From e54ce479ad21905e423ce091bf8d83391c1a54d9 Mon Sep 17 00:00:00 2001 From: zxhlyh Date: Thu, 23 Jan 2025 16:20:00 +0800 Subject: [PATCH 01/75] Feat/prompt editor dark theme (#12976) --- .../components/base/prompt-editor/index.tsx | 2 +- .../plugins/component-picker-block/hooks.tsx | 10 ++++----- .../plugins/component-picker-block/index.tsx | 6 +++--- .../component-picker-block/prompt-option.tsx | 8 +++---- .../variable-option.tsx | 8 +++---- .../prompt-editor/plugins/placeholder.tsx | 2 +- .../plugins/variable-value-block/node.tsx | 2 +- .../workflow-variable-block/component.tsx | 21 ++++++++++++------- 8 files changed, 32 insertions(+), 27 deletions(-) diff --git a/web/app/components/base/prompt-editor/index.tsx b/web/app/components/base/prompt-editor/index.tsx index 4a718527b8..b09109ef3f 100644 --- a/web/app/components/base/prompt-editor/index.tsx +++ b/web/app/components/base/prompt-editor/index.tsx @@ -149,7 +149,7 @@ const PromptEditor: FC = ({
} + contentEditable={} placeholder={} ErrorBoundary={LexicalErrorBoundary} /> diff --git a/web/app/components/base/prompt-editor/plugins/component-picker-block/hooks.tsx b/web/app/components/base/prompt-editor/plugins/component-picker-block/hooks.tsx index b14bf8112b..f39d56f72b 100644 --- a/web/app/components/base/prompt-editor/plugins/component-picker-block/hooks.tsx +++ b/web/app/components/base/prompt-editor/plugins/component-picker-block/hooks.tsx @@ -133,7 +133,7 @@ export const useVariableOptions = ( return ( } + icon={} queryString={queryString} isSelected={isSelected} onClick={onSelect} @@ -162,7 +162,7 @@ export const useVariableOptions = ( return ( } + icon={} queryString={queryString} isSelected={isSelected} onClick={onSelect} @@ -211,7 +211,7 @@ export const useExternalToolOptions = ( background={item.icon_background} /> } - extraElement={
{item.variableName}
} + extraElement={
{item.variableName}
} queryString={queryString} isSelected={isSelected} onClick={onSelect} @@ -240,8 +240,8 @@ export const useExternalToolOptions = ( return ( } - extraElement={< ArrowUpRight className='w-3 h-3 text-gray-400' />} + icon={} + extraElement={< ArrowUpRight className='w-3 h-3 text-text-tertiary' />} queryString={queryString} isSelected={isSelected} onClick={onSelect} diff --git a/web/app/components/base/prompt-editor/plugins/component-picker-block/index.tsx b/web/app/components/base/prompt-editor/plugins/component-picker-block/index.tsx index a5cb39f383..752458278b 100644 --- a/web/app/components/base/prompt-editor/plugins/component-picker-block/index.tsx +++ b/web/app/components/base/prompt-editor/plugins/component-picker-block/index.tsx @@ -135,7 +135,7 @@ const ComponentPicker = ({ // See https://github.com/facebook/lexical/blob/ac97dfa9e14a73ea2d6934ff566282d7f758e8bb/packages/lexical-react/src/shared/LexicalMenu.ts#L493
+
) } {option.renderMenuOption({ @@ -169,7 +169,7 @@ const ComponentPicker = ({ <> { (!!options.length) && ( -
+
) }
diff --git a/web/app/components/base/prompt-editor/plugins/component-picker-block/prompt-option.tsx b/web/app/components/base/prompt-editor/plugins/component-picker-block/prompt-option.tsx index 7aabbe4b26..985e195848 100644 --- a/web/app/components/base/prompt-editor/plugins/component-picker-block/prompt-option.tsx +++ b/web/app/components/base/prompt-editor/plugins/component-picker-block/prompt-option.tsx @@ -21,9 +21,9 @@ export const PromptMenuItem = memo(({ return (
{icon} -
{title}
+
{title}
) }) diff --git a/web/app/components/base/prompt-editor/plugins/component-picker-block/variable-option.tsx b/web/app/components/base/prompt-editor/plugins/component-picker-block/variable-option.tsx index 27a88ab665..ae0cdfb44b 100644 --- a/web/app/components/base/prompt-editor/plugins/component-picker-block/variable-option.tsx +++ b/web/app/components/base/prompt-editor/plugins/component-picker-block/variable-option.tsx @@ -38,8 +38,8 @@ export const VariableMenuItem = memo(({ return (
{icon}
-
+
{before} - {middle} + {middle} {after}
{extraElement} diff --git a/web/app/components/base/prompt-editor/plugins/placeholder.tsx b/web/app/components/base/prompt-editor/plugins/placeholder.tsx index f5a45faa77..2ad87917d2 100644 --- a/web/app/components/base/prompt-editor/plugins/placeholder.tsx +++ b/web/app/components/base/prompt-editor/plugins/placeholder.tsx @@ -16,7 +16,7 @@ const Placeholder = ({ return (
{value || t('common.promptEditor.placeholder')} diff --git a/web/app/components/base/prompt-editor/plugins/variable-value-block/node.tsx b/web/app/components/base/prompt-editor/plugins/variable-value-block/node.tsx index 163d4bfac4..9dd76fc1fa 100644 --- a/web/app/components/base/prompt-editor/plugins/variable-value-block/node.tsx +++ b/web/app/components/base/prompt-editor/plugins/variable-value-block/node.tsx @@ -24,7 +24,7 @@ export class VariableValueBlockNode extends TextNode { createDOM(config: EditorConfig): HTMLElement { const element = super.createDOM(config) - element.classList.add('inline-flex', 'items-center', 'px-0.5', 'h-[22px]', 'text-[#155EEF]', 'rounded-[5px]', 'align-middle') + element.classList.add('inline-flex', 'items-center', 'px-0.5', 'h-[22px]', 'text-text-accent', 'rounded-[5px]', 'align-middle') return element } diff --git a/web/app/components/base/prompt-editor/plugins/workflow-variable-block/component.tsx b/web/app/components/base/prompt-editor/plugins/workflow-variable-block/component.tsx index 0073ac300b..fc6e589807 100644 --- a/web/app/components/base/prompt-editor/plugins/workflow-variable-block/component.tsx +++ b/web/app/components/base/prompt-editor/plugins/workflow-variable-block/component.tsx @@ -77,8 +77,8 @@ const WorkflowVariableBlockComponent = ({
@@ -88,25 +88,30 @@ const WorkflowVariableBlockComponent = ({ node?.type && (
) } -
{node?.title}
- +
)} -
+
{!isEnv && !isChatVar && } {isEnv && } {isChatVar && } -
{varName}
+
{varName}
{ !node && !isEnv && !isChatVar && ( - + ) }
From da67916843249390ee75438207042b215e752183 Mon Sep 17 00:00:00 2001 From: lowell <37662342+Jhvcc@users.noreply.github.com> Date: Fri, 24 Jan 2025 10:04:46 +0800 Subject: [PATCH 02/75] feat: add glm-4-air-0111 (#12997) Co-authored-by: lowell --- .../zhipuai/llm/glm-4-air-0111.yaml | 66 +++++++++++++++++++ 1 file changed, 66 insertions(+) create mode 100644 api/core/model_runtime/model_providers/zhipuai/llm/glm-4-air-0111.yaml diff --git a/api/core/model_runtime/model_providers/zhipuai/llm/glm-4-air-0111.yaml b/api/core/model_runtime/model_providers/zhipuai/llm/glm-4-air-0111.yaml new file mode 100644 index 0000000000..8d301fc69d --- /dev/null +++ b/api/core/model_runtime/model_providers/zhipuai/llm/glm-4-air-0111.yaml @@ -0,0 +1,66 @@ +model: glm-4-air-0111 +label: + en_US: glm-4-air-0111 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call +model_properties: + mode: chat + context_size: 131072 +parameter_rules: + - name: temperature + use_template: temperature + default: 0.95 + min: 0.0 + max: 1.0 + help: + zh_Hans: 采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。 + en_US: Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time. + - name: top_p + use_template: top_p + default: 0.7 + help: + zh_Hans: 用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。 + en_US: Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time. + - name: do_sample + label: + zh_Hans: 采样策略 + en_US: Sampling strategy + type: boolean + help: + zh_Hans: do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。 + en_US: When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true. + default: true + - name: max_tokens + use_template: max_tokens + default: 1024 + min: 1 + max: 4095 + - name: web_search + type: boolean + label: + zh_Hans: 联网搜索 + en_US: Web Search + default: false + help: + zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。 + en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic. + - 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: '0.0005' + output: '0.0005' + unit: '0.001' + currency: RMB From 28067640b55cebf17ca3f3abe9b0e79c6a4b046d Mon Sep 17 00:00:00 2001 From: "IWAI, Masaharu" Date: Fri, 24 Jan 2025 14:41:20 +0900 Subject: [PATCH 03/75] fix: wrong zh_Hans translation: Ohio (#13006) --- api/core/model_runtime/model_providers/bedrock/bedrock.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/api/core/model_runtime/model_providers/bedrock/bedrock.yaml b/api/core/model_runtime/model_providers/bedrock/bedrock.yaml index 99013a95d2..0d28d02cca 100644 --- a/api/core/model_runtime/model_providers/bedrock/bedrock.yaml +++ b/api/core/model_runtime/model_providers/bedrock/bedrock.yaml @@ -54,7 +54,7 @@ provider_credential_schema: - value: us-east-2 label: en_US: US East (Ohio) - zh_Hans: 美国东部 (弗吉尼亚北部) + zh_Hans: 美国东部 (俄亥俄) - value: us-west-2 label: en_US: US West (Oregon) From a2b9adb3a20ec17dcd025a4c90477c26a476a859 Mon Sep 17 00:00:00 2001 From: "Yueh-Po Peng (Yabi)" <94939112+y10ab1@users.noreply.github.com> Date: Fri, 24 Jan 2025 13:48:21 +0800 Subject: [PATCH 04/75] Change typo in translation (#13004) --- web/i18n/zh-Hant/workflow.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/web/i18n/zh-Hant/workflow.ts b/web/i18n/zh-Hant/workflow.ts index 54599d23ff..1bfc258317 100644 --- a/web/i18n/zh-Hant/workflow.ts +++ b/web/i18n/zh-Hant/workflow.ts @@ -335,7 +335,7 @@ const translation = { retryFailed: '重試失敗', retryFailedTimes: '{{times}} 次重試失敗', times: '次', - ms: '女士', + ms: '毫秒', retries: '{{num}}重試', }, }, From a2f8bce8f5cee9d450b6350da9b565940e30b9c7 Mon Sep 17 00:00:00 2001 From: "IWAI, Masaharu" Date: Fri, 24 Jan 2025 19:43:33 +0900 Subject: [PATCH 05/75] chore: add Japanese translation: model_providers/bedrock (#13016) --- .../model_providers/bedrock/bedrock.yaml | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/api/core/model_runtime/model_providers/bedrock/bedrock.yaml b/api/core/model_runtime/model_providers/bedrock/bedrock.yaml index 0d28d02cca..63d6640348 100644 --- a/api/core/model_runtime/model_providers/bedrock/bedrock.yaml +++ b/api/core/model_runtime/model_providers/bedrock/bedrock.yaml @@ -44,6 +44,7 @@ provider_credential_schema: label: en_US: AWS Region zh_Hans: AWS 地区 + ja_JP: AWS リージョン type: select default: us-east-1 options: @@ -51,62 +52,77 @@ provider_credential_schema: label: en_US: US East (N. Virginia) zh_Hans: 美国东部 (弗吉尼亚北部) + ja_JP: 米国 (バージニア北部) - value: us-east-2 label: en_US: US East (Ohio) zh_Hans: 美国东部 (俄亥俄) + ja_JP: 米国 (オハイオ) - value: us-west-2 label: en_US: US West (Oregon) zh_Hans: 美国西部 (俄勒冈州) + ja_JP: 米国 (オレゴン) - value: ap-south-1 label: en_US: Asia Pacific (Mumbai) zh_Hans: 亚太地区（孟买） + ja_JP: アジアパシフィック (ムンバイ) - value: ap-southeast-1 label: en_US: Asia Pacific (Singapore) zh_Hans: 亚太地区 (新加坡) + ja_JP: アジアパシフィック (シンガポール) - value: ap-southeast-2 label: en_US: Asia Pacific (Sydney) zh_Hans: 亚太地区 (悉尼) + ja_JP: アジアパシフィック (シドニー) - value: ap-northeast-1 label: en_US: Asia Pacific (Tokyo) zh_Hans: 亚太地区 (东京) + ja_JP: アジアパシフィック (東京) - value: ap-northeast-2 label: en_US: Asia Pacific (Seoul) zh_Hans: 亚太地区（首尔） + ja_JP: アジアパシフィック (ソウル) - value: ca-central-1 label: en_US: Canada (Central) zh_Hans: 加拿大（中部） + ja_JP: カナダ (中部) - value: eu-central-1 label: en_US: Europe (Frankfurt) zh_Hans: 欧洲 (法兰克福) + ja_JP: 欧州 (フランクフルト) - value: eu-west-1 label: en_US: Europe (Ireland) zh_Hans: 欧洲（爱尔兰） + ja_JP: 欧州 (アイルランド) - value: eu-west-2 label: en_US: Europe (London) zh_Hans: 欧洲西部 (伦敦) + ja_JP: 欧州 (ロンドン) - value: eu-west-3 label: en_US: Europe (Paris) zh_Hans: 欧洲（巴黎） + ja_JP: 欧州 (パリ) - value: sa-east-1 label: en_US: South America (São Paulo) zh_Hans: 南美洲（圣保罗） + ja_JP: 南米 (サンパウロ) - value: us-gov-west-1 label: en_US: AWS GovCloud (US-West) zh_Hans: AWS GovCloud (US-West) + ja_JP: AWS GovCloud (米国西部) - variable: model_for_validation required: false label: From 59b3e672aa5fab4effedf72296a9e6ec7facb02d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=9D=9E=E6=B3=95=E6=93=8D=E4=BD=9C?= Date: Fri, 24 Jan 2025 20:13:42 +0800 Subject: [PATCH 06/75] feat: add agent thinking content display of deepseek R1 (#12949) --- .../model_providers/deepseek/llm/llm.py | 210 +++++++++++++++++- 1 file changed, 209 insertions(+), 1 deletion(-) diff --git a/api/core/model_runtime/model_providers/deepseek/llm/llm.py b/api/core/model_runtime/model_providers/deepseek/llm/llm.py index 610dc7b458..b280856c05 100644 --- a/api/core/model_runtime/model_providers/deepseek/llm/llm.py +++ b/api/core/model_runtime/model_providers/deepseek/llm/llm.py @@ -1,10 +1,13 @@ +import json from collections.abc import Generator from typing import Optional, Union +import requests from yarl import URL -from core.model_runtime.entities.llm_entities import LLMMode, LLMResult +from core.model_runtime.entities.llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta from core.model_runtime.entities.message_entities import ( + AssistantPromptMessage, PromptMessage, PromptMessageTool, ) @@ -36,3 +39,208 @@ class DeepseekLargeLanguageModel(OAIAPICompatLargeLanguageModel): credentials["mode"] = LLMMode.CHAT.value credentials["function_calling_type"] = "tool_call" credentials["stream_function_calling"] = "support" + + def _handle_generate_stream_response( + self, model: str, credentials: dict, response: requests.Response, prompt_messages: list[PromptMessage] + ) -> Generator: + """ + Handle llm stream response + + :param model: model name + :param credentials: model credentials + :param response: streamed response + :param prompt_messages: prompt messages + :return: llm response chunk generator + """ + full_assistant_content = "" + chunk_index = 0 + is_reasoning_started = False # Add flag to track reasoning state + + def create_final_llm_result_chunk( + id: Optional[str], index: int, message: AssistantPromptMessage, finish_reason: str, usage: dict + ) -> LLMResultChunk: + # calculate num tokens + prompt_tokens = usage and usage.get("prompt_tokens") + if prompt_tokens is None: + prompt_tokens = self._num_tokens_from_string(model, prompt_messages[0].content) + completion_tokens = usage and usage.get("completion_tokens") + if completion_tokens is None: + completion_tokens = self._num_tokens_from_string(model, full_assistant_content) + + # transform usage + usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens) + + return LLMResultChunk( + id=id, + model=model, + prompt_messages=prompt_messages, + delta=LLMResultChunkDelta(index=index, message=message, finish_reason=finish_reason, usage=usage), + ) + + # delimiter for stream response, need unicode_escape + import codecs + + delimiter = credentials.get("stream_mode_delimiter", "\n\n") + delimiter = codecs.decode(delimiter, "unicode_escape") + + tools_calls: list[AssistantPromptMessage.ToolCall] = [] + + def increase_tool_call(new_tool_calls: list[AssistantPromptMessage.ToolCall]): + def get_tool_call(tool_call_id: str): + if not tool_call_id: + return tools_calls[-1] + + tool_call = next((tool_call for tool_call in tools_calls if tool_call.id == tool_call_id), None) + if tool_call is None: + tool_call = AssistantPromptMessage.ToolCall( + id=tool_call_id, + type="function", + function=AssistantPromptMessage.ToolCall.ToolCallFunction(name="", arguments=""), + ) + tools_calls.append(tool_call) + + return tool_call + + for new_tool_call in new_tool_calls: + # get tool call + tool_call = get_tool_call(new_tool_call.function.name) + # update tool call + if new_tool_call.id: + tool_call.id = new_tool_call.id + if new_tool_call.type: + tool_call.type = new_tool_call.type + if new_tool_call.function.name: + tool_call.function.name = new_tool_call.function.name + if new_tool_call.function.arguments: + tool_call.function.arguments += new_tool_call.function.arguments + + finish_reason = None # The default value of finish_reason is None + message_id, usage = None, None + for chunk in response.iter_lines(decode_unicode=True, delimiter=delimiter): + chunk = chunk.strip() + if chunk: + # ignore sse comments + if chunk.startswith(":"): + continue + decoded_chunk = chunk.strip().removeprefix("data:").lstrip() + if