         with self._get_cursor() as cur:
-            cur.execute(f"DROP TABLE IF EXISTS {self.table_name}")
+            cur.execute(f"DROP TABLE IF EXISTS {self.table_name} cascade constraints")
 
     def _create_collection(self, dimension: int):
         cache_key = f"vector_indexing_{self._collection_name}"

From 5e4ac11df32f541488ec4639983a01202619c3b4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E7=81=B0=E7=81=B0?= <zhengminghui99@gmail.com>
Date: Thu, 25 Jul 2024 17:24:37 +0800
Subject: [PATCH 13/60] fix: code block segmentation problem of markdown
 document (#6465)

---
 api/core/rag/extractor/markdown_extractor.py | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/api/core/rag/extractor/markdown_extractor.py b/api/core/rag/extractor/markdown_extractor.py
index faa1e64057..b24cf2e170 100644
--- a/api/core/rag/extractor/markdown_extractor.py
+++ b/api/core/rag/extractor/markdown_extractor.py
@@ -54,8 +54,16 @@ class MarkdownExtractor(BaseExtractor):
 
         current_header = None
         current_text = ""
+        code_block_flag = False
 
         for line in lines:
+            if line.startswith("```"):
+                code_block_flag = not code_block_flag
+                current_text += line + "\n"
+                continue
+            if code_block_flag:
+                current_text += line + "\n"
+                continue
             header_match = re.match(r"^#+\s", line)
             if header_match:
                 if current_header is not None:

From f904df4b63a45d95a87588546a7a2355f0a9ae86 Mon Sep 17 00:00:00 2001
From: Hanqing Zhao <sherry9277@gmail.com>
Date: Thu, 25 Jul 2024 18:55:16 +0800
Subject: [PATCH 14/60] Add french and jp translation for new feature (#6675)

---
 web/i18n/fr-FR/workflow.ts  | 48 +++++++++++++++++++++++++++++++++++++
 web/i18n/ja-JP/app-debug.ts |  2 +-
 web/i18n/ja-JP/workflow.ts  | 48 +++++++++++++++++++++++++++++++++++++
 web/i18n/vi-VN/app-debug.ts |  2 +-
 4 files changed, 98 insertions(+), 2 deletions(-)

diff --git a/web/i18n/fr-FR/workflow.ts b/web/i18n/fr-FR/workflow.ts
index e9cd1834fe..c4b97870d1 100644
--- a/web/i18n/fr-FR/workflow.ts
+++ b/web/i18n/fr-FR/workflow.ts
@@ -69,6 +69,35 @@ const translation = {
     manageInTools: 'Gérer dans les outils',
     workflowAsToolTip: 'Reconfiguration de l\'outil requise après la mise à jour du flux de travail.',
     viewDetailInTracingPanel: 'Voir les détails',
+    syncingData: 'Synchroniser des données en quelques secondes.',
+    importDSL: 'Importe DSL',
+    importDSLTip: 'Le projet actuel sera écrasé. Exporter le flux de travail en tant que sauvegarde avant d\'importer.',
+    backupCurrentDraft: 'Sauvegarder le projet actuel',
+    chooseDSL: 'Choisir le fichier DSL(yml)',
+    overwriteAndImport: 'Écraser et importer',
+    importFailure: 'Echec de l\'importation',
+    importSuccess: 'Import avec succès',
+  },
+  env: {
+    envPanelTitle: 'Variables d\'Environnement',
+    envDescription: 'Les variables d\'environnement peuvent être utilisées pour stocker des informations privées et des informations d\'identification. Elles sont en lecture seule et peuvent être séparées du fichier DSL lors de l\'exportation.',
+    envPanelButton: 'Ajouter Variable',
+    modal: {
+      title: 'Ajouter Variables d\'Environnement',
+      editTitle: 'Editer titre',
+      type: 'Type',
+      name: 'Nom',
+      namePlaceholder: 'Nom de l\'env',
+      value: 'valeur',
+      valuePlaceholder: 'Valeur de l\'env',
+      secretTip: 'Utilisé pour définir des informations ou des données sensibles, avec des paramètres DSL configurés pour la prévention des fuites.',
+    },
+    export: {
+      title: 'Exporter des variables d\'environnement secrètes?',
+      checkbox: 'Exporter les valeurs secrètes',
+      ignore: 'Exporter DSL',
+      export: 'Exporter les DSL avec des valeurs secrètes',
+    },
   },
   changeHistory: {
     title: 'Historique des modifications',
@@ -440,6 +469,25 @@ const translation = {
       iteration_other: '{{count}} Itérations',
       currentIteration: 'Itération actuelle',
     },
+    note: {
+      addNote: 'Ajouter note',
+      editor: {
+        placeholder: 'Redigez votre note...',
+        small: 'Petit',
+        medium: 'Moyen',
+        large: 'Grand',
+        bold: 'Gras',
+        italic: 'Italique',
+        strikethrough: 'Barré',
+        link: 'Lien',
+        openLink: 'Ouvrir',
+        unlink: 'Annuler le lien',
+        enterUrl: 'Entrer l\'URL...',
+        invalidUrl: 'URL invalide',
+        bulletList: 'Liste à puces',
+        showAuthor: 'Afficher l\'auteur',
+      },
+    },
   },
   tracing: {
     stopBy: 'Arrêté par {{user}}',
diff --git a/web/i18n/ja-JP/app-debug.ts b/web/i18n/ja-JP/app-debug.ts
index bb0d2422e6..e38922ea10 100644
--- a/web/i18n/ja-JP/app-debug.ts
+++ b/web/i18n/ja-JP/app-debug.ts
@@ -3,7 +3,7 @@ const translation = {
     line1: 'プロンプト',
     line2: 'エンジニアリング',
   },
-  orchestrate: 'Orchestrate',
+  orchestrate: 'オーケストレーション',
   promptMode: {
     simple: 'エキスパートモードに切り替えて、PROMPT全体を編集します',
     advanced: 'エキスパートモード',
diff --git a/web/i18n/ja-JP/workflow.ts b/web/i18n/ja-JP/workflow.ts
index b757251af9..cb75516bc5 100644
--- a/web/i18n/ja-JP/workflow.ts
+++ b/web/i18n/ja-JP/workflow.ts
@@ -69,6 +69,35 @@ const translation = {
     manageInTools: 'ツールで管理',
     workflowAsToolTip: 'ワークフローの更新後、ツールの再設定が必要です。',
     viewDetailInTracingPanel: '詳細を表示',
+    syncingData: 'データを同期中，数秒程度で終わります。',
+    importDSL: 'DSLをインポート',
+    importDSLTip: '現在のドラフトは上書きされますので、インポートする際は、事前にワークフローをバックアップとしてエクスポートいただきますよう、お願い申し上げます。',
+    backupCurrentDraft: '現在のドラフトをバックアップ',
+    chooseDSL: 'DSL(yml)ファイルを選択',
+    overwriteAndImport: 'オーバライトとインポート',
+    importFailure: 'インポート失敗',
+    importSuccess: 'インポート成功',
+  },
+  env: {
+    envPanelTitle: '環境変数',
+    envDescription: '環境変数は、個人情報や認証情報を格納するために使用することができます。これらは読み取り専用であり、DSLファイルからエクスポートする際には分離されます。',
+    envPanelButton: '環境変数を追加',
+    modal: {
+      title: '環境変数を追加',
+      editTitle: '環境変数を編集',
+      type: 'タイプ',
+      name: '名前',
+      namePlaceholder: '変数名',
+      value: '値',
+      valuePlaceholder: '変数値',
+      secretTip: 'このような機密情報やデータは、定義に使用され、DSLの設定は情報漏洩を防ぐために特別に構成されています。',
+    },
+    export: {
+      title: 'シークレット環境変数をエクスポートしますか？',
+      checkbox: 'シクレート値をエクスポート',
+      ignore: 'DSLをエクスポート',
+      export: 'シクレート値を含むDSLをエクスポート',
+    },
   },
   changeHistory: {
     title: '変更履歴',
@@ -441,6 +470,25 @@ const translation = {
       iteration_other: '{{count}} イテレーション',
       currentIteration: '現在のイテレーション',
     },
+    note: {
+      addNote: 'コメントを追加',
+      editor: {
+        placeholder: 'メモを書く...',
+        small: '小',
+        medium: '中',
+        large: '大',
+        bold: '太字',
+        italic: '斜体',
+        strikethrough: '打ち消し線',
+        link: 'リンク',
+        openLink: '開く',
+        unlink: 'リンクをキャンセル',
+        enterUrl: 'リンク入力中...',
+        invalidUrl: 'リンク無効',
+        bulletList: 'リスト',
+        showAuthor: '著者を表示する',
+      },
+    },
   },
   tracing: {
     stopBy: '{{user}}によって停止',
diff --git a/web/i18n/vi-VN/app-debug.ts b/web/i18n/vi-VN/app-debug.ts
index ac8fe4b9f7..327c1f0ad2 100644
--- a/web/i18n/vi-VN/app-debug.ts
+++ b/web/i18n/vi-VN/app-debug.ts
@@ -3,7 +3,7 @@ const translation = {
     line1: 'PROMPT',
     line2: 'Engineering',
   },
-  orchestrate: 'Orchestrate',
+  orchestrate: 'Dàn nhạc',
   promptMode: {
     simple: 'Chuyển sang Chế độ Chuyên gia để chỉnh sửa toàn bộ PROMPT',
     advanced: 'Chế độ Chuyên gia',

From 78a339a7945e3ec642e5a935d01c6c0a69535b18 Mon Sep 17 00:00:00 2001
From: RookieAgent <42060616+Sakura4036@users.noreply.github.com>
Date: Thu, 25 Jul 2024 18:58:55 +0800
Subject: [PATCH 15/60] modify llama3-1 yaml filename to  support Windows pull
 operations (#6677)

---
 ...0b-instruct-v1:0.yaml => meta.llama3-1-70b-instruct-v1.0.yaml} | 0
 ...-8b-instruct-v1:0.yaml => meta.llama3-1-8b-instruct-v1.0.yaml} | 0
 2 files changed, 0 insertions(+), 0 deletions(-)
 rename api/core/model_runtime/model_providers/bedrock/llm/{meta.llama3-1-70b-instruct-v1:0.yaml => meta.llama3-1-70b-instruct-v1.0.yaml} (100%)
 rename api/core/model_runtime/model_providers/bedrock/llm/{meta.llama3-1-8b-instruct-v1:0.yaml => meta.llama3-1-8b-instruct-v1.0.yaml} (100%)

diff --git a/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-70b-instruct-v1:0.yaml b/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-70b-instruct-v1.0.yaml
similarity index 100%
rename from api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-70b-instruct-v1:0.yaml
rename to api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-70b-instruct-v1.0.yaml
diff --git a/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-8b-instruct-v1:0.yaml b/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-8b-instruct-v1.0.yaml
similarity index 100%
rename from api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-8b-instruct-v1:0.yaml
rename to api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-8b-instruct-v1.0.yaml

From 5fbfa0f2c85fee4bb740479759f70e2c9b9931fb Mon Sep 17 00:00:00 2001
From: crazywoola <100913391+crazywoola@users.noreply.github.com>
Date: Thu, 25 Jul 2024 18:59:04 +0800
Subject: [PATCH 16/60] Update bug_report.yml (#6678)

---
 .github/ISSUE_TEMPLATE/bug_report.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml
index 8824c5dba6..cf4fce3700 100644
--- a/.github/ISSUE_TEMPLATE/bug_report.yml
+++ b/.github/ISSUE_TEMPLATE/bug_report.yml
@@ -22,7 +22,7 @@ body:
   - type: input
     attributes:
       label: Dify version
-      placeholder: 0.6.11
+      placeholder: 0.6.15
       description: See about section in Dify console
     validations:
       required: true

From c5ac004f1580ca3e2b59b895e87ca091f9a5f3cf Mon Sep 17 00:00:00 2001
From: longzhihun <38651850@qq.com>
Date: Thu, 25 Jul 2024 19:26:46 +0800
Subject: [PATCH 17/60] [seanguo] fix: unsupported filename in windows & add
 Mistral Large 2 (#6679)

---
 .../bedrock/llm/_position.yaml                |  1 +
 .../llm/mistral.mistral-large-2407-v1.0.yaml  | 29 +++++++++++++++++++
 2 files changed, 30 insertions(+)
 create mode 100644 api/core/model_runtime/model_providers/bedrock/llm/mistral.mistral-large-2407-v1.0.yaml

diff --git a/api/core/model_runtime/model_providers/bedrock/llm/_position.yaml b/api/core/model_runtime/model_providers/bedrock/llm/_position.yaml
index 6789a79987..c523596b57 100644
--- a/api/core/model_runtime/model_providers/bedrock/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/llm/_position.yaml
@@ -16,6 +16,7 @@
 - meta.llama3-70b-instruct-v1:0
 - meta.llama2-13b-chat-v1
 - meta.llama2-70b-chat-v1
+- mistral.mistral-large-2407-v1:0
 - mistral.mistral-small-2402-v1:0
 - mistral.mistral-large-2402-v1:0
 - mistral.mixtral-8x7b-instruct-v0:1
diff --git a/api/core/model_runtime/model_providers/bedrock/llm/mistral.mistral-large-2407-v1.0.yaml b/api/core/model_runtime/model_providers/bedrock/llm/mistral.mistral-large-2407-v1.0.yaml
new file mode 100644
index 0000000000..19d7843a57
--- /dev/null
+++ b/api/core/model_runtime/model_providers/bedrock/llm/mistral.mistral-large-2407-v1.0.yaml
@@ -0,0 +1,29 @@
+model: mistral.mistral-large-2407-v1:0
+label:
+  en_US: Mistral Large 2 (24.07)
+model_type: llm
+features:
+  - tool-call
+model_properties:
+  mode: completion
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    required: false
+    default: 0.7
+  - name: top_p
+    use_template: top_p
+    required: false
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 8192
+pricing:
+  input: '0.003'
+  output: '0.009'
+  unit: '0.001'
+  currency: USD

From 79cb23e8ac2224e381942e4a3fd3c5c468858850 Mon Sep 17 00:00:00 2001
From: Yeuoly <45712896+Yeuoly@users.noreply.github.com>
Date: Thu, 25 Jul 2024 20:50:26 +0800
Subject: [PATCH 18/60] security/SSRF vulns (#6682)

---
 api/core/helper/ssrf_proxy.py               |  7 +++--
 api/core/rag/extractor/extract_processor.py |  5 ++--
 api/core/tools/utils/web_reader_tool.py     | 29 +++++----------------
 3 files changed, 13 insertions(+), 28 deletions(-)

diff --git a/api/core/helper/ssrf_proxy.py b/api/core/helper/ssrf_proxy.py
index 63cf548ae4..14ca8e943c 100644
--- a/api/core/helper/ssrf_proxy.py
+++ b/api/core/helper/ssrf_proxy.py
@@ -17,12 +17,15 @@ proxies = {
     'https://': SSRF_PROXY_HTTPS_URL
 } if SSRF_PROXY_HTTP_URL and SSRF_PROXY_HTTPS_URL else None
 
-
 BACKOFF_FACTOR = 0.5
 STATUS_FORCELIST = [429, 500, 502, 503, 504]
 
-
 def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
+    if "allow_redirects" in kwargs:
+        allow_redirects = kwargs.pop("allow_redirects")
+        if "follow_redirects" not in kwargs:
+            kwargs["follow_redirects"] = allow_redirects
+    
     retries = 0
     while retries <= max_retries:
         try:
diff --git a/api/core/rag/extractor/extract_processor.py b/api/core/rag/extractor/extract_processor.py
index d01cf48fac..f7a08135f5 100644
--- a/api/core/rag/extractor/extract_processor.py
+++ b/api/core/rag/extractor/extract_processor.py
@@ -4,9 +4,8 @@ from pathlib import Path
 from typing import Union
 from urllib.parse import unquote
 
-import requests
-
 from configs import dify_config
+from core.helper import ssrf_proxy
 from core.rag.extractor.csv_extractor import CSVExtractor
 from core.rag.extractor.entity.datasource_type import DatasourceType
 from core.rag.extractor.entity.extract_setting import ExtractSetting
@@ -51,7 +50,7 @@ class ExtractProcessor:
 
     @classmethod
     def load_from_url(cls, url: str, return_text: bool = False) -> Union[list[Document], str]:
-        response = requests.get(url, headers={
+        response = ssrf_proxy.get(url, headers={
             "User-Agent": USER_AGENT
         })
 
diff --git a/api/core/tools/utils/web_reader_tool.py b/api/core/tools/utils/web_reader_tool.py
index e52082541a..f6f04271d6 100644
--- a/api/core/tools/utils/web_reader_tool.py
+++ b/api/core/tools/utils/web_reader_tool.py
@@ -11,11 +11,10 @@ from contextlib import contextmanager
 from urllib.parse import unquote
 
 import cloudscraper
-import requests
 from bs4 import BeautifulSoup, CData, Comment, NavigableString
-from newspaper import Article
 from regex import regex
 
+from core.helper import ssrf_proxy
 from core.rag.extractor import extract_processor
 from core.rag.extractor.extract_processor import ExtractProcessor
 
@@ -45,7 +44,7 @@ def get_url(url: str, user_agent: str = None) -> str:
 
     main_content_type = None
     supported_content_types = extract_processor.SUPPORT_URL_CONTENT_TYPES + ["text/html"]
-    response = requests.head(url, headers=headers, allow_redirects=True, timeout=(5, 10))
+    response = ssrf_proxy.head(url, headers=headers, follow_redirects=True, timeout=(5, 10))
 
     if response.status_code == 200:
         # check content-type
@@ -67,10 +66,11 @@ def get_url(url: str, user_agent: str = None) -> str:
         if main_content_type in extract_processor.SUPPORT_URL_CONTENT_TYPES:
             return ExtractProcessor.load_from_url(url, return_text=True)
 
-        response = requests.get(url, headers=headers, allow_redirects=True, timeout=(120, 300))
+        response = ssrf_proxy.get(url, headers=headers, follow_redirects=True, timeout=(120, 300))
     elif response.status_code == 403:
         scraper = cloudscraper.create_scraper()
-        response = scraper.get(url, headers=headers, allow_redirects=True, timeout=(120, 300))
+        scraper.perform_request = ssrf_proxy.make_request
+        response = scraper.get(url, headers=headers, follow_redirects=True, timeout=(120, 300))
 
     if response.status_code != 200:
         return "URL returned status code {}.".format(response.status_code)
@@ -78,7 +78,7 @@ def get_url(url: str, user_agent: str = None) -> str:
     a = extract_using_readabilipy(response.text)
 
     if not a['plain_text'] or not a['plain_text'].strip():
-        return get_url_from_newspaper3k(url)
+        return ''
 
     res = FULL_TEMPLATE.format(
         title=a['title'],
@@ -91,23 +91,6 @@ def get_url(url: str, user_agent: str = None) -> str:
     return res
 
 
-def get_url_from_newspaper3k(url: str) -> str:
-
-    a = Article(url)
-    a.download()
-    a.parse()
-
-    res = FULL_TEMPLATE.format(
-        title=a.title,
-        authors=a.authors,
-        publish_date=a.publish_date,
-        top_image=a.top_image,
-        text=a.text,
-    )
-
-    return res
-
-
 def extract_using_readabilipy(html):
     with tempfile.NamedTemporaryFile(delete=False, mode='w+') as f_html:
         f_html.write(html)

From bd97ce94895facb59cec14ba398fa8ec10270a46 Mon Sep 17 00:00:00 2001
From: crazywoola <100913391+crazywoola@users.noreply.github.com>
Date: Fri, 26 Jul 2024 09:14:08 +0800
Subject: [PATCH 19/60] fix: doc link in knowledge base (#6691)

---
 .../datasets/(datasetDetailLayout)/[datasetId]/layout.tsx     | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/web/app/(commonLayout)/datasets/(datasetDetailLayout)/[datasetId]/layout.tsx b/web/app/(commonLayout)/datasets/(datasetDetailLayout)/[datasetId]/layout.tsx
index a1543230a9..11893ec9de 100644
--- a/web/app/(commonLayout)/datasets/(datasetDetailLayout)/[datasetId]/layout.tsx
+++ b/web/app/(commonLayout)/datasets/(datasetDetailLayout)/[datasetId]/layout.tsx
@@ -166,8 +166,8 @@ const ExtraInfo = ({ isMobile, relatedApps }: IExtraInfoProps) => {
             className='inline-flex items-center text-xs text-primary-600 mt-2 cursor-pointer'
             href={
               locale === LanguagesSupported[1]
-                ? 'https://docs.dify.ai/v/zh-hans/guides/application-design/prompt-engineering'
-                : 'https://docs.dify.ai/user-guide/creating-dify-apps/prompt-engineering'
+                ? 'https://docs.dify.ai/v/zh-hans/guides/knowledge-base/integrate_knowledge_within_application'
+                : 'https://docs.dify.ai/guides/knowledge-base/integrate-knowledge-within-application'
             }
             target='_blank' rel='noopener noreferrer'
           >

From ecb9c311b5596c0ebd9cb37fbf28bd32ddc3cbf6 Mon Sep 17 00:00:00 2001
From: Sangmin Ahn <gijigae@gmail.com>
Date: Fri, 26 Jul 2024 11:20:23 +0900
Subject: [PATCH 20/60] chore: make prompt generator max tokens configurable
 (#6693)

---
 api/.env.example                         | 1 +
 api/controllers/console/app/generator.py | 6 +++++-
 api/core/llm_generator/llm_generator.py  | 4 ++--
 3 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/api/.env.example b/api/.env.example
index 80ef185e51..cf3a0f302d 100644
--- a/api/.env.example
+++ b/api/.env.example
@@ -183,6 +183,7 @@ UPLOAD_IMAGE_FILE_SIZE_LIMIT=10
 
 # Model Configuration
 MULTIMODAL_SEND_IMAGE_FORMAT=base64
+PROMPT_GENERATION_MAX_TOKENS=512
 
 # Mail configuration, support: resend, smtp
 MAIL_TYPE=
diff --git a/api/controllers/console/app/generator.py b/api/controllers/console/app/generator.py
index 4e228a70ff..6803775e20 100644
--- a/api/controllers/console/app/generator.py
+++ b/api/controllers/console/app/generator.py
@@ -1,3 +1,5 @@
+import os
+
 from flask_login import current_user
 from flask_restful import Resource, reqparse
 
@@ -28,13 +30,15 @@ class RuleGenerateApi(Resource):
         args = parser.parse_args()
 
         account = current_user
+        PROMPT_GENERATION_MAX_TOKENS = int(os.getenv('PROMPT_GENERATION_MAX_TOKENS', '512'))
 
         try:
             rules = LLMGenerator.generate_rule_config(
                 tenant_id=account.current_tenant_id,
                 instruction=args['instruction'],
                 model_config=args['model_config'],
-                no_variable=args['no_variable']
+                no_variable=args['no_variable'],
+                rule_config_max_tokens=PROMPT_GENERATION_MAX_TOKENS
             )
         except ProviderTokenNotInitError as ex:
             raise ProviderNotInitializeError(ex.description)
diff --git a/api/core/llm_generator/llm_generator.py b/api/core/llm_generator/llm_generator.py
index d6a4399fc7..0b5029460a 100644
--- a/api/core/llm_generator/llm_generator.py
+++ b/api/core/llm_generator/llm_generator.py
@@ -118,7 +118,7 @@ class LLMGenerator:
         return questions
 
     @classmethod
-    def generate_rule_config(cls, tenant_id: str, instruction: str, model_config: dict, no_variable: bool) -> dict:
+    def generate_rule_config(cls, tenant_id: str, instruction: str, model_config: dict, no_variable: bool, rule_config_max_tokens: int = 512) -> dict:
         output_parser = RuleConfigGeneratorOutputParser()
 
         error = ""
@@ -130,7 +130,7 @@ class LLMGenerator:
             "error": ""
         }
         model_parameters = {
-            "max_tokens": 512,
+            "max_tokens": rule_config_max_tokens,
             "temperature": 0.01
         }
 

From 4839523e531299e954c5298eac899c8b311c8d04 Mon Sep 17 00:00:00 2001
From: KVOJJJin <jzongcode@gmail.com>
Date: Fri, 26 Jul 2024 11:21:51 +0800
Subject: [PATCH 21/60] Fix appId missing in annotations (#6699)

---
 web/app/components/app/log/list.tsx | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/web/app/components/app/log/list.tsx b/web/app/components/app/log/list.tsx
index edd4bf21e6..00d7ffb0fb 100644
--- a/web/app/components/app/log/list.tsx
+++ b/web/app/components/app/log/list.tsx
@@ -495,7 +495,7 @@ function DetailPanel<T extends ChatConversationFullDetailResponse | CompletionCo
             >
               <Chat
                 config={{
-                  app_id: appDetail?.id,
+                  appId: appDetail?.id,
                   text_to_speech: {
                     enabled: true,
                   },

From 6b50bb0fe61ff76fe7b3e4980279023eebd8bd37 Mon Sep 17 00:00:00 2001
From: chenxu9741 <chenxu9741@cvte.com>
Date: Fri, 26 Jul 2024 14:55:49 +0800
Subject: [PATCH 23/60] issues #6655   Open ai tts issues (#6696)

---
 api/core/model_runtime/model_providers/openai/tts/tts.py  | 3 ++-
 .../configuration/config-voice/param-config-content.tsx   | 8 +++++---
 .../features/chat-group/text-to-speech/index.tsx          | 1 +
 web/app/components/app/text-generate/item/index.tsx       | 6 ++++++
 web/app/components/base/audio-btn/audio.player.manager.ts | 2 +-
 web/app/components/base/audio-btn/audio.ts                | 5 ++---
 web/app/components/base/audio-btn/index.tsx               | 4 ++--
 web/app/components/base/chat/chat/answer/operation.tsx    | 1 +
 .../feature-panel/text-to-speech/param-config-content.tsx | 2 +-
 9 files changed, 21 insertions(+), 11 deletions(-)

diff --git a/api/core/model_runtime/model_providers/openai/tts/tts.py b/api/core/model_runtime/model_providers/openai/tts/tts.py
index 608ed897e0..d3fcf731f1 100644
--- a/api/core/model_runtime/model_providers/openai/tts/tts.py
+++ b/api/core/model_runtime/model_providers/openai/tts/tts.py
@@ -114,7 +114,8 @@ class OpenAIText2SpeechModel(_CommonOpenAI, TTSModel):
             # doc: https://platform.openai.com/docs/guides/text-to-speech
             credentials_kwargs = self._to_credential_kwargs(credentials)
             client = OpenAI(**credentials_kwargs)
-            if not voice or voice not in self.get_tts_model_voices(model=model, credentials=credentials):
+            model_support_voice = [x.get("value") for x in self.get_tts_model_voices(model=model, credentials=credentials)]
+            if not voice or voice not in model_support_voice:
                 voice = self._get_model_default_voice(model, credentials)
             word_limit = self._get_model_word_limit(model, credentials)
             if len(content_text) > word_limit:
diff --git a/web/app/components/app/configuration/config-voice/param-config-content.tsx b/web/app/components/app/configuration/config-voice/param-config-content.tsx
index cced3b0458..9b0d5bbb69 100644
--- a/web/app/components/app/configuration/config-voice/param-config-content.tsx
+++ b/web/app/components/app/configuration/config-voice/param-config-content.tsx
@@ -31,12 +31,12 @@ const VoiceParamConfig: FC = () => {
 
   let languageItem = languages.find(item => item.value === textToSpeechConfig.language)
   const localLanguagePlaceholder = languageItem?.name || t('common.placeholder.select')
-  if (languages && !languageItem)
+  if (languages && !languageItem && languages.length > 0)
     languageItem = languages[0]
   const language = languageItem?.value
   const voiceItems = useSWR({ appId, language }, fetchAppVoices).data
   let voiceItem = voiceItems?.find(item => item.value === textToSpeechConfig.voice)
-  if (voiceItems && !voiceItem)
+  if (voiceItems && !voiceItem && voiceItems.length > 0)
     voiceItem = voiceItems[0]
 
   const localVoicePlaceholder = voiceItem?.name || t('common.placeholder.select')
@@ -125,9 +125,11 @@ const VoiceParamConfig: FC = () => {
             <div
               className='mb-2 leading-[18px] text-[13px] font-semibold text-gray-800'>{t('appDebug.voice.voiceSettings.voice')}</div>
             <Listbox
-              value={voiceItem}
+              value={voiceItem ?? {}}
               disabled={!languageItem}
               onChange={(value: Item) => {
+                if (!value.value)
+                  return
                 setTextToSpeechConfig({
                   ...textToSpeechConfig,
                   voice: String(value.value),
diff --git a/web/app/components/app/configuration/features/chat-group/text-to-speech/index.tsx b/web/app/components/app/configuration/features/chat-group/text-to-speech/index.tsx
index 4c5db22513..72d617c3c3 100644
--- a/web/app/components/app/configuration/features/chat-group/text-to-speech/index.tsx
+++ b/web/app/components/app/configuration/features/chat-group/text-to-speech/index.tsx
@@ -41,6 +41,7 @@ const TextToSpeech: FC = () => {
             <AudioBtn
               value={languageInfo?.example}
               isAudition
+              voice={textToSpeechConfig.voice}
               noCache
             />
           )}
diff --git a/web/app/components/app/text-generate/item/index.tsx b/web/app/components/app/text-generate/item/index.tsx
index 3313c987c9..9794967d9d 100644
--- a/web/app/components/app/text-generate/item/index.tsx
+++ b/web/app/components/app/text-generate/item/index.tsx
@@ -29,6 +29,7 @@ import { useStore as useAppStore } from '@/app/components/app/store'
 import WorkflowProcessItem from '@/app/components/base/chat/chat/answer/workflow-process'
 import type { WorkflowProcess } from '@/app/components/base/chat/types'
 import type { SiteInfo } from '@/models/share'
+import { useChatContext } from '@/app/components/base/chat/chat/context'
 
 const MAX_DEPTH = 3
 
@@ -127,6 +128,10 @@ const GenerationItem: FC<IGenerationItemProps> = ({
   const [childFeedback, setChildFeedback] = useState<Feedbacktype>({
     rating: null,
   })
+  const {
+    config,
+  } = useChatContext()
+
   const setCurrentLogItem = useAppStore(s => s.setCurrentLogItem)
   const setShowPromptLogModal = useAppStore(s => s.setShowPromptLogModal)
 
@@ -430,6 +435,7 @@ const GenerationItem: FC<IGenerationItemProps> = ({
                     <AudioBtn
                       id={messageId!}
                       className={'mr-1'}
+                      voice={config?.text_to_speech?.voice}
                     />
                   </>
                 )}
diff --git a/web/app/components/base/audio-btn/audio.player.manager.ts b/web/app/components/base/audio-btn/audio.player.manager.ts
index 03e9e21f93..17d92f8dc2 100644
--- a/web/app/components/base/audio-btn/audio.player.manager.ts
+++ b/web/app/components/base/audio-btn/audio.player.manager.ts
@@ -41,7 +41,7 @@ export class AudioPlayerManager {
       }
 
       this.msgId = id
-      this.audioPlayers = new AudioPlayer(url, isPublic, id, msgContent, callback)
+      this.audioPlayers = new AudioPlayer(url, isPublic, id, msgContent, voice, callback)
       return this.audioPlayers
     }
   }
diff --git a/web/app/components/base/audio-btn/audio.ts b/web/app/components/base/audio-btn/audio.ts
index 638626bf8a..a61fd085d4 100644
--- a/web/app/components/base/audio-btn/audio.ts
+++ b/web/app/components/base/audio-btn/audio.ts
@@ -23,12 +23,13 @@ export default class AudioPlayer {
   isPublic: boolean
   callback: ((event: string) => {}) | null
 
-  constructor(streamUrl: string, isPublic: boolean, msgId: string | undefined, msgContent: string | null | undefined, callback: ((event: string) => {}) | null) {
+  constructor(streamUrl: string, isPublic: boolean, msgId: string | undefined, msgContent: string | null | undefined, voice: string | undefined, callback: ((event: string) => {}) | null) {
     this.audioContext = new AudioContext()
     this.msgId = msgId
     this.msgContent = msgContent
     this.url = streamUrl
     this.isPublic = isPublic
+    this.voice = voice
     this.callback = callback
 
     // Compatible with iphone ios17 ManagedMediaSource
@@ -154,7 +155,6 @@ export default class AudioPlayer {
         this.mediaSource?.endOfStream()
         clearInterval(endTimer)
       }
-      console.log('finishStream  endOfStream endTimer')
     }, 10)
   }
 
@@ -169,7 +169,6 @@ export default class AudioPlayer {
         const arrayBuffer = this.cacheBuffers.shift()!
         this.sourceBuffer?.appendBuffer(arrayBuffer)
       }
-      console.log('finishStream  timer')
     }, 10)
   }
 
diff --git a/web/app/components/base/audio-btn/index.tsx b/web/app/components/base/audio-btn/index.tsx
index 48081c170c..675f58b530 100644
--- a/web/app/components/base/audio-btn/index.tsx
+++ b/web/app/components/base/audio-btn/index.tsx
@@ -65,11 +65,11 @@ const AudioBtn = ({
   }
   const handleToggle = async () => {
     if (audioState === 'playing' || audioState === 'loading') {
-      setAudioState('paused')
+      setTimeout(() => setAudioState('paused'), 1)
       AudioPlayerManager.getInstance().getAudioPlayer(url, isPublic, id, value, voice, audio_finished_call).pauseAudio()
     }
     else {
-      setAudioState('loading')
+      setTimeout(() => setAudioState('loading'), 1)
       AudioPlayerManager.getInstance().getAudioPlayer(url, isPublic, id, value, voice, audio_finished_call).playAudio()
     }
   }
diff --git a/web/app/components/base/chat/chat/answer/operation.tsx b/web/app/components/base/chat/chat/answer/operation.tsx
index d46aa34375..3d52477d0b 100644
--- a/web/app/components/base/chat/chat/answer/operation.tsx
+++ b/web/app/components/base/chat/chat/answer/operation.tsx
@@ -125,6 +125,7 @@ const Operation: FC<OperationProps> = ({
                   id={id}
                   value={content}
                   noCache={false}
+                  voice={config?.text_to_speech?.voice}
                   className='hidden group-hover:block'
                 />
               </>
diff --git a/web/app/components/base/features/feature-panel/text-to-speech/param-config-content.tsx b/web/app/components/base/features/feature-panel/text-to-speech/param-config-content.tsx
index ea1d789d0a..a5a2eb7bb7 100644
--- a/web/app/components/base/features/feature-panel/text-to-speech/param-config-content.tsx
+++ b/web/app/components/base/features/feature-panel/text-to-speech/param-config-content.tsx
@@ -149,7 +149,7 @@ const VoiceParamConfig = ({
             <div
               className='mb-2 leading-[18px] text-[13px] font-semibold text-gray-800'>{t('appDebug.voice.voiceSettings.voice')}</div>
             <Listbox
-              value={voiceItem}
+              value={voiceItem ?? {}}
               disabled={!languageItem}
               onChange={(value: Item) => {
                 handleChange({

From c6996a48a45a79b3dfa719fa0402de1662a9c0a3 Mon Sep 17 00:00:00 2001
From: -LAN- <laipz8200@outlook.com>
Date: Fri, 26 Jul 2024 15:03:56 +0800
Subject: [PATCH 24/60] refactor(api/core/app/segments): Support more kinds of
 Segments. (#6706)

Signed-off-by: -LAN- <laipz8200@outlook.com>
---
 api/core/app/segments/__init__.py             | 17 ++++-
 api/core/app/segments/factory.py              | 53 +++++++-------
 api/core/app/segments/parser.py               |  5 +-
 api/core/app/segments/segment_group.py        | 17 +++--
 api/core/app/segments/segments.py             | 58 ++++++++++++++++
 api/core/app/segments/types.py                |  2 +
 api/core/app/segments/variables.py            | 69 ++++++-------------
 api/core/workflow/entities/variable_pool.py   | 12 ++--
 api/core/workflow/nodes/tool/tool_node.py     |  1 +
 .../unit_tests/{ => core}/app/test_segment.py |  0
 .../{ => core}/app/test_variables.py          |  9 +--
 11 files changed, 147 insertions(+), 96 deletions(-)
 rename api/tests/unit_tests/{ => core}/app/test_segment.py (100%)
 rename api/tests/unit_tests/{ => core}/app/test_variables.py (96%)

diff --git a/api/core/app/segments/__init__.py b/api/core/app/segments/__init__.py
index 0179d28887..b5d36bff3b 100644
--- a/api/core/app/segments/__init__.py
+++ b/api/core/app/segments/__init__.py
@@ -1,5 +1,14 @@
 from .segment_group import SegmentGroup
-from .segments import NoneSegment, Segment
+from .segments import (
+    ArraySegment,
+    FileSegment,
+    FloatSegment,
+    IntegerSegment,
+    NoneSegment,
+    ObjectSegment,
+    Segment,
+    StringSegment,
+)
 from .types import SegmentType
 from .variables import (
     ArrayVariable,
@@ -27,4 +36,10 @@ __all__ = [
     'Segment',
     'NoneSegment',
     'NoneVariable',
+    'IntegerSegment',
+    'FloatSegment',
+    'ObjectSegment',
+    'ArraySegment',
+    'FileSegment',
+    'StringSegment',
 ]
diff --git a/api/core/app/segments/factory.py b/api/core/app/segments/factory.py
index 187042ec03..8e77b43bb7 100644
--- a/api/core/app/segments/factory.py
+++ b/api/core/app/segments/factory.py
@@ -3,15 +3,20 @@ from typing import Any
 
 from core.file.file_obj import FileVar
 
-from .segments import Segment, StringSegment
+from .segments import (
+    ArraySegment,
+    FileSegment,
+    FloatSegment,
+    IntegerSegment,
+    NoneSegment,
+    ObjectSegment,
+    Segment,
+    StringSegment,
+)
 from .types import SegmentType
 from .variables import (
-    ArrayVariable,
-    FileVariable,
     FloatVariable,
     IntegerVariable,
-    NoneVariable,
-    ObjectVariable,
     SecretVariable,
     StringVariable,
     Variable,
@@ -39,29 +44,23 @@ def build_variable_from_mapping(m: Mapping[str, Any], /) -> Variable:
     raise ValueError(f'not supported value type {value_type}')
 
 
-def build_anonymous_variable(value: Any, /) -> Variable:
-    if value is None:
-        return NoneVariable(name='anonymous')
-    if isinstance(value, str):
-        return StringVariable(name='anonymous', value=value)
-    if isinstance(value, int):
-        return IntegerVariable(name='anonymous', value=value)
-    if isinstance(value, float):
-        return FloatVariable(name='anonymous', value=value)
-    if isinstance(value, dict):
-        # TODO: Limit the depth of the object
-        obj = {k: build_anonymous_variable(v) for k, v in value.items()}
-        return ObjectVariable(name='anonymous', value=obj)
-    if isinstance(value, list):
-        # TODO: Limit the depth of the array
-        elements = [build_anonymous_variable(v) for v in value]
-        return ArrayVariable(name='anonymous', value=elements)
-    if isinstance(value, FileVar):
-        return FileVariable(name='anonymous', value=value)
-    raise ValueError(f'not supported value {value}')
-
-
 def build_segment(value: Any, /) -> Segment:
+    if value is None:
+        return NoneSegment()
     if isinstance(value, str):
         return StringSegment(value=value)
+    if isinstance(value, int):
+        return IntegerSegment(value=value)
+    if isinstance(value, float):
+        return FloatSegment(value=value)
+    if isinstance(value, dict):
+        # TODO: Limit the depth of the object
+        obj = {k: build_segment(v) for k, v in value.items()}
+        return ObjectSegment(value=obj)
+    if isinstance(value, list):
+        # TODO: Limit the depth of the array
+        elements = [build_segment(v) for v in value]
+        return ArraySegment(value=elements)
+    if isinstance(value, FileVar):
+        return FileSegment(value=value)
     raise ValueError(f'not supported value {value}')
diff --git a/api/core/app/segments/parser.py b/api/core/app/segments/parser.py
index 21d1b89541..7061a4d878 100644
--- a/api/core/app/segments/parser.py
+++ b/api/core/app/segments/parser.py
@@ -1,8 +1,9 @@
 import re
 