decoded_chunk == "[DONE]": # Some provider returns "data: [DONE]" + continue + + try: + chunk_json: dict = json.loads(decoded_chunk) + # stream ended + except json.JSONDecodeError as e: + yield create_final_llm_result_chunk( + id=message_id, + index=chunk_index + 1, + message=AssistantPromptMessage(content=""), + finish_reason="Non-JSON encountered.", + usage=usage, + ) + break + # handle the error here. for issue #11629 + if chunk_json.get("error") and chunk_json.get("choices") is None: + raise ValueError(chunk_json.get("error")) + + if chunk_json: + if u := chunk_json.get("usage"): + usage = u + if not chunk_json or len(chunk_json["choices"]) == 0: + continue + + choice = chunk_json["choices"][0] + finish_reason = chunk_json["choices"][0].get("finish_reason") + message_id = chunk_json.get("id") + chunk_index += 1 + + if "delta" in choice: + delta = choice["delta"] + is_reasoning = delta.get("reasoning_content") + delta_content = delta.get("content") or delta.get("reasoning_content") + + assistant_message_tool_calls = None + + if "tool_calls" in delta and credentials.get("function_calling_type", "no_call") == "tool_call": + assistant_message_tool_calls = delta.get("tool_calls", None) + elif ( + "function_call" in delta + and credentials.get("function_calling_type", "no_call") == "function_call" + ): + assistant_message_tool_calls = [ + {"id": "tool_call_id", "type": "function", "function": delta.get("function_call", {})} + ] + + # assistant_message_function_call = delta.delta.function_call + + # extract tool calls from response + if assistant_message_tool_calls: + tool_calls = self._extract_response_tool_calls(assistant_message_tool_calls) + increase_tool_call(tool_calls) + + if delta_content is None or delta_content == "": + continue + + # Add markdown quote markers for reasoning content + if is_reasoning: + if not is_reasoning_started: + delta_content = "> 💭 " + delta_content + is_reasoning_started = True + elif "\n\n" in delta_content: + delta_content = delta_content.replace("\n\n", "\n> ") + elif "\n" in delta_content: + delta_content = delta_content.replace("\n", "\n> ") + elif is_reasoning_started: + # If we were in reasoning mode but now getting regular content, + # add \n\n to close the reasoning block + delta_content = "\n\n" + delta_content + is_reasoning_started = False + + # transform assistant message to prompt message + assistant_prompt_message = AssistantPromptMessage( + content=delta_content, + ) + + # reset tool calls + tool_calls = [] + full_assistant_content += delta_content + elif "text" in choice: + choice_text = choice.get("text", "") + if choice_text == "": + continue + + # transform assistant message to prompt message + assistant_prompt_message = AssistantPromptMessage(content=choice_text) + full_assistant_content += choice_text + else: + continue + + yield LLMResultChunk( + id=message_id, + model=model, + prompt_messages=prompt_messages, + delta=LLMResultChunkDelta( + index=chunk_index, + message=assistant_prompt_message, + ), + ) + + chunk_index += 1 + + if tools_calls: + yield LLMResultChunk( + id=message_id, + model=model, + prompt_messages=prompt_messages, + delta=LLMResultChunkDelta( + index=chunk_index, + message=AssistantPromptMessage(tool_calls=tools_calls, content=""), + ), + ) + + yield create_final_llm_result_chunk( + id=message_id, + index=chunk_index, + message=AssistantPromptMessage(content=""), + finish_reason=finish_reason, + usage=usage, + ) From b2bbc285802692552332ade472ca28b28fc5f531 Mon Sep 17 00:00:00 2001 From: Warren Chen Date: Sat, 25 Jan 2025 17:28:06 +0800 Subject: [PATCH 07/75] support bedrock kb: retrieve and generate (#13027) --- .../builtin/aws/tools/bedrock_config.py | 114 ++++++ .../tools/bedrock_retrieve_and_generate.py | 324 ++++++++++++++++ .../tools/bedrock_retrieve_and_generate.yaml | 358 ++++++++++++++++++ api/poetry.lock | 33 +- api/pyproject.toml | 2 +- 5 files changed, 813 insertions(+), 18 deletions(-) create mode 100644 api/core/tools/provider/builtin/aws/tools/bedrock_config.py create mode 100644 api/core/tools/provider/builtin/aws/tools/bedrock_retrieve_and_generate.py create mode 100644 api/core/tools/provider/builtin/aws/tools/bedrock_retrieve_and_generate.yaml diff --git a/api/core/tools/provider/builtin/aws/tools/bedrock_config.py b/api/core/tools/provider/builtin/aws/tools/bedrock_config.py new file mode 100644 index 0000000000..ec6a15cdb6 --- /dev/null +++ b/api/core/tools/provider/builtin/aws/tools/bedrock_config.py @@ -0,0 +1,114 @@ +""" +Configuration classes for AWS Bedrock retrieve and generate API +""" + +from dataclasses import dataclass +from typing import Any, Literal, Optional + + +@dataclass +class TextInferenceConfig: + """Text inference configuration""" + + maxTokens: Optional[int] = None + stopSequences: Optional[list[str]] = None + temperature: Optional[float] = None + topP: Optional[float] = None + + +@dataclass +class PerformanceConfig: + """Performance configuration""" + + latency: Literal["standard", "optimized"] + + +@dataclass +class PromptTemplate: + """Prompt template configuration""" + + textPromptTemplate: str + + +@dataclass +class GuardrailConfig: + """Guardrail configuration""" + + guardrailId: str + guardrailVersion: str + + +@dataclass +class GenerationConfig: + """Generation configuration""" + + additionalModelRequestFields: Optional[dict[str, Any]] = None + guardrailConfiguration: Optional[GuardrailConfig] = None + inferenceConfig: Optional[dict[str, TextInferenceConfig]] = None + performanceConfig: Optional[PerformanceConfig] = None + promptTemplate: Optional[PromptTemplate] = None + + +@dataclass +class VectorSearchConfig: + """Vector search configuration""" + + filter: Optional[dict[str, Any]] = None + numberOfResults: Optional[int] = None + overrideSearchType: Optional[Literal["HYBRID", "SEMANTIC"]] = None + + +@dataclass +class RetrievalConfig: + """Retrieval configuration""" + + vectorSearchConfiguration: VectorSearchConfig + + +@dataclass +class OrchestrationConfig: + """Orchestration configuration""" + + additionalModelRequestFields: Optional[dict[str, Any]] = None + inferenceConfig: Optional[dict[str, TextInferenceConfig]] = None + performanceConfig: Optional[PerformanceConfig] = None + promptTemplate: Optional[PromptTemplate] = None + + +@dataclass +class KnowledgeBaseConfig: + """Knowledge base configuration""" + + generationConfiguration: GenerationConfig + knowledgeBaseId: str + modelArn: str + orchestrationConfiguration: Optional[OrchestrationConfig] = None + retrievalConfiguration: Optional[RetrievalConfig] = None + + +@dataclass +class SessionConfig: + """Session configuration""" + + kmsKeyArn: Optional[str] = None + sessionId: Optional[str] = None + + +@dataclass +class RetrieveAndGenerateConfiguration: + """Retrieve and generate configuration + The use of knowledgeBaseConfiguration or externalSourcesConfiguration depends on the type value + """ + + type: str = "KNOWLEDGE_BASE" + knowledgeBaseConfiguration: Optional[KnowledgeBaseConfig] = None + + +@dataclass +class RetrieveAndGenerateConfig: + """Retrieve and generate main configuration""" + + input: dict[str, str] + retrieveAndGenerateConfiguration: RetrieveAndGenerateConfiguration + sessionConfiguration: Optional[SessionConfig] = None + sessionId: Optional[str] = None diff --git a/api/core/tools/provider/builtin/aws/tools/bedrock_retrieve_and_generate.py b/api/core/tools/provider/builtin/aws/tools/bedrock_retrieve_and_generate.py new file mode 100644 index 0000000000..2713cf7546 --- /dev/null +++ b/api/core/tools/provider/builtin/aws/tools/bedrock_retrieve_and_generate.py @@ -0,0 +1,324 @@ +import json +from typing import Any, Optional + +import boto3 + +from core.tools.entities.tool_entities import ToolInvokeMessage +from core.tools.tool.builtin_tool import BuiltinTool + + +class BedrockRetrieveAndGenerateTool(BuiltinTool): + bedrock_client: Any = None + + def _create_text_inference_config( + self, + max_tokens: Optional[int] = None, + stop_sequences: Optional[str] = None, + temperature: Optional[float] = None, + top_p: Optional[float] = None, + ) -> Optional[dict]: + """Create text inference configuration""" + if any([max_tokens, stop_sequences, temperature, top_p]): + config = {} + if max_tokens is not None: + config["maxTokens"] = max_tokens + if stop_sequences: + try: + config["stopSequences"] = json.loads(stop_sequences) + except json.JSONDecodeError: + config["stopSequences"] = [] + if temperature is not None: + config["temperature"] = temperature + if top_p is not None: + config["topP"] = top_p + return config + return None + + def _create_guardrail_config( + self, + guardrail_id: Optional[str] = None, + guardrail_version: Optional[str] = None, + ) -> Optional[dict]: + """Create guardrail configuration""" + if guardrail_id and guardrail_version: + return {"guardrailId": guardrail_id, "guardrailVersion": guardrail_version} + return None + + def _create_generation_config( + self, + additional_model_fields: Optional[str] = None, + guardrail_config: Optional[dict] = None, + text_inference_config: Optional[dict] = None, + performance_mode: Optional[str] = None, + prompt_template: Optional[str] = None, + ) -> dict: + """Create generation configuration""" + config = {} + + if additional_model_fields: + try: + config["additionalModelRequestFields"] = json.loads(additional_model_fields) + except json.JSONDecodeError: + pass + + if guardrail_config: + config["guardrailConfiguration"] = guardrail_config + + if text_inference_config: + config["inferenceConfig"] = {"textInferenceConfig": text_inference_config} + + if performance_mode: + config["performanceConfig"] = {"latency": performance_mode} + + if prompt_template: + config["promptTemplate"] = {"textPromptTemplate": prompt_template} + + return config + + def _create_orchestration_config( + self, + orchestration_additional_model_fields: Optional[str] = None, + orchestration_text_inference_config: Optional[dict] = None, + orchestration_performance_mode: Optional[str] = None, + orchestration_prompt_template: Optional[str] = None, + ) -> dict: + """Create orchestration configuration""" + config = {} + + if orchestration_additional_model_fields: + try: + config["additionalModelRequestFields"] = json.loads(orchestration_additional_model_fields) + except json.JSONDecodeError: + pass + + if orchestration_text_inference_config: + config["inferenceConfig"] = {"textInferenceConfig": orchestration_text_inference_config} + + if orchestration_performance_mode: + config["performanceConfig"] = {"latency": orchestration_performance_mode} + + if orchestration_prompt_template: + config["promptTemplate"] = {"textPromptTemplate": orchestration_prompt_template} + + return config + + def _create_vector_search_config( + self, + number_of_results: int = 5, + search_type: str = "SEMANTIC", + metadata_filter: Optional[dict] = None, + ) -> dict: + """Create vector search configuration""" + config = { + "numberOfResults": number_of_results, + "overrideSearchType": search_type, + } + + # Only add filter if metadata_filter is not empty + if metadata_filter: + config["filter"] = metadata_filter + + return config + + def _bedrock_retrieve_and_generate( + self, + query: str, + knowledge_base_id: str, + model_arn: str, + # Generation Configuration + additional_model_fields: Optional[str] = None, + guardrail_id: Optional[str] = None, + guardrail_version: Optional[str] = None, + max_tokens: Optional[int] = None, + stop_sequences: Optional[str] = None, + temperature: Optional[float] = None, + top_p: Optional[float] = None, + performance_mode: str = "standard", + prompt_template: Optional[str] = None, + # Orchestration Configuration + orchestration_additional_model_fields: Optional[str] = None, + orchestration_max_tokens: Optional[int] = None, + orchestration_stop_sequences: Optional[str] = None, + orchestration_temperature: Optional[float] = None, + orchestration_top_p: Optional[float] = None, + orchestration_performance_mode: Optional[str] = None, + orchestration_prompt_template: Optional[str] = None, + # Retrieval Configuration + number_of_results: int = 5, + search_type: str = "SEMANTIC", + metadata_filter: Optional[dict] = None, + # Additional Configuration + session_id: Optional[str] = None, + ) -> dict[str, Any]: + try: + # Create text inference configurations + text_inference_config = self._create_text_inference_config(max_tokens, stop_sequences, temperature, top_p) + orchestration_text_inference_config = self._create_text_inference_config( + orchestration_max_tokens, orchestration_stop_sequences, orchestration_temperature, orchestration_top_p + ) + + # Create guardrail configuration + guardrail_config = self._create_guardrail_config(guardrail_id, guardrail_version) + + # Create vector search configuration + vector_search_config = self._create_vector_search_config(number_of_results, search_type, metadata_filter) + + # Create generation configuration + generation_config = self._create_generation_config( + additional_model_fields, guardrail_config, text_inference_config, performance_mode, prompt_template + ) + + # Create orchestration configuration + orchestration_config = self._create_orchestration_config( + orchestration_additional_model_fields, + orchestration_text_inference_config, + orchestration_performance_mode, + orchestration_prompt_template, + ) + + # Create knowledge base configuration + knowledge_base_config = { + "knowledgeBaseId": knowledge_base_id, + "modelArn": model_arn, + "generationConfiguration": generation_config, + "orchestrationConfiguration": orchestration_config, + "retrievalConfiguration": {"vectorSearchConfiguration": vector_search_config}, + } + + # Create request configuration + request_config = { + "input": {"text": query}, + "retrieveAndGenerateConfiguration": { + "type": "KNOWLEDGE_BASE", + "knowledgeBaseConfiguration": knowledge_base_config, + }, + } + + # Add session configuration if provided + if session_id and len(session_id) >= 2: + request_config["sessionConfiguration"] = {"sessionId": session_id} + request_config["sessionId"] = session_id + + # Send request + response = self.bedrock_client.retrieve_and_generate(**request_config) + + # Process response + result = {"output": response.get("output", {}).get("text", ""), "citations": []} + + # Process citations + for citation in response.get("citations", []): + citation_info = { + "text": citation.get("generatedResponsePart", {}).get("textResponsePart", {}).get("text", ""), + "references": [], + } + + for ref in citation.get("retrievedReferences", []): + reference = { + "content": ref.get("content", {}).get("text", ""), + "metadata": ref.get("metadata", {}), + "location": None, + } + + location = ref.get("location", {}) + if location.get("type") == "S3": + reference["location"] = location.get("s3Location", {}).get("uri") + + citation_info["references"].append(reference) + + result["citations"].append(citation_info) + + return result + + except Exception as e: + raise Exception(f"Error calling Bedrock service: {str(e)}") + + def _invoke( + self, + user_id: str, + tool_parameters: dict[str, Any], + ) -> ToolInvokeMessage: + try: + # Initialize Bedrock client if not already initialized + if not self.bedrock_client: + aws_region = tool_parameters.get("aws_region") + aws_access_key_id = tool_parameters.get("aws_access_key_id") + aws_secret_access_key = tool_parameters.get("aws_secret_access_key") + + client_kwargs = { + "service_name": "bedrock-agent-runtime", + } + if aws_region: + client_kwargs["region_name"] = aws_region + # Only add credentials if both access key and secret key are provided + if aws_access_key_id and aws_secret_access_key: + client_kwargs.update( + {"aws_access_key_id": aws_access_key_id, "aws_secret_access_key": aws_secret_access_key} + ) + + try: + self.bedrock_client = boto3.client(**client_kwargs) + except Exception as e: + return self.create_text_message(f"Failed