-from core.app.segments import SegmentGroup, factory
 from core.workflow.entities.variable_pool import VariablePool
 
+from . import SegmentGroup, factory
+
 VARIABLE_PATTERN = re.compile(r'\{\{#([a-zA-Z0-9_]{1,50}(?:\.[a-zA-Z_][a-zA-Z0-9_]{0,29}){1,10})#\}\}')
 
 
@@ -14,4 +15,4 @@ def convert_template(*, template: str, variable_pool: VariablePool):
             segments.append(value)
         else:
             segments.append(factory.build_segment(part))
-    return SegmentGroup(segments=segments)
+    return SegmentGroup(value=segments)
diff --git a/api/core/app/segments/segment_group.py b/api/core/app/segments/segment_group.py
index 0d5176b885..b4ff09b6d3 100644
--- a/api/core/app/segments/segment_group.py
+++ b/api/core/app/segments/segment_group.py
@@ -1,19 +1,22 @@
-from pydantic import BaseModel
-
 from .segments import Segment
+from .types import SegmentType
 
 
-class SegmentGroup(BaseModel):
-    segments: list[Segment]
+class SegmentGroup(Segment):
+    value_type: SegmentType = SegmentType.GROUP
+    value: list[Segment]
 
     @property
     def text(self):
-        return ''.join([segment.text for segment in self.segments])
+        return ''.join([segment.text for segment in self.value])
 
     @property
     def log(self):
-        return ''.join([segment.log for segment in self.segments])
+        return ''.join([segment.log for segment in self.value])
 
     @property
     def markdown(self):
-        return ''.join([segment.markdown for segment in self.segments])
\ No newline at end of file
+        return ''.join([segment.markdown for segment in self.value])
+
+    def to_object(self):
+        return [segment.to_object() for segment in self.value]
diff --git a/api/core/app/segments/segments.py b/api/core/app/segments/segments.py
index afd383880f..f317054bc7 100644
--- a/api/core/app/segments/segments.py
+++ b/api/core/app/segments/segments.py
@@ -1,7 +1,11 @@
+import json
+from collections.abc import Mapping, Sequence
 from typing import Any
 
 from pydantic import BaseModel, ConfigDict, field_validator
 
+from core.file.file_obj import FileVar
+
 from .types import SegmentType
 
 
@@ -57,3 +61,57 @@ class NoneSegment(Segment):
 class StringSegment(Segment):
     value_type: SegmentType = SegmentType.STRING
     value: str
+
+class FloatSegment(Segment):
+    value_type: SegmentType = SegmentType.NUMBER
+    value: float
+
+
+class IntegerSegment(Segment):
+    value_type: SegmentType = SegmentType.NUMBER
+    value: int
+
+
+class ObjectSegment(Segment):
+    value_type: SegmentType = SegmentType.OBJECT
+    value: Mapping[str, Segment]
+
+    @property
+    def text(self) -> str:
+        # TODO: Process variables.
+        return json.dumps(self.model_dump()['value'], ensure_ascii=False)
+
+    @property
+    def log(self) -> str:
+        # TODO: Process variables.
+        return json.dumps(self.model_dump()['value'], ensure_ascii=False, indent=2)
+
+    @property
+    def markdown(self) -> str:
+        # TODO: Use markdown code block
+        return json.dumps(self.model_dump()['value'], ensure_ascii=False, indent=2)
+
+    def to_object(self):
+        return {k: v.to_object() for k, v in self.value.items()}
+
+
+class ArraySegment(Segment):
+    value_type: SegmentType = SegmentType.ARRAY
+    value: Sequence[Segment]
+
+    @property
+    def markdown(self) -> str:
+        return '\n'.join(['- ' + item.markdown for item in self.value])
+
+    def to_object(self):
+        return [v.to_object() for v in self.value]
+
+
+class FileSegment(Segment):
+    value_type: SegmentType = SegmentType.FILE
+    # TODO: embed FileVar in this model.
+    value: FileVar
+
+    @property
+    def markdown(self) -> str:
+        return self.value.to_markdown()
diff --git a/api/core/app/segments/types.py b/api/core/app/segments/types.py
index ebcbf507c6..133755bbc6 100644
--- a/api/core/app/segments/types.py
+++ b/api/core/app/segments/types.py
@@ -9,3 +9,5 @@ class SegmentType(str, Enum):
     ARRAY = 'array'
     OBJECT = 'object'
     FILE = 'file'
+
+    GROUP = 'group'
diff --git a/api/core/app/segments/variables.py b/api/core/app/segments/variables.py
index 5edaccc4d6..ba55022726 100644
--- a/api/core/app/segments/variables.py
+++ b/api/core/app/segments/variables.py
@@ -1,12 +1,18 @@
-import json
-from collections.abc import Mapping, Sequence
 
 from pydantic import Field
 
-from core.file.file_obj import FileVar
 from core.helper import encrypter
 
-from .segments import NoneSegment, Segment, StringSegment
+from .segments import (
+    ArraySegment,
+    FileSegment,
+    FloatSegment,
+    IntegerSegment,
+    NoneSegment,
+    ObjectSegment,
+    Segment,
+    StringSegment,
+)
 from .types import SegmentType
 
 
@@ -27,59 +33,24 @@ class StringVariable(StringSegment, Variable):
     pass
 
 
-class FloatVariable(Variable):
-    value_type: SegmentType = SegmentType.NUMBER
-    value: float
+class FloatVariable(FloatSegment, Variable):
+    pass
 
 
-class IntegerVariable(Variable):
-    value_type: SegmentType = SegmentType.NUMBER
-    value: int
+class IntegerVariable(IntegerSegment, Variable):
+    pass
 
 
-class ObjectVariable(Variable):
-    value_type: SegmentType = SegmentType.OBJECT
-    value: Mapping[str, Variable]
-
-    @property
-    def text(self) -> str:
-        # TODO: Process variables.
-        return json.dumps(self.model_dump()['value'], ensure_ascii=False)
-
-    @property
-    def log(self) -> str:
-        # TODO: Process variables.
-        return json.dumps(self.model_dump()['value'], ensure_ascii=False, indent=2)
-
-    @property
-    def markdown(self) -> str:
-        # TODO: Use markdown code block
-        return json.dumps(self.model_dump()['value'], ensure_ascii=False, indent=2)
-
-    def to_object(self):
-        return {k: v.to_object() for k, v in self.value.items()}
+class ObjectVariable(ObjectSegment, Variable):
+    pass
 
 
-class ArrayVariable(Variable):
-    value_type: SegmentType = SegmentType.ARRAY
-    value: Sequence[Variable]
-
-    @property
-    def markdown(self) -> str:
-        return '\n'.join(['- ' + item.markdown for item in self.value])
-
-    def to_object(self):
-        return [v.to_object() for v in self.value]
+class ArrayVariable(ArraySegment, Variable):
+    pass
 
 
-class FileVariable(Variable):
-    value_type: SegmentType = SegmentType.FILE
-    # TODO: embed FileVar in this model.
-    value: FileVar
-
-    @property
-    def markdown(self) -> str:
-        return self.value.to_markdown()
+class FileVariable(FileSegment, Variable):
+    pass
 
 
 class SecretVariable(StringVariable):
diff --git a/api/core/workflow/entities/variable_pool.py b/api/core/workflow/entities/variable_pool.py
index 480f5cce92..a27b4261e4 100644
--- a/api/core/workflow/entities/variable_pool.py
+++ b/api/core/workflow/entities/variable_pool.py
@@ -4,7 +4,7 @@ from typing import Any, Union
 
 from typing_extensions import deprecated
 
-from core.app.segments import Variable, factory
+from core.app.segments import Segment, Variable, factory
 from core.file.file_obj import FileVar
 from core.workflow.entities.node_entities import SystemVariable
 
@@ -33,7 +33,7 @@ class VariablePool:
         # The first element of the selector is the node id, it's the first-level key in the dictionary.
         # Other elements of the selector are the keys in the second-level dictionary. To get the key, we hash the
         # elements of the selector except the first one.
-        self._variable_dictionary: dict[str, dict[int, Variable]] = defaultdict(dict)
+        self._variable_dictionary: dict[str, dict[int, Segment]] = defaultdict(dict)
 
         # TODO: This user inputs is not used for pool.
         self.user_inputs = user_inputs
@@ -67,15 +67,15 @@ class VariablePool:
         if value is None:
             return
 
-        if not isinstance(value, Variable):
-            v = factory.build_anonymous_variable(value)
-        else:
+        if isinstance(value, Segment):
             v = value
+        else:
+            v = factory.build_segment(value)
 
         hash_key = hash(tuple(selector[1:]))
         self._variable_dictionary[selector[0]][hash_key] = v
 
-    def get(self, selector: Sequence[str], /) -> Variable | None:
+    def get(self, selector: Sequence[str], /) -> Segment | None:
         """
         Retrieves the value from the variable pool based on the given selector.
 
diff --git a/api/core/workflow/nodes/tool/tool_node.py b/api/core/workflow/nodes/tool/tool_node.py
index 238477117d..c03a17468a 100644
--- a/api/core/workflow/nodes/tool/tool_node.py
+++ b/api/core/workflow/nodes/tool/tool_node.py
@@ -126,6 +126,7 @@ class ToolNode(BaseNode):
             else:
                 tool_input = node_data.tool_parameters[parameter_name]
                 if tool_input.type == 'variable':
+                    # TODO: check if the variable exists in the variable pool
                     parameter_value = variable_pool.get(tool_input.value).value
                 else:
                     segment_group = parser.convert_template(
diff --git a/api/tests/unit_tests/app/test_segment.py b/api/tests/unit_tests/core/app/test_segment.py
similarity index 100%
rename from api/tests/unit_tests/app/test_segment.py
rename to api/tests/unit_tests/core/app/test_segment.py
diff --git a/api/tests/unit_tests/app/test_variables.py b/api/tests/unit_tests/core/app/test_variables.py
similarity index 96%
rename from api/tests/unit_tests/app/test_variables.py
rename to api/tests/unit_tests/core/app/test_variables.py
index 40872c8d53..afed29e3cb 100644
--- a/api/tests/unit_tests/app/test_variables.py
+++ b/api/tests/unit_tests/core/app/test_variables.py
@@ -5,7 +5,8 @@ from core.app.segments import (
     ArrayVariable,
     FloatVariable,
     IntegerVariable,
-    NoneVariable,
+    NoneSegment,
+    ObjectSegment,
     ObjectVariable,
     SecretVariable,
     SegmentType,
@@ -139,10 +140,10 @@ def test_variable_to_object():
 
 
 def test_build_a_object_variable_with_none_value():
-    var = factory.build_anonymous_variable(
+    var = factory.build_segment(
         {
             'key1': None,
         }
     )
-    assert isinstance(var, ObjectVariable)
-    assert isinstance(var.value['key1'], NoneVariable)
+    assert isinstance(var, ObjectSegment)
+    assert isinstance(var.value['key1'], NoneSegment)

From 427f48be6b1f67c66c65cb5b3e9f17fc51230783 Mon Sep 17 00:00:00 2001
From: Kevin9703 <51311316+Kevin9703@users.noreply.github.com>
Date: Fri, 26 Jul 2024 17:36:36 +0800
Subject: [PATCH 25/60] fix(answer/operation): feedback status in the logs
 (#6716)

---
 web/app/components/base/chat/chat/answer/operation.tsx | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/web/app/components/base/chat/chat/answer/operation.tsx b/web/app/components/base/chat/chat/answer/operation.tsx
index 3d52477d0b..8ec5c0f3b2 100644
--- a/web/app/components/base/chat/chat/answer/operation.tsx
+++ b/web/app/components/base/chat/chat/answer/operation.tsx
@@ -53,10 +53,11 @@ const Operation: FC<OperationProps> = ({
     content: messageContent,
     annotation,
     feedback,
+    adminFeedback,
     agent_thoughts,
   } = item
   const hasAnnotation = !!annotation?.id
-  const [localFeedback, setLocalFeedback] = useState(feedback)
+  const [localFeedback, setLocalFeedback] = useState(config?.supportAnnotation ? adminFeedback : feedback)
 
   const content = useMemo(() => {
     if (agent_thoughts?.length)

From 3d3677e9127a2a286fcba183858866a13b9ea3da Mon Sep 17 00:00:00 2001
From: Jason <ggbbddjm@gmail.com>
Date: Fri, 26 Jul 2024 17:37:21 +0800
Subject: [PATCH 26/60] Feat/model provider novita (#6717)

Co-authored-by: takatost <takatost@gmail.com>
---
 .../llm/Nous-Hermes-2-Mixtral-8x7B-DPO.yaml   |  5 +++
 .../novita/llm/airoboros-l2-70b.yaml          | 41 +++++++++++++++++++
 .../novita/llm/dolphin-mixtral-8x22b.yaml     | 41 +++++++++++++++++++
 .../novita/llm/gemma-2-9b-it.yaml             | 41 +++++++++++++++++++
 .../novita/llm/hermes-2-pro-llama-3-8b.yaml   | 41 +++++++++++++++++++
 .../novita/llm/l3-70b-euryale-v2.1.yaml       | 41 +++++++++++++++++++
 .../novita/llm/llama-3-70b-instruct.yaml      |  5 +++
 .../novita/llm/llama-3-8b-instruct.yaml       |  5 +++
 .../novita/llm/llama-3.1-405b-instruct.yaml   | 41 +++++++++++++++++++
 .../novita/llm/llama-3.1-70b-instruct.yaml    | 41 +++++++++++++++++++
 .../novita/llm/llama-3.1-8b-instruct.yaml     | 41 +++++++++++++++++++
 .../model_providers/novita/llm/lzlv_70b.yaml  |  5 +++
 .../novita/llm/midnight-rose-70b.yaml         | 41 +++++++++++++++++++
 .../novita/llm/mistral-7b-instruct.yaml       | 41 +++++++++++++++++++
 .../novita/llm/mythomax-l2-13b.yaml           |  5 +++
 .../novita/llm/nous-hermes-llama2-13b.yaml    |  5 +++
 .../novita/llm/openhermes-2.5-mistral-7b.yaml |  5 +++
 .../novita/llm/wizardlm-2-8x22b.yaml          |  5 +++
 .../model_providers/novita/novita.yaml        |  5 ++-
 19 files changed, 454 insertions(+), 1 deletion(-)
 create mode 100644 api/core/model_runtime/model_providers/novita/llm/airoboros-l2-70b.yaml
 create mode 100644 api/core/model_runtime/model_providers/novita/llm/dolphin-mixtral-8x22b.yaml
 create mode 100644 api/core/model_runtime/model_providers/novita/llm/gemma-2-9b-it.yaml
 create mode 100644 api/core/model_runtime/model_providers/novita/llm/hermes-2-pro-llama-3-8b.yaml
 create mode 100644 api/core/model_runtime/model_providers/novita/llm/l3-70b-euryale-v2.1.yaml
 create mode 100644 api/core/model_runtime/model_providers/novita/llm/llama-3.1-405b-instruct.yaml
 create mode 100644 api/core/model_runtime/model_providers/novita/llm/llama-3.1-70b-instruct.yaml
 create mode 100644 api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct.yaml
 create mode 100644 api/core/model_runtime/model_providers/novita/llm/midnight-rose-70b.yaml
 create mode 100644 api/core/model_runtime/model_providers/novita/llm/mistral-7b-instruct.yaml

diff --git a/api/core/model_runtime/model_providers/novita/llm/Nous-Hermes-2-Mixtral-8x7B-DPO.yaml b/api/core/model_runtime/model_providers/novita/llm/Nous-Hermes-2-Mixtral-8x7B-DPO.yaml
index 8b19316473..7ff30458e2 100644
--- a/api/core/model_runtime/model_providers/novita/llm/Nous-Hermes-2-Mixtral-8x7B-DPO.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/Nous-Hermes-2-Mixtral-8x7B-DPO.yaml
@@ -34,3 +34,8 @@ parameter_rules:
     min: -2
     max: 2
     default: 0
+pricing:
+  input: '0.0027'
+  output: '0.0027'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/airoboros-l2-70b.yaml b/api/core/model_runtime/model_providers/novita/llm/airoboros-l2-70b.yaml
new file mode 100644
index 0000000000..b599418461
--- /dev/null
+++ b/api/core/model_runtime/model_providers/novita/llm/airoboros-l2-70b.yaml
@@ -0,0 +1,41 @@
+model: jondurbin/airoboros-l2-70b
+label:
+  zh_Hans: jondurbin/airoboros-l2-70b
+  en_US: jondurbin/airoboros-l2-70b
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 4096
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.005'
+  output: '0.005'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/dolphin-mixtral-8x22b.yaml b/api/core/model_runtime/model_providers/novita/llm/dolphin-mixtral-8x22b.yaml
new file mode 100644
index 0000000000..72a181f5d3
--- /dev/null
+++ b/api/core/model_runtime/model_providers/novita/llm/dolphin-mixtral-8x22b.yaml
@@ -0,0 +1,41 @@
+model: cognitivecomputations/dolphin-mixtral-8x22b
+label:
+  zh_Hans: cognitivecomputations/dolphin-mixtral-8x22b
+  en_US: cognitivecomputations/dolphin-mixtral-8x22b
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 16000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.009'
+  output: '0.009'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/gemma-2-9b-it.yaml b/api/core/model_runtime/model_providers/novita/llm/gemma-2-9b-it.yaml
new file mode 100644
index 0000000000..d1749bc882
--- /dev/null
+++ b/api/core/model_runtime/model_providers/novita/llm/gemma-2-9b-it.yaml
@@ -0,0 +1,41 @@
+model: google/gemma-2-9b-it
+label:
+  zh_Hans: google/gemma-2-9b-it
+  en_US: google/gemma-2-9b-it
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.0008'
+  output: '0.0008'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/hermes-2-pro-llama-3-8b.yaml b/api/core/model_runtime/model_providers/novita/llm/hermes-2-pro-llama-3-8b.yaml
new file mode 100644
index 0000000000..8b3228e56a
--- /dev/null
+++ b/api/core/model_runtime/model_providers/novita/llm/hermes-2-pro-llama-3-8b.yaml
@@ -0,0 +1,41 @@
+model: nousresearch/hermes-2-pro-llama-3-8b
+label:
+  zh_Hans: nousresearch/hermes-2-pro-llama-3-8b
+  en_US: nousresearch/hermes-2-pro-llama-3-8b
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.0014'
+  output: '0.0014'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/l3-70b-euryale-v2.1.yaml b/api/core/model_runtime/model_providers/novita/llm/l3-70b-euryale-v2.1.yaml
new file mode 100644
index 0000000000..5e27941c52
--- /dev/null
+++ b/api/core/model_runtime/model_providers/novita/llm/l3-70b-euryale-v2.1.yaml
@@ -0,0 +1,41 @@
+model: sao10k/l3-70b-euryale-v2.1
+label:
+  zh_Hans: sao10k/l3-70b-euryale-v2.1
+  en_US: sao10k/l3-70b-euryale-v2.1
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 16000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.0148'
+  output: '0.0148'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/llama-3-70b-instruct.yaml b/api/core/model_runtime/model_providers/novita/llm/llama-3-70b-instruct.yaml
index 5298296de3..39709e1063 100644
--- a/api/core/model_runtime/model_providers/novita/llm/llama-3-70b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/llama-3-70b-instruct.yaml
@@ -34,3 +34,8 @@ parameter_rules:
     min: -2
     max: 2
     default: 0
+pricing:
+  input: '0.0051'
+  output: '0.0074'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/llama-3-8b-instruct.yaml b/api/core/model_runtime/model_providers/novita/llm/llama-3-8b-instruct.yaml
index 45e62ee52a..9b5e5df4d0 100644
--- a/api/core/model_runtime/model_providers/novita/llm/llama-3-8b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/llama-3-8b-instruct.yaml
@@ -34,3 +34,8 @@ parameter_rules:
     min: -2
     max: 2
     default: 0
+pricing:
+  input: '0.00063'
+  output: '0.00063'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/llama-3.1-405b-instruct.yaml b/api/core/model_runtime/model_providers/novita/llm/llama-3.1-405b-instruct.yaml
new file mode 100644
index 0000000000..c5a45271ae
--- /dev/null
+++ b/api/core/model_runtime/model_providers/novita/llm/llama-3.1-405b-instruct.yaml
@@ -0,0 +1,41 @@
+model: meta-llama/llama-3.1-405b-instruct
+label:
+  zh_Hans: meta-llama/llama-3.1-405b-instruct
+  en_US: meta-llama/llama-3.1-405b-instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.03'
+  output: '0.05'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/llama-3.1-70b-instruct.yaml b/api/core/model_runtime/model_providers/novita/llm/llama-3.1-70b-instruct.yaml
new file mode 100644
index 0000000000..3a5c29c40f
--- /dev/null
+++ b/api/core/model_runtime/model_providers/novita/llm/llama-3.1-70b-instruct.yaml
@@ -0,0 +1,41 @@
+model: meta-llama/llama-3.1-70b-instruct
+label:
+  zh_Hans: meta-llama/llama-3.1-70b-instruct
+  en_US: meta-llama/llama-3.1-70b-instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.0055'
+  output: '0.0076'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct.yaml b/api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct.yaml
new file mode 100644
index 0000000000..e6ef772a3f
--- /dev/null
+++ b/api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct.yaml
@@ -0,0 +1,41 @@
+model: meta-llama/llama-3.1-8b-instruct
+label:
+  zh_Hans: meta-llama/llama-3.1-8b-instruct
+  en_US: meta-llama/llama-3.1-8b-instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.001'
+  output: '0.001'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/lzlv_70b.yaml b/api/core/model_runtime/model_providers/novita/llm/lzlv_70b.yaml
index 0facc0c112..0cc68a8c45 100644
--- a/api/core/model_runtime/model_providers/novita/llm/lzlv_70b.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/lzlv_70b.yaml
@@ -34,3 +34,8 @@ parameter_rules:
     min: -2
     max: 2
     default: 0
+pricing:
+  input: '0.0058'
+  output: '0.0078'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/midnight-rose-70b.yaml b/api/core/model_runtime/model_providers/novita/llm/midnight-rose-70b.yaml
new file mode 100644
index 0000000000..19876bee17
--- /dev/null
+++ b/api/core/model_runtime/model_providers/novita/llm/midnight-rose-70b.yaml
@@ -0,0 +1,41 @@
+model: sophosympatheia/midnight-rose-70b
+label:
+  zh_Hans: sophosympatheia/midnight-rose-70b
+  en_US: sophosympatheia/midnight-rose-70b
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 4096
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.008'
+  output: '0.008'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/mistral-7b-instruct.yaml b/api/core/model_runtime/model_providers/novita/llm/mistral-7b-instruct.yaml
new file mode 100644
index 0000000000..6fba47bcf0
--- /dev/null
+++ b/api/core/model_runtime/model_providers/novita/llm/mistral-7b-instruct.yaml
@@ -0,0 +1,41 @@
+model: mistralai/mistral-7b-instruct
+label:
+  zh_Hans: mistralai/mistral-7b-instruct
+  en_US: mistralai/mistral-7b-instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 2
+    default: 1
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 2048
+    default: 512
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
+pricing:
+  input: '0.00059'
+  output: '0.00059'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/mythomax-l2-13b.yaml b/api/core/model_runtime/model_providers/novita/llm/mythomax-l2-13b.yaml
index 28a8630ff2..7e4ac3ffe0 100644
--- a/api/core/model_runtime/model_providers/novita/llm/mythomax-l2-13b.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/mythomax-l2-13b.yaml
@@ -34,3 +34,8 @@ parameter_rules:
     min: -2
     max: 2
     default: 0
+pricing:
+  input: '0.00119'
+  output: '0.00119'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/nous-hermes-llama2-13b.yaml b/api/core/model_runtime/model_providers/novita/llm/nous-hermes-llama2-13b.yaml
index ce714a118b..75671c414c 100644
--- a/api/core/model_runtime/model_providers/novita/llm/nous-hermes-llama2-13b.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/nous-hermes-llama2-13b.yaml
@@ -34,3 +34,8 @@ parameter_rules:
     min: -2
     max: 2
     default: 0
+pricing:
+  input: '0.0017'
+  output: '0.0017'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/openhermes-2.5-mistral-7b.yaml b/api/core/model_runtime/model_providers/novita/llm/openhermes-2.5-mistral-7b.yaml
index 6cef39f847..8b0deba4f7 100644
--- a/api/core/model_runtime/model_providers/novita/llm/openhermes-2.5-mistral-7b.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/openhermes-2.5-mistral-7b.yaml
@@ -34,3 +34,8 @@ parameter_rules:
     min: -2
     max: 2
     default: 0
+pricing:
+  input: '0.0017'
+  output: '0.0017'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/llm/wizardlm-2-8x22b.yaml b/api/core/model_runtime/model_providers/novita/llm/wizardlm-2-8x22b.yaml
index b3e3a03697..ef42568e8f 100644
--- a/api/core/model_runtime/model_providers/novita/llm/wizardlm-2-8x22b.yaml
+++ b/api/core/model_runtime/model_providers/novita/llm/wizardlm-2-8x22b.yaml
@@ -34,3 +34,8 @@ parameter_rules:
     min: -2
     max: 2
     default: 0
+pricing:
+  input: '0.0064'
+  output: '0.0064'
+  unit: '0.0001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/novita/novita.yaml b/api/core/model_runtime/model_providers/novita/novita.yaml
index ef6a863569..f634197989 100644
--- a/api/core/model_runtime/model_providers/novita/novita.yaml
+++ b/api/core/model_runtime/model_providers/novita/novita.yaml
@@ -1,6 +1,9 @@
 provider: novita
 label:
   en_US: novita.ai
+description:
+  en_US: An LLM API that matches various application scenarios with high cost-effectiveness.
+  zh_Hans: 适配多种海外应用场景的高性价比 LLM API
 icon_small:
   en_US: icon_s_en.svg
 icon_large:
@@ -11,7 +14,7 @@ help:
     en_US: Get your API key from novita.ai
     zh_Hans: 从 novita.ai 获取 API Key
   url:
-    en_US: https://novita.ai/dashboard/key?utm_source=dify
+    en_US: https://novita.ai/settings#key-management?utm_source=dify&utm_medium=ch&utm_campaign=api
 supported_model_types:
   - llm
 configurate_methods:

From e4542215ccc51d14e9e8b6f707a9dbbfd607a0aa Mon Sep 17 00:00:00 2001
From: Joe <79627742+ZhouhaoJiang@users.noreply.github.com>
Date: Fri, 26 Jul 2024 18:10:13 +0800
Subject: [PATCH 27/60] fix: tongyi empty tool_calls is not supported in
 message (#6719)

---
 api/core/model_runtime/model_providers/tongyi/llm/llm.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/api/core/model_runtime/model_providers/tongyi/llm/llm.py b/api/core/model_runtime/model_providers/tongyi/llm/llm.py
index 1f018c4078..6f768131fb 100644
--- a/api/core/model_runtime/model_providers/tongyi/llm/llm.py
+++ b/api/core/model_runtime/model_providers/tongyi/llm/llm.py
@@ -501,8 +501,7 @@ You should also complete the text started with ``` but not tell ``` directly.
                     'role': 'assistant',
                     'content': content if not rich_content else [{"text": content}],
                     'tool_calls': [tool_call.model_dump() for tool_call in
-                                   prompt_message.tool_calls] if prompt_message.tool_calls else []
-
+                                   prompt_message.tool_calls] if prompt_message.tool_calls else None
                 })
             elif isinstance(prompt_message, ToolPromptMessage):
                 tongyi_messages.append({

From 5d77dc4f582060f02dae0dd95aded60718062a20 Mon Sep 17 00:00:00 2001
From: -LAN- <laipz8200@outlook.com>
Date: Fri, 26 Jul 2024 18:19:33 +0800
Subject: [PATCH 28/60] feat(api/core/app/segments/parser.py): Remove blank
 segment in `convert_template` (#6709)

Signed-off-by: -LAN- <laipz8200@outlook.com>
---
 api/core/app/segments/parser.py               | 2 +-
 api/tests/unit_tests/core/app/test_segment.py | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/api/core/app/segments/parser.py b/api/core/app/segments/parser.py
index 7061a4d878..de6c796652 100644
--- a/api/core/app/segments/parser.py
+++ b/api/core/app/segments/parser.py
@@ -10,7 +10,7 @@ VARIABLE_PATTERN = re.compile(r'\{\{#([a-zA-Z0-9_]{1,50}(?:\.[a-zA-Z_][a-zA-Z0-9
 def convert_template(*, template: str, variable_pool: VariablePool):
     parts = re.split(VARIABLE_PATTERN, template)
     segments = []
-    for part in parts:
+    for part in filter(lambda x: x, parts):
         if '.' in part and (value := variable_pool.get(part.split('.'))):
             segments.append(value)
         else:
diff --git a/api/tests/unit_tests/core/app/test_segment.py b/api/tests/unit_tests/core/app/test_segment.py
index 7ef37ff646..414404b7d0 100644
--- a/api/tests/unit_tests/core/app/test_segment.py
+++ b/api/tests/unit_tests/core/app/test_segment.py
@@ -1,4 +1,4 @@
-from core.app.segments import SecretVariable, parser
+from core.app.segments import SecretVariable, StringSegment, parser
 from core.helper import encrypter
 from core.workflow.entities.node_entities import SystemVariable
 from core.workflow.entities.variable_pool import VariablePool
@@ -51,3 +51,4 @@ def test_convert_variable_to_segment_group():
     segments_group = parser.convert_template(template=template, variable_pool=variable_pool)
     assert segments_group.text == 'fake-user-id'
     assert segments_group.log == 'fake-user-id'
+    assert segments_group.value == [StringSegment(value='fake-user-id')]

From cf258b7a677d42ba83c739d7f7581ee79f5ac62c Mon Sep 17 00:00:00 2001
From: Jyong <76649700+JohnJyong@users.noreply.github.com>
Date: Fri, 26 Jul 2024 19:26:52 +0800
Subject: [PATCH 29/60] add xlsx support hyperlink extract (#6722)

---
 api/core/rag/extractor/excel_extractor.py | 51 ++++++++++++++++-------
 api/poetry.lock                           |  2 +-
 api/pyproject.toml                        |  1 +
 3 files changed, 39 insertions(+), 15 deletions(-)

diff --git a/api/core/rag/extractor/excel_extractor.py b/api/core/rag/extractor/excel_extractor.py
index 2b16275dc8..f0c302a619 100644
--- a/api/core/rag/extractor/excel_extractor.py
+++ b/api/core/rag/extractor/excel_extractor.py
@@ -3,6 +3,7 @@ import os
 from typing import Optional
 
 import pandas as pd
+from openpyxl import load_workbook
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document
@@ -28,26 +29,48 @@ class ExcelExtractor(BaseExtractor):
         self._autodetect_encoding = autodetect_encoding
 
     def extract(self) -> list[Document]:
-        """ Load from Excel file in xls or xlsx format using Pandas."""
+        """ Load from Excel file in xls or xlsx format using Pandas and openpyxl."""
         documents = []
-        # Determine the file extension
         file_extension = os.path.splitext(self._file_path)[-1].lower()
-        # Read each worksheet of an Excel file using Pandas
+
         if file_extension == '.xlsx':
-            excel_file = pd.ExcelFile(self._file_path, engine='openpyxl')
+            wb = load_workbook(self._file_path, data_only=True)
+            for sheet_name in wb.sheetnames:
+                sheet = wb[sheet_name]
+                data = sheet.values
+                cols = next(data)
+                df = pd.DataFrame(data, columns=cols)
+
+                df.dropna(how='all', inplace=True)
+
+                for index, row in df.iterrows():
+                    page_content = []
+                    for col_index, (k, v) in enumerate(row.items()):
+                        if pd.notna(v):
+                            cell = sheet.cell(row=index + 2,
+                                              column=col_index + 1)  # +2 to account for header and 1-based index
+                            if cell.hyperlink:
+                                value = f"[{v}]({cell.hyperlink.target})"
+                                page_content.append(f'"{k}":"{value}"')
+                            else:
+                                page_content.append(f'"{k}":"{v}"')
+                    documents.append(Document(page_content=';'.join(page_content),
+                                              metadata={'source': self._file_path}))
+
         elif file_extension == '.xls':
             excel_file = pd.ExcelFile(self._file_path, engine='xlrd')
+            for sheet_name in excel_file.sheet_names:
+                df = excel_file.parse(sheet_name=sheet_name)
+                df.dropna(how='all', inplace=True)
+
+                for _, row in df.iterrows():
+                    page_content = []
+                    for k, v in row.items():
+                        if pd.notna(v):
+                            page_content.append(f'"{k}":"{v}"')
+                    documents.append(Document(page_content=';'.join(page_content),
+                                              metadata={'source': self._file_path}))
         else:
             raise ValueError(f"Unsupported file extension: {file_extension}")
-        for sheet_name in excel_file.sheet_names:
-            df: pd.DataFrame = excel_file.parse(sheet_name=sheet_name)
-
-            # filter out rows with all NaN values
-            df.dropna(how='all', inplace=True)
-
-            # transform each row into a Document
-            documents += [Document(page_content=';'.join(f'"{k}":"{v}"' for k, v in row.items() if pd.notna(v)),
-                                   metadata={'source': self._file_path},
-                                   ) for _, row in df.iterrows()]
 
         return documents
diff --git a/api/poetry.lock b/api/poetry.lock
index 2a277dac2d..0abd2d2175 100644
--- a/api/poetry.lock
+++ b/api/poetry.lock
@@ -9543,4 +9543,4 @@ cffi = ["cffi (>=1.11)"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "6b7d8b1333ae9c71ba2e1c5800eecf1535ed3945cd55ebb1e253b7a29ba09559"
+content-hash = "9619ddabdd67710981c13dcfa3ddae0a48497c9f694afc81b820e882440c1265"
diff --git a/api/pyproject.toml b/api/pyproject.toml
index 7be3c7af64..430e3d79c4 100644
--- a/api/pyproject.toml
+++ b/api/pyproject.toml
@@ -177,6 +177,7 @@ xinference-client = "0.9.4"
 yarl = "~1.9.4"
 zhipuai = "1.0.7"
 rank-bm25 = "~0.2.2"
+openpyxl = "^3.1.5"
 ############################################################
 # Tool dependencies required by tool implementations
 ############################################################

From 83af50368f2367f6d8ee82f1e83e171fc36cc1f4 Mon Sep 17 00:00:00 2001
From: -LAN- <laipz8200@outlook.com>
Date: Sat, 27 Jul 2024 00:05:21 +0800
Subject: [PATCH 30/60] 
 fix(api/core/model_runtime/model_providers/azure_openai/llm/llm.py): Try to
 skip if `delta.delta` is None. (#6727)

Signed-off-by: -LAN- <laipz8200@outlook.com>
---
 .../model_runtime/model_providers/azure_openai/llm/llm.py     | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/api/core/model_runtime/model_providers/azure_openai/llm/llm.py b/api/core/model_runtime/model_providers/azure_openai/llm/llm.py
index 34d1f64210..1911caa952 100644
--- a/api/core/model_runtime/model_providers/azure_openai/llm/llm.py
+++ b/api/core/model_runtime/model_providers/azure_openai/llm/llm.py
@@ -375,6 +375,10 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
                 continue
 
             delta = chunk.choices[0]
+            # NOTE: For fix https://github.com/langgenius/dify/issues/5790
+            if delta.delta is None:
+                continue
+
 
             # extract tool calls from response
             self._update_tool_calls(tool_calls=tool_calls, tool_calls_response=delta.delta.tool_calls)

From 90d2c0121843243c3130f81cd9057f971b423e78 Mon Sep 17 00:00:00 2001
From: crazywoola <100913391+crazywoola@users.noreply.github.com>
Date: Sat, 27 Jul 2024 00:07:31 +0800
Subject: [PATCH 31/60] Feat/6725 can not get image url from cogview tool
 (#6728)

---
 api/core/tools/provider/builtin/cogview/tools/cogview3.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/api/core/tools/provider/builtin/cogview/tools/cogview3.py b/api/core/tools/provider/builtin/cogview/tools/cogview3.py
index bb2720196f..89ffcf3347 100644
--- a/api/core/tools/provider/builtin/cogview/tools/cogview3.py
+++ b/api/core/tools/provider/builtin/cogview/tools/cogview3.py
@@ -30,7 +30,6 @@ class CogView3Tool(BuiltinTool):
         if not prompt:
             return self.create_text_message('Please input prompt')
         # get size
-        print(tool_parameters.get('prompt', 'square'))
         size = size_mapping[tool_parameters.get('size', 'square')]
         # get n
         n = tool_parameters.get('n', 1)
@@ -58,8 +57,9 @@ class CogView3Tool(BuiltinTool):
         result = []
         for image in response.data:
             result.append(self.create_image_message(image=image.url))
-        result.append(self.create_text_message(
-            f'\nGenerate image source to Seed ID: {seed_id}'))
+            result.append(self.create_json_message({
+                "url": image.url,
+            }))
         return result
 
     @staticmethod

From b6c3010f025c834fb99f93d22fe376e33d6c91e5 Mon Sep 17 00:00:00 2001
From: -LAN- <laipz8200@outlook.com>
Date: Sat, 27 Jul 2024 14:43:25 +0800
Subject: [PATCH 32/60] refactor(api/core/workflow/nodes/base_node.py): Update
 extract_variable_selector_to_variable_mapping method signature. (#6733)

Signed-off-by: -LAN- <laipz8200@outlook.com>
---
 api/core/workflow/nodes/base_node.py         |  7 +++----
 api/core/workflow/workflow_engine_manager.py | 16 +++++++---------
 2 files changed, 10 insertions(+), 13 deletions(-)

diff --git a/api/core/workflow/nodes/base_node.py b/api/core/workflow/nodes/base_node.py
index b83a0ae19b..f42cee4ccd 100644
--- a/api/core/workflow/nodes/base_node.py
+++ b/api/core/workflow/nodes/base_node.py
@@ -115,7 +115,7 @@ class BaseNode(ABC):
                 )
 
     @classmethod
-    def extract_variable_selector_to_variable_mapping(cls, config: dict) -> dict[str, list[str]]:
+    def extract_variable_selector_to_variable_mapping(cls, config: dict):
         """
         Extract variable selector to variable mapping
         :param config: node config
@@ -125,14 +125,13 @@ class BaseNode(ABC):
         return cls._extract_variable_selector_to_variable_mapping(node_data)
 
     @classmethod
-    @abstractmethod
-    def _extract_variable_selector_to_variable_mapping(cls, node_data: BaseNodeData) -> dict[str, list[str]]:
+    def _extract_variable_selector_to_variable_mapping(cls, node_data: BaseNodeData) -> Mapping[str, Sequence[str]]:
         """
         Extract variable selector to variable mapping
         :param node_data: node data
         :return:
         """
-        raise NotImplementedError
+        return {}
 
     @classmethod
     def get_default_config(cls, filters: Optional[dict] = None) -> dict:
diff --git a/api/core/workflow/workflow_engine_manager.py b/api/core/workflow/workflow_engine_manager.py
index c3b80c5b97..32f0dbba06 100644
--- a/api/core/workflow/workflow_engine_manager.py
+++ b/api/core/workflow/workflow_engine_manager.py
@@ -389,11 +389,10 @@ class WorkflowEngineManager:
                 environment_variables=workflow.environment_variables,
             )
 
+            if node_cls is None:
+                raise ValueError('Node class not found')
             # variable selector to variable mapping
-            try:
-                variable_mapping = node_cls.extract_variable_selector_to_variable_mapping(node_config)
-            except NotImplementedError:
-                variable_mapping = {}
+            variable_mapping = node_cls.extract_variable_selector_to_variable_mapping(node_config)
 
             self._mapping_user_inputs_to_variable_pool(
                 variable_mapping=variable_mapping,
@@ -473,10 +472,9 @@ class WorkflowEngineManager:
         for node_config in iteration_nested_nodes:
             # mapping user inputs to variable pool
             node_cls = node_classes.get(NodeType.value_of(node_config.get('data', {}).get('type')))
-            try:
-                variable_mapping = node_cls.extract_variable_selector_to_variable_mapping(node_config)
-            except NotImplementedError:
-                variable_mapping = {}
+            if node_cls is None:
+                raise ValueError('Node class not found')
+            variable_mapping = node_cls.extract_variable_selector_to_variable_mapping(node_config)
 
             # remove iteration variables
             variable_mapping = {
@@ -942,7 +940,7 @@ class WorkflowEngineManager:
         return new_value
 
     def _mapping_user_inputs_to_variable_pool(self,
-                                              variable_mapping: dict,
+                                              variable_mapping: Mapping[str, Sequence[str]],
                                               user_inputs: dict,
                                               variable_pool: VariablePool,
                                               tenant_id: str,

From 6a3bef83788a73572de04d9001c532d74f3ae626 Mon Sep 17 00:00:00 2001
From: -LAN- <laipz8200@outlook.com>
Date: Sat, 27 Jul 2024 14:43:51 +0800
Subject: [PATCH 33/60] feat(api/core/app/segments): Update segment types and
 variables (#6734)

Signed-off-by: -LAN- <laipz8200@outlook.com>
---
 api/core/app/segments/__init__.py             |  16 +-
 api/core/app/segments/factory.py              |  28 +-
 api/core/app/segments/segments.py             |  43 ++-
 api/core/app/segments/types.py                |   6 +-
 api/core/app/segments/variables.py            |  27 +-
 .../core/app/segments/test_factory.py         | 307 ++++++++++++++++++
 .../core/app/{ => segments}/test_segment.py   |   0
 .../core/app/{ => segments}/test_variables.py |  67 +---
 8 files changed, 410 insertions(+), 84 deletions(-)
 create mode 100644 api/tests/unit_tests/core/app/segments/test_factory.py
 rename api/tests/unit_tests/core/app/{ => segments}/test_segment.py (100%)
 rename api/tests/unit_tests/core/app/{ => segments}/test_variables.py (54%)

diff --git a/api/core/app/segments/__init__.py b/api/core/app/segments/__init__.py
index b5d36bff3b..d5cd0a589c 100644
--- a/api/core/app/segments/__init__.py
+++ b/api/core/app/segments/__init__.py
@@ -1,6 +1,6 @@
 from .segment_group import SegmentGroup
 from .segments import (
-    ArraySegment,
+    ArrayAnySegment,
     FileSegment,
     FloatSegment,
     IntegerSegment,
@@ -11,7 +11,11 @@ from .segments import (
 )
 from .types import SegmentType
 from .variables import (
-    ArrayVariable,
+    ArrayAnyVariable,
+    ArrayFileVariable,
+    ArrayNumberVariable,
+    ArrayObjectVariable,
+    ArrayStringVariable,
     FileVariable,
     FloatVariable,
     IntegerVariable,
@@ -29,7 +33,7 @@ __all__ = [
     'SecretVariable',
     'FileVariable',
     'StringVariable',
-    'ArrayVariable',
+    'ArrayAnyVariable',
     'Variable',
     'SegmentType',
     'SegmentGroup',
@@ -39,7 +43,11 @@ __all__ = [
     'IntegerSegment',
     'FloatSegment',
     'ObjectSegment',
-    'ArraySegment',
+    'ArrayAnySegment',
     'FileSegment',
     'StringSegment',
+    'ArrayStringVariable',
+    'ArrayNumberVariable',
+    'ArrayObjectVariable',
+    'ArrayFileVariable',
 ]
diff --git a/api/core/app/segments/factory.py b/api/core/app/segments/factory.py
index 8e77b43bb7..f62e44bf07 100644
--- a/api/core/app/segments/factory.py
+++ b/api/core/app/segments/factory.py
@@ -4,7 +4,7 @@ from typing import Any
 from core.file.file_obj import FileVar
 
 from .segments import (
-    ArraySegment,
+    ArrayAnySegment,
     FileSegment,
     FloatSegment,
     IntegerSegment,
@@ -15,8 +15,14 @@ from .segments import (
 )
 from .types import SegmentType
 from .variables import (
+    ArrayFileVariable,
+    ArrayNumberVariable,
+    ArrayObjectVariable,
+    ArrayStringVariable,
+    FileVariable,
     FloatVariable,
     IntegerVariable,
+    ObjectVariable,
     SecretVariable,
     StringVariable,
     Variable,
@@ -33,14 +39,28 @@ def build_variable_from_mapping(m: Mapping[str, Any], /) -> Variable:
     match value_type:
         case SegmentType.STRING:
             return StringVariable.model_validate(m)
+        case SegmentType.SECRET:
+            return SecretVariable.model_validate(m)
         case SegmentType.NUMBER if isinstance(value, int):
             return IntegerVariable.model_validate(m)
         case SegmentType.NUMBER if isinstance(value, float):
             return FloatVariable.model_validate(m)
-        case SegmentType.SECRET:
-            return SecretVariable.model_validate(m)
         case SegmentType.NUMBER if not isinstance(value, float | int):
             raise ValueError(f'invalid number value {value}')
+        case SegmentType.FILE:
+            return FileVariable.model_validate(m)
+        case SegmentType.OBJECT if isinstance(value, dict):
+            return ObjectVariable.model_validate(
+                {**m, 'value': {k: build_variable_from_mapping(v) for k, v in value.items()}}
+            )
+        case SegmentType.ARRAY_STRING if isinstance(value, list):
+            return ArrayStringVariable.model_validate({**m, 'value': [build_variable_from_mapping(v) for v in value]})
+        case SegmentType.ARRAY_NUMBER if isinstance(value, list):
+            return ArrayNumberVariable.model_validate({**m, 'value': [build_variable_from_mapping(v) for v in value]})
+        case SegmentType.ARRAY_OBJECT if isinstance(value, list):
+            return ArrayObjectVariable.model_validate({**m, 'value': [build_variable_from_mapping(v) for v in value]})
+        case SegmentType.ARRAY_FILE if isinstance(value, list):
+            return ArrayFileVariable.model_validate({**m, 'value': [build_variable_from_mapping(v) for v in value]})
     raise ValueError(f'not supported value type {value_type}')
 
 
@@ -60,7 +80,7 @@ def build_segment(value: Any, /) -> Segment:
     if isinstance(value, list):
         # TODO: Limit the depth of the array
         elements = [build_segment(v) for v in value]
-        return ArraySegment(value=elements)
+        return ArrayAnySegment(value=elements)
     if isinstance(value, FileVar):
         return FileSegment(value=value)
     raise ValueError(f'not supported value {value}')
diff --git a/api/core/app/segments/segments.py b/api/core/app/segments/segments.py
index f317054bc7..4227f154e6 100644
--- a/api/core/app/segments/segments.py
+++ b/api/core/app/segments/segments.py
@@ -62,6 +62,7 @@ class StringSegment(Segment):
     value_type: SegmentType = SegmentType.STRING
     value: str
 
+
 class FloatSegment(Segment):
     value_type: SegmentType = SegmentType.NUMBER
     value: float
@@ -72,6 +73,16 @@ class IntegerSegment(Segment):
     value: int
 
 
+class FileSegment(Segment):
+    value_type: SegmentType = SegmentType.FILE
+    # TODO: embed FileVar in this model.
+    value: FileVar
+
+    @property
+    def markdown(self) -> str:
+        return self.value.to_markdown()
+
+
 class ObjectSegment(Segment):
     value_type: SegmentType = SegmentType.OBJECT
     value: Mapping[str, Segment]
@@ -96,9 +107,6 @@ class ObjectSegment(Segment):
 
 
 class ArraySegment(Segment):
-    value_type: SegmentType = SegmentType.ARRAY
-    value: Sequence[Segment]
-
     @property
     def markdown(self) -> str:
         return '\n'.join(['- ' + item.markdown for item in self.value])
@@ -107,11 +115,26 @@ class ArraySegment(Segment):
         return [v.to_object() for v in self.value]
 
 
-class FileSegment(Segment):
-    value_type: SegmentType = SegmentType.FILE
-    # TODO: embed FileVar in this model.
-    value: FileVar
+class ArrayAnySegment(ArraySegment):
+    value_type: SegmentType = SegmentType.ARRAY_ANY
+    value: Sequence[Segment]
 
-    @property
-    def markdown(self) -> str:
-        return self.value.to_markdown()
+
+class ArrayStringSegment(ArraySegment):
+    value_type: SegmentType = SegmentType.ARRAY_STRING
+    value: Sequence[StringSegment]
+
+
+class ArrayNumberSegment(ArraySegment):
+    value_type: SegmentType = SegmentType.ARRAY_NUMBER
+    value: Sequence[FloatSegment | IntegerSegment]
+
+
+class ArrayObjectSegment(ArraySegment):
+    value_type: SegmentType = SegmentType.ARRAY_OBJECT
+    value: Sequence[ObjectSegment]
+
+
+class ArrayFileSegment(ArraySegment):
+    value_type: SegmentType = SegmentType.ARRAY_FILE
+    value: Sequence[FileSegment]
diff --git a/api/core/app/segments/types.py b/api/core/app/segments/types.py
index 133755bbc6..a371058ef5 100644
--- a/api/core/app/segments/types.py
+++ b/api/core/app/segments/types.py
@@ -6,7 +6,11 @@ class SegmentType(str, Enum):
     NUMBER = 'number'
     STRING = 'string'
     SECRET = 'secret'
-    ARRAY = 'array'
+    ARRAY_ANY = 'array[any]'
+    ARRAY_STRING = 'array[string]'
+    ARRAY_NUMBER = 'array[number]'
+    ARRAY_OBJECT = 'array[object]'
+    ARRAY_FILE = 'array[file]'
     OBJECT = 'object'
     FILE = 'file'
 
diff --git a/api/core/app/segments/variables.py b/api/core/app/segments/variables.py
index ba55022726..ac26e16542 100644
--- a/api/core/app/segments/variables.py
+++ b/api/core/app/segments/variables.py
@@ -1,10 +1,13 @@
-
 from pydantic import Field
 
 from core.helper import encrypter
 
 from .segments import (
-    ArraySegment,
+    ArrayAnySegment,
+    ArrayFileSegment,
+    ArrayNumberSegment,
+    ArrayObjectSegment,
+    ArrayStringSegment,
     FileSegment,
     FloatSegment,
     IntegerSegment,
@@ -41,15 +44,31 @@ class IntegerVariable(IntegerSegment, Variable):
     pass
 
 
+class FileVariable(FileSegment, Variable):
+    pass
+
+
 class ObjectVariable(ObjectSegment, Variable):
     pass
 
 
-class ArrayVariable(ArraySegment, Variable):
+class ArrayAnyVariable(ArrayAnySegment, Variable):
     pass
 
 
-class FileVariable(FileSegment, Variable):
+class ArrayStringVariable(ArrayStringSegment, Variable):
+    pass
+
+
+class ArrayNumberVariable(ArrayNumberSegment, Variable):
+    pass
+
+
+class ArrayObjectVariable(ArrayObjectSegment, Variable):
+    pass
+
+
+class ArrayFileVariable(ArrayFileSegment, Variable):
     pass
 
 
diff --git a/api/tests/unit_tests/core/app/segments/test_factory.py b/api/tests/unit_tests/core/app/segments/test_factory.py
new file mode 100644
index 0000000000..85321ee374
--- /dev/null
+++ b/api/tests/unit_tests/core/app/segments/test_factory.py
@@ -0,0 +1,307 @@
+from uuid import uuid4
+
+import pytest
+
+from core.app.segments import (
+    ArrayFileVariable,
+    ArrayNumberVariable,
+    ArrayObjectVariable,
+    ArrayStringVariable,
+    FileVariable,
+    FloatVariable,
+    IntegerVariable,
+    NoneSegment,
+    ObjectSegment,
+    SecretVariable,
+    StringVariable,
+    factory,
+)
+
+
+def test_string_variable():
+    test_data = {'value_type': 'string', 'name': 'test_text', 'value': 'Hello, World!'}
+    result = factory.build_variable_from_mapping(test_data)
+    assert isinstance(result, StringVariable)
+
+
+def test_integer_variable():
+    test_data = {'value_type': 'number', 'name': 'test_int', 'value': 42}
+    result = factory.build_variable_from_mapping(test_data)
+    assert isinstance(result, IntegerVariable)
+
+
+def test_float_variable():
+    test_data = {'value_type': 'number', 'name': 'test_float', 'value': 3.14}
+    result = factory.build_variable_from_mapping(test_data)
+    assert isinstance(result, FloatVariable)
+
+
+def test_secret_variable():
+    test_data = {'value_type': 'secret', 'name': 'test_secret', 'value': 'secret_value'}
+    result = factory.build_variable_from_mapping(test_data)
+    assert isinstance(result, SecretVariable)
+
+
+def test_invalid_value_type():
+    test_data = {'value_type': 'unknown', 'name': 'test_invalid', 'value': 'value'}
+    with pytest.raises(ValueError):
+        factory.build_variable_from_mapping(test_data)
+
+
+def test_build_a_blank_string():
+    result = factory.build_variable_from_mapping(
+        {
+            'value_type': 'string',
+            'name': 'blank',
+            'value': '',
+        }
+    )
+    assert isinstance(result, StringVariable)
+    assert result.value == ''
+
+
+def test_build_a_object_variable_with_none_value():
+    var = factory.build_segment(
+        {
+            'key1': None,
+        }
+    )
+    assert isinstance(var, ObjectSegment)
+    assert isinstance(var.value['key1'], NoneSegment)
+
+
+def test_object_variable():
+    mapping = {
+        'id': str(uuid4()),
+        'value_type': 'object',
+        'name': 'test_object',
+        'description': 'Description of the variable.',
+        'value': {
+            'key1': {
+                'id': str(uuid4()),
+                'value_type': 'string',
+                'name': 'text',
+                'value': 'text',
+                'description': 'Description of the variable.',
+            },
+            'key2': {
+                'id': str(uuid4()),
+                'value_type': 'number',
+                'name': 'number',
+                'value': 1,
+                'description': 'Description of the variable.',
+            },
+        },
+    }
+    variable = factory.build_variable_from_mapping(mapping)
+    assert isinstance(variable, ObjectSegment)
+    assert isinstance(variable.value['key1'], StringVariable)
+    assert isinstance(variable.value['key2'], IntegerVariable)
+
+
+def test_array_string_variable():
+    mapping = {
+        'id': str(uuid4()),
+        'value_type': 'array[string]',
+        'name': 'test_array',
+        'description': 'Description of the variable.',
+        'value': [
+            {
+                'id': str(uuid4()),
+                'value_type': 'string',
+                'name': 'text',
+                'value': 'text',
+                'description': 'Description of the variable.',
+            },
+            {
+                'id': str(uuid4()),
+                'value_type': 'string',
+                'name': 'text',
+                'value': 'text',
+                'description': 'Description of the variable.',
+            },
+        ],
+    }
+    variable = factory.build_variable_from_mapping(mapping)
+    assert isinstance(variable, ArrayStringVariable)
+    assert isinstance(variable.value[0], StringVariable)
+    assert isinstance(variable.value[1], StringVariable)
+
+
+def test_array_number_variable():
+    mapping = {
+        'id': str(uuid4()),
+        'value_type': 'array[number]',
+        'name': 'test_array',
+        'description': 'Description of the variable.',
+        'value': [
+            {
+                'id': str(uuid4()),
+                'value_type': 'number',
+                'name': 'number',
+                'value': 1,
+                'description': 'Description of the variable.',
+            },
+            {
+                'id': str(uuid4()),
+                'value_type': 'number',
+                'name': 'number',
+                'value': 2.0,
+                'description': 'Description of the variable.',
+            },
+        ],
+    }
+    variable = factory.build_variable_from_mapping(mapping)
+    assert isinstance(variable, ArrayNumberVariable)
+    assert isinstance(variable.value[0], IntegerVariable)
+    assert isinstance(variable.value[1], FloatVariable)
+
+
+def test_array_object_variable():
+    mapping = {
+        'id': str(uuid4()),
+        'value_type': 'array[object]',
+        'name': 'test_array',
+        'description': 'Description of the variable.',
+        'value': [
+            {
+                'id': str(uuid4()),
+                'value_type': 'object',
+                'name': 'object',
+                'description': 'Description of the variable.',
+                'value': {
+                    'key1': {
+                        'id': str(uuid4()),
+                        'value_type': 'string',
+                        'name': 'text',
+                        'value': 'text',
+                        'description': 'Description of the variable.',
+                    },
+                    'key2': {
+                        'id': str(uuid4()),
+                        'value_type': 'number',
+                        'name': 'number',
+                        'value': 1,
+                        'description': 'Description of the variable.',
+                    },
+                },
+            },
+            {
+                'id': str(uuid4()),
+                'value_type': 'object',
+                'name': 'object',
+                'description': 'Description of the variable.',
+                'value': {
+                    'key1': {
+                        'id': str(uuid4()),
+                        'value_type': 'string',
+                        'name': 'text',
+                        'value': 'text',
+                        'description': 'Description of the variable.',
+                    },
+                    'key2': {
+                        'id': str(uuid4()),
+                        'value_type': 'number',
+                        'name': 'number',
+                        'value': 1,
+                        'description': 'Description of the variable.',
+                    },
+                },
+            },
+        ],
+    }
+    variable = factory.build_variable_from_mapping(mapping)
+    assert isinstance(variable, ArrayObjectVariable)
+    assert isinstance(variable.value[0], ObjectSegment)
+    assert isinstance(variable.value[1], ObjectSegment)
+    assert isinstance(variable.value[0].value['key1'], StringVariable)
+    assert isinstance(variable.value[0].value['key2'], IntegerVariable)
+    assert isinstance(variable.value[1].value['key1'], StringVariable)
+    assert isinstance(variable.value[1].value['key2'], IntegerVariable)
+
+
+def test_file_variable():
+    mapping = {
+        'id': str(uuid4()),
+        'value_type': 'file',
+        'name': 'test_file',
+        'description': 'Description of the variable.',
+        'value': {
+            'id': str(uuid4()),
+            'tenant_id': 'tenant_id',
+            'type': 'image',
+            'transfer_method': 'local_file',
+            'url': 'url',
+            'related_id': 'related_id',
+            'extra_config': {
+                'image_config': {
+                    'width': 100,
+                    'height': 100,
+                },
+            },
+            'filename': 'filename',
+            'extension': 'extension',
+            'mime_type': 'mime_type',
+        },
+    }
+    variable = factory.build_variable_from_mapping(mapping)
+    assert isinstance(variable, FileVariable)
+
+
+def test_array_file_variable():
+    mapping = {
+        'id': str(uuid4()),
+        'value_type': 'array[file]',
+        'name': 'test_array_file',
+        'description': 'Description of the variable.',
+        'value': [
+            {
+                'id': str(uuid4()),
+                'name': 'file',
+                'value_type': 'file',
+                'value': {
+                    'id': str(uuid4()),
+                    'tenant_id': 'tenant_id',
+                    'type': 'image',
+                    'transfer_method': 'local_file',
+                    'url': 'url',
+                    'related_id': 'related_id',
+                    'extra_config': {
+                        'image_config': {
+                            'width': 100,
+                            'height': 100,
+                        },
+                    },
+                    'filename': 'filename',
+                    'extension': 'extension',
+                    'mime_type': 'mime_type',
+                },
+            },
+            {
+                'id': str(uuid4()),
+                'name': 'file',
+                'value_type': 'file',
+                'value': {
+                    'id': str(uuid4()),
+                    'tenant_id': 'tenant_id',
+                    'type': 'image',
+                    'transfer_method': 'local_file',
+                    'url': 'url',
+                    'related_id': 'related_id',
+                    'extra_config': {
+                        'image_config': {
+                            'width': 100,
+                            'height': 100,
+                        },
+                    },
+                    'filename': 'filename',
+                    'extension': 'extension',
+                    'mime_type': 'mime_type',
+                },
+            },
+        ],
+    }
+    variable = factory.build_variable_from_mapping(mapping)
+    assert isinstance(variable, ArrayFileVariable)
+    assert isinstance(variable.value[0], FileVariable)
+    assert isinstance(variable.value[1], FileVariable)
diff --git a/api/tests/unit_tests/core/app/test_segment.py b/api/tests/unit_tests/core/app/segments/test_segment.py
similarity index 100%
rename from api/tests/unit_tests/core/app/test_segment.py
rename to api/tests/unit_tests/core/app/segments/test_segment.py
diff --git a/api/tests/unit_tests/core/app/test_variables.py b/api/tests/unit_tests/core/app/segments/test_variables.py
similarity index 54%
rename from api/tests/unit_tests/core/app/test_variables.py
rename to api/tests/unit_tests/core/app/segments/test_variables.py
index afed29e3cb..e3f513971a 100644
--- a/api/tests/unit_tests/core/app/test_variables.py
+++ b/api/tests/unit_tests/core/app/segments/test_variables.py
@@ -2,49 +2,16 @@ import pytest
 from pydantic import ValidationError
 
 from core.app.segments import (
-    ArrayVariable,
+    ArrayAnyVariable,
     FloatVariable,
     IntegerVariable,
-    NoneSegment,
-    ObjectSegment,
     ObjectVariable,
     SecretVariable,
     SegmentType,
     StringVariable,
-    factory,
 )
 
 
-def test_string_variable():
-    test_data = {'value_type': 'string', 'name': 'test_text', 'value': 'Hello, World!'}
-    result = factory.build_variable_from_mapping(test_data)
-    assert isinstance(result, StringVariable)
-
-
-def test_integer_variable():
-    test_data = {'value_type': 'number', 'name': 'test_int', 'value': 42}
-    result = factory.build_variable_from_mapping(test_data)
-    assert isinstance(result, IntegerVariable)
-
-
-def test_float_variable():
-    test_data = {'value_type': 'number', 'name': 'test_float', 'value': 3.14}
-    result = factory.build_variable_from_mapping(test_data)
-    assert isinstance(result, FloatVariable)
-
-
-def test_secret_variable():
-    test_data = {'value_type': 'secret', 'name': 'test_secret', 'value': 'secret_value'}
-    result = factory.build_variable_from_mapping(test_data)
-    assert isinstance(result, SecretVariable)
-
-
-def test_invalid_value_type():
-    test_data = {'value_type': 'unknown', 'name': 'test_invalid', 'value': 'value'}
-    with pytest.raises(ValueError):
-        factory.build_variable_from_mapping(test_data)
-
-
 def test_frozen_variables():
     var = StringVariable(name='text', value='text')
     with pytest.raises(ValidationError):
@@ -65,34 +32,22 @@ def test_frozen_variables():
 
 def test_variable_value_type_immutable():
     with pytest.raises(ValidationError):
-        StringVariable(value_type=SegmentType.ARRAY, name='text', value='text')
+        StringVariable(value_type=SegmentType.ARRAY_ANY, name='text', value='text')
 
     with pytest.raises(ValidationError):
         StringVariable.model_validate({'value_type': 'not text', 'name': 'text', 'value': 'text'})
 
     var = IntegerVariable(name='integer', value=42)
     with pytest.raises(ValidationError):
-        IntegerVariable(value_type=SegmentType.ARRAY, name=var.name, value=var.value)
+        IntegerVariable(value_type=SegmentType.ARRAY_ANY, name=var.name, value=var.value)
 
     var = FloatVariable(name='float', value=3.14)
     with pytest.raises(ValidationError):
-        FloatVariable(value_type=SegmentType.ARRAY, name=var.name, value=var.value)
+        FloatVariable(value_type=SegmentType.ARRAY_ANY, name=var.name, value=var.value)
 
     var = SecretVariable(name='secret', value='secret_value')
     with pytest.raises(ValidationError):
-        SecretVariable(value_type=SegmentType.ARRAY, name=var.name, value=var.value)
-
-
-def test_build_a_blank_string():
-    result = factory.build_variable_from_mapping(
-        {
-            'value_type': 'string',
-            'name': 'blank',
-            'value': '',
-        }
-    )
-    assert isinstance(result, StringVariable)
-    assert result.value == ''
+        SecretVariable(value_type=SegmentType.ARRAY_ANY, name=var.name, value=var.value)
 
 
 def test_object_variable_to_object():
@@ -105,7 +60,7 @@ def test_object_variable_to_object():
                     'key2': StringVariable(name='key2', value='value2'),
                 },
             ),
-            'key2': ArrayVariable(
+            'key2': ArrayAnyVariable(
                 name='array',
                 value=[
                     StringVariable(name='key5_1', value='value5_1'),
@@ -137,13 +92,3 @@ def test_variable_to_object():
     assert var.to_object() == 3.14
     var = SecretVariable(name='secret', value='secret_value')
     assert var.to_object() == 'secret_value'
-
-
-def test_build_a_object_variable_with_none_value():
-    var = factory.build_segment(
-        {
-            'key1': None,
-        }
-    )
-    assert isinstance(var, ObjectSegment)
-    assert isinstance(var.value['key1'], NoneSegment)

From 082c46a90363a38803b84fca0df8312c7479dca7 Mon Sep 17 00:00:00 2001
From: Pascal M <11357019+perzeuss@users.noreply.github.com>
Date: Sat, 27 Jul 2024 08:49:34 +0200
Subject: [PATCH 34/60] chore: migrate to poetry in devcontainer commands
 (#6724)

---
 .devcontainer/post_create_command.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.devcontainer/post_create_command.sh b/.devcontainer/post_create_command.sh
index ddf976c47a..b0322dd2b2 100755
--- a/.devcontainer/post_create_command.sh
+++ b/.devcontainer/post_create_command.sh
@@ -3,8 +3,8 @@
 cd web && npm install
 pipx install poetry
 
-echo 'alias start-api="cd /workspaces/dify/api && flask run --host 0.0.0.0 --port=5001 --debug"' >> ~/.bashrc
-echo 'alias start-worker="cd /workspaces/dify/api && celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion"' >> ~/.bashrc
+echo 'alias start-api="cd /workspaces/dify/api && poetry run python -m flask run --host 0.0.0.0 --port=5001 --debug"' >> ~/.bashrc
+echo 'alias start-worker="cd /workspaces/dify/api && poetry run python -m celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion"' >> ~/.bashrc
 echo 'alias start-web="cd /workspaces/dify/web && npm run dev"' >> ~/.bashrc
 echo 'alias start-containers="cd /workspaces/dify/docker && docker-compose -f docker-compose.middleware.yaml -p dify up -d"' >> ~/.bashrc
 

From 21f6caacd4d08817a5ce3243d36600665c30daba Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=9D=9E=E6=B3=95=E6=93=8D=E4=BD=9C?= <hjlarry@163.com>
Date: Sat, 27 Jul 2024 15:00:06 +0800
Subject: [PATCH 35/60] feat: enhance the firecrawl tool (#6705)

---
 .../provider/builtin/firecrawl/firecrawl.py   |  13 +-
 .../provider/builtin/firecrawl/firecrawl.yaml |   5 +-
 .../builtin/firecrawl/firecrawl_appx.py       |  60 +++--
 .../provider/builtin/firecrawl/tools/crawl.py |  62 +++--
 .../builtin/firecrawl/tools/crawl.yaml        | 229 +++++++++++++++---
 .../builtin/firecrawl/tools/crawl_job.py      |  20 ++
 .../builtin/firecrawl/tools/crawl_job.yaml    |  37 +++
 .../builtin/firecrawl/tools/scrape.py         |  45 ++--
 .../builtin/firecrawl/tools/scrape.yaml       | 159 +++++++++++-
 .../builtin/firecrawl/tools/search.py         |  34 +--
 .../builtin/firecrawl/tools/search.yaml       |  52 ++++
 11 files changed, 598 insertions(+), 118 deletions(-)
 create mode 100644 api/core/tools/provider/builtin/firecrawl/tools/crawl_job.py
 create mode 100644 api/core/tools/provider/builtin/firecrawl/tools/crawl_job.yaml

diff --git a/api/core/tools/provider/builtin/firecrawl/firecrawl.py b/api/core/tools/provider/builtin/firecrawl/firecrawl.py
index adcb7ebdd6..24dc35759d 100644
--- a/api/core/tools/provider/builtin/firecrawl/firecrawl.py
+++ b/api/core/tools/provider/builtin/firecrawl/firecrawl.py
@@ -1,22 +1,19 @@
 from core.tools.errors import ToolProviderCredentialValidationError
-from core.tools.provider.builtin.firecrawl.tools.crawl import CrawlTool
+from core.tools.provider.builtin.firecrawl.tools.scrape import ScrapeTool
 from core.tools.provider.builtin_tool_provider import BuiltinToolProviderController
 
 
 class FirecrawlProvider(BuiltinToolProviderController):
     def _validate_credentials(self, credentials: dict) -> None:
         try:
-            # Example validation using the Crawl tool
-            CrawlTool().fork_tool_runtime(
+            # Example validation using the ScrapeTool, only scraping title for minimize content
+            ScrapeTool().fork_tool_runtime(
                 runtime={"credentials": credentials}
             ).invoke(
                 user_id='',
                 tool_parameters={
-                    "url": "https://example.com",
-                    "includes": '', 
-                    "excludes": '', 
-                    "limit": 1,
-                    "onlyMainContent": True,
+                    "url": "https://google.com",
+                    "onlyIncludeTags": 'title'
                 }
             )
         except Exception as e:
diff --git a/api/core/tools/provider/builtin/firecrawl/firecrawl.yaml b/api/core/tools/provider/builtin/firecrawl/firecrawl.yaml
index 613a0e4679..a48b9d9f54 100644
--- a/api/core/tools/provider/builtin/firecrawl/firecrawl.yaml
+++ b/api/core/tools/provider/builtin/firecrawl/firecrawl.yaml
@@ -31,8 +31,5 @@ credentials_for_provider:
     label:
       en_US: Firecrawl server's Base URL
       zh_Hans: Firecrawl服务器的API URL
-      pt_BR: Firecrawl server's Base URL
     placeholder:
-      en_US: https://www.firecrawl.dev
-      zh_HansL: https://www.firecrawl.dev
-      pt_BR: https://www.firecrawl.dev
+      en_US: https://api.firecrawl.dev
diff --git a/api/core/tools/provider/builtin/firecrawl/firecrawl_appx.py b/api/core/tools/provider/builtin/firecrawl/firecrawl_appx.py
index bfe3e7999d..3b3f78731b 100644
--- a/api/core/tools/provider/builtin/firecrawl/firecrawl_appx.py
+++ b/api/core/tools/provider/builtin/firecrawl/firecrawl_appx.py
@@ -1,3 +1,4 @@
+import json
 import logging
 import time
 from collections.abc import Mapping
@@ -8,6 +9,7 @@ from requests.exceptions import HTTPError
 
 logger = logging.getLogger(__name__)
 
+
 class FirecrawlApp:
     def __init__(self, api_key: str | None = None, base_url: str | None = None):
         self.api_key = api_key
@@ -25,14 +27,16 @@ class FirecrawlApp:
         return headers
 
     def _request(
-        self,
-        method: str,
-        url: str,
-        data: Mapping[str, Any] | None = None,
-        headers: Mapping[str, str] | None = None,
-        retries: int = 3,
-        backoff_factor: float = 0.3,
+            self,
+            method: str,
+            url: str,
+            data: Mapping[str, Any] | None = None,
+            headers: Mapping[str, str] | None = None,
+            retries: int = 3,
+            backoff_factor: float = 0.3,
     ) -> Mapping[str, Any] | None:
+        if not headers:
+            headers = self._prepare_headers()
         for i in range(retries):
             try:
                 response = requests.request(method, url, json=data, headers=headers)
@@ -47,47 +51,51 @@ class FirecrawlApp:
 
     def scrape_url(self, url: str, **kwargs):
         endpoint = f'{self.base_url}/v0/scrape'
-        headers = self._prepare_headers()
         data = {'url': url, **kwargs}
-        response = self._request('POST', endpoint, data, headers)
         logger.debug(f"Sent request to {endpoint=} body={data}")
+        response = self._request('POST', endpoint, data)
         if response is None:
             raise HTTPError("Failed to scrape URL after multiple retries")
         return response
 
     def search(self, query: str, **kwargs):
         endpoint = f'{self.base_url}/v0/search'
-        headers = self._prepare_headers()
         data = {'query': query, **kwargs}
-        response = self._request('POST', endpoint, data, headers)
         logger.debug(f"Sent request to {endpoint=} body={data}")
+        response = self._request('POST', endpoint, data)
         if response is None:
             raise HTTPError("Failed to perform search after multiple retries")
         return response
 
     def crawl_url(
-        self, url: str, wait: bool = False, poll_interval: int = 5, idempotency_key: str | None = None, **kwargs
+            self, url: str, wait: bool = True, poll_interval: int = 5, idempotency_key: str | None = None, **kwargs
     ):
         endpoint = f'{self.base_url}/v0/crawl'
         headers = self._prepare_headers(idempotency_key)
-        data = {'url': url, **kwargs['params']}
-        response = self._request('POST', endpoint, data, headers)
+        data = {'url': url, **kwargs}
         logger.debug(f"Sent request to {endpoint=} body={data}")
+        response = self._request('POST', endpoint, data, headers)
         if response is None:
             raise HTTPError("Failed to initiate crawl after multiple retries")
         job_id: str = response['jobId']
         if wait:
             return self._monitor_job_status(job_id=job_id, poll_interval=poll_interval)
-        return job_id
+        return response
 
     def check_crawl_status(self, job_id: str):
         endpoint = f'{self.base_url}/v0/crawl/status/{job_id}'
-        headers = self._prepare_headers()
-        response = self._request('GET', endpoint, headers=headers)
+        response = self._request('GET', endpoint)
         if response is None:
             raise HTTPError(f"Failed to check status for job {job_id} after multiple retries")
         return response
 
+    def cancel_crawl_job(self, job_id: str):
+        endpoint = f'{self.base_url}/v0/crawl/cancel/{job_id}'
+        response = self._request('DELETE', endpoint)
+        if response is None:
+            raise HTTPError(f"Failed to cancel job {job_id} after multiple retries")
+        return response
+
     def _monitor_job_status(self, job_id: str, poll_interval: int):
         while True:
             status = self.check_crawl_status(job_id)
@@ -96,3 +104,21 @@ class FirecrawlApp:
             elif status['status'] == 'failed':
                 raise HTTPError(f'Job {job_id} failed: {status["error"]}')
             time.sleep(poll_interval)
+
+
+def get_array_params(tool_parameters: dict[str, Any], key):
+    param = tool_parameters.get(key)
+    if param:
+        return param.split(',')
+
+
+def get_json_params(tool_parameters: dict[str, Any], key):
+    param = tool_parameters.get(key)
+    if param:
+        try:
+            # support both single quotes and double quotes
+            param = param.replace("'", '"')
+            param = json.loads(param)
+        except:
+            raise ValueError(f"Invalid {key} format.")
+        return param
diff --git a/api/core/tools/provider/builtin/firecrawl/tools/crawl.py b/api/core/tools/provider/builtin/firecrawl/tools/crawl.py
index b000c1c6ce..08c40a4064 100644
--- a/api/core/tools/provider/builtin/firecrawl/tools/crawl.py
+++ b/api/core/tools/provider/builtin/firecrawl/tools/crawl.py
@@ -1,36 +1,48 @@
-import json
-from typing import Any, Union
+from typing import Any
 
 from core.tools.entities.tool_entities import ToolInvokeMessage
-from core.tools.provider.builtin.firecrawl.firecrawl_appx import FirecrawlApp
+from core.tools.provider.builtin.firecrawl.firecrawl_appx import FirecrawlApp, get_array_params, get_json_params
 from core.tools.tool.builtin_tool import BuiltinTool
 
 
 class CrawlTool(BuiltinTool):
-    def _invoke(self, user_id: str, tool_parameters: dict[str, Any]) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
-        app = FirecrawlApp(api_key=self.runtime.credentials['firecrawl_api_key'], base_url=self.runtime.credentials['base_url'])
+    def _invoke(self, user_id: str, tool_parameters: dict[str, Any]) -> ToolInvokeMessage:
+        """
+        the crawlerOptions and pageOptions comes from doc here:
+        https://docs.firecrawl.dev/api-reference/endpoint/crawl
+        """
+        app = FirecrawlApp(api_key=self.runtime.credentials['firecrawl_api_key'],
+                           base_url=self.runtime.credentials['base_url'])
+        crawlerOptions = {}
+        pageOptions = {}
 
-        options = {
-            'crawlerOptions': {
-                'excludes': tool_parameters.get('excludes', '').split(',') if tool_parameters.get('excludes') else [],
-                'includes': tool_parameters.get('includes', '').split(',') if tool_parameters.get('includes') else [],
-                'limit': tool_parameters.get('limit', 5)
-            },
-            'pageOptions': {
-                'onlyMainContent': tool_parameters.get('onlyMainContent', False)
-            }
-        }
+        wait_for_results = tool_parameters.get('wait_for_results', True)
+
+        crawlerOptions['excludes'] = get_array_params(tool_parameters, 'excludes')
+        crawlerOptions['includes'] = get_array_params(tool_parameters, 'includes')
+        crawlerOptions['returnOnlyUrls'] = tool_parameters.get('returnOnlyUrls', False)
+        crawlerOptions['maxDepth'] = tool_parameters.get('maxDepth')
+        crawlerOptions['mode'] = tool_parameters.get('mode')
+        crawlerOptions['ignoreSitemap'] = tool_parameters.get('ignoreSitemap', False)
+        crawlerOptions['limit'] = tool_parameters.get('limit', 5)
+        crawlerOptions['allowBackwardCrawling'] = tool_parameters.get('allowBackwardCrawling', False)
+        crawlerOptions['allowExternalContentLinks'] = tool_parameters.get('allowExternalContentLinks', False)
+
+        pageOptions['headers'] = get_json_params(tool_parameters, 'headers')
+        pageOptions['includeHtml'] = tool_parameters.get('includeHtml', False)
+        pageOptions['includeRawHtml'] = tool_parameters.get('includeRawHtml', False)
+        pageOptions['onlyIncludeTags'] = get_array_params(tool_parameters, 'onlyIncludeTags')
+        pageOptions['removeTags'] = get_array_params(tool_parameters, 'removeTags')
+        pageOptions['onlyMainContent'] = tool_parameters.get('onlyMainContent', False)
+        pageOptions['replaceAllPathsWithAbsolutePaths'] = tool_parameters.get('replaceAllPathsWithAbsolutePaths', False)
+        pageOptions['screenshot'] = tool_parameters.get('screenshot', False)
+        pageOptions['waitFor'] = tool_parameters.get('waitFor', 0)
 
         crawl_result = app.crawl_url(
-            url=tool_parameters['url'], 
-            params=options,
-            wait=True
+            url=tool_parameters['url'],
+            wait=wait_for_results,
+            crawlerOptions=crawlerOptions,
+            pageOptions=pageOptions
         )
 
-        if not isinstance(crawl_result, str):
-            crawl_result = json.dumps(crawl_result, ensure_ascii=False, indent=4)
-
-        if not crawl_result:
-            return self.create_text_message("Crawl request failed.")
-
-        return self.create_text_message(crawl_result)
+        return self.create_json_message(crawl_result)
diff --git a/api/core/tools/provider/builtin/firecrawl/tools/crawl.yaml b/api/core/tools/provider/builtin/firecrawl/tools/crawl.yaml
index 3861670140..0c5399f973 100644
--- a/api/core/tools/provider/builtin/firecrawl/tools/crawl.yaml
+++ b/api/core/tools/provider/builtin/firecrawl/tools/crawl.yaml
@@ -3,76 +3,243 @@ identity:
   author: Richards Tu
   label:
     en_US: Crawl
-    zh_Hans: 爬取
+    zh_Hans: 深度爬取
 description:
   human:
-    en_US: Extract data from a website by crawling through a URL.
-    zh_Hans: 通过URL从网站中提取数据。
+    en_US: Recursively search through a urls subdomains, and gather the content.
+    zh_Hans: 递归爬取一个网址的子域名，并收集内容。
   llm: This tool initiates a web crawl to extract data from a specified URL. It allows configuring crawler options such as including or excluding URL patterns, generating alt text for images using LLMs (paid plan required), limiting the maximum number of pages to crawl, and returning only the main content of the page. The tool can return either a list of crawled documents or a list of URLs based on the provided options.
 parameters:
   - name: url
     type: string
     required: true
     label:
-      en_US: URL to crawl
-      zh_Hans: 要爬取的URL
+      en_US: Start URL
+      zh_Hans: 起始URL
     human_description:
-      en_US: The URL of the website to crawl and extract data from.
-      zh_Hans: 要爬取并提取数据的网站URL。
+      en_US: The base URL to start crawling from.
+      zh_Hans: 要爬取网站的起始URL。
     llm_description: The URL of the website that needs to be crawled. This is a required parameter.
     form: llm
+  - name: wait_for_results
+    type: boolean
+    default: true
+    label:
+      en_US: Wait For Results
+      zh_Hans: 等待爬取结果
+    human_description:
+      en_US: If you choose not to wait, it will directly return a job ID. You can use this job ID to check the crawling results or cancel the crawling task, which is usually very useful for a large-scale crawling task.
+      zh_Hans: 如果选择不等待，则会直接返回一个job_id，可以通过job_id查询爬取结果或取消爬取任务，这通常对于一个大型爬取任务来说非常有用。
+    form: form
+############## Crawl Options #######################
   - name: includes
     type: string
     required: false
     label:
       en_US: URL patterns to include
       zh_Hans: 要包含的URL模式
+    placeholder:
+      en_US: Use commas to separate multiple tags
+      zh_Hans: 多个标签时使用半角逗号分隔
     human_description:
-      en_US: Specify URL patterns to include during the crawl. Only pages matching these patterns will be crawled, you can use ',' to separate multiple patterns.
-      zh_Hans: 指定爬取过程中要包含的URL模式。只有与这些模式匹配的页面才会被爬取。
+      en_US: |
+       Only pages matching these patterns will be crawled. Example: blog/*, about/*
+      zh_Hans: 只有与这些模式匹配的页面才会被爬取。示例：blog/*, about/*
     form: form
-    default: ''
   - name: excludes
     type: string
-    required: false
     label:
       en_US: URL patterns to exclude
       zh_Hans: 要排除的URL模式
+    placeholder:
+      en_US: Use commas to separate multiple tags
+      zh_Hans: 多个标签时使用半角逗号分隔
     human_description:
-      en_US: Specify URL patterns to exclude during the crawl. Pages matching these patterns will be skipped, you can use ',' to separate multiple patterns.
-      zh_Hans: 指定爬取过程中要排除的URL模式。匹配这些模式的页面将被跳过。
+      en_US: |
+       Pages matching these patterns will be skipped. Example: blog/*, about/*
+      zh_Hans: 匹配这些模式的页面将被跳过。示例：blog/*, about/*
+    form: form
+  - name: returnOnlyUrls
+    type: boolean
+    default: false
+    label:
+      en_US: return Only Urls
+      zh_Hans: 仅返回URL
+    human_description:
+      en_US: |
+       If true, returns only the URLs as a list on the crawl status. Attention: the return response will be a list of URLs inside the data, not a list of documents.
+      zh_Hans: 只返回爬取到的网页链接，而不是网页内容本身。
+    form: form
+  - name: maxDepth
+    type: number
+    label:
+      en_US: Maximum crawl depth
+      zh_Hans: 爬取深度
+    human_description:
+      en_US: Maximum depth to crawl relative to the entered URL. A maxDepth of 0 scrapes only the entered URL. A maxDepth of 1 scrapes the entered URL and all pages one level deep. A maxDepth of 2 scrapes the entered URL and all pages up to two levels deep. Higher values follow the same pattern.
+      zh_Hans: 相对于输入的URL，爬取的最大深度。maxDepth为0时，仅抓取输入的URL。maxDepth为1时，抓取输入的URL以及所有一级深层页面。maxDepth为2时，抓取输入的URL以及所有两级深层页面。更高值遵循相同模式。
+    form: form
+    min: 0
+  - name: mode
+    type: select
+    required: false
+    form: form
+    options:
+      - value: default
+        label:
+          en_US: default
+      - value: fast
+        label:
+          en_US: fast
+    default: default
+    label:
+      en_US: Crawl Mode
+      zh_Hans: 爬取模式
+    human_description:
+      en_US: The crawling mode to use. Fast mode crawls 4x faster websites without sitemap, but may not be as accurate and shouldn't be used in heavy js-rendered websites.
+      zh_Hans: 使用fast模式将不会使用其站点地图，比普通模式快4倍，但是可能不够准确，也不适用于大量js渲染的网站。
+  - name: ignoreSitemap
+    type: boolean
+    default: false
+    label:
+      en_US: ignore Sitemap
+      zh_Hans: 忽略站点地图
+    human_description:
+      en_US: Ignore the website sitemap when crawling.
+      zh_Hans: 爬取时忽略网站站点地图。
     form: form
-    default: 'blog/*'
   - name: limit
     type: number
     required: false
     label:
-      en_US: Maximum number of pages to crawl
+      en_US: Maximum pages to crawl
       zh_Hans: 最大爬取页面数
     human_description:
       en_US: Specify the maximum number of pages to crawl. The crawler will stop after reaching this limit.
       zh_Hans: 指定要爬取的最大页面数。爬虫将在达到此限制后停止。
     form: form
     min: 1
-    max: 20
     default: 5
+  - name: allowBackwardCrawling
+    type: boolean
+    default: false
+    label:
+      en_US: allow Backward Crawling
+      zh_Hans: 允许向后爬取
+    human_description:
+      en_US: Enables the crawler to navigate from a specific URL to previously linked pages. For instance, from 'example.com/product/123' back to 'example.com/product'
+      zh_Hans: 使爬虫能够从特定URL导航到之前链接的页面。例如，从'example.com/product/123'返回到'example.com/product'
+    form: form
+  - name: allowExternalContentLinks
+    type: boolean
+    default: false
+    label:
+      en_US: allow External Content Links
+      zh_Hans: 允许爬取外链
+    human_description:
+      en_US: Allows the crawler to follow links to external websites.
+      zh_Hans:
+    form: form
+############## Page Options #######################
+  - name: headers
+    type: string
+    label:
+      en_US: headers
+      zh_Hans: 请求头
+    human_description:
+      en_US: |
+        Headers to send with the request. Can be used to send cookies, user-agent, etc. Example: {"cookies": "testcookies"}
+      zh_Hans: |
+        随请求发送的头部。可以用来发送cookies、用户代理等。示例：{"cookies": "testcookies"}
+    placeholder:
+      en_US: Please enter an object that can be serialized in JSON
+      zh_Hans: 请输入可以json序列化的对象
+    form: form
+  - name: includeHtml
+    type: boolean
+    default: false
+    label:
+      en_US: include Html
+      zh_Hans: 包含HTML
+    human_description:
+      en_US: Include the HTML version of the content on page. Will output a html key in the response.
+      zh_Hans: 返回中包含一个HTML版本的内容，将以html键返回。
+    form: form
+  - name: includeRawHtml
+    type: boolean
+    default: false
+    label:
+      en_US: include Raw Html
+      zh_Hans: 包含原始HTML
+    human_description:
+      en_US: Include the raw HTML content of the page. Will output a rawHtml key in the response.
+      zh_Hans: 返回中包含一个原始HTML版本的内容，将以rawHtml键返回。
+    form: form
+  - name: onlyIncludeTags
+    type: string
+    label:
+      en_US: only Include Tags
+      zh_Hans: 仅抓取这些标签
+    placeholder:
+      en_US: Use commas to separate multiple tags
+      zh_Hans: 多个标签时使用半角逗号分隔
+    human_description:
+      en_US: |
+        Only include tags, classes and ids from the page in the final output. Use comma separated values. Example: script, .ad, #footer
+      zh_Hans: |
+        仅在最终输出中包含HTML页面的这些标签，可以通过标签名、类或ID来设定，使用逗号分隔值。示例：script, .ad, #footer
+    form: form
   - name: onlyMainContent
     type: boolean
-    required: false
+    default: false
     label:
-      en_US: Only return the main content of the page
-      zh_Hans: 仅返回页面的主要内容
+      en_US: only Main Content
+      zh_Hans: 仅抓取主要内容
     human_description:
-      en_US: If enabled, the crawler will only return the main content of the page, excluding headers, navigation, footers, etc.
-      zh_Hans: 如果启用，爬虫将仅返回页面的主要内容，不包括标题、导航、页脚等。
+      en_US: Only return the main content of the page excluding headers, navs, footers, etc.
+      zh_Hans: 只返回页面的主要内容，不包括头部、导航栏、尾部等。
+    form: form
+  - name: removeTags
+    type: string
+    label:
+      en_US: remove Tags
+      zh_Hans: 要移除这些标签
+    human_description:
+      en_US: |
+        Tags, classes and ids to remove from the page. Use comma separated values. Example: script, .ad, #footer
+      zh_Hans: |
+        要在最终输出中移除HTML页面的这些标签，可以通过标签名、类或ID来设定，使用逗号分隔值。示例：script, .ad, #footer
+    placeholder:
+      en_US: Use commas to separate multiple tags
+      zh_Hans: 多个标签时使用半角逗号分隔
+    form: form
+  - name: replaceAllPathsWithAbsolutePaths
+    type: boolean
+    default: false
+    label:
+      en_US: All AbsolutePaths
+      zh_Hans: 使用绝对路径
+    human_description:
+      en_US: Replace all relative paths with absolute paths for images and links.
+      zh_Hans: 将所有图片和链接的相对路径替换为绝对路径。
+    form: form
+  - name: screenshot
+    type: boolean
+    default: false
+    label:
+      en_US: screenshot
+      zh_Hans: 截图
+    human_description:
+      en_US: Include a screenshot of the top of the page that you are scraping.
+      zh_Hans: 提供正在抓取的页面的顶部的截图。
+    form: form
+  - name: waitFor
+    type: number
+    min: 0
+    label:
+      en_US: wait For
+      zh_Hans: 等待时间
+    human_description:
+      en_US: Wait x amount of milliseconds for the page to load to fetch content.
+      zh_Hans: 等待x毫秒以使页面加载并获取内容。
     form: form
-    options:
-      - value: 'true'
-        label:
-          en_US: 'Yes'
-          zh_Hans: 是
-      - value: 'false'
-        label:
-          en_US: 'No'
-          zh_Hans: 否
-    default: 'false'
diff --git a/api/core/tools/provider/builtin/firecrawl/tools/crawl_job.py b/api/core/tools/provider/builtin/firecrawl/tools/crawl_job.py
new file mode 100644
index 0000000000..fa6c1f87ee
--- /dev/null
+++ b/api/core/tools/provider/builtin/firecrawl/tools/crawl_job.py
@@ -0,0 +1,20 @@
+from typing import Any
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.provider.builtin.firecrawl.firecrawl_appx import FirecrawlApp
+from core.tools.tool.builtin_tool import BuiltinTool
+
+
+class CrawlJobTool(BuiltinTool):
+    def _invoke(self, user_id: str, tool_parameters: dict[str, Any]) -> ToolInvokeMessage:
+        app = FirecrawlApp(api_key=self.runtime.credentials['firecrawl_api_key'],
+                           base_url=self.runtime.credentials['base_url'])
+        operation = tool_parameters.get('operation', 'get')
+        if operation == 'get':
+            result = app.check_crawl_status(job_id=tool_parameters['job_id'])
+        elif operation == 'cancel':
+            result = app.cancel_crawl_job(job_id=tool_parameters['job_id'])
+        else:
+            raise ValueError(f'Invalid operation: {operation}')
+
+        return self.create_json_message(result)
diff --git a/api/core/tools/provider/builtin/firecrawl/tools/crawl_job.yaml b/api/core/tools/provider/builtin/firecrawl/tools/crawl_job.yaml
new file mode 100644
index 0000000000..78008e4ad4
--- /dev/null
+++ b/api/core/tools/provider/builtin/firecrawl/tools/crawl_job.yaml
@@ -0,0 +1,37 @@
+identity:
+  name: crawl_job
+  author: hjlarry
+  label:
+    en_US: Crawl Job
+    zh_Hans: 爬取任务处理
+description:
+  human:
+    en_US: Retrieve the scraping results based on the job ID, or cancel the scraping task.
+    zh_Hans: 根据爬取任务ID获取爬取结果，或者取消爬取任务
+  llm: Retrieve the scraping results based on the job ID, or cancel the scraping task.
+parameters:
+  - name: job_id
+    type: string
+    required: true
+    label:
+      en_US: Job ID
+    human_description:
+      en_US: Set wait_for_results to false in the Crawl tool can get the job ID.
+      zh_Hans: 在深度爬取工具中将等待爬取结果设置为否可以获取Job ID。
+    llm_description: Set wait_for_results to false in the Crawl tool can get the job ID.
+    form: llm
+  - name: operation
+    type: select
+    required: true
+    options:
+      - value: get
+        label:
+          en_US: get crawl status
+      - value: cancel
+        label:
+          en_US: cancel crawl job
+    label:
+      en_US: operation
+      zh_Hans: 操作
+    llm_description: choose the operation to perform. `get` is for getting the crawl status, `cancel` is for cancelling the crawl job.
+    form: llm
diff --git a/api/core/tools/provider/builtin/firecrawl/tools/scrape.py b/api/core/tools/provider/builtin/firecrawl/tools/scrape.py
index 3a78dce8d0..91412da548 100644
--- a/api/core/tools/provider/builtin/firecrawl/tools/scrape.py
+++ b/api/core/tools/provider/builtin/firecrawl/tools/scrape.py
@@ -1,26 +1,39 @@
-import json
-from typing import Any, Union
+from typing import Any
 
 from core.tools.entities.tool_entities import ToolInvokeMessage
-from core.tools.provider.builtin.firecrawl.firecrawl_appx import FirecrawlApp
+from core.tools.provider.builtin.firecrawl.firecrawl_appx import FirecrawlApp, get_array_params, get_json_params
 from core.tools.tool.builtin_tool import BuiltinTool
 
 
 class ScrapeTool(BuiltinTool):
-    def _invoke(self, user_id: str, tool_parameters: dict[str, Any]) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
-        app = FirecrawlApp(api_key=self.runtime.credentials['firecrawl_api_key'], base_url=self.runtime.credentials['base_url'])
 
-        crawl_result = app.scrape_url(
-            url=tool_parameters['url'],
-            wait=True
-        )
+    def _invoke(self, user_id: str, tool_parameters: dict[str, Any]) -> ToolInvokeMessage:
+        """
+        the pageOptions and extractorOptions comes from doc here:
+        https://docs.firecrawl.dev/api-reference/endpoint/scrape
+        """
+        app = FirecrawlApp(api_key=self.runtime.credentials['firecrawl_api_key'],
+                           base_url=self.runtime.credentials['base_url'])
 
-        if isinstance(crawl_result, dict):
-            result_message = json.dumps(crawl_result, ensure_ascii=False, indent=4)
-        else:
-            result_message = str(crawl_result)
+        pageOptions = {}
+        extractorOptions = {}
 
-        if not crawl_result:
-            return self.create_text_message("Scrape request failed.")
+        pageOptions['headers'] = get_json_params(tool_parameters, 'headers')
+        pageOptions['includeHtml'] = tool_parameters.get('includeHtml', False)
+        pageOptions['includeRawHtml'] = tool_parameters.get('includeRawHtml', False)
+        pageOptions['onlyIncludeTags'] = get_array_params(tool_parameters, 'onlyIncludeTags')
+        pageOptions['removeTags'] = get_array_params(tool_parameters, 'removeTags')
+        pageOptions['onlyMainContent'] = tool_parameters.get('onlyMainContent', False)
+        pageOptions['replaceAllPathsWithAbsolutePaths'] = tool_parameters.get('replaceAllPathsWithAbsolutePaths', False)
+        pageOptions['screenshot'] = tool_parameters.get('screenshot', False)
+        pageOptions['waitFor'] = tool_parameters.get('waitFor', 0)
 
-        return self.create_text_message(result_message)
+        extractorOptions['mode'] = tool_parameters.get('mode', '')
+        extractorOptions['extractionPrompt'] = tool_parameters.get('extractionPrompt', '')
+        extractorOptions['extractionSchema'] = get_json_params(tool_parameters, 'extractionSchema')
+
+        crawl_result = app.scrape_url(url=tool_parameters['url'],
+                                      pageOptions=pageOptions,
+                                      extractorOptions=extractorOptions)
+
+        return self.create_json_message(crawl_result)
diff --git a/api/core/tools/provider/builtin/firecrawl/tools/scrape.yaml b/api/core/tools/provider/builtin/firecrawl/tools/scrape.yaml
index 29aa5991aa..598429de5e 100644
--- a/api/core/tools/provider/builtin/firecrawl/tools/scrape.yaml
+++ b/api/core/tools/provider/builtin/firecrawl/tools/scrape.yaml
@@ -3,7 +3,7 @@ identity:
   author: ahasasjeb
   label:
     en_US: Scrape
-    zh_Hans: 抓取
+    zh_Hans: 单页面抓取
 description:
   human:
     en_US: Extract data from a single URL.
@@ -21,3 +21,160 @@ parameters:
       zh_Hans: 要抓取并提取数据的网站URL。
     llm_description: The URL of the website that needs to be crawled. This is a required parameter.
     form: llm
+############## Page Options #######################
+  - name: headers
+    type: string
+    label:
+      en_US: headers
+      zh_Hans: 请求头
+    human_description:
+      en_US: |
+        Headers to send with the request. Can be used to send cookies, user-agent, etc. Example: {"cookies": "testcookies"}
+      zh_Hans: |
+        随请求发送的头部。可以用来发送cookies、用户代理等。示例：{"cookies": "testcookies"}
+    placeholder:
+      en_US: Please enter an object that can be serialized in JSON
+      zh_Hans: 请输入可以json序列化的对象
+    form: form
+  - name: includeHtml
+    type: boolean
+    default: false
+    label:
+      en_US: include Html
+      zh_Hans: 包含HTML
+    human_description:
+      en_US: Include the HTML version of the content on page. Will output a html key in the response.
+      zh_Hans: 返回中包含一个HTML版本的内容，将以html键返回。
+    form: form
+  - name: includeRawHtml
+    type: boolean
+    default: false
+    label:
+      en_US: include Raw Html
+      zh_Hans: 包含原始HTML
+    human_description:
+      en_US: Include the raw HTML content of the page. Will output a rawHtml key in the response.
+      zh_Hans: 返回中包含一个原始HTML版本的内容，将以rawHtml键返回。
+    form: form
+  - name: onlyIncludeTags
+    type: string
+    label:
+      en_US: only Include Tags
+      zh_Hans: 仅抓取这些标签
+    placeholder:
+      en_US: Use commas to separate multiple tags
+      zh_Hans: 多个标签时使用半角逗号分隔
+    human_description:
+      en_US: |
+        Only include tags, classes and ids from the page in the final output. Use comma separated values. Example: script, .ad, #footer
+      zh_Hans: |
+        仅在最终输出中包含HTML页面的这些标签，可以通过标签名、类或ID来设定，使用逗号分隔值。示例：script, .ad, #footer
+    form: form
+  - name: onlyMainContent
+    type: boolean
+    default: false
+    label:
+      en_US: only Main Content
+      zh_Hans: 仅抓取主要内容
+    human_description:
+      en_US: Only return the main content of the page excluding headers, navs, footers, etc.
+      zh_Hans: 只返回页面的主要内容，不包括头部、导航栏、尾部等。
+    form: form
+  - name: removeTags
+    type: string
+    label:
+      en_US: remove Tags
+      zh_Hans: 要移除这些标签
+    human_description:
+      en_US: |
+        Tags, classes and ids to remove from the page. Use comma separated values. Example: script, .ad, #footer
+      zh_Hans: |
+        要在最终输出中移除HTML页面的这些标签，可以通过标签名、类或ID来设定，使用逗号分隔值。示例：script, .ad, #footer
+    placeholder:
+      en_US: Use commas to separate multiple tags
+      zh_Hans: 多个标签时使用半角逗号分隔
+    form: form
+  - name: replaceAllPathsWithAbsolutePaths
+    type: boolean
+    default: false
+    label:
+      en_US: All AbsolutePaths
+      zh_Hans: 使用绝对路径
+    human_description:
+      en_US: Replace all relative paths with absolute paths for images and links.
+      zh_Hans: 将所有图片和链接的相对路径替换为绝对路径。
+    form: form
+  - name: screenshot
+    type: boolean
+    default: false
+    label:
+      en_US: screenshot
+      zh_Hans: 截图
+    human_description:
+      en_US: Include a screenshot of the top of the page that you are scraping.
+      zh_Hans: 提供正在抓取的页面的顶部的截图。
+    form: form
+  - name: waitFor
+    type: number
+    min: 0
+    label:
+      en_US: wait For
+      zh_Hans: 等待时间
+    human_description:
+      en_US: Wait x amount of milliseconds for the page to load to fetch content.
+      zh_Hans: 等待x毫秒以使页面加载并获取内容。
+    form: form
+############## Extractor Options #######################
+  - name: mode
+    type: select
+    options:
+      - value: markdown
+        label:
+          en_US: markdown
+      - value: llm-extraction
+        label:
+          en_US: llm-extraction
+      - value: llm-extraction-from-raw-html
+        label:
+          en_US: llm-extraction-from-raw-html
+      - value: llm-extraction-from-markdown
+        label:
+          en_US: llm-extraction-from-markdown
+    label:
+      en_US: Extractor Mode
+      zh_Hans: 提取模式
+    human_description:
+      en_US: |
+       The extraction mode to use. 'markdown': Returns the scraped markdown content, does not perform LLM extraction. 'llm-extraction': Extracts information from the cleaned and parsed content using LLM.
+      zh_Hans: 使用的提取模式。“markdown”：返回抓取的markdown内容，不执行LLM提取。“llm-extractioin”：使用LLM按Extractor Schema从内容中提取信息。
+    form: form
+  - name: extractionPrompt
+    type: string
+    label:
+      en_US: Extractor Prompt
+      zh_Hans: 提取时的提示词
+    human_description:
+      en_US: A prompt describing what information to extract from the page, applicable for LLM extraction modes.
+      zh_Hans: 当使用LLM提取模式时，用于给LLM描述提取规则。
+    form: form
+  - name: extractionSchema
+    type: string
+    label:
+      en_US: Extractor Schema
+      zh_Hans: 提取时的结构
+    placeholder:
+      en_US: Please enter an object that can be serialized in JSON
+    human_description:
+      en_US: |
+        The schema for the data to be extracted, required only for LLM extraction modes. Example: {
+            "type": "object",
+            "properties": {"company_mission": {"type": "string"}},
+            "required": ["company_mission"]
+        }
+      zh_Hans: |
+       当使用LLM提取模式时，使用该结构去提取，示例：{
+            "type": "object",
+            "properties": {"company_mission": {"type": "string"}},
+            "required": ["company_mission"]
+        }
+    form: form
diff --git a/api/core/tools/provider/builtin/firecrawl/tools/search.py b/api/core/tools/provider/builtin/firecrawl/tools/search.py
index 0b118aa5f1..e2b2ac6b4d 100644
--- a/api/core/tools/provider/builtin/firecrawl/tools/search.py
+++ b/api/core/tools/provider/builtin/firecrawl/tools/search.py
@@ -1,5 +1,4 @@
-import json
-from typing import Any, Union
+from typing import Any
 
 from core.tools.entities.tool_entities import ToolInvokeMessage
 from core.tools.provider.builtin.firecrawl.firecrawl_appx import FirecrawlApp
@@ -7,20 +6,23 @@ from core.tools.tool.builtin_tool import BuiltinTool
 
 
 class SearchTool(BuiltinTool):
-    def _invoke(self, user_id: str, tool_parameters: dict[str, Any]) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
-        app = FirecrawlApp(api_key=self.runtime.credentials['firecrawl_api_key'], base_url=self.runtime.credentials['base_url'])
-
-        crawl_result = app.search(
+    def _invoke(self, user_id: str, tool_parameters: dict[str, Any]) -> ToolInvokeMessage:
+        """
+        the pageOptions and searchOptions comes from doc here:
+        https://docs.firecrawl.dev/api-reference/endpoint/search
+        """
+        app = FirecrawlApp(api_key=self.runtime.credentials['firecrawl_api_key'],
+                           base_url=self.runtime.credentials['base_url'])
+        pageOptions = {}
+        pageOptions['onlyMainContent'] = tool_parameters.get('onlyMainContent', False)
+        pageOptions['fetchPageContent'] = tool_parameters.get('fetchPageContent', True)
+        pageOptions['includeHtml'] = tool_parameters.get('includeHtml', False)
+        pageOptions['includeRawHtml'] = tool_parameters.get('includeRawHtml', False)
+        searchOptions = {'limit': tool_parameters.get('limit')}
+        search_result = app.search(
             query=tool_parameters['keyword'],
-            wait=True
+            pageOptions=pageOptions,
+            searchOptions=searchOptions
         )
 
-        if isinstance(crawl_result, dict):
-            result_message = json.dumps(crawl_result, ensure_ascii=False, indent=4)
-        else:
-            result_message = str(crawl_result)
-
-        if not crawl_result:
-            return self.create_text_message("Search request failed.")
-
-        return self.create_text_message(result_message)
+        return self.create_json_message(search_result)
diff --git a/api/core/tools/provider/builtin/firecrawl/tools/search.yaml b/api/core/tools/provider/builtin/firecrawl/tools/search.yaml
index b1513c914e..29df0cfaaa 100644
--- a/api/core/tools/provider/builtin/firecrawl/tools/search.yaml
+++ b/api/core/tools/provider/builtin/firecrawl/tools/search.yaml
@@ -21,3 +21,55 @@ parameters:
       zh_Hans: 输入关键词即可使用Firecrawl API进行搜索。
     llm_description: Efficiently extract keywords from user text.
     form: llm
+############## Page Options #######################
+  - name: onlyMainContent
+    type: boolean
+    default: false
+    label:
+      en_US: only Main Content
+      zh_Hans: 仅抓取主要内容
+    human_description:
+      en_US: Only return the main content of the page excluding headers, navs, footers, etc.
+      zh_Hans: 只返回页面的主要内容，不包括头部、导航栏、尾部等。
+    form: form
+  - name: fetchPageContent
+    type: boolean
+    default: true
+    label:
+      en_US: fetch Page Content
+      zh_Hans: 抓取页面内容
+    human_description:
+      en_US: Fetch the content of each page. If false, defaults to a basic fast serp API.
+      zh_Hans: 获取每个页面的内容。如果为否，则使用基本的快速搜索结果页面API。
+    form: form
+  - name: includeHtml
+    type: boolean
+    default: false
+    label:
+      en_US: include Html
+      zh_Hans: 包含HTML
+    human_description:
+      en_US: Include the HTML version of the content on page. Will output a html key in the response.
+      zh_Hans: 返回中包含一个HTML版本的内容，将以html键返回。
+    form: form
+  - name: includeRawHtml
+    type: boolean
+    default: false
+    label:
+      en_US: include Raw Html
+      zh_Hans: 包含原始HTML
+    human_description:
+      en_US: Include the raw HTML content of the page. Will output a rawHtml key in the response.
+      zh_Hans: 返回中包含一个原始HTML版本的内容，将以rawHtml键返回。
+    form: form
+############## Search Options #######################
+  - name: limit
+    type: number
+    min: 0
+    label:
+      en_US: Maximum results
+      zh_Hans: 最大结果数量
+    human_description:
+      en_US: Maximum number of results. Max is 20 during beta.
+      zh_Hans: 最大结果数量。在测试阶段，最大为20。
+    form: form

From e23461c837b099c2e65fd539ad01ca7bd36ab789 Mon Sep 17 00:00:00 2001
From: Hiroshige Aoki <58395317+HiroshigeAoki@users.noreply.github.com>
Date: Sun, 28 Jul 2024 10:42:58 +0900
Subject: [PATCH 36/60] Fix/6615 40 varchar limit on DatasetCollectionBinding
 and Embedding model name (#6723)

---
 ...e349e6ac_increase_max_model_name_length.py | 53 +++++++++++++++++++
 api/models/dataset.py                         |  4 +-
 2 files changed, 55 insertions(+), 2 deletions(-)
 create mode 100644 api/migrations/versions/eeb2e349e6ac_increase_max_model_name_length.py

diff --git a/api/migrations/versions/eeb2e349e6ac_increase_max_model_name_length.py b/api/migrations/versions/eeb2e349e6ac_increase_max_model_name_length.py
new file mode 100644
index 0000000000..434531b6c8
--- /dev/null
+++ b/api/migrations/versions/eeb2e349e6ac_increase_max_model_name_length.py
@@ -0,0 +1,53 @@
+"""increase max model_name length
+
+Revision ID: eeb2e349e6ac
+Revises: 53bf8af60645
+Create Date: 2024-07-26 12:02:00.750358
+
+"""
+import sqlalchemy as sa
+from alembic import op
+
+import models as models
+
+# revision identifiers, used by Alembic.
+revision = 'eeb2e349e6ac'
+down_revision = '53bf8af60645'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('dataset_collection_bindings', schema=None) as batch_op:
+        batch_op.alter_column('model_name',
+               existing_type=sa.VARCHAR(length=40),
+               type_=sa.String(length=255),
+               existing_nullable=False)
+
+    with op.batch_alter_table('embeddings', schema=None) as batch_op:
+        batch_op.alter_column('model_name',
+               existing_type=sa.VARCHAR(length=40),
+               type_=sa.String(length=255),
+               existing_nullable=False,
+               existing_server_default=sa.text("'text-embedding-ada-002'::character varying"))
+
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('embeddings', schema=None) as batch_op:
+        batch_op.alter_column('model_name',
+               existing_type=sa.String(length=255),
+               type_=sa.VARCHAR(length=40),
+               existing_nullable=False,
+               existing_server_default=sa.text("'text-embedding-ada-002'::character varying"))
+
+    with op.batch_alter_table('dataset_collection_bindings', schema=None) as batch_op:
+        batch_op.alter_column('model_name',
+               existing_type=sa.String(length=255),
+               type_=sa.VARCHAR(length=40),
+               existing_nullable=False)
+
+    # ### end Alembic commands ###
diff --git a/api/models/dataset.py b/api/models/dataset.py
index ca1c4583a6..40f9f4cf83 100644
--- a/api/models/dataset.py
+++ b/api/models/dataset.py
@@ -635,7 +635,7 @@ class Embedding(db.Model):
     )
 
     id = db.Column(StringUUID, primary_key=True, server_default=db.text('uuid_generate_v4()'))
-    model_name = db.Column(db.String(40), nullable=False,
+    model_name = db.Column(db.String(255), nullable=False,
                            server_default=db.text("'text-embedding-ada-002'::character varying"))
     hash = db.Column(db.String(64), nullable=False)
     embedding = db.Column(db.LargeBinary, nullable=False)
@@ -660,7 +660,7 @@ class DatasetCollectionBinding(db.Model):
 
     id = db.Column(StringUUID, primary_key=True, server_default=db.text('uuid_generate_v4()'))
     provider_name = db.Column(db.String(40), nullable=False)
-    model_name = db.Column(db.String(40), nullable=False)
+    model_name = db.Column(db.String(255), nullable=False)
     type = db.Column(db.String(40), server_default=db.text("'dataset'::character varying"), nullable=False)
     collection_name = db.Column(db.String(64), nullable=False)
     created_at = db.Column(db.DateTime, nullable=False, server_default=db.text('CURRENT_TIMESTAMP(0)'))

From 829472a1d75301bd04d3ae45b8eac2ba5ebf5e1a Mon Sep 17 00:00:00 2001
From: Vicky Guo <vicky.guo97@gmail.com>
Date: Sun, 28 Jul 2024 14:57:45 -0400
Subject: [PATCH 37/60] switch to diffy_config with Pydantic in files,
 moderation and app (#6747)

Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
---
 api/core/app/apps/base_app_queue_manager.py |  4 ++--
 api/core/file/upload_file_parser.py         | 13 ++++++-------
 api/core/moderation/output_moderation.py    |  3 ++-
 3 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/api/core/app/apps/base_app_queue_manager.py b/api/core/app/apps/base_app_queue_manager.py
index dd2343d0b1..f929a979f1 100644
--- a/api/core/app/apps/base_app_queue_manager.py
+++ b/api/core/app/apps/base_app_queue_manager.py
@@ -5,9 +5,9 @@ from collections.abc import Generator
 from enum import Enum
 from typing import Any
 
-from flask import current_app
 from sqlalchemy.orm import DeclarativeMeta
 
+from configs import dify_config
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.app.entities.queue_entities import (
     AppQueueEvent,
@@ -48,7 +48,7 @@ class AppQueueManager:
         :return:
         """
         # wait for APP_MAX_EXECUTION_TIME seconds to stop listen
-        listen_timeout = current_app.config.get("APP_MAX_EXECUTION_TIME")
+        listen_timeout = dify_config.APP_MAX_EXECUTION_TIME
         start_time = time.time()
         last_ping_time = 0
         while True:
diff --git a/api/core/file/upload_file_parser.py b/api/core/file/upload_file_parser.py
index 9e454f08d4..737a11e426 100644
--- a/api/core/file/upload_file_parser.py
+++ b/api/core/file/upload_file_parser.py
@@ -6,8 +6,7 @@ import os
 import time
 from typing import Optional
 
-from flask import current_app
-
+from configs import dify_config
 from extensions.ext_storage import storage
 
 IMAGE_EXTENSIONS = ['jpg', 'jpeg', 'png', 'webp', 'gif', 'svg']
@@ -23,7 +22,7 @@ class UploadFileParser:
         if upload_file.extension not in IMAGE_EXTENSIONS:
             return None
 
-        if current_app.config['MULTIMODAL_SEND_IMAGE_FORMAT'] == 'url' or force_url:
+        if dify_config.MULTIMODAL_SEND_IMAGE_FORMAT == 'url' or force_url:
             return cls.get_signed_temp_image_url(upload_file.id)
         else:
             # get image file base64
@@ -44,13 +43,13 @@ class UploadFileParser:
         :param upload_file: UploadFile object
         :return:
         """
-        base_url = current_app.config.get('FILES_URL')
+        base_url = dify_config.FILES_URL
         image_preview_url = f'{base_url}/files/{upload_file_id}/image-preview'
 
         timestamp = str(int(time.time()))
         nonce = os.urandom(16).hex()
         data_to_sign = f"image-preview|{upload_file_id}|{timestamp}|{nonce}"
-        secret_key = current_app.config['SECRET_KEY'].encode()
+        secret_key = dify_config.SECRET_KEY.encode()
         sign = hmac.new(secret_key, data_to_sign.encode(), hashlib.sha256).digest()
         encoded_sign = base64.urlsafe_b64encode(sign).decode()
 
@@ -68,7 +67,7 @@ class UploadFileParser:
         :return:
         """
         data_to_sign = f"image-preview|{upload_file_id}|{timestamp}|{nonce}"
-        secret_key = current_app.config['SECRET_KEY'].encode()
+        secret_key = dify_config.SECRET_KEY.encode()
         recalculated_sign = hmac.new(secret_key, data_to_sign.encode(), hashlib.sha256).digest()
         recalculated_encoded_sign = base64.urlsafe_b64encode(recalculated_sign).decode()
 
@@ -77,4 +76,4 @@ class UploadFileParser:
             return False
 
         current_time = int(time.time())
-        return current_time - int(timestamp) <= current_app.config.get('FILES_ACCESS_TIMEOUT')
+        return current_time - int(timestamp) <= dify_config.FILES_ACCESS_TIMEOUT
diff --git a/api/core/moderation/output_moderation.py b/api/core/moderation/output_moderation.py
index 3587466952..4fd08ca021 100644
--- a/api/core/moderation/output_moderation.py
+++ b/api/core/moderation/output_moderation.py
@@ -6,6 +6,7 @@ from typing import Any, Optional
 from flask import Flask, current_app
 from pydantic import BaseModel, ConfigDict
 
+from configs import dify_config
 from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom
 from core.app.entities.queue_entities import QueueMessageReplaceEvent
 from core.moderation.base import ModerationAction, ModerationOutputsResult
@@ -76,7 +77,7 @@ class OutputModeration(BaseModel):
         return final_output
 
     def start_thread(self) -> threading.Thread:
-        buffer_size = int(current_app.config.get('MODERATION_BUFFER_SIZE', self.DEFAULT_BUFFER_SIZE))
+        buffer_size = int(dify_config.config.MODERATION_BUFFER_SIZE)
         thread = threading.Thread(target=self.worker, kwargs={
             'flask_app': current_app._get_current_object(),
             'buffer_size': buffer_size if buffer_size > 0 else self.DEFAULT_BUFFER_SIZE

From c8da4a1b7edc3be04d0fbe970508e024109ac079 Mon Sep 17 00:00:00 2001
From: Hanqing Zhao <sherry9277@gmail.com>
Date: Mon, 29 Jul 2024 08:58:48 +0800
Subject: [PATCH 38/60] Add jp translation for new features (#6749)

---
 CONTRIBUTING_JA.md                   |  10 +--
 web/i18n/en-US/dataset-creation.ts   |   2 +-
 web/i18n/en-US/dataset.ts            |   2 +-
 web/i18n/es-ES/dataset-creation.ts   |   2 +-
 web/i18n/ja-JP/app-annotation.ts     |   2 +-
 web/i18n/ja-JP/app-api.ts            |   1 +
 web/i18n/ja-JP/app-debug.ts          |  58 +++++++++++++-
 web/i18n/ja-JP/app-overview.ts       |   4 +-
 web/i18n/ja-JP/app.ts                |  42 +++++++++-
 web/i18n/ja-JP/billing.ts            |   7 +-
 web/i18n/ja-JP/common.ts             | 110 +++++++++++++++++++++++----
 web/i18n/ja-JP/dataset-creation.ts   |  31 ++++++++
 web/i18n/ja-JP/dataset-documents.ts  |   3 +
 web/i18n/ja-JP/dataset-settings.ts   |   2 +
 web/i18n/ja-JP/dataset.ts            |  41 +++++++---
 web/i18n/ja-JP/login.ts              |   6 +-
 web/i18n/ja-JP/tools.ts              |  36 ++++++++-
 web/i18n/zh-Hans/dataset-creation.ts |   2 +-
 18 files changed, 318 insertions(+), 43 deletions(-)

diff --git a/CONTRIBUTING_JA.md b/CONTRIBUTING_JA.md
index 1ce8436a78..6d5bfb205c 100644
--- a/CONTRIBUTING_JA.md
+++ b/CONTRIBUTING_JA.md
@@ -1,7 +1,7 @@
 Dify にコントリビュートしたいとお考えなのですね。それは素晴らしいことです。
 私たちは、LLM アプリケーションの構築と管理のための最も直感的なワークフローを設計するという壮大な野望を持っています。人数も資金も限られている新興企業として、コミュニティからの支援は本当に重要です。
 
-私たちは現状を鑑み、機敏かつ迅速に開発をする必要がありますが、同時にあなたのようなコントリビューターの方々に、可能な限りスムーズな貢献体験をしていただきたいと思っています。そのためにこのコントリビュートガイドを作成しました。
+私たちは現状を鑑み、機敏かつ迅速に開発をする必要がありますが、同時にあなた様のようなコントリビューターの方々に、可能な限りスムーズな貢献体験をしていただきたいと思っています。そのためにこのコントリビュートガイドを作成しました。
 コードベースやコントリビュータの方々と私たちがどのように仕事をしているのかに慣れていただき、楽しいパートにすぐに飛び込めるようにすることが目的です。
 
 このガイドは Dify そのものと同様に、継続的に改善されています。実際のプロジェクトに遅れをとることがあるかもしれませんが、ご理解のほどよろしくお願いいたします。
@@ -14,13 +14,13 @@ Dify にコントリビュートしたいとお考えなのですね。それは
 
 ### 機能リクエスト
 
-* 新しい機能要望を出す場合は、提案する機能が何を実現するものなのかを説明し、可能な限り多くのコンテキストを含めてください。[@perzeusss](https://github.com/perzeuss)は、あなたの要望を書き出すのに役立つ [Feature Request Copilot](https://udify.app/chat/MK2kVSnw1gakVwMX) を作ってくれました。気軽に試してみてください。
+* 新しい機能要望を出す場合は、提案する機能が何を実現するものなのかを説明し、可能な限り多くのコンテキストを含めてください。[@perzeusss](https://github.com/perzeuss)は、あなた様の要望を書き出すのに役立つ [Feature Request Copilot](https://udify.app/chat/MK2kVSnw1gakVwMX) を作ってくれました。気軽に試してみてください。
 
 * 既存の課題から 1 つ選びたい場合は、その下にコメントを書いてください。
 
-  関連する方向で作業しているチームメンバーが参加します。すべてが良好であれば、コーディングを開始する許可が与えられます。私たちが変更を提案した場合にあなたの作業が無駄になることがないよう、それまでこの機能の作業を控えていただくようお願いいたします。
+  関連する方向で作業しているチームメンバーが参加します。すべてが良好であれば、コーディングを開始する許可が与えられます。私たちが変更を提案した場合にあなた様の作業が無駄になることがないよう、それまでこの機能の作業を控えていただくようお願いいたします。
 
-  提案された機能がどの分野に属するかによって、あなたは異なるチーム・メンバーと話をするかもしれません。以下は、各チームメンバーが現在取り組んでいる分野の概要です。
+  提案された機能がどの分野に属するかによって、あなた様は異なるチーム・メンバーと話をするかもしれません。以下は、各チームメンバーが現在取り組んでいる分野の概要です。
 
 | Member                                                                                  | Scope                                |
 | --------------------------------------------------------------------------------------- | ------------------------------------ |
@@ -153,7 +153,7 @@ Dify のバックエンドは[Flask](https://flask.palletsprojects.com/en/3.0.x/
 いよいよ、私たちのリポジトリにプルリクエスト (PR) を提出する時が来ました。主要な機能については、まず `deploy/dev` ブランチにマージしてテストしてから `main` ブランチにマージします。
 マージ競合などの問題が発生した場合、またはプル リクエストを開く方法がわからない場合は、[GitHub's pull request tutorial](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests) をチェックしてみてください。
 
-これで完了です！あなたの PR がマージされると、[README](https://github.com/langgenius/dify/blob/main/README.md) にコントリビューターとして紹介されます。
+これで完了です！あなた様の PR がマージされると、[README](https://github.com/langgenius/dify/blob/main/README.md) にコントリビューターとして紹介されます。
 
 ## ヘルプを得る
 
diff --git a/web/i18n/en-US/dataset-creation.ts b/web/i18n/en-US/dataset-creation.ts
index 23e1aab89f..1ead19f7e6 100644
--- a/web/i18n/en-US/dataset-creation.ts
+++ b/web/i18n/en-US/dataset-creation.ts
@@ -62,7 +62,7 @@ const translation = {
       run: 'Run',
       firecrawlTitle: 'Extract web content with 🔥Firecrawl',
       firecrawlDoc: 'Firecrawl docs',
-      firecrawlDocLink: 'https://docs.dify.ai/guides/knowledge-base/sync_from_website',
+      firecrawlDocLink: 'https://docs.dify.ai/guides/knowledge-base/sync-from-website',
       options: 'Options',
       crawlSubPage: 'Crawl sub-pages',
       limit: 'Limit',
diff --git a/web/i18n/en-US/dataset.ts b/web/i18n/en-US/dataset.ts
index d26c3fd061..f64a7dbf8d 100644
--- a/web/i18n/en-US/dataset.ts
+++ b/web/i18n/en-US/dataset.ts
@@ -60,7 +60,7 @@ const translation = {
   rerankSettings: 'Rerank Setting',
   weightedScore: {
     title: 'Weighted Score',
-    description: 'By adjusting the weights assigned， this rerank strategy determines whether to prioritize semantic or keyword matching.',
+    description: 'By adjusting the weights assigned, this rerank strategy determines whether to prioritize semantic or keyword matching.',
     semanticFirst: 'Semantic first',
     keywordFirst: 'Keyword first',
     customized: 'Customized',
diff --git a/web/i18n/es-ES/dataset-creation.ts b/web/i18n/es-ES/dataset-creation.ts
index f8ef14f89b..66b8e9b302 100644
--- a/web/i18n/es-ES/dataset-creation.ts
+++ b/web/i18n/es-ES/dataset-creation.ts
@@ -62,7 +62,7 @@ const translation = {
       run: 'Ejecutar',
       firecrawlTitle: 'Extraer contenido web con 🔥Firecrawl',
       firecrawlDoc: 'Documentación de Firecrawl',
-      firecrawlDocLink: 'https://docs.dify.ai/guides/knowledge-base/sync_from_website',
+      firecrawlDocLink: 'https://docs.dify.ai/guides/knowledge-base/sync-from-website',
       options: 'Opciones',
       crawlSubPage: 'Rastrear subpáginas',
       limit: 'Límite',
diff --git a/web/i18n/ja-JP/app-annotation.ts b/web/i18n/ja-JP/app-annotation.ts
index ec91a1448c..6c6c98cdd0 100644
--- a/web/i18n/ja-JP/app-annotation.ts
+++ b/web/i18n/ja-JP/app-annotation.ts
@@ -23,7 +23,7 @@ const translation = {
     title: '注釈の返信を編集',
     queryName: 'ユーザーのクエリ',
     answerName: 'ストーリーテラーボット',
-    yourAnswer: 'あなたの回答',
+    yourAnswer: '貴方の回答',
     answerPlaceholder: 'ここに回答を入力してください',
     yourQuery: 'あなたのクエリ',
     queryPlaceholder: 'ここにクエリを入力してください',
diff --git a/web/i18n/ja-JP/app-api.ts b/web/i18n/ja-JP/app-api.ts
index 0f86e8028a..63beaeb45c 100644
--- a/web/i18n/ja-JP/app-api.ts
+++ b/web/i18n/ja-JP/app-api.ts
@@ -9,6 +9,7 @@ const translation = {
   play: '再生',
   pause: '一時停止',
   playing: '再生中',
+  loading: '読み込み中',
   merMaind: {
     rerender: '再レンダリング',
   },
diff --git a/web/i18n/ja-JP/app-debug.ts b/web/i18n/ja-JP/app-debug.ts
index e38922ea10..8535f79b95 100644
--- a/web/i18n/ja-JP/app-debug.ts
+++ b/web/i18n/ja-JP/app-debug.ts
@@ -38,7 +38,6 @@ const translation = {
     description: 'LLMプロバイダーキーが設定されていません。デバッグする前に設定する必要があります。',
     settingBtn: '設定に移動',
   },
-
   trailUseGPT4Info: {
     title: '現在、gpt-4はサポートされていません',
     description: 'gpt-4を使用するには、APIキーを設定してください。',
@@ -161,7 +160,6 @@ const translation = {
     toolbox: {
       title: 'ツールボックス',
     },
-
     moderation: {
       title: 'コンテンツのモデレーション',
       description: 'モデレーションAPIを使用するか、機密語リストを維持することで、モデルの出力を安全にします。',
@@ -200,7 +198,59 @@ const translation = {
         },
       },
     },
-
+  },
+  generate: {
+    title: 'プロンプト生成器',
+    description: 'プロンプト生成器は、設定済みのモデルを使って、高品質で構造的に優れたプロンプトを作成するための最適化を行います。具体的で詳細な指示をお書きください。',
+    tryIt: '試してみる',
+    instruction: '指示',
+    instructionPlaceHolder: '具体的で明確な指示を入力してください。',
+    generate: '生成',
+    resTitle: '生成されたプロンプト',
+    noDataLine1: '左側に使用例を記入してください,',
+    noDataLine2: 'オーケストレーションのプレビューがこちらに表示されます。',
+    apply: '適用',
+    loading: 'アプリケーションを処理中です',
+    overwriteTitle: '既存の設定を上書きしますか？',
+    overwriteMessage: 'このプロンプトを適用すると、既存の設定が上書きされます。',
+    template: {
+      pythonDebugger: {
+        name: 'Python デバッガー',
+        instruction: '指示に従ってコードを生成し、デバッグを行うボット',
+      },
+      translation: {
+        name: '翻訳',
+        instruction: '複数言語に対応した翻訳機能',
+      },
+      professionalAnalyst: {
+        name: '専門アナリスト',
+        instruction: '長文のレポートから洞察を引き出し、リスクを特定し、重要情報をまとめる',
+      },
+      excelFormulaExpert: {
+        name: 'エクセル式エキスパート',
+        instruction: 'ユーザーの指示に基づき、エクセル式の理解、使用、作成をサポートするチャットボット',
+      },
+      travelPlanning: {
+        name: '旅行計画',
+        instruction: 'ユーザーが簡単に旅行計画を立てられるように設計されたツール',
+      },
+      SQLSorcerer: {
+        name: 'SQLソーサラー',
+        instruction: '日常言語をSQLクエリに変換する',
+      },
+      GitGud: {
+        name: 'Git gud',
+        instruction: 'ユーザーが記述したバージョン管理アクションに対応するGitコマンドを生成する',
+      },
+      meetingTakeaways: {
+        name: '会議の要点',
+        instruction: '議題、重要点、行動項目を含む要約を作成する',
+      },
+      writingsPolisher: {
+        name: 'ライティングポリッシャー',
+        instruction: '文章を改善するための高度な編集技法を用いる',
+      },
+    },
   },
   resetConfig: {
     title: 'リセットを確認しますか？',
@@ -264,6 +314,7 @@ const translation = {
     'varName': '変数名',
     'labelName': 'ラベル名',
     'inputPlaceholder': '入力してください',
+    'content': 'コンテンツ',
     'required': '必須',
     'errorMsg': {
       varNameRequired: '変数名は必須です',
@@ -362,7 +413,6 @@ const translation = {
     score_thresholdTip: 'チャンクフィルタリングの類似性閾値を設定するために使用されます。',
     retrieveChangeTip: 'インデックスモードとリトリーバルモードを変更すると、このナレッジに関連付けられたアプリケーションに影響を与える可能性があります。',
   },
-
   debugAsSingleModel: '単一モデルでデバッグ',
   debugAsMultipleModel: '複数モデルでデバッグ',
   duplicateModel: '複製',
diff --git a/web/i18n/ja-JP/app-overview.ts b/web/i18n/ja-JP/app-overview.ts
index b7c87c94d1..1eb6fd1795 100644
--- a/web/i18n/ja-JP/app-overview.ts
+++ b/web/i18n/ja-JP/app-overview.ts
@@ -3,7 +3,7 @@ const translation = {
     firstStepTip: 'はじめるには、',
     enterKeyTip: '以下にOpenAI APIキーを入力してください',
     getKeyTip: 'OpenAIダッシュボードからAPIキーを取得してください',
-    placeholder: 'あなたのOpenAI APIキー（例：sk-xxxx）',
+    placeholder: 'あなた様のOpenAI APIキー（例：sk-xxxx）',
   },
   apiKeyInfo: {
     cloud: {
@@ -104,7 +104,7 @@ const translation = {
     },
     apiInfo: {
       title: 'バックエンドサービスAPI',
-      explanation: 'あなたのアプリケーションに簡単に統合できます',
+      explanation: 'あなた様のアプリケーションに簡単に統合できます',
       accessibleAddress: 'サービスAPIエンドポイント',
       doc: 'APIリファレンス',
     },
diff --git a/web/i18n/ja-JP/app.ts b/web/i18n/ja-JP/app.ts
index d5e2401687..91bca235f5 100644
--- a/web/i18n/ja-JP/app.ts
+++ b/web/i18n/ja-JP/app.ts
@@ -13,9 +13,13 @@ const translation = {
   exportFailed: 'DSL のエクスポートに失敗しました。',
   importDSL: 'DSL ファイルをインポート',
   createFromConfigFile: 'DSL ファイルから作成する',
+  importFromDSL: 'DSLからインポート',
+  importFromDSLFile: 'DSLファイルから',
+  importFromDSLUrl: 'URLから',
+  importFromDSLUrlPlaceholder: 'DSLリンクをここに貼り付けます',
   deleteAppConfirmTitle: 'このアプリを削除しますか？',
   deleteAppConfirmContent:
-    'アプリを削除すると、元に戻すことはできません。ユーザーはもはやあなたのアプリにアクセスできず、すべてのプロンプトの設定とログが永久に削除されます。',
+    'アプリを削除すると、元に戻すことはできません。ユーザーはもはやあなた様のアプリにアクセスできず、すべてのプロンプトの設定とログが永久に削除されます。',
   appDeleted: 'アプリが削除されました',
   appDeleteFailed: 'アプリの削除に失敗しました',
   join: 'コミュニティに参加する',
@@ -86,6 +90,42 @@ const translation = {
     workflow: 'ワークフロー',
     completion: 'テキスト生成',
   },
+  tracing: {
+    title: 'アプリのパフォーマンスの追跡',
+    description: 'サードパーティのLLMOpsサービスとトレースアプリケーションのパフォーマンス設定を行います。',
+    config: '設定',
+    collapse: 'Collapse',
+    expand: '展開',
+    tracing: '追跡',
+    disabled: '無効しました',
+    disabledTip: 'まずはサービスの設定から始めましょう。',
+    enabled: '有効しました',
+    tracingDescription: 'LLMの呼び出し、コンテキスト、プロンプト、HTTPリクエストなど、アプリケーション実行の全ての文脈をサードパーティのトレースプラットフォームで取り込みます。',
+    configProviderTitle: {
+      configured: '設定しました',
+      notConfigured: 'トレース機能を有効化するためには、サービスの設定が必要です。',
+      moreProvider: 'その他のプロバイダー',
+    },
+    langsmith: {
+      title: 'LangSmith',
+      description: 'LLMを利用したアプリケーションのライフサイクル全段階を支援する、オールインワンの開発者向けプラットフォームです。',
+    },
+    langfuse: {
+      title: 'Langfuse',
+      description: 'トレース、評価、プロンプトの管理、そしてメトリクスを駆使して、LLMアプリケーションのデバッグや改善に役立てます。',
+    },
+    inUse: '使用中',
+    configProvider: {
+      title: '配置 ',
+      placeholder: 'あなた様の{{key}}を入力しでください',
+      project: 'プロジェクト',
+      publicKey: '公開キー',
+      secretKey: '秘密キー',
+      viewDocsLink: '{{key}}のドキュメントを見る',
+      removeConfirmTitle: '{{key}}の設定を削除しますか？',
+      removeConfirmContent: '現在の設定は使用中です。これを削除すると、トレース機能が無効になります。',
+    },
+  },
 }
 
 export default translation
diff --git a/web/i18n/ja-JP/billing.ts b/web/i18n/ja-JP/billing.ts
index ace11503e7..6f90982506 100644
--- a/web/i18n/ja-JP/billing.ts
+++ b/web/i18n/ja-JP/billing.ts
@@ -8,7 +8,7 @@ const translation = {
   viewBilling: '請求とサブスクリプションの管理',
   buyPermissionDeniedTip: 'サブスクリプションするには、エンタープライズ管理者に連絡してください',
   plansCommon: {
-    title: 'あなたに合ったプランを選択してください',
+    title: 'あなた様に合ったプランを選択してください',
     yearlyTip: '年間購読で2か月無料！',
     mostPopular: '最も人気のある',
     planRange: {
@@ -28,10 +28,12 @@ const translation = {
     talkToSales: '営業と話す',
     modelProviders: 'モデルプロバイダー',
     teamMembers: 'チームメンバー',
+    annotationQuota: 'アノテーション・クォータ',
     buildApps: 'アプリを作成する',
     vectorSpace: 'ベクトルスペース',
     vectorSpaceBillingTooltip: '1MBあたり約120万文字のベクトル化データを保存できます（OpenAI Embeddingsを使用して推定され、モデルによって異なります）。',
     vectorSpaceTooltip: 'ベクトルスペースは、LLMがデータを理解するために必要な長期記憶システムです。',
+    documentsUploadQuota: 'ドキュメント・アップロード・クォータ',
     documentProcessingPriority: 'ドキュメント処理の優先度',
     documentProcessingPriorityTip: 'より高いドキュメント処理の優先度をご希望の場合は、プランをアップグレードしてください。',
     documentProcessingPriorityUpgrade: 'より高い精度と高速な速度でデータを処理します。',
@@ -56,8 +58,11 @@ const translation = {
       dedicatedAPISupport: '専用APIサポート',
       customIntegration: 'カスタム統合とサポート',
       ragAPIRequest: 'RAG APIリクエスト',
+      bulkUpload: 'ドキュメントの一括アップロード',
       agentMode: 'エージェントモード',
       workflow: 'ワークフロー',
+      llmLoadingBalancing: 'LLMロードバランシング',
+      llmLoadingBalancingTooltip: 'APIレート制限を効果的に回避するために、モデルに複数のAPIキーを追加する。',
     },
     comingSoon: '近日公開',
     member: 'メンバー',
diff --git a/web/i18n/ja-JP/common.ts b/web/i18n/ja-JP/common.ts
index b92a2ccd21..081b6dfb65 100644
--- a/web/i18n/ja-JP/common.ts
+++ b/web/i18n/ja-JP/common.ts
@@ -12,6 +12,7 @@ const translation = {
     cancel: 'キャンセル',
     clear: 'クリア',
     save: '保存',
+    saveAndEnable: '保存 & 有効に',
     edit: '編集',
     add: '追加',
     added: '追加済み',
@@ -37,6 +38,10 @@ const translation = {
     duplicate: '重複',
     rename: '名前の変更',
   },
+  errorMsg: {
+    fieldRequired: '{{field}}は必要です',
+    urlError: 'URL は http:// または https:// で始まる必要があります',
+  },
   placeholder: {
     input: '入力してください',
     select: '選択してください',
@@ -173,17 +178,21 @@ const translation = {
     adminTip: 'アプリの構築およびチーム設定の管理ができます',
     normal: '通常',
     normalTip: 'アプリの使用のみが可能で、アプリの構築はできません',
+    builder: 'ビルダー',
+    builderTip: '独自のアプリを作成・編集できる',
     editor: 'エディター',
     editorTip: 'アプリの構築ができますが、チーム設定の管理はできません',
+    datasetOperator: 'ナレッジ管理員',
+    datasetOperatorTip: 'ナレッジベースのみを管理できる',
     inviteTeamMember: 'チームメンバーを招待する',
-    inviteTeamMemberTip: '彼らはサインイン後、直接あなたのチームデータにアクセスできます。',
+    inviteTeamMemberTip: '彼らはサインイン後、直接あなた様のチームデータにアクセスできます。',
     email: 'メール',
     emailInvalid: '無効なメール形式',
     emailPlaceholder: 'メールを入力してください',
     sendInvite: '招待を送る',
     invitedAsRole: '{{role}}ユーザーとして招待されました',
     invitationSent: '招待が送信されました',
-    invitationSentTip: '招待が送信され、彼らはDifyにサインインしてあなたのチームデータにアクセスできます。',
+    invitationSentTip: '招待が送信され、彼らはDifyにサインインしてあなた様のチームデータにアクセスできます。',
     invitationLink: '招待リンク',
     failedinvitationEmails: '以下のユーザーは正常に招待されませんでした',
     ok: 'OK',
@@ -191,10 +200,11 @@ const translation = {
     removeFromTeamTip: 'チームへのアクセスが削除されます',
     setAdmin: '管理者に設定',
     setMember: '通常のメンバーに設定',
+    setBuilder: 'ビルダーに設定',
     setEditor: 'エディターに設定',
     disinvite: '招待をキャンセル',
     deleteMember: 'メンバーを削除',
-    you: '(あなた)',
+    you: '(あなた様)',
   },
   integrations: {
     connected: '接続済み',
@@ -285,6 +295,7 @@ const translation = {
       key: '再ランクモデル',
       tip: '再ランクモデルは、ユーザークエリとの意味的一致に基づいて候補文書リストを再配置し、意味的ランキングの結果を向上させます。',
     },
+    apiKey: 'API-キー',
     quota: 'クォータ',
     searchModel: '検索モデル',
     noModelFound: '{{model}}に対するモデルが見つかりません',
@@ -303,18 +314,91 @@ const translation = {
       quotaExhausted: 'クォータが使い果たされました',
       callTimes: '通話回数',
       tokens: 'トークン',
-      fee: '費用',
-      feeToken: 'トークン毎の費用',
-      basicSettings: '基本設定',
-      advancedSettings: '高度な設定',
-      comingSoon: '近日公開',
-      installPlugin: 'プラグインをインストール',
+      buyQuota: 'クォータを購入',
+      priorityUse: '優先利用',
+      removeKey: 'APIキーを削除',
+      tip: '有料クォータは優先して使用されます。有料クォータを使用し終えた後、トライアルクォータが利用されます。',
     },
+    item: {
+      deleteDesc: '{{modelName}}はシステムが推測するモデルとして利用されています。削除すると、一部の機能が使用不可能になる可能性があります。ご確認ください。',
+      freeQuota: '無料のクォータ',
+    },
+    addApiKey: 'APIキーを追加',
+    invalidApiKey: '無効なAPIキー',
+    encrypted: {
+      front: 'APIキーは',
+      back: ' の技術で暗号化されて保存されます。',
+    },
+    freeQuota: {
+      howToEarn: '獲得方法',
+    },
+    addMoreModelProvider: 'モデルプロバイダを追加',
+    addModel: 'モデルを追加',
+    modelsNum: '{{num}}のモデル',
+    showModels: 'モデルの表示',
+    showModelsNum: '{{num}}のモデルを表示',
+    collapse: '折り畳み',
+    config: '設定',
+    modelAndParameters: 'モデルとパラメータ',
+    model: 'モデル',
+    featureSupported: '{{feature}}に対応',
+    callTimes: '呼び出し回数',
+    credits: 'クレジット',
+    buyQuota: 'クォータ購入',
+    getFreeTokens: '無料トークンを獲得',
+    priorityUsing: '優先利用',
+    deprecated: '廃止予定',
+    confirmDelete: '削除を確認',
+    quotaTip: '残りの無料トークン',
+    loadPresets: 'プリセットの読み込み',
+    parameters: 'パラメータ',
+    loadBalancing: '負荷分散',
+    loadBalancingDescription: '複数の認証情報を使って負荷を分散させます。',
+    loadBalancingHeadline: '負荷分散',
+    configLoadBalancing: '負荷分散の設定',
+    modelHasBeenDeprecated: 'このモデルは廃止予定です',
+    providerManaged: 'プロバイダ管理',
+    providerManagedDescription: 'モデルプロバイダによって提供される認証情報を使用します。',
+    defaultConfig: 'デフォルトの設定',
+    apiKeyStatusNormal: 'APIキーの状態は正常',
+    apiKeyRateLimit: 'レート制限に到達しました。{{seconds}}秒後に再度利用可能です',
+    addConfig: '設定を追加',
+    editConfig: '設定を編集',
+    loadBalancingLeastKeyWarning: '負荷分散を利用するには、最低2つのキーを有効化する必要があります。',
+    loadBalancingInfo: 'デフォルトでは、負荷分散はラウンドロビン方式を採用しています。レート制限が発生した場合、1分間のクールダウン期間が適用されます。',
+    upgradeForLoadBalancing: '負荷分散を利用するには、プランのアップグレードが必要です。',
   },
   dataSource: {
-    externalAPI: '外部API',
-    webhooks: 'Webhook',
-    custom: 'カスタム',
+    add: 'データソースの追加',
+    connect: '接続',
+    configure: '設定',
+    notion: {
+      title: 'ノーション',
+      description: '知識データソースとしてノーションを使用します。',
+      connectedWorkspace: '接続済みワークスペース',
+      addWorkspace: 'ワークスペースの追加',
+      connected: '接続済み',
+      disconnected: '接続解除',
+      changeAuthorizedPages: '認証済みページの変更',
+      pagesAuthorized: '認証済みページ',
+      sync: '同期',
+      remove: '削除',
+      selector: {
+        pageSelected: '選択済みページ',
+        searchPages: 'ページ検索...',
+        noSearchResult: '検索結果なし',
+        addPages: 'ページの追加',
+        preview: 'プレビュー',
+      },
+    },
+    website: {
+      title: 'ウェブサイト',
+      description: 'ウェブクローラーを使ってウェブサイトからコンテンツを取り込みます。',
+      with: 'による',
+      configuredCrawlers: '設定済みクローラー',
+      active: 'アクティブ',
+      inactive: '非アクティブ',
+    },
   },
   plugin: {
     serpapi: {
@@ -360,7 +444,7 @@ const translation = {
   },
   appMenus: {
     overview: '概要',
-    promptEng: 'Orchestrate',
+    promptEng: 'オーケストレート',
     apiAccess: 'APIアクセス',
     logAndAnn: 'ログ＆アナウンス',
     logs: 'ログ',
diff --git a/web/i18n/ja-JP/dataset-creation.ts b/web/i18n/ja-JP/dataset-creation.ts
index 384c655214..448e208222 100644
--- a/web/i18n/ja-JP/dataset-creation.ts
+++ b/web/i18n/ja-JP/dataset-creation.ts
@@ -11,6 +11,11 @@ const translation = {
   error: {
     unavailable: 'このナレッジは利用できません',
   },
+  firecrawl: {
+    configFirecrawl: '🔥Firecrawlの設定',
+    apiKeyPlaceholder: 'firecrawl.devからのAPIキー',
+    getApiKeyLinkText: 'firecrawl.devからAPIキーを取得する',
+  },
   stepOne: {
     filePreview: 'ファイルプレビュー',
     pagePreview: 'ページプレビュー',
@@ -50,6 +55,30 @@ const translation = {
       confirmButton: '作成',
       failed: '作成に失敗しました',
     },
+    website: {
+      fireCrawlNotConfigured: 'Firecrawlが設定されていません',
+      fireCrawlNotConfiguredDescription: 'Firecrawl を使用するには、Firecrawl の API キーを設定してください。',
+      configure: '設定',
+      run: '実行',
+      firecrawlTitle: '🔥Firecrawlを使っでウエブコンテンツを抽出',
+      firecrawlDoc: 'Firecrawlドキュメント',
+      firecrawlDocLink: 'https://docs.dify.ai/guides/knowledge-base/sync-from-website',
+      options: 'オプション',
+      crawlSubPage: 'サブページをクロールする',
+      limit: '制限',
+      maxDepth: '最大深度',
+      excludePaths: 'パスを除外する',
+      includeOnlyPaths: 'パスのみを含める',
+      extractOnlyMainContent: 'メインコンテンツのみを抽出する(ヘッダー、ナビ、フッターなどは抽出しない)',
+      exceptionErrorTitle: 'Firecrawl ジョブの実行中に例外が発生しました:',
+      unknownError: '不明なエラー',
+      totalPageScraped: 'スクレイピングされた総ページ数:',
+      selectAll: 'すべて選択',
+      resetAll: 'すべてリセット',
+      scrapTimeInfo: '{{time}} 秒以内に合計 {{total}} ページをスクレイピングしました',
+      preview: 'プレビュー',
+      maxDepthTooltip: '入力されたURLを基にしたクローリング作業での設定可能な最大深度について説明します。深度0は入力されたURL自体のページを対象としたスクレイピングを意味します。深度1では、元のURLの直下にあるページ（URLに続く最初の"/"以降の内容）もスクレイピングの対象になります。この深度は指定した数値まで増加させることができ、それに応じてスクレイピングの範囲も広がっていきます。',
+    },
   },
   stepTwo: {
     segmentation: 'チャンク設定',
@@ -86,9 +115,11 @@ const translation = {
     calculating: '計算中...',
     fileSource: 'ドキュメントの前処理',
     notionSource: 'ページの前処理',
+    websiteSource: 'ウエブサイドの前処理',
     other: 'その他',
     fileUnit: 'ファイル',
     notionUnit: 'ページ',
+    webpageUnit: ' ページ',
     previousStep: '前のステップ',
     nextStep: '保存して処理',
     save: '保存して処理',
diff --git a/web/i18n/ja-JP/dataset-documents.ts b/web/i18n/ja-JP/dataset-documents.ts
index 0152d10616..53af92aa60 100644
--- a/web/i18n/ja-JP/dataset-documents.ts
+++ b/web/i18n/ja-JP/dataset-documents.ts
@@ -4,6 +4,7 @@ const translation = {
     desc: 'ナレッジのすべてのファイルがここに表示され、ナレッジ全体がDifyの引用やチャットプラグインを介してリンクされるか、インデックス化されることができます。',
     addFile: 'ファイルを追加',
     addPages: 'ページを追加',
+    addUrl: 'URLを追加',
     table: {
       header: {
         fileName: 'ファイル名',
@@ -13,6 +14,8 @@ const translation = {
         status: 'ステータス',
         action: 'アクション',
       },
+      rename: '名前を変更',
+      name: '名前',
     },
     action: {
       uploadFile: '新しいファイルをアップロード',
diff --git a/web/i18n/ja-JP/dataset-settings.ts b/web/i18n/ja-JP/dataset-settings.ts
index 3703b8f1ba..d7913cb54a 100644
--- a/web/i18n/ja-JP/dataset-settings.ts
+++ b/web/i18n/ja-JP/dataset-settings.ts
@@ -12,6 +12,8 @@ const translation = {
     permissions: '権限',
     permissionsOnlyMe: '自分のみ',
     permissionsAllMember: 'すべてのチームメンバー',
+    permissionsInvitedMembers: '一部のチームメンバー',
+    me: '(あなた様)',
     indexMethod: 'インデックス方法',
     indexMethodHighQuality: '高品質',
     indexMethodHighQualityTip: 'ユーザーがクエリを実行する際により高い精度を提供するために、Embeddingモデルを呼び出して処理を行う。',
diff --git a/web/i18n/ja-JP/dataset.ts b/web/i18n/ja-JP/dataset.ts
index 869a169027..c1160b4206 100644
--- a/web/i18n/ja-JP/dataset.ts
+++ b/web/i18n/ja-JP/dataset.ts
@@ -1,18 +1,18 @@
 const translation = {
-  knowledge: '知識',
+  knowledge: 'ナレッジ',
   documentCount: ' ドキュメント',
   wordCount: ' k 単語',
   appCount: ' リンクされたアプリ',
-  createDataset: '知識を作成',
+  createDataset: 'ナレッジを作成',
   createDatasetIntro: '独自のテキストデータをインポートするか、LLMコンテキストの強化のためにWebhookを介してリアルタイムでデータを書き込むことができます。',
-  deleteDatasetConfirmTitle: 'この知識を削除しますか？',
+  deleteDatasetConfirmTitle: 'このナレッジを削除しますか？',
   deleteDatasetConfirmContent:
-    '知識を削除すると元に戻すことはできません。ユーザーはもはやあなたの知識にアクセスできず、すべてのプロンプトの設定とログが永久に削除されます。',
-  datasetUsedByApp: 'この知識は一部のアプリによって使用されています。アプリはこの知識を使用できなくなり、すべてのプロンプト設定とログは永久に削除されます。',
-  datasetDeleted: '知識が削除されました',
-  datasetDeleteFailed: '知識の削除に失敗しました',
+    'ナレッジを削除すると元に戻すことはできません。ユーザーはもはやあなた様のナレッジにアクセスできず、すべてのプロンプトの設定とログが永久に削除されます。',
+  datasetUsedByApp: 'このナレッジは一部のアプリによって使用されています。アプリはこのナレッジを使用できなくなり、すべてのプロンプト設定とログは永久に削除されます。',
+  datasetDeleted: 'ナレッジが削除されました',
+  datasetDeleteFailed: 'ナレッジの削除に失敗しました',
   didYouKnow: 'ご存知ですか？',
-  intro1: '知識はDifyアプリケーションに統合することができます',
+  intro1: 'ナレッジはDifyアプリケーションに統合することができます',
   intro2: 'コンテキストとして',
   intro3: '、',
   intro4: 'または',
@@ -20,7 +20,7 @@ const translation = {
   intro6: '単体のChatGPTインデックスプラグインとして公開するために',
   unavailable: '利用不可',
   unavailableTip: '埋め込みモデルが利用できません。デフォルトの埋め込みモデルを設定する必要があります',
-  datasets: '知識',
+  datasets: 'ナレッジ',
   datasetsApi: 'API',
   retrieval: {
     semantic_search: {
@@ -45,6 +45,29 @@ const translation = {
   },
   docsFailedNotice: 'ドキュメントのインデックスに失敗しました',
   retry: '再試行',
+  indexingTechnique: {
+    high_quality: '高品質',
+    economy: '経済',
+  },
+  indexingMethod: {
+    semantic_search: 'ベクトル検索',
+    full_text_search: 'フルテキスト検索',
+    hybrid_search: 'ハイブリッド検索',
+  },
+  mixtureHighQualityAndEconomicTip: '高品質なナレッジベースと経済的なナレッジベースを混在させるには、Rerankモデルを構成する必要がある。',
+  inconsistentEmbeddingModelTip: '選択されたナレッジベースが一貫性のない埋め込みモデルで構成されている場合、Rerankモデルの構成が必要です。',
+  retrievalSettings: '設定を回収',
+  rerankSettings: 'Rerank設定',
+  weightedScore: {
+    title: 'ウェイト設定',
+    description: '割り当てられた重みを調整することで、並べ替え戦略はセマンティックマッチングとキーワードマッチングのどちらを優先するかを決定します。',
+    semanticFirst: 'セマンティック優先',
+    keywordFirst: 'キーワード優先',
+    customized: 'カスタマイズ',
+    semantic: 'セマンティクス',
+    keyword: 'キーワード',
+  },
+  nTo1RetrievalLegacy: '製品計画によると、N To 1 Retrievalは9月に正式に廃止される予定です。それまでは通常通り使用できます。',
 }
 
 export default translation
diff --git a/web/i18n/ja-JP/login.ts b/web/i18n/ja-JP/login.ts
index 4015bf448d..dd01e3b96a 100644
--- a/web/i18n/ja-JP/login.ts
+++ b/web/i18n/ja-JP/login.ts
@@ -9,6 +9,7 @@ const translation = {
   namePlaceholder: 'ユーザー名を入力してください',
   forget: 'パスワードをお忘れですか？',
   signBtn: 'サインイン',
+  sso: 'SSOに続ける',
   installBtn: 'セットアップ',
   setAdminAccount: '管理者アカウントの設定',
   setAdminAccountDesc: 'アプリケーションの作成やLLMプロバイダの管理など、管理者アカウントの最大権限を設定します。',
@@ -52,6 +53,7 @@ const translation = {
     emailInValid: '有効なメールアドレスを入力してください',
     nameEmpty: '名前は必須です',
     passwordEmpty: 'パスワードは必須です',
+    passwordLengthInValid: 'パスワードは8文字以上でなければなりません',
     passwordInvalid: 'パスワードは文字と数字を含み、長さは8以上である必要があります',
   },
   license: {
@@ -59,11 +61,11 @@ const translation = {
     link: 'オープンソースライセンス',
   },
   join: '参加する',
-  joinTipStart: 'あなたを招待します',
+  joinTipStart: 'あなた様を招待します',
   joinTipEnd: 'チームに参加する',
   invalid: 'リンクの有効期限が切れています',
   explore: 'Difyを探索する',
-  activatedTipStart: 'あなたは',
+  activatedTipStart: 'あなた様は',
   activatedTipEnd: 'チームに参加しました',
   activated: '今すぐサインイン',
   adminInitPassword: '管理者初期化パスワード',
diff --git a/web/i18n/ja-JP/tools.ts b/web/i18n/ja-JP/tools.ts
index 8173a9903f..ec2897161f 100644
--- a/web/i18n/ja-JP/tools.ts
+++ b/web/i18n/ja-JP/tools.ts
@@ -1,10 +1,12 @@
 const translation = {
   title: 'ツール',
   createCustomTool: 'カスタムツールを作成する',
+  customToolTip: 'Difyカスタムツールの詳細',
   type: {
     all: 'すべて',
     builtIn: '組み込み',
     custom: 'カスタム',
+    workflow: 'ワークフロー',
   },
   contribute: {
     line1: '私は',
@@ -21,12 +23,26 @@ const translation = {
   },
   includeToolNum: '{{num}}個のツールが含まれています',
   addTool: 'ツールを追加する',
+  addToolModal: {
+    type: 'タイプ',
+    category: 'カテゴリー',
+    add: '追加',
+    added: '追加されだ',
+    manageInTools: 'ツールリストに移動して管理する',
+    emptyTitle: '利用可能なワークフローツールはありません',
+    emptyTip: '追加するには、「ワークフロー -> ツールとして公開 」に移動する',
+  },
   createTool: {
     title: 'カスタムツールを作成する',
     editAction: '設定',
     editTitle: 'カスタムツールを編集する',
     name: '名前',
     toolNamePlaceHolder: 'ツール名を入力してください',
+    nameForToolCall: 'ツールコールの名前',
+    nameForToolCallPlaceHolder: '機械認識に使用される名前, 例えば、getCurrentWeather、list_pets',
+    nameForToolCallTip: '数字、文字、アンダースコアのみがサポートされます。',
+    description: 'ツールの説明',
+    descriptionPlaceholder: 'ツールの使い方の簡単な説明。例えば、特定の場所の温度を知るためなど。',
     schema: 'スキーマ',
     schemaPlaceHolder: 'ここにOpenAPIスキーマを入力してください',
     viewSchemaSpec: 'OpenAPI-Swagger仕様を表示する',
@@ -71,10 +87,26 @@ const translation = {
     },
     privacyPolicy: 'プライバシーポリシー',
     privacyPolicyPlaceholder: 'プライバシーポリシーを入力してください',
+    toolInput: {
+      title: 'ツール入力',
+      name: '名前',
+      required: '必須',
+      method: 'メソッド',
+      methodSetting: '設定',
+      methodSettingTip: 'ユーザーがツール設定を入力する',
+      methodParameter: 'LLM入力',
+      methodParameterTip: 'LLM は推論中に入力されます',
+      label: 'ラベル',
+      labelPlaceholder: 'ラベルを選択します(オプション)',
+      description: '説明',
+      descriptionPlaceholder: 'パラメータの意味の説明',
+    },
     customDisclaimer: 'カスタム免責事項',
     customDisclaimerPlaceholder: 'カスタム免責事項を入力してください',
+    confirmTitle: '保存しますか？',
+    confirmTip: '新しバージョン保存すると、このツールを使用されているアプリは影響を受けます',
     deleteToolConfirmTitle: 'このツールを削除しますか？',
-    deleteToolConfirmContent: 'ツールの削除は取り消しできません。ユーザーはもうあなたのツールにアクセスできません。',
+    deleteToolConfirmContent: 'ツールの削除は取り消しできません。ユーザーはもうあなた様のツールにアクセスできません。',
   },
   test: {
     title: 'テスト',
@@ -114,6 +146,8 @@ const translation = {
   toolRemoved: 'ツールが削除されました',
   notAuthorized: 'ツールが認可されていません',
   howToGet: '取得方法',
+  openInStudio: 'スタジオで開く',
+  toolNameUsageTip: 'ツール呼び出し名、エージェントの推論とプロンプトの単語に使用されます',
 }
 
 export default translation
diff --git a/web/i18n/zh-Hans/dataset-creation.ts b/web/i18n/zh-Hans/dataset-creation.ts
index 26e29fcbbb..257f409abd 100644
--- a/web/i18n/zh-Hans/dataset-creation.ts
+++ b/web/i18n/zh-Hans/dataset-creation.ts
@@ -62,7 +62,7 @@ const translation = {
       run: '运行',
       firecrawlTitle: '使用 🔥Firecrawl 提取网页内容',
       firecrawlDoc: 'Firecrawl 文档',
-      firecrawlDocLink: 'https://docs.dify.ai/v/zh-hans/guides/knowledge-base/sync_from_website',
+      firecrawlDocLink: 'https://docs.dify.ai/v/zh-hans/guides/knowledge-base/sync-from-website',
       options: '选项',
       crawlSubPage: '爬取子页面',
       limit: '限制数量',

From 20268708cca2dfcf79e6b7c4731bf888b6618147 Mon Sep 17 00:00:00 2001
From: Bowen Liang <liangbowen@gf.com.cn>
Date: Mon, 29 Jul 2024 10:32:11 +0800
Subject: [PATCH 39/60] chore: improve position map conversion and tolerate
 empty position yaml file (#6541)

---
 api/core/helper/position_helper.py            | 16 ++++---------
 .../model_providers/__base/ai_model.py        |  2 +-
 .../model_providers/__base/model_provider.py  |  2 +-
 .../tools/provider/builtin_tool_provider.py   |  4 ++--
 api/core/tools/utils/yaml_utils.py            | 24 ++++++++-----------
 .../position_helper/test_position_helper.py   | 21 ++++++++++++++++
 .../unit_tests/utils/yaml/test_yaml_utils.py  |  7 ++++--
 7 files changed, 44 insertions(+), 32 deletions(-)

diff --git a/api/core/helper/position_helper.py b/api/core/helper/position_helper.py
index 04675d85bb..dd1534c791 100644
--- a/api/core/helper/position_helper.py
+++ b/api/core/helper/position_helper.py
@@ -13,18 +13,10 @@ def get_position_map(folder_path: str, *, file_name: str = "_position.yaml") ->
     :param file_name: the YAML file name, default to '_position.yaml'
     :return: a dict with name as key and index as value
     """
-    position_file_name = os.path.join(folder_path, file_name)
-    if not position_file_name or not os.path.exists(position_file_name):
-        return {}
-    
-    positions = load_yaml_file(position_file_name, ignore_error=True)
-    position_map = {}
-    index = 0
-    for _, name in enumerate(positions):
-        if name and isinstance(name, str):
-            position_map[name.strip()] = index
-            index += 1
-    return position_map
+    position_file_path = os.path.join(folder_path, file_name)
+    yaml_content = load_yaml_file(file_path=position_file_path, default_value=[])
+    positions = [item.strip() for item in yaml_content if item and isinstance(item, str) and item.strip()]
+    return {name: index for index, name in enumerate(positions)}
 
 
 def sort_by_position_map(
diff --git a/api/core/model_runtime/model_providers/__base/ai_model.py b/api/core/model_runtime/model_providers/__base/ai_model.py
index 04b539433c..0de216bf89 100644
--- a/api/core/model_runtime/model_providers/__base/ai_model.py
+++ b/api/core/model_runtime/model_providers/__base/ai_model.py
@@ -162,7 +162,7 @@ class AIModel(ABC):
         # traverse all model_schema_yaml_paths
         for model_schema_yaml_path in model_schema_yaml_paths:
             # read yaml data from yaml file
-            yaml_data = load_yaml_file(model_schema_yaml_path, ignore_error=True)
+            yaml_data = load_yaml_file(model_schema_yaml_path)
 
             new_parameter_rules = []
             for parameter_rule in yaml_data.get('parameter_rules', []):
diff --git a/api/core/model_runtime/model_providers/__base/model_provider.py b/api/core/model_runtime/model_providers/__base/model_provider.py
index 51dd3b7e28..780460a3f7 100644
--- a/api/core/model_runtime/model_providers/__base/model_provider.py
+++ b/api/core/model_runtime/model_providers/__base/model_provider.py
@@ -44,7 +44,7 @@ class ModelProvider(ABC):
     
         # read provider schema from yaml file
         yaml_path = os.path.join(current_path, f'{provider_name}.yaml')
-        yaml_data = load_yaml_file(yaml_path, ignore_error=True)
+        yaml_data = load_yaml_file(yaml_path)
     
         try:
             # yaml_data to entity
diff --git a/api/core/tools/provider/builtin_tool_provider.py b/api/core/tools/provider/builtin_tool_provider.py
index 47e33b70c9..bcf41c90ed 100644
--- a/api/core/tools/provider/builtin_tool_provider.py
+++ b/api/core/tools/provider/builtin_tool_provider.py
@@ -27,7 +27,7 @@ class BuiltinToolProviderController(ToolProviderController):
         provider = self.__class__.__module__.split('.')[-1]
         yaml_path = path.join(path.dirname(path.realpath(__file__)), 'builtin', provider, f'{provider}.yaml')
         try:
-            provider_yaml = load_yaml_file(yaml_path)
+            provider_yaml = load_yaml_file(yaml_path, ignore_error=False)
         except Exception as e:
             raise ToolProviderNotFoundError(f'can not load provider yaml for {provider}: {e}')
 
@@ -58,7 +58,7 @@ class BuiltinToolProviderController(ToolProviderController):
         for tool_file in tool_files:
             # get tool name
             tool_name = tool_file.split(".")[0]
-            tool = load_yaml_file(path.join(tool_path, tool_file))
+            tool = load_yaml_file(path.join(tool_path, tool_file), ignore_error=False)
 
             # get tool class, import the module
             assistant_tool_class = load_single_subclass_from_source(
diff --git a/api/core/tools/utils/yaml_utils.py b/api/core/tools/utils/yaml_utils.py
index 3526647b4f..11486da7da 100644
--- a/api/core/tools/utils/yaml_utils.py
+++ b/api/core/tools/utils/yaml_utils.py
@@ -1,35 +1,31 @@
 import logging
-import os
+from typing import Any
 
 import yaml
 from yaml import YAMLError
 
 logger = logging.getLogger(__name__)
 
-def load_yaml_file(file_path: str, ignore_error: bool = False) -> dict:
+
+def load_yaml_file(file_path: str, ignore_error: bool = True, default_value: Any = {}) -> Any:
     """
-    Safe loading a YAML file to a dict
+    Safe loading a YAML file
     :param file_path: the path of the YAML file
     :param ignore_error:
-        if True, return empty dict if error occurs and the error will be logged in warning level
+        if True, return default_value if error occurs and the error will be logged in warning level
         if False, raise error if error occurs
-    :return: a dict of the YAML content
+    :param default_value: the value returned when errors ignored
+    :return: an object of the YAML content
     """
     try:
-        if not file_path or not os.path.exists(file_path):
-            raise FileNotFoundError(f'Failed to load YAML file {file_path}: file not found')
-
-        with open(file_path, encoding='utf-8') as file:
+        with open(file_path, encoding='utf-8') as yaml_file:
             try:
-                return yaml.safe_load(file)
+                return yaml.safe_load(yaml_file)
             except Exception as e:
                 raise YAMLError(f'Failed to load YAML file {file_path}: {e}')
-    except FileNotFoundError as e:
-        logger.debug(f'Failed to load YAML file {file_path}: {e}')
-        return {}
     except Exception as e:
         if ignore_error:
             logger.warning(f'Failed to load YAML file {file_path}: {e}')
-            return {}
+            return default_value
         else:
             raise e
diff --git a/api/tests/unit_tests/utils/position_helper/test_position_helper.py b/api/tests/unit_tests/utils/position_helper/test_position_helper.py
index c389461454..2237319904 100644
--- a/api/tests/unit_tests/utils/position_helper/test_position_helper.py
+++ b/api/tests/unit_tests/utils/position_helper/test_position_helper.py
@@ -21,6 +21,20 @@ def prepare_example_positions_yaml(tmp_path, monkeypatch) -> str:
     return str(tmp_path)
 
 
+@pytest.fixture
+def prepare_empty_commented_positions_yaml(tmp_path, monkeypatch) -> str:
+    monkeypatch.chdir(tmp_path)
+    tmp_path.joinpath("example_positions_all_commented.yaml").write_text(dedent(
+        """\
+        # - commented1
+        # - commented2
+        - 
+        -   
+        
+        """))
+    return str(tmp_path)
+
+
 def test_position_helper(prepare_example_positions_yaml):
     position_map = get_position_map(
         folder_path=prepare_example_positions_yaml,
@@ -32,3 +46,10 @@ def test_position_helper(prepare_example_positions_yaml):
         'third': 2,
         'forth': 3,
     }
+
+
+def test_position_helper_with_all_commented(prepare_empty_commented_positions_yaml):
+    position_map = get_position_map(
+        folder_path=prepare_empty_commented_positions_yaml,
+        file_name='example_positions_all_commented.yaml')
+    assert position_map == {}
diff --git a/api/tests/unit_tests/utils/yaml/test_yaml_utils.py b/api/tests/unit_tests/utils/yaml/test_yaml_utils.py
index 446588cde1..c0452b4e4d 100644
--- a/api/tests/unit_tests/utils/yaml/test_yaml_utils.py
+++ b/api/tests/unit_tests/utils/yaml/test_yaml_utils.py
@@ -53,6 +53,9 @@ def test_load_yaml_non_existing_file():
     assert load_yaml_file(file_path=NON_EXISTING_YAML_FILE) == {}
     assert load_yaml_file(file_path='') == {}
 
+    with pytest.raises(FileNotFoundError):
+        load_yaml_file(file_path=NON_EXISTING_YAML_FILE, ignore_error=False)
+
 
 def test_load_valid_yaml_file(prepare_example_yaml_file):
     yaml_data = load_yaml_file(file_path=prepare_example_yaml_file)
@@ -68,7 +71,7 @@ def test_load_valid_yaml_file(prepare_example_yaml_file):
 def test_load_invalid_yaml_file(prepare_invalid_yaml_file):
     # yaml syntax error
     with pytest.raises(YAMLError):
-        load_yaml_file(file_path=prepare_invalid_yaml_file)
+        load_yaml_file(file_path=prepare_invalid_yaml_file, ignore_error=False)
 
     # ignore error
-    assert load_yaml_file(file_path=prepare_invalid_yaml_file, ignore_error=True) == {}
+    assert load_yaml_file(file_path=prepare_invalid_yaml_file) == {}

From f43e27814cbc3c833ae21546d917a2995e87bd4e Mon Sep 17 00:00:00 2001
From: Yi Xiao <54782454+YIXIAO0@users.noreply.github.com>
Date: Mon, 29 Jul 2024 13:19:15 +0800
Subject: [PATCH 40/60] Fix action button size (#6753)

---
 web/app/components/base/action-button/index.css | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/web/app/components/base/action-button/index.css b/web/app/components/base/action-button/index.css
index b87dbc8d4a..96fbb14c6c 100644
--- a/web/app/components/base/action-button/index.css
+++ b/web/app/components/base/action-button/index.css
@@ -16,7 +16,7 @@
     }
 
     .action-btn-l {
-        @apply p-1.5 w-[34px] h-[34px] rounded-lg
+        @apply p-1.5 w-8 h-8 rounded-lg
     }
 
     /* m is for the regular button */
@@ -25,7 +25,7 @@
     }
 
     .action-btn-xs {
-        @apply p-0 w-5 h-5 rounded
+        @apply p-0 w-4 h-4 rounded
     }
 
     .action-btn.action-btn-active {

From cb01bf2986daa8d932d33525393588da871cde68 Mon Sep 17 00:00:00 2001
From: Bowen Liang <liangbowen@gf.com.cn>
Date: Mon, 29 Jul 2024 13:40:18 +0800
Subject: [PATCH 41/60] chore: set logging level to debug when reading YAML
 files and falling back to default value in case of None (#6758)

---
 api/core/tools/utils/yaml_utils.py | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/api/core/tools/utils/yaml_utils.py b/api/core/tools/utils/yaml_utils.py
index 11486da7da..21155a6960 100644
--- a/api/core/tools/utils/yaml_utils.py
+++ b/api/core/tools/utils/yaml_utils.py
@@ -12,7 +12,7 @@ def load_yaml_file(file_path: str, ignore_error: bool = True, default_value: Any
     Safe loading a YAML file
     :param file_path: the path of the YAML file
     :param ignore_error:
-        if True, return default_value if error occurs and the error will be logged in warning level
+        if True, return default_value if error occurs and the error will be logged in debug level
         if False, raise error if error occurs
     :param default_value: the value returned when errors ignored
     :return: an object of the YAML content
@@ -20,12 +20,13 @@ def load_yaml_file(file_path: str, ignore_error: bool = True, default_value: Any
     try:
         with open(file_path, encoding='utf-8') as yaml_file:
             try:
-                return yaml.safe_load(yaml_file)
+                yaml_content = yaml.safe_load(yaml_file)
+                return yaml_content if yaml_content else default_value
             except Exception as e:
                 raise YAMLError(f'Failed to load YAML file {file_path}: {e}')
     except Exception as e:
         if ignore_error:
-            logger.warning(f'Failed to load YAML file {file_path}: {e}')
+            logger.debug(f'Failed to load YAML file {file_path}: {e}')
             return default_value
         else:
             raise e

From 4945184f8cbb2806159ec7b0f0e2c4516894526e Mon Sep 17 00:00:00 2001
From: zxhlyh <jasonapring2015@outlook.com>
Date: Mon, 29 Jul 2024 16:03:47 +0800
Subject: [PATCH 42/60] fix: n to 1 retrieval legacy text (#6760)

---
 web/i18n/en-US/dataset.ts   | 2 +-
 web/i18n/zh-Hans/dataset.ts | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/web/i18n/en-US/dataset.ts b/web/i18n/en-US/dataset.ts
index f64a7dbf8d..40b5e9170e 100644
--- a/web/i18n/en-US/dataset.ts
+++ b/web/i18n/en-US/dataset.ts
@@ -67,7 +67,7 @@ const translation = {
     semantic: 'Semantic',
     keyword: 'Keyword',
   },
-  nTo1RetrievalLegacy: 'According to product planning, N-to-1 retrieval will be officially deprecated in September. Until then you can still use it normally.',
+  nTo1RetrievalLegacy: 'According to the optimization and upgrade of the retrieval strategy, N-to-1 retrieval will be officially deprecated in September. Until then you can still use it normally.',
 }
 
 export default translation
diff --git a/web/i18n/zh-Hans/dataset.ts b/web/i18n/zh-Hans/dataset.ts
index b0cf8cf057..3cd3813535 100644
--- a/web/i18n/zh-Hans/dataset.ts
+++ b/web/i18n/zh-Hans/dataset.ts
@@ -67,7 +67,7 @@ const translation = {
     semantic: '语义',
     keyword: '关键词',
   },
-  nTo1RetrievalLegacy: '根据产品规划，N 选 1 召回将于 9 月正式弃用。在那之前，您仍然可以正常使用它。',
+  nTo1RetrievalLegacy: '为了对检索策略进行优化和升级，N 选 1 检索功能将于九月份正式被优化。在此之前，您仍然可以正常使用该功能。',
 }
 
 export default translation

From 2cd662c43b0a6ddf64ebfc03121834a97e99171e Mon Sep 17 00:00:00 2001
From: zxhlyh <jasonapring2015@outlook.com>
Date: Mon, 29 Jul 2024 18:09:44 +0800
Subject: [PATCH 43/60] chore: n to 1 retrieval legacy text (#6767)

---
 web/i18n/en-US/app-debug.ts   | 2 +-
 web/i18n/en-US/dataset.ts     | 2 +-
 web/i18n/zh-Hans/app-debug.ts | 2 +-
 web/i18n/zh-Hans/dataset.ts   | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/web/i18n/en-US/app-debug.ts b/web/i18n/en-US/app-debug.ts
index 6970c38f6a..a4e8a4f7fa 100644
--- a/web/i18n/en-US/app-debug.ts
+++ b/web/i18n/en-US/app-debug.ts
@@ -409,7 +409,7 @@ const translation = {
     },
     retrieveMultiWay: {
       title: 'Multi-path retrieval',
-      description: 'Based on user intent, queries across all Knowledge, retrieves relevant text from multi-sources, and selects the best results matching the user query after reranking. Configuration of the Rerank model API is required.',
+      description: 'Based on user intent, queries across all Knowledge, retrieves relevant text from multi-sources, and selects the best results matching the user query after reranking. ',
     },
     rerankModelRequired: 'Rerank model is required',
     params: 'Params',
diff --git a/web/i18n/en-US/dataset.ts b/web/i18n/en-US/dataset.ts
index 40b5e9170e..61ed3225e6 100644
--- a/web/i18n/en-US/dataset.ts
+++ b/web/i18n/en-US/dataset.ts
@@ -33,7 +33,7 @@ const translation = {
     },
     hybrid_search: {
       title: 'Hybrid Search',
-      description: 'Execute full-text search and vector searches simultaneously, re-rank to select the best match for the user\'s query. Configuration of the Rerank model APIs necessary.',
+      description: 'Execute full-text search and vector searches simultaneously, re-rank to select the best match for the user\'s query. Users can choose to set weights or configure to a Rerank model.',
       recommend: 'Recommend',
     },
     invertedIndex: {
diff --git a/web/i18n/zh-Hans/app-debug.ts b/web/i18n/zh-Hans/app-debug.ts
index cd446e0466..b95bb8ce51 100644
--- a/web/i18n/zh-Hans/app-debug.ts
+++ b/web/i18n/zh-Hans/app-debug.ts
@@ -404,7 +404,7 @@ const translation = {
     },
     retrieveMultiWay: {
       title: '多路召回',
-      description: '根据用户意图同时匹配所有知识库，从多路知识库查询相关文本片段，经过重排序步骤，从多路查询结果中选择匹配用户问题的最佳结果，需配置 Rerank 模型 API。',
+      description: '根据用户意图同时匹配所有知识库，从多路知识库查询相关文本片段，经过重排序步骤，从多路查询结果中选择匹配用户问题的最佳结果。',
     },
     rerankModelRequired: '请选择 Rerank 模型',
     params: '参数设置',
diff --git a/web/i18n/zh-Hans/dataset.ts b/web/i18n/zh-Hans/dataset.ts
index 3cd3813535..1750c88ce3 100644
--- a/web/i18n/zh-Hans/dataset.ts
+++ b/web/i18n/zh-Hans/dataset.ts
@@ -33,7 +33,7 @@ const translation = {
     },
     hybrid_search: {
       title: '混合检索',
-      description: '同时执行全文检索和向量检索，并应用重排序步骤，从两类查询结果中选择匹配用户问题的最佳结果，需配置 Rerank 模型 API',
+      description: '同时执行全文检索和向量检索，并应用重排序步骤，从两类查询结果中选择匹配用户问题的最佳结果，用户可以选择设置权重或配置重新排序模型。',
       recommend: '推荐',
     },
     invertedIndex: {

From 8dd68e2034a847200ac5717e25c6cf260e79d980 Mon Sep 17 00:00:00 2001
From: -LAN- <laipz8200@outlook.com>
Date: Mon, 29 Jul 2024 18:30:29 +0800
Subject: [PATCH 44/60] fix(api/core/moderation/output_moderation.py): Fix
 config call. (#6769)

---
 api/configs/app_config.py                | 4 +++-
 api/core/moderation/output_moderation.py | 6 ++----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/api/configs/app_config.py b/api/configs/app_config.py
index d1099a9036..a5a4fc788d 100644
--- a/api/configs/app_config.py
+++ b/api/configs/app_config.py
@@ -64,4 +64,6 @@ class DifyConfig(
         return f'{self.HTTP_REQUEST_NODE_MAX_TEXT_SIZE / 1024 / 1024:.2f}MB'
 
     SSRF_PROXY_HTTP_URL: str | None = None
-    SSRF_PROXY_HTTPS_URL: str | None = None
\ No newline at end of file
+    SSRF_PROXY_HTTPS_URL: str | None = None
+
+    MODERATION_BUFFER_SIZE: int = Field(default=300, description='The buffer size for moderation.')
diff --git a/api/core/moderation/output_moderation.py b/api/core/moderation/output_moderation.py
index 4fd08ca021..9a4d8db4e2 100644
--- a/api/core/moderation/output_moderation.py
+++ b/api/core/moderation/output_moderation.py
@@ -21,8 +21,6 @@ class ModerationRule(BaseModel):
 
 
 class OutputModeration(BaseModel):
-    DEFAULT_BUFFER_SIZE: int = 300
-
     tenant_id: str
     app_id: str
 
@@ -77,10 +75,10 @@ class OutputModeration(BaseModel):
         return final_output
 
     def start_thread(self) -> threading.Thread:
-        buffer_size = int(dify_config.config.MODERATION_BUFFER_SIZE)
+        buffer_size = dify_config.MODERATION_BUFFER_SIZE
         thread = threading.Thread(target=self.worker, kwargs={
             'flask_app': current_app._get_current_object(),
-            'buffer_size': buffer_size if buffer_size > 0 else self.DEFAULT_BUFFER_SIZE
+            'buffer_size': buffer_size if buffer_size > 0 else dify_config.MODERATION_BUFFER_SIZE
         })
 
         thread.start()

From c9ff0e3961646e5ee1bee46b89fb6a4d581ca885 Mon Sep 17 00:00:00 2001
From: Giga Group <88305215+maybemaynot@users.noreply.github.com>
Date: Mon, 29 Jul 2024 18:30:52 +0800
Subject: [PATCH 45/60] Add model hunyuan-embedding (#6657)

Co-authored-by: sun <sun@centen.cn>
---
 .../model_providers/hunyuan/hunyuan.yaml      |   1 +
 .../hunyuan/text_embedding/__init__.py        |   0
 .../hunyuan-text-embedding.yaml               |   5 +
 .../hunyuan/text_embedding/text_embedding.py  | 173 ++++++++++++++++++
 .../hunyuan/test_text_embedding.py            | 104 +++++++++++
 5 files changed, 283 insertions(+)
 create mode 100644 api/core/model_runtime/model_providers/hunyuan/text_embedding/__init__.py
 create mode 100644 api/core/model_runtime/model_providers/hunyuan/text_embedding/hunyuan-text-embedding.yaml
 create mode 100644 api/core/model_runtime/model_providers/hunyuan/text_embedding/text_embedding.py
 create mode 100644 api/tests/integration_tests/model_runtime/hunyuan/test_text_embedding.py

diff --git a/api/core/model_runtime/model_providers/hunyuan/hunyuan.yaml b/api/core/model_runtime/model_providers/hunyuan/hunyuan.yaml
index 835a7716f7..812b51ddcd 100644
--- a/api/core/model_runtime/model_providers/hunyuan/hunyuan.yaml
+++ b/api/core/model_runtime/model_providers/hunyuan/hunyuan.yaml
@@ -18,6 +18,7 @@ help:
     en_US: https://console.cloud.tencent.com/cam/capi
 supported_model_types:
   - llm
+  - text-embedding
 configurate_methods:
   - predefined-model
 provider_credential_schema:
diff --git a/api/core/model_runtime/model_providers/hunyuan/text_embedding/__init__.py b/api/core/model_runtime/model_providers/hunyuan/text_embedding/__init__.py
new file mode 100644
index 0000000000..e69de29bb2
diff --git a/api/core/model_runtime/model_providers/hunyuan/text_embedding/hunyuan-text-embedding.yaml b/api/core/model_runtime/model_providers/hunyuan/text_embedding/hunyuan-text-embedding.yaml
new file mode 100644
index 0000000000..ab014e4344
--- /dev/null
+++ b/api/core/model_runtime/model_providers/hunyuan/text_embedding/hunyuan-text-embedding.yaml
@@ -0,0 +1,5 @@
+model: hunyuan-embedding
+model_type: text-embedding
+model_properties:
+  context_size: 1024
+  max_chunks: 1
diff --git a/api/core/model_runtime/model_providers/hunyuan/text_embedding/text_embedding.py b/api/core/model_runtime/model_providers/hunyuan/text_embedding/text_embedding.py
new file mode 100644
index 0000000000..64d8dcf795
--- /dev/null
+++ b/api/core/model_runtime/model_providers/hunyuan/text_embedding/text_embedding.py
@@ -0,0 +1,173 @@
+import json
+import logging
+import time
+from typing import Optional
+
+from tencentcloud.common import credential
+from tencentcloud.common.exception import TencentCloudSDKException
+from tencentcloud.common.profile.client_profile import ClientProfile
+from tencentcloud.common.profile.http_profile import HttpProfile
+from tencentcloud.hunyuan.v20230901 import hunyuan_client, models
+
+from core.model_runtime.entities.model_entities import PriceType
+from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
+from core.model_runtime.errors.invoke import (
+    InvokeError,
+)
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.model_runtime.model_providers.__base.text_embedding_model import TextEmbeddingModel
+
+logger = logging.getLogger(__name__)
+
+class HunyuanTextEmbeddingModel(TextEmbeddingModel):
+    """
+    Model class for Hunyuan text embedding model.
+    """
+
+    def _invoke(self, model: str, credentials: dict,
+                texts: list[str], user: Optional[str] = None) \
+            -> TextEmbeddingResult:
+        """
+        Invoke text embedding model
+
+        :param model: model name
+        :param credentials: model credentials
+        :param texts: texts to embed
+        :param user: unique user id
+        :return: embeddings result
+        """
+
+        if model != 'hunyuan-embedding':
+            raise ValueError('Invalid model name')
+        
+        client = self._setup_hunyuan_client(credentials)
+
+        embeddings = []
+        token_usage = 0
+
+        for input in texts:
+            request = models.GetEmbeddingRequest()
+            params = {
+                "Input": input
+            }
+            request.from_json_string(json.dumps(params))
+            response = client.GetEmbedding(request)
+            usage = response.Usage.TotalTokens
+
+            embeddings.extend([data.Embedding for data in response.Data])
+            token_usage += usage
+
+        result = TextEmbeddingResult(
+            model=model,
+            embeddings=embeddings,
+            usage=self._calc_response_usage(
+                model=model,
+                credentials=credentials,
+                tokens=token_usage
+            )
+        )
+
+        return result
+
+    def validate_credentials(self, model: str, credentials: dict) -> None:
+        """
+        Validate credentials
+        """
+        try:
+            client = self._setup_hunyuan_client(credentials)
+
+            req = models.ChatCompletionsRequest()
+            params = {
+                "Model": model,
+                "Messages": [{
+                    "Role": "user",
+                    "Content": "hello"
+                }],
+                "TopP": 1,
+                "Temperature": 0,
+                "Stream": False
+            }
+            req.from_json_string(json.dumps(params))
+            client.ChatCompletions(req)
+        except Exception as e:
+            raise CredentialsValidateFailedError(f'Credentials validation failed: {e}')
+
+    def _setup_hunyuan_client(self, credentials):
+        secret_id = credentials['secret_id']
+        secret_key = credentials['secret_key']
+        cred = credential.Credential(secret_id, secret_key)
+        httpProfile = HttpProfile()
+        httpProfile.endpoint = "hunyuan.tencentcloudapi.com"
+        clientProfile = ClientProfile()
+        clientProfile.httpProfile = httpProfile
+        client = hunyuan_client.HunyuanClient(cred, "", clientProfile)
+        return client
+    
+    def _calc_response_usage(self, model: str, credentials: dict, tokens: int) -> EmbeddingUsage:
+        """
+        Calculate response usage
+
+        :param model: model name
+        :param credentials: model credentials
+        :param tokens: input tokens
+        :return: usage
+        """
+        # get input price info
+        input_price_info = self.get_price(
+            model=model,
+            credentials=credentials,
+            price_type=PriceType.INPUT,
+            tokens=tokens
+        )
+
+        # transform usage
+        usage = EmbeddingUsage(
+            tokens=tokens,
+            total_tokens=tokens,
+            unit_price=input_price_info.unit_price,
+            price_unit=input_price_info.unit,
+            total_price=input_price_info.total_amount,
+            currency=input_price_info.currency,
+            latency=time.perf_counter() - self.started_at
+        )
+
+        return usage
+    
+    @property
+    def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
+        """
+        Map model invoke error to unified error
+        The key is the error type thrown to the caller
+        The value is the error type thrown by the model,
+        which needs to be converted into a unified error type for the caller.
+
+        :return: Invoke error mapping
+        """
+        return {
+            InvokeError: [TencentCloudSDKException],
+        }
+    
+    def get_num_tokens(self, model: str, credentials: dict, texts: list[str]) -> int:
+        """
+        Get number of tokens for given prompt messages
+
+        :param model: model name
+        :param credentials: model credentials
+        :param texts: texts to embed
+        :return:
+        """
+        # client = self._setup_hunyuan_client(credentials)
+
+        num_tokens = 0
+        for text in texts:
+            num_tokens += self._get_num_tokens_by_gpt2(text)
+            # use client.GetTokenCount to get num tokens
+            # request = models.GetTokenCountRequest()
+            # params = {
+            #     "Prompt": text
+            # }
+            # request.from_json_string(json.dumps(params))
+            # response = client.GetTokenCount(request)
+            # num_tokens += response.TokenCount
+
+        return num_tokens
\ No newline at end of file
diff --git a/api/tests/integration_tests/model_runtime/hunyuan/test_text_embedding.py b/api/tests/integration_tests/model_runtime/hunyuan/test_text_embedding.py
new file mode 100644
index 0000000000..7ae6c0e456
--- /dev/null
+++ b/api/tests/integration_tests/model_runtime/hunyuan/test_text_embedding.py
@@ -0,0 +1,104 @@
+import os
+
+import pytest
+
+from core.model_runtime.entities.text_embedding_entities import TextEmbeddingResult
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.model_runtime.model_providers.hunyuan.text_embedding.text_embedding import HunyuanTextEmbeddingModel
+
+
+def test_validate_credentials():
+    model = HunyuanTextEmbeddingModel()
+
+    with pytest.raises(CredentialsValidateFailedError):
+        model.validate_credentials(
+            model='hunyuan-embedding',
+            credentials={
+                'secret_id': 'invalid_key',
+                'secret_key': 'invalid_key'
+            }
+        )
+
+    model.validate_credentials(
+        model='hunyuan-embedding',
+        credentials={
+            'secret_id': os.environ.get('HUNYUAN_SECRET_ID'),
+            'secret_key': os.environ.get('HUNYUAN_SECRET_KEY')
+        }
+    )
+
+
+def test_invoke_model():
+    model = HunyuanTextEmbeddingModel()
+
+    result = model.invoke(
+        model='hunyuan-embedding',
+        credentials={
+            'secret_id': os.environ.get('HUNYUAN_SECRET_ID'),
+            'secret_key': os.environ.get('HUNYUAN_SECRET_KEY')
+        },
+        texts=[
+            "hello",
+            "world"
+        ],
+        user="abc-123"
+    )
+
+    assert isinstance(result, TextEmbeddingResult)
+    assert len(result.embeddings) == 2
+    assert result.usage.total_tokens == 6
+
+def test_get_num_tokens():
+    model = HunyuanTextEmbeddingModel()
+
+    num_tokens = model.get_num_tokens(
+        model='hunyuan-embedding',
+        credentials={
+            'secret_id': os.environ.get('HUNYUAN_SECRET_ID'),
+            'secret_key': os.environ.get('HUNYUAN_SECRET_KEY')
+        },
+        texts=[
+            "hello",
+            "world"
+        ]
+    )
+
+    assert num_tokens == 2
+
+def test_max_chunks():
+    model = HunyuanTextEmbeddingModel()
+
+    result = model.invoke(
+        model='hunyuan-embedding',
+        credentials={
+            'secret_id': os.environ.get('HUNYUAN_SECRET_ID'),
+            'secret_key': os.environ.get('HUNYUAN_SECRET_KEY')
+        },
+        texts=[
+            "hello",
+            "world",
+            "hello",
+            "world",
+            "hello",
+            "world",
+            "hello",
+            "world",
+            "hello",
+            "world",
+            "hello",
+            "world",
+            "hello",
+            "world",
+            "hello",
+            "world",
+            "hello",
+            "world",
+            "hello",
+            "world",
+            "hello",
+            "world",
+        ]
+    )
+
+    assert isinstance(result, TextEmbeddingResult)
+    assert len(result.embeddings) == 22
\ No newline at end of file

From 94d68b6a081aa88a5b5a21799e43e0d754345dba Mon Sep 17 00:00:00 2001
From: Charles <ggwzzk@outlook.com>
Date: Mon, 29 Jul 2024 18:31:56 +0800
Subject: [PATCH 46/60] upgrade deepseek params (#6744)

---
 .../deepseek/llm/deepseek-chat.yaml                | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/api/core/model_runtime/model_providers/deepseek/llm/deepseek-chat.yaml b/api/core/model_runtime/model_providers/deepseek/llm/deepseek-chat.yaml
index d50529926b..6832576524 100644
--- a/api/core/model_runtime/model_providers/deepseek/llm/deepseek-chat.yaml
+++ b/api/core/model_runtime/model_providers/deepseek/llm/deepseek-chat.yaml
@@ -23,7 +23,7 @@ parameter_rules:
     type: int
     default: 4096
     min: 1
-    max: 4096
+    max: 8192
     help:
       zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
@@ -57,6 +57,18 @@ parameter_rules:
     help:
       zh_Hans: 介于 -2.0 和 2.0 之间的数字。如果该值为正，那么新 token 会根据其在已有文本中的出现频率受到相应的惩罚，降低模型重复相同内容的可能性。
       en_US: A number between -2.0 and 2.0. If the value is positive, new tokens are penalized based on their frequency of occurrence in existing text, reducing the likelihood that the model will repeat the same content.
+  - name: response_format
+    label:
+      zh_Hans: 回复格式
+      en_US: response_format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
 pricing:
   input: '1'
   output: '2'

From 3e18d32ce52730d4697483ce585ae987f746fb47 Mon Sep 17 00:00:00 2001
From: "SiliconFlow, Inc" <chkain@gmail.com>
Date: Mon, 29 Jul 2024 18:45:19 +0800
Subject: [PATCH 47/60] add deepseek-coder-v2 in siliconflow (#6149)

---
 .../llm/deepdeek-coder-v2-instruct.yaml       |  30 +++++
 .../siliconflow/llm/deepseek-v2-chat.yaml     |   4 +-
 .../siliconflow/llm/glm4-9b-chat.yaml         |   4 +-
 .../llm/qwen2-57b-a14b-instruct.yaml          |   4 +-
 .../siliconflow/llm/qwen2-72b-instruct.yaml   |   4 +-
 .../siliconflow/llm/qwen2-7b-instruct.yaml    |   4 +-
 .../siliconflow/llm/yi-1.5-34b-chat.yaml      |   4 +-
 .../siliconflow/llm/yi-1.5-6b-chat.yaml       |   2 -
 .../siliconflow/llm/yi-1.5-9b-chat.yaml       |   4 +-
 .../siliconflow/siliconflow.py                |   2 +-
 .../model_runtime/siliconflow/__init__.py     |   0
 .../model_runtime/siliconflow/test_llm.py     | 106 ++++++++++++++++++
 .../siliconflow/test_provider.py              |  21 ++++
 13 files changed, 165 insertions(+), 24 deletions(-)
 create mode 100644 api/core/model_runtime/model_providers/siliconflow/llm/deepdeek-coder-v2-instruct.yaml
 create mode 100644 api/tests/integration_tests/model_runtime/siliconflow/__init__.py
 create mode 100644 api/tests/integration_tests/model_runtime/siliconflow/test_llm.py
 create mode 100644 api/tests/integration_tests/model_runtime/siliconflow/test_provider.py

diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/deepdeek-coder-v2-instruct.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/deepdeek-coder-v2-instruct.yaml
new file mode 100644
index 0000000000..d4431179e5
--- /dev/null
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/deepdeek-coder-v2-instruct.yaml
@@ -0,0 +1,30 @@
+model: deepseek-ai/DeepSeek-Coder-V2-Instruct
+label:
+  en_US: deepseek-ai/DeepSeek-Coder-V2-Instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '1.33'
+  output: '1.33'
+  unit: '0.000001'
+  currency: RMB
diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-v2-chat.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-v2-chat.yaml
index da58e822f9..3926568db6 100644
--- a/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-v2-chat.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-v2-chat.yaml
@@ -1,11 +1,9 @@
 model: deepseek-ai/deepseek-v2-chat
 label:
-  en_US: deepseek-ai/deepseek-v2-chat
+  en_US: deepseek-ai/DeepSeek-V2-Chat
 model_type: llm
 features:
-  - multi-tool-call
   - agent-thought
-  - stream-tool-call
 model_properties:
   mode: chat
   context_size: 32768
diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/glm4-9b-chat.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/glm4-9b-chat.yaml
index 115fc50b94..d6a4b21b66 100644
--- a/api/core/model_runtime/model_providers/siliconflow/llm/glm4-9b-chat.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/glm4-9b-chat.yaml
@@ -1,11 +1,9 @@
 model: zhipuai/glm4-9B-chat
 label:
-  en_US: zhipuai/glm4-9B-chat
+  en_US: THUDM/glm-4-9b-chat
 model_type: llm
 features:
-  - multi-tool-call
   - agent-thought
-  - stream-tool-call
 model_properties:
   mode: chat
   context_size: 32768
diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/qwen2-57b-a14b-instruct.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/qwen2-57b-a14b-instruct.yaml
index 75eca7720c..39624dc5b9 100644
--- a/api/core/model_runtime/model_providers/siliconflow/llm/qwen2-57b-a14b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/qwen2-57b-a14b-instruct.yaml
@@ -1,11 +1,9 @@
 model: alibaba/Qwen2-57B-A14B-Instruct
 label:
-  en_US: alibaba/Qwen2-57B-A14B-Instruct
+  en_US: Qwen/Qwen2-57B-A14B-Instruct
 model_type: llm
 features:
-  - multi-tool-call
   - agent-thought
-  - stream-tool-call
 model_properties:
   mode: chat
   context_size: 32768
diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/qwen2-72b-instruct.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/qwen2-72b-instruct.yaml
index fcbc9e0b68..fb7ff6cb14 100644
--- a/api/core/model_runtime/model_providers/siliconflow/llm/qwen2-72b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/qwen2-72b-instruct.yaml
@@ -1,11 +1,9 @@
 model: alibaba/Qwen2-72B-Instruct
 label:
-  en_US: alibaba/Qwen2-72B-Instruct
+  en_US: Qwen/Qwen2-72B-Instruct
 model_type: llm
 features:
-  - multi-tool-call
   - agent-thought
-  - stream-tool-call
 model_properties:
   mode: chat
   context_size: 32768
diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/qwen2-7b-instruct.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/qwen2-7b-instruct.yaml
index eda1d40642..efda4abbd9 100644
--- a/api/core/model_runtime/model_providers/siliconflow/llm/qwen2-7b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/qwen2-7b-instruct.yaml
@@ -1,11 +1,9 @@
 model: alibaba/Qwen2-7B-Instruct
 label:
-  en_US: alibaba/Qwen2-7B-Instruct
+  en_US: Qwen/Qwen2-7B-Instruct
 model_type: llm
 features:
-  - multi-tool-call
   - agent-thought
-  - stream-tool-call
 model_properties:
   mode: chat
   context_size: 32768
diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-34b-chat.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-34b-chat.yaml
index 6656e663e9..864ba46f1a 100644
--- a/api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-34b-chat.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-34b-chat.yaml
@@ -1,11 +1,9 @@
 model: 01-ai/Yi-1.5-34B-Chat
 label:
-  en_US: 01-ai/Yi-1.5-34B-Chat
+  en_US: 01-ai/Yi-1.5-34B-Chat-16K
 model_type: llm
 features:
-  - multi-tool-call
   - agent-thought
-  - stream-tool-call
 model_properties:
   mode: chat
   context_size: 16384
diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-6b-chat.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-6b-chat.yaml
index ba6e0c5113..38cd4197d4 100644
--- a/api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-6b-chat.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-6b-chat.yaml
@@ -3,9 +3,7 @@ label:
   en_US: 01-ai/Yi-1.5-6B-Chat
 model_type: llm
 features:
-  - multi-tool-call
   - agent-thought
-  - stream-tool-call
 model_properties:
   mode: chat
   context_size: 4096
diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-9b-chat.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-9b-chat.yaml
index 64be8998c5..042eeea81a 100644
--- a/api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-9b-chat.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-9b-chat.yaml
@@ -1,11 +1,9 @@
 model: 01-ai/Yi-1.5-9B-Chat
 label:
-  en_US: 01-ai/Yi-1.5-9B-Chat
+  en_US: 01-ai/Yi-1.5-9B-Chat-16K
 model_type: llm
 features:
-  - multi-tool-call
   - agent-thought
-  - stream-tool-call
 model_properties:
   mode: chat
   context_size: 16384
diff --git a/api/core/model_runtime/model_providers/siliconflow/siliconflow.py b/api/core/model_runtime/model_providers/siliconflow/siliconflow.py
index 63f76fa8b5..a53f16c929 100644
--- a/api/core/model_runtime/model_providers/siliconflow/siliconflow.py
+++ b/api/core/model_runtime/model_providers/siliconflow/siliconflow.py
@@ -19,7 +19,7 @@ class SiliconflowProvider(ModelProvider):
             model_instance = self.get_model_instance(ModelType.LLM)
 
             model_instance.validate_credentials(
-                model='deepseek-ai/deepseek-v2-chat',
+                model='deepseek-ai/DeepSeek-V2-Chat',
                 credentials=credentials
             )
         except CredentialsValidateFailedError as ex:
diff --git a/api/tests/integration_tests/model_runtime/siliconflow/__init__.py b/api/tests/integration_tests/model_runtime/siliconflow/__init__.py
new file mode 100644
index 0000000000..e69de29bb2
diff --git a/api/tests/integration_tests/model_runtime/siliconflow/test_llm.py b/api/tests/integration_tests/model_runtime/siliconflow/test_llm.py
new file mode 100644
index 0000000000..befdd82352
--- /dev/null
+++ b/api/tests/integration_tests/model_runtime/siliconflow/test_llm.py
@@ -0,0 +1,106 @@
+import os
+from collections.abc import Generator
+
+import pytest
+
+from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta
+from core.model_runtime.entities.message_entities import AssistantPromptMessage, SystemPromptMessage, UserPromptMessage
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.model_runtime.model_providers.siliconflow.llm.llm import SiliconflowLargeLanguageModel
+
+
+def test_validate_credentials():
+    model = SiliconflowLargeLanguageModel()
+
+    with pytest.raises(CredentialsValidateFailedError):
+        model.validate_credentials(
+            model='deepseek-ai/DeepSeek-V2-Chat',
+            credentials={
+                'api_key': 'invalid_key'
+            }
+        )
+
+    model.validate_credentials(
+        model='deepseek-ai/DeepSeek-V2-Chat',
+        credentials={
+            'api_key': os.environ.get('API_KEY')
+        }
+    )
+
+
+def test_invoke_model():
+    model = SiliconflowLargeLanguageModel()
+
+    response = model.invoke(
+        model='deepseek-ai/DeepSeek-V2-Chat',
+        credentials={
+            'api_key': os.environ.get('API_KEY')
+        },
+        prompt_messages=[
+            UserPromptMessage(
+                content='Who are you?'
+            )
+        ],
+        model_parameters={
+            'temperature': 0.5,
+            'max_tokens': 10
+        },
+        stop=['How'],
+        stream=False,
+        user="abc-123"
+    )
+
+    assert isinstance(response, LLMResult)
+    assert len(response.message.content) > 0
+
+
+def test_invoke_stream_model():
+    model = SiliconflowLargeLanguageModel()
+
+    response = model.invoke(
+        model='deepseek-ai/DeepSeek-V2-Chat',
+        credentials={
+            'api_key': os.environ.get('API_KEY')
+        },
+        prompt_messages=[
+            UserPromptMessage(
+                content='Hello World!'
+            )
+        ],
+        model_parameters={
+            'temperature': 0.5,
+            'max_tokens': 100,
+            'seed': 1234
+        },
+        stream=True,
+        user="abc-123"
+    )
+
+    assert isinstance(response, Generator)
+
+    for chunk in response:
+        assert isinstance(chunk, LLMResultChunk)
+        assert isinstance(chunk.delta, LLMResultChunkDelta)
+        assert isinstance(chunk.delta.message, AssistantPromptMessage)
+        assert len(chunk.delta.message.content) > 0 if chunk.delta.finish_reason is None else True
+
+
+def test_get_num_tokens():
+    model = SiliconflowLargeLanguageModel()
+
+    num_tokens = model.get_num_tokens(
+        model='deepseek-ai/DeepSeek-V2-Chat',
+        credentials={
+            'api_key': os.environ.get('API_KEY')
+        },
+        prompt_messages=[
+            SystemPromptMessage(
+                content='You are a helpful AI assistant.',
+            ),
+            UserPromptMessage(
+                content='Hello World!'
+            )
+        ]
+    )
+
+    assert num_tokens == 12
diff --git a/api/tests/integration_tests/model_runtime/siliconflow/test_provider.py b/api/tests/integration_tests/model_runtime/siliconflow/test_provider.py
new file mode 100644
index 0000000000..7b9211a5db
--- /dev/null
+++ b/api/tests/integration_tests/model_runtime/siliconflow/test_provider.py
@@ -0,0 +1,21 @@
+import os
+
+import pytest
+
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.model_runtime.model_providers.siliconflow.siliconflow import SiliconflowProvider
+
+
+def test_validate_provider_credentials():
+    provider = SiliconflowProvider()
+
+    with pytest.raises(CredentialsValidateFailedError):
+        provider.validate_provider_credentials(
+            credentials={}
+        )
+
+    provider.validate_provider_credentials(
+        credentials={
+            'api_key': os.environ.get('API_KEY')
+        }
+    )

From f78d0082aea76c5c1f05dfd302e2b493854bd378 Mon Sep 17 00:00:00 2001
From: Joe <79627742+ZhouhaoJiang@users.noreply.github.com>
Date: Mon, 29 Jul 2024 18:47:25 +0800
Subject: [PATCH 48/60] feat: implement function dispatch table for trace
 processing (#6628)

---
 api/core/ops/ops_trace_manager.py | 41 ++++++++++++++-----------------
 1 file changed, 18 insertions(+), 23 deletions(-)

diff --git a/api/core/ops/ops_trace_manager.py b/api/core/ops/ops_trace_manager.py
index ff15aa999b..4f6ab2fb94 100644
--- a/api/core/ops/ops_trace_manager.py
+++ b/api/core/ops/ops_trace_manager.py
@@ -298,34 +298,29 @@ class TraceTask:
         self.file_base_url = os.getenv("FILES_URL", "http://127.0.0.1:5001")
 
     def execute(self):
-        method_name, trace_info = self.preprocess()
-        return trace_info
+        return self.preprocess()
 
     def preprocess(self):
-        if self.trace_type == TraceTaskName.CONVERSATION_TRACE:
-            return TraceTaskName.CONVERSATION_TRACE, self.conversation_trace(**self.kwargs)
-        if self.trace_type == TraceTaskName.WORKFLOW_TRACE:
-            return TraceTaskName.WORKFLOW_TRACE, self.workflow_trace(self.workflow_run, self.conversation_id)
-        elif self.trace_type == TraceTaskName.MESSAGE_TRACE:
-            return TraceTaskName.MESSAGE_TRACE, self.message_trace(self.message_id)
-        elif self.trace_type == TraceTaskName.MODERATION_TRACE:
-            return TraceTaskName.MODERATION_TRACE, self.moderation_trace(self.message_id, self.timer, **self.kwargs)
-        elif self.trace_type == TraceTaskName.SUGGESTED_QUESTION_TRACE:
-            return TraceTaskName.SUGGESTED_QUESTION_TRACE, self.suggested_question_trace(
+        preprocess_map = {
+            TraceTaskName.CONVERSATION_TRACE: lambda: self.conversation_trace(**self.kwargs),
+            TraceTaskName.WORKFLOW_TRACE: lambda: self.workflow_trace(self.workflow_run, self.conversation_id),
+            TraceTaskName.MESSAGE_TRACE: lambda: self.message_trace(self.message_id),
+            TraceTaskName.MODERATION_TRACE: lambda: self.moderation_trace(
                 self.message_id, self.timer, **self.kwargs
-            )
-        elif self.trace_type == TraceTaskName.DATASET_RETRIEVAL_TRACE:
-            return TraceTaskName.DATASET_RETRIEVAL_TRACE, self.dataset_retrieval_trace(
+            ),
+            TraceTaskName.SUGGESTED_QUESTION_TRACE: lambda: self.suggested_question_trace(
                 self.message_id, self.timer, **self.kwargs
-            )
-        elif self.trace_type == TraceTaskName.TOOL_TRACE:
-            return TraceTaskName.TOOL_TRACE, self.tool_trace(self.message_id, self.timer, **self.kwargs)
-        elif self.trace_type == TraceTaskName.GENERATE_NAME_TRACE:
-            return TraceTaskName.GENERATE_NAME_TRACE, self.generate_name_trace(
+            ),
+            TraceTaskName.DATASET_RETRIEVAL_TRACE: lambda: self.dataset_retrieval_trace(
+                self.message_id, self.timer, **self.kwargs
+            ),
+            TraceTaskName.TOOL_TRACE: lambda: self.tool_trace(self.message_id, self.timer, **self.kwargs),
+            TraceTaskName.GENERATE_NAME_TRACE: lambda: self.generate_name_trace(
                 self.conversation_id, self.timer, **self.kwargs
-            )
-        else:
-            return '', {}
+            ),
+        }
+
+        return preprocess_map.get(self.trace_type, lambda: None)()
 
     # process methods for different trace types
     def conversation_trace(self, **kwargs):

From b414ea41d6fc608ce52cf7c896902ebe89bf2c2c Mon Sep 17 00:00:00 2001
From: Bowen Liang <liangbowen@gf.com.cn>
Date: Mon, 29 Jul 2024 19:56:45 +0800
Subject: [PATCH 49/60] dep: initial support for Milvus 2.4.x (#6084)

---
 .../datasource/vdb/milvus/milvus_vector.py    |  11 +-
 api/poetry.lock                               | 111 ++++++------------
 api/pyproject.toml                            |   2 +-
 docker-legacy/docker-compose.milvus.yaml      |   2 +-
 4 files changed, 45 insertions(+), 81 deletions(-)

diff --git a/api/core/rag/datasource/vdb/milvus/milvus_vector.py b/api/core/rag/datasource/vdb/milvus/milvus_vector.py
index b679577c04..cfc533ed33 100644
--- a/api/core/rag/datasource/vdb/milvus/milvus_vector.py
+++ b/api/core/rag/datasource/vdb/milvus/milvus_vector.py
@@ -5,6 +5,7 @@ from uuid import uuid4
 
 from pydantic import BaseModel, model_validator
 from pymilvus import MilvusClient, MilvusException, connections
+from pymilvus.milvus_client import IndexParams
 
 from configs import dify_config
 from core.rag.datasource.entity.embedding import Embeddings
@@ -250,11 +251,15 @@ class MilvusVector(BaseVector):
                 # Since primary field is auto-id, no need to track it
                 self._fields.remove(Field.PRIMARY_KEY.value)
 
+                # Create Index params for the collection
+                index_params_obj = IndexParams()
+                index_params_obj.add_index(field_name=Field.VECTOR.value, **index_params)
+
                 # Create the collection
                 collection_name = self._collection_name
-                self._client.create_collection_with_schema(collection_name=collection_name,
-                                                           schema=schema, index_param=index_params,
-                                                           consistency_level=self._consistency_level)
+                self._client.create_collection(collection_name=collection_name,
+                                               schema=schema, index_params=index_params_obj,
+                                               consistency_level=self._consistency_level)
             redis_client.set(collection_exist_cache_key, 1, ex=3600)
 
     def _init_client(self, config) -> MilvusClient:
diff --git a/api/poetry.lock b/api/poetry.lock
index 0abd2d2175..eb74367676 100644
--- a/api/poetry.lock
+++ b/api/poetry.lock
@@ -448,63 +448,6 @@ doc = ["Sphinx (>=7)", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphin
 test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.17)"]
 trio = ["trio (>=0.23)"]
 
-[[package]]
-name = "argon2-cffi"
-version = "23.1.0"
-description = "Argon2 for Python"
-optional = false
-python-versions = ">=3.7"
-files = [
-    {file = "argon2_cffi-23.1.0-py3-none-any.whl", hash = "sha256:c670642b78ba29641818ab2e68bd4e6a78ba53b7eff7b4c3815ae16abf91c7ea"},
-    {file = "argon2_cffi-23.1.0.tar.gz", hash = "sha256:879c3e79a2729ce768ebb7d36d4609e3a78a4ca2ec3a9f12286ca057e3d0db08"},
-]
-
-[package.dependencies]
-argon2-cffi-bindings = "*"
-
-[package.extras]
-dev = ["argon2-cffi[tests,typing]", "tox (>4)"]
-docs = ["furo", "myst-parser", "sphinx", "sphinx-copybutton", "sphinx-notfound-page"]
-tests = ["hypothesis", "pytest"]
-typing = ["mypy"]
-
-[[package]]
-name = "argon2-cffi-bindings"
-version = "21.2.0"
-description = "Low-level CFFI bindings for Argon2"
-optional = false
-python-versions = ">=3.6"
-files = [
-    {file = "argon2-cffi-bindings-21.2.0.tar.gz", hash = "sha256:bb89ceffa6c791807d1305ceb77dbfacc5aa499891d2c55661c6459651fc39e3"},
-    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-macosx_10_9_x86_64.whl", hash = "sha256:ccb949252cb2ab3a08c02024acb77cfb179492d5701c7cbdbfd776124d4d2367"},
-    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9524464572e12979364b7d600abf96181d3541da11e23ddf565a32e70bd4dc0d"},
-    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b746dba803a79238e925d9046a63aa26bf86ab2a2fe74ce6b009a1c3f5c8f2ae"},
-    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:58ed19212051f49a523abb1dbe954337dc82d947fb6e5a0da60f7c8471a8476c"},
-    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:bd46088725ef7f58b5a1ef7ca06647ebaf0eb4baff7d1d0d177c6cc8744abd86"},
-    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-musllinux_1_1_i686.whl", hash = "sha256:8cd69c07dd875537a824deec19f978e0f2078fdda07fd5c42ac29668dda5f40f"},
-    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:f1152ac548bd5b8bcecfb0b0371f082037e47128653df2e8ba6e914d384f3c3e"},
-    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-win32.whl", hash = "sha256:603ca0aba86b1349b147cab91ae970c63118a0f30444d4bc80355937c950c082"},
-    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-win_amd64.whl", hash = "sha256:b2ef1c30440dbbcba7a5dc3e319408b59676e2e039e2ae11a8775ecf482b192f"},
-    {file = "argon2_cffi_bindings-21.2.0-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:e415e3f62c8d124ee16018e491a009937f8cf7ebf5eb430ffc5de21b900dad93"},
-    {file = "argon2_cffi_bindings-21.2.0-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:3e385d1c39c520c08b53d63300c3ecc28622f076f4c2b0e6d7e796e9f6502194"},
-    {file = "argon2_cffi_bindings-21.2.0-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2c3e3cc67fdb7d82c4718f19b4e7a87123caf8a93fde7e23cf66ac0337d3cb3f"},
-    {file = "argon2_cffi_bindings-21.2.0-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6a22ad9800121b71099d0fb0a65323810a15f2e292f2ba450810a7316e128ee5"},
-    {file = "argon2_cffi_bindings-21.2.0-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f9f8b450ed0547e3d473fdc8612083fd08dd2120d6ac8f73828df9b7d45bb351"},
-    {file = "argon2_cffi_bindings-21.2.0-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:93f9bf70084f97245ba10ee36575f0c3f1e7d7724d67d8e5b08e61787c320ed7"},
-    {file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:3b9ef65804859d335dc6b31582cad2c5166f0c3e7975f324d9ffaa34ee7e6583"},
-    {file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d4966ef5848d820776f5f562a7d45fdd70c2f330c961d0d745b784034bd9f48d"},
-    {file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:20ef543a89dee4db46a1a6e206cd015360e5a75822f76df533845c3cbaf72670"},
-    {file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ed2937d286e2ad0cc79a7087d3c272832865f779430e0cc2b4f3718d3159b0cb"},
-    {file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:5e00316dabdaea0b2dd82d141cc66889ced0cdcbfa599e8b471cf22c620c329a"},
-]
-
-[package.dependencies]
-cffi = ">=1.0.1"
-
-[package.extras]
-dev = ["cogapp", "pre-commit", "pytest", "wheel"]
-tests = ["pytest"]
-
 [[package]]
 name = "arxiv"
 version = "2.1.0"
@@ -4616,22 +4559,20 @@ files = [
 ]
 
 [[package]]
-name = "minio"
-version = "7.2.7"
-description = "MinIO Python SDK for Amazon S3 Compatible Cloud Storage"
+name = "milvus-lite"
+version = "2.4.8"
+description = "A lightweight version of Milvus wrapped with Python."
 optional = false
-python-versions = "*"
+python-versions = ">=3.7"
 files = [
-    {file = "minio-7.2.7-py3-none-any.whl", hash = "sha256:59d1f255d852fe7104018db75b3bebbd987e538690e680f7c5de835e422de837"},
-    {file = "minio-7.2.7.tar.gz", hash = "sha256:473d5d53d79f340f3cd632054d0c82d2f93177ce1af2eac34a235bea55708d98"},
+    {file = "milvus_lite-2.4.8-py3-none-macosx_10_9_x86_64.whl", hash = "sha256:b7e90b34b214884cd44cdc112ab243d4cb197b775498355e2437b6cafea025fe"},
+    {file = "milvus_lite-2.4.8-py3-none-macosx_11_0_arm64.whl", hash = "sha256:519dfc62709d8f642d98a1c5b1dcde7080d107e6e312d677fef5a3412a40ac08"},
+    {file = "milvus_lite-2.4.8-py3-none-manylinux2014_aarch64.whl", hash = "sha256:b21f36d24cbb0e920b4faad607019bb28c1b2c88b4d04680ac8c7697a4ae8a4d"},
+    {file = "milvus_lite-2.4.8-py3-none-manylinux2014_x86_64.whl", hash = "sha256:08332a2b9abfe7c4e1d7926068937e46f8fb81f2707928b7bc02c9dc99cebe41"},
 ]
 
 [package.dependencies]
-argon2-cffi = "*"
-certifi = "*"
-pycryptodome = "*"
-typing-extensions = "*"
-urllib3 = "*"
+tqdm = "*"
 
 [[package]]
 name = "mmh3"
@@ -6078,6 +6019,19 @@ files = [
     {file = "pyarrow-17.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:392bc9feabc647338e6c89267635e111d71edad5fcffba204425a7c8d13610d7"},
     {file = "pyarrow-17.0.0-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:af5ff82a04b2171415f1410cff7ebb79861afc5dae50be73ce06d6e870615204"},
     {file = "pyarrow-17.0.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:edca18eaca89cd6382dfbcff3dd2d87633433043650c07375d095cd3517561d8"},
+    {file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7c7916bff914ac5d4a8fe25b7a25e432ff921e72f6f2b7547d1e325c1ad9d155"},
+    {file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f553ca691b9e94b202ff741bdd40f6ccb70cdd5fbf65c187af132f1317de6145"},
+    {file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:0cdb0e627c86c373205a2f94a510ac4376fdc523f8bb36beab2e7f204416163c"},
+    {file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:d7d192305d9d8bc9082d10f361fc70a73590a4c65cf31c3e6926cd72b76bc35c"},
+    {file = "pyarrow-17.0.0-cp38-cp38-win_amd64.whl", hash = "sha256:02dae06ce212d8b3244dd3e7d12d9c4d3046945a5933d28026598e9dbbda1fca"},
+    {file = "pyarrow-17.0.0-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:13d7a460b412f31e4c0efa1148e1d29bdf18ad1411eb6757d38f8fbdcc8645fb"},
+    {file = "pyarrow-17.0.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:9b564a51fbccfab5a04a80453e5ac6c9954a9c5ef2890d1bcf63741909c3f8df"},
+    {file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:32503827abbc5aadedfa235f5ece8c4f8f8b0a3cf01066bc8d29de7539532687"},
+    {file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a155acc7f154b9ffcc85497509bcd0d43efb80d6f733b0dc3bb14e281f131c8b"},
+    {file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:dec8d129254d0188a49f8a1fc99e0560dc1b85f60af729f47de4046015f9b0a5"},
+    {file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:a48ddf5c3c6a6c505904545c25a4ae13646ae1f8ba703c4df4a1bfe4f4006bda"},
+    {file = "pyarrow-17.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:42bf93249a083aca230ba7e2786c5f673507fa97bbd9725a1e2754715151a204"},
+    {file = "pyarrow-17.0.0.tar.gz", hash = "sha256:4beca9521ed2c0921c1023e68d097d0299b62c362639ea315572a58f3f50fd28"},
 ]
 
 [package.dependencies]
@@ -6374,24 +6328,29 @@ tests = ["coverage[toml] (==5.0.4)", "pytest (>=6.0.0,<7.0.0)"]
 
 [[package]]
 name = "pymilvus"
-version = "2.3.1"
+version = "2.4.4"
 description = "Python Sdk for Milvus"
 optional = false
-python-versions = ">=3.7"
+python-versions = ">=3.8"
 files = [
-    {file = "pymilvus-2.3.1-py3-none-any.whl", hash = "sha256:ce65e1de8700f33bd9aade20f013291629702e25b05726773208f1f0b22548ff"},
-    {file = "pymilvus-2.3.1.tar.gz", hash = "sha256:d460f6204d7deb2cff93716bd65670c1b440694b77701fb0ab0ead791aa582c6"},
+    {file = "pymilvus-2.4.4-py3-none-any.whl", hash = "sha256:073b76bc36f6f4e70f0f0a0023a53324f0ba8ef9a60883f87cd30a44b6c6f2b5"},
+    {file = "pymilvus-2.4.4.tar.gz", hash = "sha256:50c53eb103e034fbffe936fe942751ea3dbd2452e18cf79acc52360ed4987fb7"},
 ]
 
 [package.dependencies]
 environs = "<=9.5.0"
-grpcio = ">=1.49.1,<=1.58.0"
-minio = "*"
+grpcio = ">=1.49.1,<=1.63.0"
+milvus-lite = {version = ">=2.4.0,<2.5.0", markers = "sys_platform != \"win32\""}
 pandas = ">=1.2.4"
 protobuf = ">=3.20.0"
-requests = "*"
+setuptools = ">=67"
 ujson = ">=2.0.0"
 
+[package.extras]
+bulk-writer = ["azure-storage-blob", "minio (>=7.0.0)", "pyarrow (>=12.0.0)", "requests"]
+dev = ["black", "grpcio (==1.62.2)", "grpcio-testing (==1.62.2)", "grpcio-tools (==1.62.2)", "pytest (>=5.3.4)", "pytest-cov (>=2.8.1)", "pytest-timeout (>=1.3.4)", "ruff (>0.4.0)"]
+model = ["milvus-model (>=0.1.0)"]
+
 [[package]]
 name = "pymysql"
 version = "1.1.1"
@@ -9543,4 +9502,4 @@ cffi = ["cffi (>=1.11)"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "9619ddabdd67710981c13dcfa3ddae0a48497c9f694afc81b820e882440c1265"
+content-hash = "65ba64d7ae9594fa275b5ea067ff6fd02ed0880922dc449e9991aa36dd6f742f"
diff --git a/api/pyproject.toml b/api/pyproject.toml
index 430e3d79c4..8a99a55e76 100644
--- a/api/pyproject.toml
+++ b/api/pyproject.toml
@@ -206,7 +206,7 @@ chromadb = "0.5.1"
 oracledb = "~2.2.1"
 pgvecto-rs = "0.1.4"
 pgvector = "0.2.5"
-pymilvus = "2.3.1"
+pymilvus = "~2.4.4"
 pymysql = "1.1.1"
 tcvectordb = "1.3.2"
 tidb-vector = "0.0.9"
diff --git a/docker-legacy/docker-compose.milvus.yaml b/docker-legacy/docker-compose.milvus.yaml
index c422efbf4b..f4a7afa3a1 100644
--- a/docker-legacy/docker-compose.milvus.yaml
+++ b/docker-legacy/docker-compose.milvus.yaml
@@ -38,7 +38,7 @@ services:
 
   milvus-standalone:
     container_name: milvus-standalone
-    image: milvusdb/milvus:v2.3.1
+    image: milvusdb/milvus:v2.4.6
     command: ["milvus", "run", "standalone"]
     environment:
       ETCD_ENDPOINTS: etcd:2379

From daa31b2cb3b7b79a9628a3eed56539306a1ef41b Mon Sep 17 00:00:00 2001
From: Bowen Liang <liangbowen@gf.com.cn>
Date: Tue, 30 Jul 2024 08:45:57 +0800
Subject: [PATCH 50/60] chore: remove redundant version pinning for indirect
 dependencies (#6772)

---
 api/poetry.lock    |  2 +-
 api/pyproject.toml | 12 ------------
 2 files changed, 1 insertion(+), 13 deletions(-)

diff --git a/api/poetry.lock b/api/poetry.lock
index eb74367676..abde108a7a 100644
--- a/api/poetry.lock
+++ b/api/poetry.lock
@@ -9502,4 +9502,4 @@ cffi = ["cffi (>=1.11)"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "65ba64d7ae9594fa275b5ea067ff6fd02ed0880922dc449e9991aa36dd6f742f"
+content-hash = "a8b61d74d9322302b7447b6f8728ad606abc160202a8a122a05a8ef3cec7055b"
diff --git a/api/pyproject.toml b/api/pyproject.toml
index 8a99a55e76..25778f323d 100644
--- a/api/pyproject.toml
+++ b/api/pyproject.toml
@@ -216,18 +216,6 @@ alibabacloud_gpdb20160503 = "~3.8.0"
 alibabacloud_tea_openapi = "~0.3.9"
 clickhouse-connect = "~0.7.16"
 
-############################################################
-# Transparent dependencies required by main dependencies
-# for pinning versions
-############################################################
-
-[tool.poetry.group.transparent.dependencies]
-kaleido = "0.2.1"
-lxml = "5.1.0"
-sympy = "1.12"
-tenacity = "~8.3.0"
-xlrd = "~2.0.1"
-
 ############################################################
 # Dev dependencies for running tests
 ############################################################

From a98284b1ef2fb0081cb96670da79470d9c9f9aa2 Mon Sep 17 00:00:00 2001
From: -LAN- <laipz8200@outlook.com>
Date: Tue, 30 Jul 2024 11:15:26 +0800
Subject: [PATCH 51/60] refactor(api): Switch to `dify_config` (#6750)

Signed-off-by: -LAN- <laipz8200@outlook.com>
---
 api/commands.py                                | 18 +++++++++---------
 api/controllers/console/auth/login.py          |  4 ++--
 api/core/indexing_runner.py                    |  5 +++--
 api/core/rag/datasource/keyword/jieba/jieba.py |  4 ++--
 api/libs/passport.py                           |  9 +++++----
 5 files changed, 21 insertions(+), 19 deletions(-)

diff --git a/api/commands.py b/api/commands.py
index 6719539cc8..c7ffb47b51 100644
--- a/api/commands.py
+++ b/api/commands.py
@@ -249,8 +249,7 @@ def migrate_knowledge_vector_database():
     create_count = 0
     skipped_count = 0
     total_count = 0
-    config = current_app.config
-    vector_type = config.get('VECTOR_STORE')
+    vector_type = dify_config.VECTOR_STORE
     page = 1
     while True:
         try:
@@ -484,8 +483,7 @@ def convert_to_agent_apps():
 @click.option('--field', default='metadata.doc_id', prompt=False, help='index field , default is metadata.doc_id.')
 def add_qdrant_doc_id_index(field: str):
     click.echo(click.style('Start add qdrant doc_id index.', fg='green'))
-    config = current_app.config
-    vector_type = config.get('VECTOR_STORE')
+    vector_type = dify_config.VECTOR_STORE
     if vector_type != "qdrant":
         click.echo(click.style('Sorry, only support qdrant vector store.', fg='red'))
         return
@@ -502,13 +500,15 @@ def add_qdrant_doc_id_index(field: str):
 
         from core.rag.datasource.vdb.qdrant.qdrant_vector import QdrantConfig
         for binding in bindings:
+            if dify_config.QDRANT_URL is None:
+                raise ValueError('Qdrant url is required.')
             qdrant_config = QdrantConfig(
-                endpoint=config.get('QDRANT_URL'),
-                api_key=config.get('QDRANT_API_KEY'),
+                endpoint=dify_config.QDRANT_URL,
+                api_key=dify_config.QDRANT_API_KEY,
                 root_path=current_app.root_path,
-                timeout=config.get('QDRANT_CLIENT_TIMEOUT'),
-                grpc_port=config.get('QDRANT_GRPC_PORT'),
-                prefer_grpc=config.get('QDRANT_GRPC_ENABLED')
+                timeout=dify_config.QDRANT_CLIENT_TIMEOUT,
+                grpc_port=dify_config.QDRANT_GRPC_PORT,
+                prefer_grpc=dify_config.QDRANT_GRPC_ENABLED
             )
             try:
                 client = qdrant_client.QdrantClient(**qdrant_config.to_qdrant_params())
diff --git a/api/controllers/console/auth/login.py b/api/controllers/console/auth/login.py
index 3a0e5ea94d..c135ece67e 100644
--- a/api/controllers/console/auth/login.py
+++ b/api/controllers/console/auth/login.py
@@ -71,7 +71,7 @@ class ResetPasswordApi(Resource):
         # AccountService.update_password(account, new_password)
 
         # todo: Send email
-        # MAILCHIMP_API_KEY = current_app.config['MAILCHIMP_TRANSACTIONAL_API_KEY']
+        # MAILCHIMP_API_KEY = dify_config.MAILCHIMP_TRANSACTIONAL_API_KEY
         # mailchimp = MailchimpTransactional(MAILCHIMP_API_KEY)
 
         # message = {
@@ -92,7 +92,7 @@ class ResetPasswordApi(Resource):
         #     'message': message,
         #     # required for transactional email
         #     ' settings': {
-        #         'sandbox_mode': current_app.config['MAILCHIMP_SANDBOX_MODE'],
+        #         'sandbox_mode': dify_config.MAILCHIMP_SANDBOX_MODE,
         #     },
         # })
 
diff --git a/api/core/indexing_runner.py b/api/core/indexing_runner.py
index 83dbacbfcc..b20c6ed187 100644
--- a/api/core/indexing_runner.py
+++ b/api/core/indexing_runner.py
@@ -12,6 +12,7 @@ from flask import Flask, current_app
 from flask_login import current_user
 from sqlalchemy.orm.exc import ObjectDeletedError
 
+from configs import dify_config
 from core.errors.error import ProviderTokenNotInitError
 from core.llm_generator.llm_generator import LLMGenerator
 from core.model_manager import ModelInstance, ModelManager
@@ -224,7 +225,7 @@ class IndexingRunner:
         features = FeatureService.get_features(tenant_id)
         if features.billing.enabled:
             count = len(extract_settings)
-            batch_upload_limit = int(current_app.config['BATCH_UPLOAD_LIMIT'])
+            batch_upload_limit = dify_config.BATCH_UPLOAD_LIMIT
             if count > batch_upload_limit:
                 raise ValueError(f"You have reached the batch upload limit of {batch_upload_limit}.")
 
@@ -427,7 +428,7 @@ class IndexingRunner:
             # The user-defined segmentation rule
             rules = json.loads(processing_rule.rules)
             segmentation = rules["segmentation"]
-            max_segmentation_tokens_length = int(current_app.config['INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH'])
+            max_segmentation_tokens_length = dify_config.INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH
             if segmentation["max_tokens"] < 50 or segmentation["max_tokens"] > max_segmentation_tokens_length:
                 raise ValueError(f"Custom segment length should be between 50 and {max_segmentation_tokens_length}.")
 
diff --git a/api/core/rag/datasource/keyword/jieba/jieba.py b/api/core/rag/datasource/keyword/jieba/jieba.py
index 7f7c46e2dd..a3714c2fd3 100644
--- a/api/core/rag/datasource/keyword/jieba/jieba.py
+++ b/api/core/rag/datasource/keyword/jieba/jieba.py
@@ -2,9 +2,9 @@ import json
 from collections import defaultdict
 from typing import Any, Optional
 
-from flask import current_app
 from pydantic import BaseModel
 
+from configs import dify_config
 from core.rag.datasource.keyword.jieba.jieba_keyword_table_handler import JiebaKeywordTableHandler
 from core.rag.datasource.keyword.keyword_base import BaseKeyword
 from core.rag.models.document import Document
@@ -139,7 +139,7 @@ class Jieba(BaseKeyword):
             if keyword_table_dict:
                 return keyword_table_dict['__data__']['table']
         else:
-            keyword_data_source_type = current_app.config['KEYWORD_DATA_SOURCE_TYPE']
+            keyword_data_source_type = dify_config.KEYWORD_DATA_SOURCE_TYPE
             dataset_keyword_table = DatasetKeywordTable(
                 dataset_id=self.dataset.id,
                 keyword_table='',
diff --git a/api/libs/passport.py b/api/libs/passport.py
index 530709f18c..34bdc55997 100644
--- a/api/libs/passport.py
+++ b/api/libs/passport.py
@@ -1,15 +1,16 @@
 import jwt
-from flask import current_app
 from werkzeug.exceptions import Unauthorized
 
+from configs import dify_config
+
 
 class PassportService:
     def __init__(self):
-        self.sk = current_app.config.get('SECRET_KEY')
-    
+        self.sk = dify_config.SECRET_KEY
+
     def issue(self, payload):
         return jwt.encode(payload, self.sk, algorithm='HS256')
-    
+
     def verify(self, token):
         try:
             return jwt.decode(token, self.sk, algorithms=['HS256'])

From 028261f760e330859dd0ba1360c3a0f70d623497 Mon Sep 17 00:00:00 2001
From: Chenhe Gu <guchenhe@gmail.com>
Date: Tue, 30 Jul 2024 14:17:45 +0800
Subject: [PATCH 52/60] improve issue templates (#6785)

---
 .github/DISCUSSION_TEMPLATE/general.yml      | 2 +-
 .github/DISCUSSION_TEMPLATE/help.yml         | 2 +-
 .github/DISCUSSION_TEMPLATE/suggestion.yml   | 2 +-
 .github/ISSUE_TEMPLATE/bug_report.yml        | 3 +--
 .github/ISSUE_TEMPLATE/document_issue.yml    | 2 +-
 .github/ISSUE_TEMPLATE/feature_request.yml   | 2 +-
 .github/ISSUE_TEMPLATE/translation_issue.yml | 3 +--
 7 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/.github/DISCUSSION_TEMPLATE/general.yml b/.github/DISCUSSION_TEMPLATE/general.yml
index 5af61ea64c..487d719c85 100644
--- a/.github/DISCUSSION_TEMPLATE/general.yml
+++ b/.github/DISCUSSION_TEMPLATE/general.yml
@@ -9,7 +9,7 @@ body:
           required: true
         - label: I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)).
           required: true
-        - label: "请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
+        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
           required: true
         - label: "Please do not modify this template :) and fill in all the required fields."
           required: true
diff --git a/.github/DISCUSSION_TEMPLATE/help.yml b/.github/DISCUSSION_TEMPLATE/help.yml
index abebaa9727..86de4057ae 100644
--- a/.github/DISCUSSION_TEMPLATE/help.yml
+++ b/.github/DISCUSSION_TEMPLATE/help.yml
@@ -9,7 +9,7 @@ body:
           required: true
         - label: I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)).
           required: true
-        - label: "请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
+        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
           required: true
         - label: "Please do not modify this template :) and fill in all the required fields."
           required: true
diff --git a/.github/DISCUSSION_TEMPLATE/suggestion.yml b/.github/DISCUSSION_TEMPLATE/suggestion.yml
index 0893a10b2d..fa1b4e0251 100644
--- a/.github/DISCUSSION_TEMPLATE/suggestion.yml
+++ b/.github/DISCUSSION_TEMPLATE/suggestion.yml
@@ -9,7 +9,7 @@ body:
           required: true
         - label: I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)).
           required: true
-        - label: "请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
+        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
           required: true
         - label: "Please do not modify this template :) and fill in all the required fields."
           required: true
diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml
index cf4fce3700..f767e8ba32 100644
--- a/.github/ISSUE_TEMPLATE/bug_report.yml
+++ b/.github/ISSUE_TEMPLATE/bug_report.yml
@@ -14,7 +14,7 @@ body:
           required: true
         - label: I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)).
           required: true
-        - label: "请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
+        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
           required: true
         - label: "Please do not modify this template :) and fill in all the required fields."
           required: true
@@ -22,7 +22,6 @@ body:
   - type: input
     attributes:
       label: Dify version
-      placeholder: 0.6.15
       description: See about section in Dify console
     validations:
       required: true
diff --git a/.github/ISSUE_TEMPLATE/document_issue.yml b/.github/ISSUE_TEMPLATE/document_issue.yml
index 45ee37ca39..db8be32d95 100644
--- a/.github/ISSUE_TEMPLATE/document_issue.yml
+++ b/.github/ISSUE_TEMPLATE/document_issue.yml
@@ -12,7 +12,7 @@ body:
           required: true
         - label: I confirm that I am using English to submit report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)).
           required: true
-        - label: "请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
+        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
           required: true
         - label: "Please do not modify this template :) and fill in all the required fields."
           required: true
diff --git a/.github/ISSUE_TEMPLATE/feature_request.yml b/.github/ISSUE_TEMPLATE/feature_request.yml
index 1b0eaaf4ab..f6764d35ad 100644
--- a/.github/ISSUE_TEMPLATE/feature_request.yml
+++ b/.github/ISSUE_TEMPLATE/feature_request.yml
@@ -12,7 +12,7 @@ body:
           required: true
         - label: I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)).
           required: true
-        - label: "请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
+        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
           required: true
         - label: "Please do not modify this template :) and fill in all the required fields."
           required: true
diff --git a/.github/ISSUE_TEMPLATE/translation_issue.yml b/.github/ISSUE_TEMPLATE/translation_issue.yml
index 440ea92616..5d2f020f45 100644
--- a/.github/ISSUE_TEMPLATE/translation_issue.yml
+++ b/.github/ISSUE_TEMPLATE/translation_issue.yml
@@ -12,14 +12,13 @@ body:
           required: true
         - label: I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)).
           required: true
-        - label: "请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
+        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
           required: true
         - label: "Please do not modify this template :) and fill in all the required fields."
           required: true
   - type: input
     attributes:
       label: Dify version
-      placeholder: 0.3.21
       description: Hover over system tray icon or look at Settings
     validations:
       required: true

From 72963d1f13416089d9fba67a9f232d461665e51f Mon Sep 17 00:00:00 2001
From: Yeuoly <45712896+Yeuoly@users.noreply.github.com>
Date: Tue, 30 Jul 2024 14:45:14 +0800
Subject: [PATCH 53/60] fix: nonetype in webscraper validation (#6788)

---
 api/core/tools/provider/builtin/spider/spiderApp.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/api/core/tools/provider/builtin/spider/spiderApp.py b/api/core/tools/provider/builtin/spider/spiderApp.py
index 82c0df19ca..f0ed64867a 100644
--- a/api/core/tools/provider/builtin/spider/spiderApp.py
+++ b/api/core/tools/provider/builtin/spider/spiderApp.py
@@ -116,6 +116,7 @@ class Spider:
         :param params: Optional dictionary of additional parameters for the scrape request.
         :return: JSON response containing the scraping results.
         """
+        params = params or {}
 
         # Add { "return_format": "markdown" } to the params if not already present
         if "return_format" not in params:
@@ -143,6 +144,7 @@ class Spider:
         :param stream: Boolean indicating if the response should be streamed. Defaults to False.
         :return: JSON response or the raw response stream if streaming enabled.
         """
+        params = params or {}
 
         # Add { "return_format": "markdown" } to the params if not already present
         if "return_format" not in params:

From 0675c5f71614fc9498c18be38e28a0b194a1901c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=9D=9E=E6=B3=95=E6=93=8D=E4=BD=9C?= <hjlarry@163.com>
Date: Tue, 30 Jul 2024 16:18:58 +0800
Subject: [PATCH 54/60] chore: add shortcut keys and hints for the shortcuts
 (#6779)

---
 web/app/components/workflow/header/undo-redo.tsx |  4 ++--
 web/app/components/workflow/operator/control.tsx | 13 +++++++++----
 2 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/web/app/components/workflow/header/undo-redo.tsx b/web/app/components/workflow/header/undo-redo.tsx
index bd27e09173..796038ce98 100644
--- a/web/app/components/workflow/header/undo-redo.tsx
+++ b/web/app/components/workflow/header/undo-redo.tsx
@@ -30,7 +30,7 @@ const UndoRedo: FC<UndoRedoProps> = ({ handleUndo, handleRedo }) => {
 
   return (
     <div className='flex items-center p-0.5 rounded-lg border-[0.5px] border-gray-100 bg-white shadow-lg text-gray-500'>
-      <TipPopup title={t('workflow.common.undo')!} >
+      <TipPopup title={t('workflow.common.undo')!} shortcuts={['ctrl', 'z']}>
         <div
           data-tooltip-id='workflow.undo'
           className={`
@@ -43,7 +43,7 @@ const UndoRedo: FC<UndoRedoProps> = ({ handleUndo, handleRedo }) => {
           <RiArrowGoBackLine className='h-4 w-4' />
         </div>
       </TipPopup>
-      <TipPopup title={t('workflow.common.redo')!} >
+      <TipPopup title={t('workflow.common.redo')!} shortcuts={['ctrl', 'y']}>
         <div
           data-tooltip-id='workflow.redo'
           className={`
diff --git a/web/app/components/workflow/operator/control.tsx b/web/app/components/workflow/operator/control.tsx
index daf628a2e3..4c1e952688 100644
--- a/web/app/components/workflow/operator/control.tsx
+++ b/web/app/components/workflow/operator/control.tsx
@@ -16,7 +16,7 @@ import {
   useSelectionInteractions,
   useWorkflow,
 } from '../hooks'
-import { isEventTargetInputArea } from '../utils'
+import { getKeyboardKeyCodeBySystem, isEventTargetInputArea } from '../utils'
 import { useStore } from '../store'
 import AddBlock from './add-block'
 import TipPopup from './tip-popup'
@@ -78,6 +78,11 @@ const Control = () => {
     handleLayout()
   }
 
+  useKeyPress(`${getKeyboardKeyCodeBySystem('ctrl')}.o`, (e) => {
+    e.preventDefault()
+    goLayout()
+  }, { exactMatch: true, useCapture: true })
+
   const addNote = (e: MouseEvent<HTMLDivElement>) => {
     if (getNodesReadOnly())
       return
@@ -101,7 +106,7 @@ const Control = () => {
         </div>
       </TipPopup>
       <div className='mx-[3px] w-[1px] h-3.5 bg-gray-200'></div>
-      <TipPopup title={t('workflow.common.pointerMode')}>
+      <TipPopup title={t('workflow.common.pointerMode')} shortcuts={['v']}>
         <div
           className={cn(
             'flex items-center justify-center mr-[1px] w-8 h-8 rounded-lg cursor-pointer',
@@ -113,7 +118,7 @@ const Control = () => {
           <RiCursorLine className='w-4 h-4' />
         </div>
       </TipPopup>
-      <TipPopup title={t('workflow.common.handMode')}>
+      <TipPopup title={t('workflow.common.handMode')} shortcuts={['h']}>
         <div
           className={cn(
             'flex items-center justify-center w-8 h-8 rounded-lg cursor-pointer',
@@ -126,7 +131,7 @@ const Control = () => {
         </div>
       </TipPopup>
       <div className='mx-[3px] w-[1px] h-3.5 bg-gray-200'></div>
-      <TipPopup title={t('workflow.panel.organizeBlocks')}>
+      <TipPopup title={t('workflow.panel.organizeBlocks')} shortcuts={['ctrl', 'o']}>
         <div
           className={cn(
             'flex items-center justify-center w-8 h-8 rounded-lg hover:bg-black/5 hover:text-gray-700 cursor-pointer',

From 0a744a73b3cdb646ee9a863fe7d03c38cadeafe2 Mon Sep 17 00:00:00 2001
From: zxhlyh <jasonapring2015@outlook.com>
Date: Tue, 30 Jul 2024 16:59:03 +0800
Subject: [PATCH 55/60] fix: eco knowledge retrieval method (#6798)

---
 .../params-config/config-content.tsx          | 23 ++++++++++++++++++-
 web/hooks/use-knowledge.ts                    |  7 ++++--
 web/i18n/en-US/dataset.ts                     |  4 +++-
 web/i18n/zh-Hans/dataset.ts                   |  4 +++-
 4 files changed, 33 insertions(+), 5 deletions(-)

diff --git a/web/app/components/app/configuration/dataset-config/params-config/config-content.tsx b/web/app/components/app/configuration/dataset-config/params-config/config-content.tsx
index d71d26bbed..683617bf25 100644
--- a/web/app/components/app/configuration/dataset-config/params-config/config-content.tsx
+++ b/web/app/components/app/configuration/dataset-config/params-config/config-content.tsx
@@ -32,6 +32,7 @@ import { RerankingModeEnum } from '@/models/datasets'
 import cn from '@/utils/classnames'
 import { useSelectedDatasetsMode } from '@/app/components/workflow/nodes/knowledge-retrieval/hooks'
 import Switch from '@/app/components/base/switch'
+import { useGetLanguage } from '@/context/i18n'
 
 type Props = {
   datasetConfigs: DatasetConfigs
@@ -43,6 +44,11 @@ type Props = {
   selectedDatasets?: DataSet[]
 }
 
+const LEGACY_LINK_MAP = {
+  en_US: 'https://docs.dify.ai/guides/knowledge-base/integrate-knowledge-within-application',
+  zh_Hans: 'https://docs.dify.ai/v/zh-hans/guides/knowledge-base/integrate_knowledge_within_application',
+} as Record<string, string>
+
 const ConfigContent: FC<Props> = ({
   datasetConfigs,
   onChange,
@@ -53,6 +59,7 @@ const ConfigContent: FC<Props> = ({
   selectedDatasets = [],
 }) => {
   const { t } = useTranslation()
+  const language = useGetLanguage()
   const selectedDatasetsMode = useSelectedDatasetsMode(selectedDatasets)
   const type = datasetConfigs.retrieval_model
   const setType = (value: RETRIEVE_TYPE) => {
@@ -167,7 +174,21 @@ const ConfigContent: FC<Props> = ({
           title={(
             <div className='flex items-center'>
               {t('appDebug.datasetConfig.retrieveOneWay.title')}
-              <TooltipPlus popupContent={<div className='w-[320px]'>{t('dataset.nTo1RetrievalLegacy')}</div>}>
+              <TooltipPlus
+                popupContent={(
+                  <div className='w-[320px]'>
+                    {t('dataset.nTo1RetrievalLegacy')}
+                    <a
+                      className='underline'
+                      href={LEGACY_LINK_MAP[language]}
+                      target='_blank'
+                      rel='noopener noreferrer'
+                    >
+                      ({t('dataset.nTo1RetrievalLegacyLink')})
+                    </a>
+                  </div>
+                )}
+              >
                 <div className='ml-1 flex items-center px-[5px] h-[18px] rounded-[5px] border border-text-accent-secondary system-2xs-medium-uppercase text-text-accent-secondary'>legacy</div>
               </TooltipPlus>
             </div>
diff --git a/web/hooks/use-knowledge.ts b/web/hooks/use-knowledge.ts
index 657acb3f51..400d9722de 100644
--- a/web/hooks/use-knowledge.ts
+++ b/web/hooks/use-knowledge.ts
@@ -8,7 +8,10 @@ export const useKnowledge = () => {
     return t(`dataset.indexingTechnique.${indexingTechnique}`)
   }, [t])
 
-  const formatIndexingMethod = useCallback((indexingMethod: string) => {
+  const formatIndexingMethod = useCallback((indexingMethod: string, isEco?: boolean) => {
+    if (isEco)
+      return t('dataset.indexingMethod.invertedIndex')
+
     return t(`dataset.indexingMethod.${indexingMethod}`)
   }, [t])
 
@@ -16,7 +19,7 @@ export const useKnowledge = () => {
     let result = formatIndexingTechnique(indexingTechnique)
 
     if (indexingMethod)
-      result += ` · ${formatIndexingMethod(indexingMethod)}`
+      result += ` · ${formatIndexingMethod(indexingMethod, indexingTechnique === 'economy')}`
 
     return result
   }, [formatIndexingTechnique, formatIndexingMethod])
diff --git a/web/i18n/en-US/dataset.ts b/web/i18n/en-US/dataset.ts
index 61ed3225e6..64fda36c10 100644
--- a/web/i18n/en-US/dataset.ts
+++ b/web/i18n/en-US/dataset.ts
@@ -53,6 +53,7 @@ const translation = {
     semantic_search: 'VECTOR',
     full_text_search: 'FULL TEXT',
     hybrid_search: 'HYBRID',
+    invertedIndex: 'INVERTED',
   },
   mixtureHighQualityAndEconomicTip: 'The Rerank model is required for mixture of high quality and economical knowledge bases.',
   inconsistentEmbeddingModelTip: 'The Rerank model is required if the Embedding models of the selected knowledge bases are inconsistent.',
@@ -67,7 +68,8 @@ const translation = {
     semantic: 'Semantic',
     keyword: 'Keyword',
   },
-  nTo1RetrievalLegacy: 'According to the optimization and upgrade of the retrieval strategy, N-to-1 retrieval will be officially deprecated in September. Until then you can still use it normally.',
+  nTo1RetrievalLegacy: 'N-to-1 retrieval will be officially deprecated from September. It is recommended to use the latest Multi-path retrieval to obtain better results. ',
+  nTo1RetrievalLegacyLink: 'Learn more',
 }
 
 export default translation
diff --git a/web/i18n/zh-Hans/dataset.ts b/web/i18n/zh-Hans/dataset.ts
index 1750c88ce3..1dd11c5c33 100644
--- a/web/i18n/zh-Hans/dataset.ts
+++ b/web/i18n/zh-Hans/dataset.ts
@@ -53,6 +53,7 @@ const translation = {
     semantic_search: '向量检索',
     full_text_search: '全文检索',
     hybrid_search: '混合检索',
+    invertedIndex: '倒排索引',
   },
   mixtureHighQualityAndEconomicTip: '混合使用高质量和经济型知识库需要配置 Rerank 模型。',
   inconsistentEmbeddingModelTip: '当所选知识库配置的 Embedding 模型不一致时，需要配置 Rerank 模型。',
@@ -67,7 +68,8 @@ const translation = {
     semantic: '语义',
     keyword: '关键词',
   },
-  nTo1RetrievalLegacy: '为了对检索策略进行优化和升级，N 选 1 检索功能将于九月份正式被优化。在此之前，您仍然可以正常使用该功能。',
+  nTo1RetrievalLegacy: '9 月 1 日起我们将不再提供此能力，推荐使用最新的多路召回获得更好的检索效果。',
+  nTo1RetrievalLegacyLink: '了解更多',
 }
 
 export default translation

From 53a89bbbc75edddfdfcf2b774a4b9b567c369785 Mon Sep 17 00:00:00 2001
From: Joel <iamjoel007@gmail.com>
Date: Tue, 30 Jul 2024 17:33:08 +0800
Subject: [PATCH 56/60] chore : option card (#6800)

---
 .../nodes/_base/components/option-card.tsx    | 62 +++++++++++++++++++
 .../llm/components/resolution-picker.tsx      | 45 ++++----------
 2 files changed, 74 insertions(+), 33 deletions(-)
 create mode 100644 web/app/components/workflow/nodes/_base/components/option-card.tsx

diff --git a/web/app/components/workflow/nodes/_base/components/option-card.tsx b/web/app/components/workflow/nodes/_base/components/option-card.tsx
new file mode 100644
index 0000000000..62fe8937fd
--- /dev/null
+++ b/web/app/components/workflow/nodes/_base/components/option-card.tsx
@@ -0,0 +1,62 @@
+'use client'
+import type { FC } from 'react'
+import React, { useCallback } from 'react'
+import type { VariantProps } from 'class-variance-authority'
+import { cva } from 'class-variance-authority'
+import cn from '@/utils/classnames'
+
+const variants = cva([], {
+  variants: {
+    align: {
+      left: 'justify-start',
+      center: 'justify-center',
+      right: 'justify-end',
+    },
+  },
+  defaultVariants: {
+    align: 'center',
+  },
+},
+)
+
+type Props = {
+  className?: string
+  title: string
+  onSelect: () => void
+  selected: boolean
+  disabled?: boolean
+  align?: 'left' | 'center' | 'right'
+} & VariantProps<typeof variants>
+
+const OptionCard: FC<Props> = ({
+  className,
+  title,
+  onSelect,
+  selected,
+  disabled,
+  align = 'center',
+}) => {
+  const handleSelect = useCallback(() => {
+    if (selected || disabled)
+      return
+    onSelect()
+  }, [onSelect, selected, disabled])
+
+  return (
+    <div
+      className={cn(
+        'flex items-center px-2 h-8 rounded-md system-sm-regular bg-components-option-card-option-bg border border-components-option-card-option-bg text-text-secondary cursor-default',
+        (!selected && !disabled) && 'hover:bg-components-option-card-option-bg-hover hover:border-components-option-card-option-border-hover hover:shadow-xs cursor-pointer',
+        selected && 'bg-components-option-card-option-selected-bg border-[1.5px] border-components-option-card-option-selected-border system-sm-medium shadow-xs',
+        disabled && 'text-text-disabled',
+        variants({ align }),
+        className,
+      )}
+      onClick={handleSelect}
+    >
+      {title}
+    </div>
+  )
+}
+
+export default React.memo(OptionCard)
diff --git a/web/app/components/workflow/nodes/llm/components/resolution-picker.tsx b/web/app/components/workflow/nodes/llm/components/resolution-picker.tsx
index 6ea48b1f72..76763de520 100644
--- a/web/app/components/workflow/nodes/llm/components/resolution-picker.tsx
+++ b/web/app/components/workflow/nodes/llm/components/resolution-picker.tsx
@@ -2,35 +2,11 @@
 import type { FC } from 'react'
 import React, { useCallback } from 'react'
 import { useTranslation } from 'react-i18next'
-import cn from '@/utils/classnames'
+import OptionCard from '@/app/components/workflow/nodes/_base/components/option-card'
 import { Resolution } from '@/types/app'
 
 const i18nPrefix = 'workflow.nodes.llm'
 
-type ItemProps = {
-  title: string
-  value: Resolution
-  onSelect: (value: Resolution) => void
-  isSelected: boolean
-}
-
-const Item: FC<ItemProps> = ({ title, value, onSelect, isSelected }) => {
-  const handleSelect = useCallback(() => {
-    if (isSelected)
-      return
-    onSelect(value)
-  }, [value, onSelect, isSelected])
-
-  return (
-    <div
-      className={cn(isSelected ? 'bg-white border-[2px] border-primary-400  shadow-xs' : 'bg-gray-25 border border-gray-100', 'flex items-center h-8 px-3 rounded-lg text-[13px] font-normal text-gray-900 cursor-pointer')}
-      onClick={handleSelect}
-    >
-      {title}
-    </div>
-  )
-}
-
 type Props = {
   value: Resolution
   onChange: (value: Resolution) => void
@@ -42,21 +18,24 @@ const ResolutionPicker: FC<Props> = ({
 }) => {
   const { t } = useTranslation()
 
+  const handleOnChange = useCallback((value: Resolution) => {
+    return () => {
+      onChange(value)
+    }
+  }, [onChange])
   return (
     <div className='flex items-center justify-between'>
       <div className='mr-2 text-xs font-medium text-gray-500 uppercase'>{t(`${i18nPrefix}.resolution.name`)}</div>
       <div className='flex items-center space-x-1'>
-        <Item
+        <OptionCard
           title={t(`${i18nPrefix}.resolution.high`)}
-          value={Resolution.high}
-          onSelect={onChange}
-          isSelected={value === Resolution.high}
+          onSelect={handleOnChange(Resolution.high)}
+          selected={value === Resolution.high}
         />
-        <Item
+        <OptionCard
           title={t(`${i18nPrefix}.resolution.low`)}
-          value={Resolution.low}
-          onSelect={onChange}
-          isSelected={value === Resolution.low}
+          onSelect={handleOnChange(Resolution.low)}
+          selected={value === Resolution.low}
         />
       </div>
     </div>

From 98d9837fbc78d21d96e6a2e1d608c818040ebc51 Mon Sep 17 00:00:00 2001
From: eric-0x72 <1466870240@qq.com>
Date: Tue, 30 Jul 2024 21:32:45 +0800
Subject: [PATCH 57/60] fix wrong charset when decoding Chinese content (#6774)

Co-authored-by: zhangwb <zhangwb@zts.com.cn>
---
 api/core/tools/utils/web_reader_tool.py | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/api/core/tools/utils/web_reader_tool.py b/api/core/tools/utils/web_reader_tool.py
index f6f04271d6..a461328ae6 100644
--- a/api/core/tools/utils/web_reader_tool.py
+++ b/api/core/tools/utils/web_reader_tool.py
@@ -10,6 +10,7 @@ import unicodedata
 from contextlib import contextmanager
 from urllib.parse import unquote
 
+import chardet
 import cloudscraper
 from bs4 import BeautifulSoup, CData, Comment, NavigableString
 from regex import regex
@@ -75,7 +76,18 @@ def get_url(url: str, user_agent: str = None) -> str:
     if response.status_code != 200:
         return "URL returned status code {}.".format(response.status_code)
 
-    a = extract_using_readabilipy(response.text)
+    # Detect encoding using chardet
+    detected_encoding = chardet.detect(response.content)
+    encoding = detected_encoding['encoding']
+    if encoding:
+        try:
+            content = response.content.decode(encoding)
+        except (UnicodeDecodeError, TypeError):
+            content = response.text
+    else:
+        content = response.text
+
+    a = extract_using_readabilipy(content)
 
     if not a['plain_text'] or not a['plain_text'].strip():
         return ''

From 9ce5cea911589f5f80f5b302b5fcbf0cef618bfb Mon Sep 17 00:00:00 2001
From: longzhihun <38651850@qq.com>
Date: Tue, 30 Jul 2024 21:57:18 +0800
Subject: [PATCH 58/60] feat: bedrock invoke enhancement (#6808)

---
 .../bedrock/llm/_position.yaml                |   1 +
 .../llm/cohere.command-r-plus-v1.0.yaml       |   3 +-
 .../bedrock/llm/cohere.command-r-v1.0.yaml    |   4 +-
 .../model_providers/bedrock/llm/llm.py        | 184 +-----------------
 .../llm/meta.llama3-1-405b-instruct-v1.0.yaml |  25 +++
 5 files changed, 37 insertions(+), 180 deletions(-)
 create mode 100644 api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-405b-instruct-v1.0.yaml

diff --git a/api/core/model_runtime/model_providers/bedrock/llm/_position.yaml b/api/core/model_runtime/model_providers/bedrock/llm/_position.yaml
index c523596b57..86c8061dee 100644
--- a/api/core/model_runtime/model_providers/bedrock/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/llm/_position.yaml
@@ -12,6 +12,7 @@
 - cohere.command-r-v1.0
 - meta.llama3-1-8b-instruct-v1:0
 - meta.llama3-1-70b-instruct-v1:0
+- meta.llama3-1-405b-instruct-v1:0
 - meta.llama3-8b-instruct-v1:0
 - meta.llama3-70b-instruct-v1:0
 - meta.llama2-13b-chat-v1
diff --git a/api/core/model_runtime/model_providers/bedrock/llm/cohere.command-r-plus-v1.0.yaml b/api/core/model_runtime/model_providers/bedrock/llm/cohere.command-r-plus-v1.0.yaml
index 4ecf3dd2fd..3c0bb4e8d5 100644
--- a/api/core/model_runtime/model_providers/bedrock/llm/cohere.command-r-plus-v1.0.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/llm/cohere.command-r-plus-v1.0.yaml
@@ -3,8 +3,7 @@ label:
   en_US: Command R+
 model_type: llm
 features:
-  #- multi-tool-call
-  - agent-thought
+  - tool-call
   #- stream-tool-call
 model_properties:
   mode: chat
diff --git a/api/core/model_runtime/model_providers/bedrock/llm/cohere.command-r-v1.0.yaml b/api/core/model_runtime/model_providers/bedrock/llm/cohere.command-r-v1.0.yaml
index b7a12b480a..a34f48319f 100644
--- a/api/core/model_runtime/model_providers/bedrock/llm/cohere.command-r-v1.0.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/llm/cohere.command-r-v1.0.yaml
@@ -3,9 +3,7 @@ label:
   en_US: Command R
 model_type: llm
 features:
-  #- multi-tool-call
-  - agent-thought
-  #- stream-tool-call
+  - tool-call
 model_properties:
   mode: chat
   context_size: 128000
diff --git a/api/core/model_runtime/model_providers/bedrock/llm/llm.py b/api/core/model_runtime/model_providers/bedrock/llm/llm.py
index e9906c8294..ff34a116c7 100644
--- a/api/core/model_runtime/model_providers/bedrock/llm/llm.py
+++ b/api/core/model_runtime/model_providers/bedrock/llm/llm.py
@@ -17,7 +17,6 @@ from botocore.exceptions import (
     ServiceNotInRegionError,
     UnknownServiceError,
 )
-from cohere import ChatMessage
 
 # local import
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta
@@ -42,7 +41,6 @@ from core.model_runtime.errors.invoke import (
 )
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
-from core.model_runtime.model_providers.cohere.llm.llm import CohereLargeLanguageModel
 
 logger = logging.getLogger(__name__)
 
@@ -59,6 +57,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
         {'prefix': 'mistral.mixtral-8x7b-instruct', 'support_system_prompts': False, 'support_tool_use': False},
         {'prefix': 'mistral.mistral-large', 'support_system_prompts': True, 'support_tool_use': True},
         {'prefix': 'mistral.mistral-small', 'support_system_prompts': True, 'support_tool_use': True},
+        {'prefix': 'cohere.command-r', 'support_system_prompts': True, 'support_tool_use': True},
         {'prefix': 'amazon.titan', 'support_system_prompts': False, 'support_tool_use': False}
     ]
 
@@ -94,86 +93,8 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
             model_info['model'] = model
             # invoke models via boto3 converse API
             return self._generate_with_converse(model_info, credentials, prompt_messages, model_parameters, stop, stream, user, tools)
-        # invoke Cohere models via boto3 client
-        if "cohere.command-r" in model:
-            return self._generate_cohere_chat(model, credentials, prompt_messages, model_parameters, stop, stream, user, tools)
         # invoke other models via boto3 client
         return self._generate(model, credentials, prompt_messages, model_parameters, stop, stream, user)
-    
-    def _generate_cohere_chat(
-            self, model: str, credentials: dict, prompt_messages: list[PromptMessage], model_parameters: dict,
-            stop: Optional[list[str]] = None, stream: bool = True, user: Optional[str] = None,
-            tools: Optional[list[PromptMessageTool]] = None,) -> Union[LLMResult, Generator]:
-        cohere_llm = CohereLargeLanguageModel()
-        client_config = Config(
-            region_name=credentials["aws_region"]
-        )
-
-        runtime_client = boto3.client(
-            service_name='bedrock-runtime',
-            config=client_config,
-            aws_access_key_id=credentials["aws_access_key_id"],
-            aws_secret_access_key=credentials["aws_secret_access_key"]
-        )
-
-        extra_model_kwargs = {}
-        if stop:
-            extra_model_kwargs['stop_sequences'] = stop
-
-        if tools:
-            tools = cohere_llm._convert_tools(tools)
-            model_parameters['tools'] = tools
-
-        message, chat_histories, tool_results \
-            = cohere_llm._convert_prompt_messages_to_message_and_chat_histories(prompt_messages)
-
-        if tool_results:
-            model_parameters['tool_results'] = tool_results
-
-        payload = {
-            **model_parameters,
-            "message": message,
-            "chat_history": chat_histories,
-        }
-
-        # need workaround for ai21 models which doesn't support streaming
-        if stream:
-            invoke = runtime_client.invoke_model_with_response_stream
-        else:
-            invoke = runtime_client.invoke_model
-
-        def serialize(obj):
-            if isinstance(obj, ChatMessage):
-                return obj.__dict__
-            raise TypeError(f"Type {type(obj)} not serializable")
-
-        try:
-            body_jsonstr=json.dumps(payload, default=serialize)
-            response = invoke(
-                modelId=model,
-                contentType="application/json",
-                accept="*/*",
-                body=body_jsonstr
-            )
-        except ClientError as ex:
-            error_code = ex.response['Error']['Code']
-            full_error_msg = f"{error_code}: {ex.response['Error']['Message']}"
-            raise self._map_client_to_invoke_error(error_code, full_error_msg)
-
-        except (EndpointConnectionError, NoRegionError, ServiceNotInRegionError) as ex:
-            raise InvokeConnectionError(str(ex))
-
-        except UnknownServiceError as ex:
-            raise InvokeServerUnavailableError(str(ex))
-
-        except Exception as ex:
-            raise InvokeError(str(ex))
-
-        if stream:
-            return self._handle_generate_stream_response(model, credentials, response, prompt_messages)
-
-        return self._handle_generate_response(model, credentials, response, prompt_messages)
-
 
     def _generate_with_converse(self, model_info: dict, credentials: dict, prompt_messages: list[PromptMessage], model_parameters: dict,
                 stop: Optional[list[str]] = None, stream: bool = True, user: Optional[str] = None, tools: Optional[list[PromptMessageTool]] = None,) -> Union[LLMResult, Generator]:
@@ -581,38 +502,9 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
         :param message: PromptMessage to convert.
         :return: String representation of the message.
         """
-        
-        if model_prefix == "anthropic":
-            human_prompt_prefix = "\n\nHuman:"
-            human_prompt_postfix = ""
-            ai_prompt = "\n\nAssistant:"
-
-        elif model_prefix == "meta":
-            # LLAMA3
-            if model_name.startswith("llama3"):
-                human_prompt_prefix = "<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n"
-                human_prompt_postfix = "<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
-                ai_prompt = "\n\nAssistant:"
-            else:
-                # LLAMA2
-                human_prompt_prefix = "\n[INST]"
-                human_prompt_postfix = "[\\INST]\n"
-                ai_prompt = ""
-
-        elif model_prefix == "mistral":
-            human_prompt_prefix = "<s>[INST]"
-            human_prompt_postfix = "[\\INST]\n"
-            ai_prompt = "\n\nAssistant:"
-
-        elif model_prefix == "amazon":
-            human_prompt_prefix = "\n\nUser:"
-            human_prompt_postfix = ""
-            ai_prompt = "\n\nBot:"
-        
-        else:
-            human_prompt_prefix = ""
-            human_prompt_postfix = ""
-            ai_prompt = ""
+        human_prompt_prefix = ""
+        human_prompt_postfix = ""
+        ai_prompt = ""
 
         content = message.content
 
@@ -663,13 +555,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
         model_prefix = model.split('.')[0]
         model_name = model.split('.')[1]
 
-        if model_prefix == "amazon":
-            payload["textGenerationConfig"] = { **model_parameters }
-            payload["textGenerationConfig"]["stopSequences"] = ["User:"]
-            
-            payload["inputText"] = self._convert_messages_to_prompt(prompt_messages, model_prefix)
-        
-        elif model_prefix == "ai21":
+        if model_prefix == "ai21":
             payload["temperature"] = model_parameters.get("temperature")
             payload["topP"] = model_parameters.get("topP")
             payload["maxTokens"] = model_parameters.get("maxTokens")
@@ -681,28 +567,12 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
                 payload["frequencyPenalty"] = {model_parameters.get("frequencyPenalty")}
             if model_parameters.get("countPenalty"):
                 payload["countPenalty"] = {model_parameters.get("countPenalty")}
-        
-        elif model_prefix == "mistral":
-            payload["temperature"] = model_parameters.get("temperature")
-            payload["top_p"] = model_parameters.get("top_p")
-            payload["max_tokens"] = model_parameters.get("max_tokens")
-            payload["prompt"] = self._convert_messages_to_prompt(prompt_messages, model_prefix)
-            payload["stop"] = stop[:10] if stop else []
-
-        elif model_prefix == "anthropic":
-            payload = { **model_parameters }
-            payload["prompt"] = self._convert_messages_to_prompt(prompt_messages, model_prefix)
-            payload["stop_sequences"] = ["\n\nHuman:"] + (stop if stop else [])
-            
+                    
         elif model_prefix == "cohere":
             payload = { **model_parameters }
             payload["prompt"] = prompt_messages[0].content
             payload["stream"] = stream
         
-        elif model_prefix == "meta":
-            payload = { **model_parameters }
-            payload["prompt"] = self._convert_messages_to_prompt(prompt_messages, model_prefix, model_name)
-
         else:
             raise ValueError(f"Got unknown model prefix {model_prefix}")
         
@@ -793,36 +663,16 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
         # get output text and calculate num tokens based on model / provider
         model_prefix = model.split('.')[0]
 
-        if model_prefix == "amazon":
-            output = response_body.get("results")[0].get("outputText").strip('\n')
-            prompt_tokens = response_body.get("inputTextTokenCount")
-            completion_tokens = response_body.get("results")[0].get("tokenCount")
-
-        elif model_prefix == "ai21":
+        if model_prefix == "ai21":
             output = response_body.get('completions')[0].get('data').get('text')
             prompt_tokens = len(response_body.get("prompt").get("tokens"))
             completion_tokens = len(response_body.get('completions')[0].get('data').get('tokens'))
-
-        elif model_prefix == "anthropic":
-            output = response_body.get("completion")
-            prompt_tokens = self.get_num_tokens(model, credentials, prompt_messages)
-            completion_tokens = self.get_num_tokens(model, credentials, output if output else '')
             
         elif model_prefix == "cohere":
             output = response_body.get("generations")[0].get("text")
             prompt_tokens = self.get_num_tokens(model, credentials, prompt_messages)
             completion_tokens = self.get_num_tokens(model, credentials, output if output else '')
-            
-        elif model_prefix == "meta":
-            output = response_body.get("generation").strip('\n')
-            prompt_tokens = response_body.get("prompt_token_count")
-            completion_tokens = response_body.get("generation_token_count")
-        
-        elif model_prefix == "mistral":
-            output = response_body.get("outputs")[0].get("text")
-            prompt_tokens = response.get('ResponseMetadata').get('HTTPHeaders').get('x-amzn-bedrock-input-token-count')
-            completion_tokens = response.get('ResponseMetadata').get('HTTPHeaders').get('x-amzn-bedrock-output-token-count')
-
+                        
         else:
             raise ValueError(f"Got unknown model prefix {model_prefix} when handling block response")
 
@@ -893,26 +743,10 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
             payload = json.loads(chunk.get('bytes').decode())
 
             model_prefix = model.split('.')[0]
-            if model_prefix == "amazon":
-                content_delta = payload.get("outputText").strip('\n')
-                finish_reason = payload.get("completion_reason")
- 
-            elif model_prefix == "anthropic":
-                content_delta = payload.get("completion")
-                finish_reason = payload.get("stop_reason")
-
-            elif model_prefix == "cohere":
+            if model_prefix == "cohere":
                 content_delta = payload.get("text")
                 finish_reason = payload.get("finish_reason")
             
-            elif model_prefix == "mistral":
-                content_delta = payload.get('outputs')[0].get("text")
-                finish_reason = payload.get('outputs')[0].get("stop_reason")
-
-            elif model_prefix == "meta":
-                content_delta = payload.get("generation").strip('\n')
-                finish_reason = payload.get("stop_reason")
-            
             else:
                 raise ValueError(f"Got unknown model prefix {model_prefix} when handling stream response")
 
diff --git a/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-405b-instruct-v1.0.yaml b/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-405b-instruct-v1.0.yaml
new file mode 100644
index 0000000000..401de65f89
--- /dev/null
+++ b/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-1-405b-instruct-v1.0.yaml
@@ -0,0 +1,25 @@
+model: meta.llama3-1-405b-instruct-v1:0
+label:
+  en_US: Llama 3.1 405B Instruct
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.5
+  - name: top_p
+    use_template: top_p
+    default: 0.9
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.00532'
+  output: '0.016'
+  unit: '0.001'
+  currency: USD

From 3c371a6cb0fd74785055b8a6cb56b9de7dfc1c7a Mon Sep 17 00:00:00 2001
From: crazywoola <100913391+crazywoola@users.noreply.github.com>
Date: Tue, 30 Jul 2024 23:51:48 +0800
Subject: [PATCH 59/60] fix: workflow api (#6810)

---
 api/controllers/service_api/app/workflow.py | 34 ++++++++++-----------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/api/controllers/service_api/app/workflow.py b/api/controllers/service_api/app/workflow.py
index 10484c9027..9446f9d588 100644
--- a/api/controllers/service_api/app/workflow.py
+++ b/api/controllers/service_api/app/workflow.py
@@ -29,22 +29,21 @@ from services.app_generate_service import AppGenerateService
 
 logger = logging.getLogger(__name__)
 
+workflow_run_fields = {
+    'id': fields.String,
+    'workflow_id': fields.String,
+    'status': fields.String,
+    'inputs': fields.Raw,
+    'outputs': fields.Raw,
+    'error': fields.String,
+    'total_steps': fields.Integer,
+    'total_tokens': fields.Integer,
+    'created_at': fields.DateTime,
+    'finished_at': fields.DateTime,
+    'elapsed_time': fields.Float,
+}
 
-class WorkflowRunApi(Resource):
-    workflow_run_fields = {
-        'id': fields.String,
-        'workflow_id': fields.String,
-        'status': fields.String,
-        'inputs': fields.Raw,
-        'outputs': fields.Raw,
-        'error': fields.String,
-        'total_steps': fields.Integer,
-        'total_tokens': fields.Integer,
-        'created_at': fields.DateTime,
-        'finished_at': fields.DateTime,
-        'elapsed_time': fields.Float,
-    }
-
+class WorkflowRunDetailApi(Resource):
     @validate_app_token
     @marshal_with(workflow_run_fields)
     def get(self, app_model: App, workflow_id: str):
@@ -57,7 +56,7 @@ class WorkflowRunApi(Resource):
 
         workflow_run = db.session.query(WorkflowRun).filter(WorkflowRun.id == workflow_id).first()
         return workflow_run
-
+class WorkflowRunApi(Resource):
     @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON, required=True))
     def post(self, app_model: App, end_user: EndUser):
         """
@@ -117,5 +116,6 @@ class WorkflowTaskStopApi(Resource):
         }
 
 
-api.add_resource(WorkflowRunApi, '/workflows/run/<string:workflow_id>', '/workflows/run')
+api.add_resource(WorkflowRunApi, '/workflows/run')
+api.add_resource(WorkflowRunDetailApi, '/workflows/run/<string:workflow_id>')
 api.add_resource(WorkflowTaskStopApi, '/workflows/tasks/<string:task_id>/stop')

From 545d3c5a93216067b5df4185c2a997904e1817b0 Mon Sep 17 00:00:00 2001
From: Ever <439674061@qq.com>
Date: Wed, 31 Jul 2024 00:21:16 +0800
Subject: [PATCH 60/60] chore: Add processId field for metrics of
 threads/db-pool-stat/health (#6797)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Co-authored-by: 老潮 <zhangyongsheng@3vjia.com>
Co-authored-by: takatost <takatost@users.noreply.github.com>
Co-authored-by: takatost <takatost@gmail.com>
---
 api/app.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/api/app.py b/api/app.py
index 2c484ace85..50441cb81d 100644
--- a/api/app.py
+++ b/api/app.py
@@ -261,6 +261,7 @@ def after_request(response):
 @app.route('/health')
 def health():
     return Response(json.dumps({
+        'pid': os.getpid(),
         'status': 'ok',
         'version': app.config['CURRENT_VERSION']
     }), status=200, content_type="application/json")
@@ -284,6 +285,7 @@ def threads():
         })
 
     return {
+        'pid': os.getpid(),
         'thread_num': num_threads,
         'threads': thread_list
     }
@@ -293,6 +295,7 @@ def threads():
 def pool_stat():
     engine = db.engine
     return {
+        'pid': os.getpid(),
         'pool_size': engine.pool.size(),
         'checked_in_connections': engine.pool.checkedin(),
         'checked_out_connections': engine.pool.checkedout(),