to initialize Bedrock client: {str(e)}") + + # Parse metadata filter if provided + metadata_filter = None + if metadata_filter_str := tool_parameters.get("metadata_filter"): + try: + parsed_filter = json.loads(metadata_filter_str) + if parsed_filter: # Only set if not empty + metadata_filter = parsed_filter + except json.JSONDecodeError: + return self.create_text_message("metadata_filter must be a valid JSON string") + + try: + response = self._bedrock_retrieve_and_generate( + query=tool_parameters["query"], + knowledge_base_id=tool_parameters["knowledge_base_id"], + model_arn=tool_parameters["model_arn"], + # Generation Configuration + additional_model_fields=tool_parameters.get("additional_model_fields"), + guardrail_id=tool_parameters.get("guardrail_id"), + guardrail_version=tool_parameters.get("guardrail_version"), + max_tokens=tool_parameters.get("max_tokens"), + stop_sequences=tool_parameters.get("stop_sequences"), + temperature=tool_parameters.get("temperature"), + top_p=tool_parameters.get("top_p"), + performance_mode=tool_parameters.get("performance_mode", "standard"), + prompt_template=tool_parameters.get("prompt_template"), + # Orchestration Configuration + orchestration_additional_model_fields=tool_parameters.get("orchestration_additional_model_fields"), + orchestration_max_tokens=tool_parameters.get("orchestration_max_tokens"), + orchestration_stop_sequences=tool_parameters.get("orchestration_stop_sequences"), + orchestration_temperature=tool_parameters.get("orchestration_temperature"), + orchestration_top_p=tool_parameters.get("orchestration_top_p"), + orchestration_performance_mode=tool_parameters.get("orchestration_performance_mode"), + orchestration_prompt_template=tool_parameters.get("orchestration_prompt_template"), + # Retrieval Configuration + number_of_results=tool_parameters.get("number_of_results", 5), + search_type=tool_parameters.get("search_type", "SEMANTIC"), + metadata_filter=metadata_filter, + # Additional Configuration + session_id=tool_parameters.get("session_id"), + ) + return self.create_json_message(response) + + except Exception as e: + return self.create_text_message(f"Tool invocation error: {str(e)}") + + except Exception as e: + return self.create_text_message(f"Tool execution error: {str(e)}") + + def validate_parameters(self, parameters: dict[str, Any]) -> None: + """Validate the parameters""" + required_params = ["query", "model_arn", "knowledge_base_id"] + for param in required_params: + if not parameters.get(param): + raise ValueError(f"{param} is required") + + # Validate metadata filter if provided + if metadata_filter_str := parameters.get("metadata_filter"): + try: + if not isinstance(json.loads(metadata_filter_str), dict): + raise ValueError("metadata_filter must be a valid JSON object") + except json.JSONDecodeError: + raise ValueError("metadata_filter must be a valid JSON string") diff --git a/api/core/tools/provider/builtin/aws/tools/bedrock_retrieve_and_generate.yaml b/api/core/tools/provider/builtin/aws/tools/bedrock_retrieve_and_generate.yaml new file mode 100644 index 0000000000..f8a3b76aba --- /dev/null +++ b/api/core/tools/provider/builtin/aws/tools/bedrock_retrieve_and_generate.yaml @@ -0,0 +1,358 @@ +identity: + name: bedrock_retrieve_and_generate + author: AWS + label: + en_US: Bedrock Retrieve and Generate + zh_Hans: Bedrock检索和生成 + icon: icon.svg + +description: + human: + en_US: A tool for retrieving and generating information using Amazon Bedrock Knowledge Base + zh_Hans: 使用Amazon Bedrock知识库进行信息检索和生成的工具 + llm: A tool for retrieving and generating information using Amazon Bedrock Knowledge Base + +parameters: +# Additional Configuration + - name: session_id + type: string + required: false + label: + en_US: Session ID + zh_Hans: 会话ID + human_description: + en_US: Optional session ID for continuous conversations + zh_Hans: 用于连续对话的可选会话ID + form: form + + # AWS Configuration + - name: aws_region + type: string + required: false + label: + en_US: AWS Region + zh_Hans: AWS区域 + human_description: + en_US: AWS region for the Bedrock service + zh_Hans: Bedrock服务的AWS区域 + form: form + + - name: aws_access_key_id + type: string + required: false + label: + en_US: AWS Access Key ID + zh_Hans: AWS访问密钥ID + human_description: + en_US: AWS access key ID for authentication (optional) + zh_Hans: 用于身份验证的AWS访问密钥ID（可选） + form: form + + - name: aws_secret_access_key + type: string + required: false + label: + en_US: AWS Secret Access Key + zh_Hans: AWS秘密访问密钥 + human_description: + en_US: AWS secret access key for authentication (optional) + zh_Hans: 用于身份验证的AWS秘密访问密钥（可选） + form: form + + # Knowledge Base Configuration + - name: knowledge_base_id + type: string + required: true + label: + en_US: Knowledge Base ID + zh_Hans: 知识库ID + human_description: + en_US: ID of the Bedrock Knowledge Base + zh_Hans: Bedrock知识库的ID + form: form + + - name: model_arn + type: string + required: true + label: + en_US: Model ARN + zh_Hans: 模型ARN + human_description: + en_US: The ARN of the model to use + zh_Hans: 要使用的模型ARN + form: form + + # Retrieval Configuration + - name: query + type: string + required: true + label: + en_US: Query + zh_Hans: 查询 + human_description: + en_US: The search query to retrieve information + zh_Hans: 用于检索信息的查询语句 + form: llm + + - name: number_of_results + type: number + required: false + label: + en_US: Number of Results + zh_Hans: 结果数量 + human_description: + en_US: Number of results to retrieve (1-10) + zh_Hans: 要检索的结果数量（1-10） + default: 5 + min: 1 + max: 10 + form: form + + - name: search_type + type: select + required: false + label: + en_US: Search Type + zh_Hans: 搜索类型 + human_description: + en_US: Type of search to perform + zh_Hans: 要执行的搜索类型 + default: SEMANTIC + options: + - value: SEMANTIC + label: + en_US: Semantic Search + zh_Hans: 语义搜索 + - value: HYBRID + label: + en_US: Hybrid Search + zh_Hans: 混合搜索 + form: form + + - name: metadata_filter + type: string + required: false + label: + en_US: Metadata Filter + zh_Hans: 元数据过滤器 + human_description: + en_US: JSON formatted filter conditions for metadata, supporting operations like equals, greaterThan, lessThan, etc. + zh_Hans: 元数据的JSON格式过滤条件，支持等于、大于、小于等操作 + default: "{}" + form: form + +# Generation Configuration + - name: guardrail_id + type: string + required: false + label: + en_US: Guardrail ID + zh_Hans: 防护栏ID + human_description: + en_US: ID of the guardrail to apply + zh_Hans: 要应用的防护栏ID + form: form + + - name: guardrail_version + type: string + required: false + label: + en_US: Guardrail Version + zh_Hans: 防护栏版本 + human_description: + en_US: Version of the guardrail to apply + zh_Hans: 要应用的防护栏版本 + form: form + + - name: max_tokens + type: number + required: false + label: + en_US: Maximum Tokens + zh_Hans: 最大令牌数 + human_description: + en_US: Maximum number of tokens to generate + zh_Hans: 生成的最大令牌数 + default: 2048 + form: form + + - name: stop_sequences + type: string + required: false + label: + en_US: Stop Sequences + zh_Hans: 停止序列 + human_description: + en_US: JSON array of strings that will stop generation when encountered + zh_Hans: JSON数组格式的字符串，遇到这些序列时将停止生成 + default: "[]" + form: form + + - name: temperature + type: number + required: false + label: + en_US: Temperature + zh_Hans: 温度 + human_description: + en_US: Controls randomness in the output (0-1) + zh_Hans: 控制输出的随机性（0-1） + default: 0.7 + min: 0 + max: 1 + form: form + + - name: top_p + type: number + required: false + label: + en_US: Top P + zh_Hans: Top P值 + human_description: + en_US: Controls diversity via nucleus sampling (0-1) + zh_Hans: 通过核采样控制多样性（0-1） + default: 0.95 + min: 0 + max: 1 + form: form + + - name: performance_mode + type: select + required: false + label: + en_US: Performance Mode + zh_Hans: 性能模式 + human_description: + en_US: Select performance optimization mode(performanceConfig.latency) + zh_Hans: 选择性能优化模式(performanceConfig.latency) + default: standard + options: + - value: standard + label: + en_US: Standard + zh_Hans: 标准 + - value: optimized + label: + en_US: Optimized + zh_Hans: 优化 + form: form + + - name: prompt_template + type: string + required: false + label: + en_US: Prompt Template + zh_Hans: 提示模板 + human_description: + en_US: Custom prompt template for generation + zh_Hans: 用于生成的自定义提示模板 + form: form + + - name: additional_model_fields + type: string + required: false + label: + en_US: Additional Model Fields + zh_Hans: 额外模型字段 + human_description: + en_US: JSON formatted additional fields for model configuration + zh_Hans: JSON格式的额外模型配置字段 + default: "{}" + form: form + +# Orchestration Configuration + - name: orchestration_max_tokens + type: number + required: false + label: + en_US: Orchestration Maximum Tokens + zh_Hans: 编排最大令牌数 + human_description: + en_US: Maximum number of tokens for orchestration + zh_Hans: 编排过程的最大令牌数 + default: 2048 + form: form + + - name: orchestration_stop_sequences + type: string + required: false + label: + en_US: Orchestration Stop Sequences + zh_Hans: 编排停止序列 + human_description: + en_US: JSON array of strings that will stop orchestration when encountered + zh_Hans: JSON数组格式的字符串，遇到这些序列时将停止编排 + default: "[]" + form: form + + - name: orchestration_temperature + type: number + required: false + label: + en_US: Orchestration Temperature + zh_Hans: 编排温度 + human_description: + en_US: Controls randomness in the orchestration output (0-1) + zh_Hans: 控制编排输出的随机性（0-1） + default: 0.7 + min: 0 + max: 1 + form: form + + - name: orchestration_top_p + type: number + required: false + label: + en_US: Orchestration Top P + zh_Hans: 编排Top P值 + human_description: + en_US: Controls diversity via nucleus sampling in orchestration (0-1) + zh_Hans: 通过核采样控制编排的多样性（0-1） + default: 0.95 + min: 0 + max: 1 + form: form + + - name: orchestration_performance_mode + type: select + required: false + label: + en_US: Orchestration Performance Mode + zh_Hans: 编排性能模式 + human_description: + en_US: Select performance optimization mode for orchestration + zh_Hans: 选择编排的性能优化模式 + default: standard + options: + - value: standard + label: + en_US: Standard + zh_Hans: 标准 + - value: optimized + label: + en_US: Optimized + zh_Hans: 优化 + form: form + + - name: orchestration_prompt_template + type: string + required: false + label: + en_US: Orchestration Prompt Template + zh_Hans: 编排提示模板 + human_description: + en_US: Custom prompt template for orchestration + zh_Hans: 用于编排的自定义提示模板 + form: form + + - name: orchestration_additional_model_fields + type: string + required: false + label: + en_US: Orchestration Additional Model Fields + zh_Hans: 编排额外模型字段 + human_description: + en_US: JSON formatted additional fields for orchestration model configuration + zh_Hans: JSON格式的编排模型额外配置字段 + default: "{}" + form: form diff --git a/api/poetry.lock b/api/poetry.lock index 038979330f..1f72270dd4 100644 --- a/api/poetry.lock +++ b/api/poetry.lock @@ -931,36 +931,36 @@ files = [ [[package]] name = "boto3" -version = "1.35.74" +version = "1.36.4" description = "The AWS SDK for Python" optional = false python-versions = ">=3.8" groups = ["main"] markers = "python_version == \"3.11\" or python_version >= \"3.12\"" files = [ - {file = "boto3-1.35.74-py3-none-any.whl", hash = "sha256:dab5bddbbe57dc707b6f6a1f25dc2823b8e234b6fe99fafef7fc406ab73031b9"}, - {file = "boto3-1.35.74.tar.gz", hash = "sha256:88370c6845ba71a4dae7f6b357099df29b3965da584be040c8e72c9902bc9492"}, + {file = "boto3-1.36.4-py3-none-any.whl", hash = "sha256:9f8f699e75ec63fcc98c4dd7290997c7c06c68d3ac8161ad4735fe71f5fe945c"}, + {file = "boto3-1.36.4.tar.gz", hash = "sha256:eeceeb74ef8b65634d358c27aa074917f4449dc828f79301f1075232618eb502"}, ] [package.dependencies] -botocore = ">=1.35.74,<1.36.0" +botocore = ">=1.36.4,<1.37.0" jmespath = ">=0.7.1,<2.0.0" -s3transfer = ">=0.10.0,<0.11.0" +s3transfer = ">=0.11.0,<0.12.0" [package.extras] crt = ["botocore[crt] (>=1.21.0,<2.0a0)"] [[package]] name = "botocore" -version = "1.35.94" +version = "1.36.5" description = "Low-level, data-driven core of boto 3." optional = false python-versions = ">=3.8" groups = ["main"] markers = "python_version == \"3.11\" or python_version >= \"3.12\"" files = [ - {file = "botocore-1.35.94-py3-none-any.whl", hash = "sha256:d784d944865d8279c79d2301fc09ac28b5221d4e7328fb4e23c642c253b9932c"}, - {file = "botocore-1.35.94.tar.gz", hash = "sha256:2b3309b356541faa4d88bb957dcac1d8004aa44953c0b7d4521a6cc5d3d5d6ba"}, + {file = "botocore-1.36.5-py3-none-any.whl", hash = "sha256:6d9f70afa9bf9d21407089dc22b8cc8ec6fa44866d4660858c062c74fc8555eb"}, + {file = "botocore-1.36.5.tar.gz", hash = "sha256:234ed3d29a8954c37a551c933453bf14c6ae44a69a4f273ffef377a2612ca6a6"}, ] [package.dependencies] @@ -969,7 +969,7 @@ python-dateutil = ">=2.1,<3.0.0" urllib3 = {version = ">=1.25.4,<2.2.0 || >2.2.0,<3", markers = "python_version >= \"3.10\""} [package.extras] -crt = ["awscrt (==0.22.0)"] +crt = ["awscrt (==0.23.4)"] [[package]] name = "bottleneck" @@ -2126,7 +2126,6 @@ files = [ {file = "cryptography-44.0.0-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:761817a3377ef15ac23cd7834715081791d4ec77f9297ee694ca1ee9c2c7e5eb"}, {file = "cryptography-44.0.0-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:3c672a53c0fb4725a29c303be906d3c1fa99c32f58abe008a82705f9ee96f40b"}, {file = "cryptography-44.0.0-cp37-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:4ac4c9f37eba52cb6fbeaf5b59c152ea976726b865bd4cf87883a7e7006cc543"}, - {file = "cryptography-44.0.0-cp37-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:60eb32934076fa07e4316b7b2742fa52cbb190b42c2df2863dbc4230a0a9b385"}, {file = "cryptography-44.0.0-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:ed3534eb1090483c96178fcb0f8893719d96d5274dfde98aa6add34614e97c8e"}, {file = "cryptography-44.0.0-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:f3f6fdfa89ee2d9d496e2c087cebef9d4fcbb0ad63c40e821b39f74bf48d9c5e"}, {file = "cryptography-44.0.0-cp37-abi3-win32.whl", hash = "sha256:eb33480f1bad5b78233b0ad3e1b0be21e8ef1da745d8d2aecbb20671658b9053"}, @@ -2137,7 +2136,6 @@ files = [ {file = "cryptography-44.0.0-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:c5eb858beed7835e5ad1faba59e865109f3e52b3783b9ac21e7e47dc5554e289"}, {file = "cryptography-44.0.0-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:f53c2c87e0fb4b0c00fa9571082a057e37690a8f12233306161c8f4b819960b7"}, {file = "cryptography-44.0.0-cp39-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:9e6fc8a08e116fb7c7dd1f040074c9d7b51d74a8ea40d4df2fc7aa08b76b9e6c"}, - {file = "cryptography-44.0.0-cp39-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:9abcc2e083cbe8dde89124a47e5e53ec38751f0d7dfd36801008f316a127d7ba"}, {file = "cryptography-44.0.0-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:d2436114e46b36d00f8b72ff57e598978b37399d2786fd39793c36c6d5cb1c64"}, {file = "cryptography-44.0.0-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:a01956ddfa0a6790d594f5b34fc1bfa6098aca434696a03cfdbe469b8ed79285"}, {file = "cryptography-44.0.0-cp39-abi3-win32.whl", hash = "sha256:eca27345e1214d1b9f9490d200f9db5a874479be914199194e746c893788d417"}, @@ -7803,6 +7801,7 @@ files = [ {file = "psycopg2_binary-2.9.10-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:bb89f0a835bcfc1d42ccd5f41f04870c1b936d8507c6df12b7737febc40f0909"}, {file = "psycopg2_binary-2.9.10-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:f0c2d907a1e102526dd2986df638343388b94c33860ff3bbe1384130828714b1"}, {file = "psycopg2_binary-2.9.10-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:f8157bed2f51db683f31306aa497311b560f2265998122abe1dce6428bd86567"}, + {file = "psycopg2_binary-2.9.10-cp313-cp313-win_amd64.whl", hash = "sha256:27422aa5f11fbcd9b18da48373eb67081243662f9b46e6fd07c3eb46e4535142"}, {file = "psycopg2_binary-2.9.10-cp38-cp38-macosx_12_0_x86_64.whl", hash = "sha256:eb09aa7f9cecb45027683bb55aebaaf45a0df8bf6de68801a6afdc7947bb09d4"}, {file = "psycopg2_binary-2.9.10-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b73d6d7f0ccdad7bc43e6d34273f70d587ef62f824d7261c4ae9b8b1b6af90e8"}, {file = "psycopg2_binary-2.9.10-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ce5ab4bf46a211a8e924d307c1b1fcda82368586a19d0a24f8ae166f5c784864"}, @@ -9563,22 +9562,22 @@ files = [ [[package]] name = "s3transfer" -version = "0.10.4" +version = "0.11.2" description = "An Amazon S3 Transfer Manager" optional = false python-versions = ">=3.8" groups = ["main"] markers = "python_version == \"3.11\" or python_version >= \"3.12\"" files = [ - {file = "s3transfer-0.10.4-py3-none-any.whl", hash = "sha256:244a76a24355363a68164241438de1b72f8781664920260c48465896b712a41e"}, - {file = "s3transfer-0.10.4.tar.gz", hash = "sha256:29edc09801743c21eb5ecbc617a152df41d3c287f67b615f73e5f750583666a7"}, + {file = "s3transfer-0.11.2-py3-none-any.whl", hash = "sha256:be6ecb39fadd986ef1701097771f87e4d2f821f27f6071c872143884d2950fbc"}, + {file = "s3transfer-0.11.2.tar.gz", hash = "sha256:3b39185cb72f5acc77db1a58b6e25b977f28d20496b6e58d6813d75f464d632f"}, ] [package.dependencies] -botocore = ">=1.33.2,<2.0a.0" +botocore = ">=1.36.0,<2.0a.0" [package.extras] -crt = ["botocore[crt] (>=1.33.2,<2.0a.0)"] +crt = ["botocore[crt] (>=1.36.0,<2.0a.0)"] [[package]] name = "safetensors" @@ -12248,4 +12247,4 @@ cffi = ["cffi (>=1.11)"] [metadata] lock-version = "2.1" python-versions = ">=3.11,<3.13" -content-hash = "fdc2199389f0e4b6d81b4b7fe2c1d303b1995643fe802ad3a28b196e68c258ae" +content-hash = "a8fff72e974a1bd5c28f4ae326d120410a5628ad0bc65d87adca4e943130ec8f" diff --git a/api/pyproject.toml b/api/pyproject.toml index 12455a0e63..8c4d5fd283 100644 --- a/api/pyproject.toml +++ b/api/pyproject.toml @@ -21,7 +21,7 @@ azure-ai-inference = "~1.0.0b3" azure-ai-ml = "~1.20.0" azure-identity = "1.16.1" beautifulsoup4 = "4.12.2" -boto3 = "1.35.74" +boto3 = "1.36.4" bs4 = "~0.0.1" cachetools = "~5.3.0" celery = "~5.4.0" From 1374be5a315d06ea9fee733a7c4c960c405885c5 Mon Sep 17 00:00:00 2001 From: Shun Miyazawa <34241526+miya@users.noreply.github.com> Date: Sat, 25 Jan 2025 20:30:26 +0900 Subject: [PATCH 08/75] fix: Unexpected tag creation when pressing enter during tag conversion (#13041) --- web/app/components/base/tag-management/index.tsx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/web/app/components/base/tag-management/index.tsx b/web/app/components/base/tag-management/index.tsx index 9a747910d2..1b859db910 100644 --- a/web/app/components/base/tag-management/index.tsx +++ b/web/app/components/base/tag-management/index.tsx @@ -75,7 +75,7 @@ const TagManagementModal = ({ show, type }: TagManagementModalProps) => { autoFocus value={name} onChange={e => setName(e.target.value)} - onKeyDown={e => e.key === 'Enter' && createNewTag()} + onKeyDown={e => e.key === 'Enter' && !e.nativeEvent.isComposing && createNewTag()} onBlur={createNewTag} /> {tagList.map(tag => ( From d4be5ef9de3b9e963586709c99e3d54fe36e2a79 Mon Sep 17 00:00:00 2001 From: Jason Date: Sun, 26 Jan 2025 09:25:29 +0800 Subject: [PATCH 09/75] Update Novita AI predefined models (#13045) --- .../novita/_assets/icon_l_en.svg | 24 ++++------- .../novita/_assets/icon_s_en.svg | 11 +---- .../novita/llm/L3-8B-Stheno-v3.2.yaml | 41 +++++++++++++++++++ .../model_providers/novita/llm/_position.yaml | 40 ++++++++++++++++++ .../novita/llm/deepseek_v3.yaml | 41 +++++++++++++++++++ .../novita/llm/l3-8b-lunaris.yaml | 41 +++++++++++++++++++ .../novita/llm/l31-70b-euryale-v2.2.yaml | 41 +++++++++++++++++++ .../novita/llm/llama-3-8b-instruct.yaml | 4 +- .../novita/llm/llama-3.1-70b-instruct.yaml | 6 +-- .../llm/llama-3.1-8b-instruct-bf16.yaml | 41 +++++++++++++++++++ .../novita/llm/llama-3.1-8b-instruct-max.yaml | 41 +++++++++++++++++++ .../novita/llm/llama-3.1-8b-instruct.yaml | 6 +-- .../llm/llama-3.2-11b-vision-instruct.yaml | 41 +++++++++++++++++++ .../novita/llm/llama-3.2-1b-instruct.yaml | 41 +++++++++++++++++++ ...struct.yaml => llama-3.2-3b-instruct.yaml} | 10 ++--- .../novita/llm/llama-3.3-70b-instruct.yaml | 41 +++++++++++++++++++ .../novita/llm/mistral-nemo.yaml | 41 +++++++++++++++++++ .../novita/llm/mythomax-l2-13b.yaml | 4 +- .../llm/{lzlv_70b.yaml => openchat-7b.yaml} | 10 ++--- ...8x7B-DPO.yaml => qwen-2-72b-instruct.yaml} | 10 ++--- .../novita/llm/qwen-2-7b-instruct.yaml | 41 +++++++++++++++++++ .../novita/llm/qwen-2-vl-72b-instruct.yaml | 41 +++++++++++++++++++ .../novita/llm/qwen-2.5-72b-instruct.yaml | 41 +++++++++++++++++++ .../novita/llm/wizardlm-2-8x22b.yaml | 4 +- .../model_providers/novita/novita.yaml | 8 ++-- 25 files changed, 614 insertions(+), 56 deletions(-) create mode 100644 api/core/model_runtime/model_providers/novita/llm/L3-8B-Stheno-v3.2.yaml create mode 100644 api/core/model_runtime/model_providers/novita/llm/_position.yaml create mode 100644 api/core/model_runtime/model_providers/novita/llm/deepseek_v3.yaml create mode 100644 api/core/model_runtime/model_providers/novita/llm/l3-8b-lunaris.yaml create mode 100644 api/core/model_runtime/model_providers/novita/llm/l31-70b-euryale-v2.2.yaml create mode 100644 api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct-bf16.yaml create mode 100644 api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct-max.yaml create mode 100644 api/core/model_runtime/model_providers/novita/llm/llama-3.2-11b-vision-instruct.yaml create mode 100644 api/core/model_runtime/model_providers/novita/llm/llama-3.2-1b-instruct.yaml rename api/core/model_runtime/model_providers/novita/llm/{llama-3.1-405b-instruct.yaml => llama-3.2-3b-instruct.yaml} (79%) create mode 100644 api/core/model_runtime/model_providers/novita/llm/llama-3.3-70b-instruct.yaml create mode 100644 api/core/model_runtime/model_providers/novita/llm/mistral-nemo.yaml rename api/core/model_runtime/model_providers/novita/llm/{lzlv_70b.yaml => openchat-7b.yaml} (83%) rename api/core/model_runtime/model_providers/novita/llm/{Nous-Hermes-2-Mixtral-8x7B-DPO.yaml => qwen-2-72b-instruct.yaml} (79%) create mode 100644 api/core/model_runtime/model_providers/novita/llm/qwen-2-7b-instruct.yaml create mode 100644 api/core/model_runtime/model_providers/novita/llm/qwen-2-vl-72b-instruct.yaml create mode 100644 api/core/model_runtime/model_providers/novita/llm/qwen-2.5-72b-instruct.yaml diff --git a/api/core/model_runtime/model_providers/novita/_assets/icon_l_en.svg b/api/core/model_runtime/model_providers/novita/_assets/icon_l_en.svg index 5c92cdbc6d..c27089a2ac 100644 --- a/api/core/model_runtime/model_providers/novita/_assets/icon_l_en.svg +++ b/api/core/model_runtime/model_providers/novita/_assets/icon_l_en.svg @@ -1,19 +1,11 @@ - - - - - - - - - - - - + + + + + - - - - + + + diff --git a/api/core/model_runtime/model_providers/novita/_assets/icon_s_en.svg b/api/core/model_runtime/model_providers/novita/_assets/icon_s_en.svg index 798c1d6348..ae2d4815c4 100644 --- a/api/core/model_runtime/model_providers/novita/_assets/icon_s_en.svg +++ b/api/core/model_runtime/model_providers/novita/_assets/icon_s_en.svg @@ -1,10 +1,3 @@ - - - - - - - - - + + diff --git a/api/core/model_runtime/model_providers/novita/llm/L3-8B-Stheno-v3.2.yaml b/api/core/model_runtime/model_providers/novita/llm/L3-8B-Stheno-v3.2.yaml new file mode 100644 index 0000000000..443cbef4b3 --- /dev/null +++ b/api/core/model_runtime/model_providers/novita/llm/L3-8B-Stheno-v3.2.yaml @@ -0,0 +1,41 @@ +model: Sao10K/L3-8B-Stheno-v3.2 +label: + zh_Hans: Sao10K/L3-8B-Stheno-v3.2 + en_US: Sao10K/L3-8B-Stheno-v3.2 +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: '0.0005' + output: '0.0005' + unit: '0.0001' + currency: USD diff --git a/api/core/model_runtime/model_providers/novita/llm/_position.yaml b/api/core/model_runtime/model_providers/novita/llm/_position.yaml new file mode 100644 index 0000000000..4176fc19ca --- /dev/null +++ b/api/core/model_runtime/model_providers/novita/llm/_position.yaml @@ -0,0 +1,40 @@ +# Deepseek Models +- deepseek/deepseek_v3 + +# LLaMA Models +- meta-llama/llama-3.3-70b-instruct +- meta-llama/llama-3.2-11b-vision-instruct +- meta-llama/llama-3.2-3b-instruct +- meta-llama/llama-3.2-1b-instruct +- meta-llama/llama-3.1-70b-instruct +- meta-llama/llama-3.1-8b-instruct +- meta-llama/llama-3.1-8b-instruct-max +- meta-llama/llama-3.1-8b-instruct-bf16 +- meta-llama/llama-3-70b-instruct +- meta-llama/llama-3-8b-instruct + +# Mistral Models +- mistralai/mistral-nemo +- mistralai/mistral-7b-instruct + +# Qwen Models +- qwen/qwen-2.5-72b-instruct +- qwen/qwen-2-72b-instruct +- qwen/qwen-2-vl-72b-instruct +- qwen/qwen-2-7b-instruct + +# Other Models +- sao10k/L3-8B-Stheno-v3.2 +- sao10k/l3-70b-euryale-v2.1 +- sao10k/l31-70b-euryale-v2.2 +- sao10k/l3-8b-lunaris +- jondurbin/airoboros-l2-70b +- cognitivecomputations/dolphin-mixtral-8x22b +- google/gemma-2-9b-it +- nousresearch/hermes-2-pro-llama-3-8b +- sophosympatheia/midnight-rose-70b +- gryphe/mythomax-l2-13b +- nousresearch/nous-hermes-llama2-13b +- openchat/openchat-7b +- teknium/openhermes-2.5-mistral-7b +- microsoft/wizardlm-2-8x22b diff --git a/api/core/model_runtime/model_providers/novita/llm/deepseek_v3.yaml b/api/core/model_runtime/model_providers/novita/llm/deepseek_v3.yaml new file mode 100644 index 0000000000..b18746622c --- /dev/null +++ b/api/core/model_runtime/model_providers/novita/llm/deepseek_v3.yaml @@ -0,0 +1,41 @@ +model: deepseek/deepseek_v3 +label: + zh_Hans: deepseek/deepseek_v3 + en_US: deepseek/deepseek_v3 +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 64000 +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: '0.0089' + output: '0.0089' + unit: '0.0001' + currency: USD diff --git a/api/core/model_runtime/model_providers/novita/llm/l3-8b-lunaris.yaml b/api/core/model_runtime/model_providers/novita/llm/l3-8b-lunaris.yaml new file mode 100644 index 0000000000..d28c84084a --- /dev/null +++ b/api/core/model_runtime/model_providers/novita/llm/l3-8b-lunaris.yaml @@ -0,0 +1,41 @@ +model: sao10k/l3-8b-lunaris +label: + zh_Hans: sao10k/l3-8b-lunaris + en_US: sao10k/l3-8b-lunaris +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: '0.0005' + output: '0.0005' + unit: '0.0001' + currency: USD diff --git a/api/core/model_runtime/model_providers/novita/llm/l31-70b-euryale-v2.2.yaml b/api/core/model_runtime/model_providers/novita/llm/l31-70b-euryale-v2.2.yaml new file mode 100644 index 0000000000..9c39ce51c3 --- /dev/null +++ b/api/core/model_runtime/model_providers/novita/llm/l31-70b-euryale-v2.2.yaml @@ -0,0 +1,41 @@ +model: sao10k/l31-70b-euryale-v2.2 +label: + zh_Hans: sao10k/l31-70b-euryale-v2.2 + en_US: sao10k/l31-70b-euryale-v2.2 +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-3-8b-instruct.yaml b/api/core/model_runtime/model_providers/novita/llm/llama-3-8b-instruct.yaml index 9b5e5df4d0..7a754dfc11 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 @@ -35,7 +35,7 @@ parameter_rules: max: 2 default: 0 pricing: - input: '0.00063' - output: '0.00063' + input: '0.0004' + output: '0.0004' 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 index 3a5c29c40f..96ef12a41c 100644 --- 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 @@ -7,7 +7,7 @@ features: - agent-thought model_properties: mode: chat - context_size: 8192 + context_size: 32768 parameter_rules: - name: temperature use_template: temperature @@ -35,7 +35,7 @@ parameter_rules: max: 2 default: 0 pricing: - input: '0.0055' - output: '0.0076' + input: '0.0034' + output: '0.0039' unit: '0.0001' currency: USD diff --git a/api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct-bf16.yaml b/api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct-bf16.yaml new file mode 100644 index 0000000000..5ef72c770f --- /dev/null +++ b/api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct-bf16.yaml @@ -0,0 +1,41 @@ +model: meta-llama/llama-3.1-8b-instruct-bf16 +label: + zh_Hans: meta-llama/llama-3.1-8b-instruct-bf16 + en_US: meta-llama/llama-3.1-8b-instruct-bf16 +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: '0.0006' + output: '0.0006' + unit: '0.0001' + currency: USD diff --git a/api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct-max.yaml b/api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct-max.yaml new file mode 100644 index 0000000000..d75b3e461f --- /dev/null +++ b/api/core/model_runtime/model_providers/novita/llm/llama-3.1-8b-instruct-max.yaml @@ -0,0 +1,41 @@ +model: meta-llama/llama-3.1-8b-instruct-max +label: + zh_Hans: meta-llama/llama-3.1-8b-instruct-max + en_US: meta-llama/llama-3.1-8b-instruct-max +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 16384 +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: '0.0005' + output: '0.0005' + 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 index e6ef772a3f..49d9393e4d 100644 --- 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 @@ -7,7 +7,7 @@ features: - agent-thought model_properties: mode: chat - context_size: 8192 + context_size: 16384 parameter_rules: - name: temperature use_template: temperature @@ -35,7 +35,7 @@ parameter_rules: max: 2 default: 0 pricing: - input: '0.001' - output: '0.001' + input: '0.0005' + output: '0.0005' unit: '0.0001' currency: USD diff --git a/api/core/model_runtime/model_providers/novita/llm/llama-3.2-11b-vision-instruct.yaml b/api/core/model_runtime/model_providers/novita/llm/llama-3.2-11b-vision-instruct.yaml new file mode 100644 index 0000000000..3952a86cac --- /dev/null +++ b/api/core/model_runtime/model_providers/novita/llm/llama-3.2-11b-vision-instruct.yaml @@ -0,0 +1,41 @@ +model: meta-llama/llama-3.2-11b-vision-instruct +label: + zh_Hans: meta-llama/llama-3.2-11b-vision-instruct + en_US: meta-llama/llama-3.2-11b-vision-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: '0.0006' + output: '0.0006' + unit: '0.0001' + currency: USD diff --git a/api/core/model_runtime/model_providers/novita/llm/llama-3.2-1b-instruct.yaml b/api/core/model_runtime/model_providers/novita/llm/llama-3.2-1b-instruct.yaml new file mode 100644 index 0000000000..bf73b5cfc2 --- /dev/null +++ b/api/core/model_runtime/model_providers/novita/llm/llama-3.2-1b-instruct.yaml @@ -0,0 +1,41 @@ +model: meta-llama/llama-3.2-1b-instruct +label: + zh_Hans: meta-llama/llama-3.2-1b-instruct + en_US: meta-llama/llama-3.2-1b-instruct +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 131000 +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: '0.0002' + output: '0.0002' + 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-3.2-3b-instruct.yaml similarity index 79% rename from api/core/model_runtime/model_providers/novita/llm/llama-3.1-405b-instruct.yaml rename to api/core/model_runtime/model_providers/novita/llm/llama-3.2-3b-instruct.yaml index c5a45271ae..66b4842faf 100644 --- 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-3.2-3b-instruct.yaml @@ -1,7 +1,7 @@ -model: meta-llama/llama-3.1-405b-instruct +model: meta-llama/llama-3.2-3b-instruct label: - zh_Hans: meta-llama/llama-3.1-405b-instruct - en_US: meta-llama/llama-3.1-405b-instruct + zh_Hans: meta-llama/llama-3.2-3b-instruct + en_US: meta-llama/llama-3.2-3b-instruct model_type: llm features: - agent-thought @@ -35,7 +35,7 @@ parameter_rules: max: 2 default: 0 pricing: - input: '0.03' - output: '0.05' + input: '0.0003' + output: '0.0005' unit: '0.0001' currency: USD diff --git a/api/core/model_runtime/model_providers/novita/llm/llama-3.3-70b-instruct.yaml b/api/core/model_runtime/model_providers/novita/llm/llama-3.3-70b-instruct.yaml new file mode 100644 index 0000000000..0046dc92f1 --- /dev/null +++ b/api/core/model_runtime/model_providers/novita/llm/llama-3.3-70b-instruct.yaml @@ -0,0 +1,41 @@ +model: meta-llama/llama-3.3-70b-instruct +label: + zh_Hans: meta-llama/llama-3.3-70b-instruct + en_US: meta-llama/llama-3.3-70b-instruct +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 131072 +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: '0.0039' + output: '0.0039' + unit: '0.0001' + currency: USD diff --git a/api/core/model_runtime/model_providers/novita/llm/mistral-nemo.yaml b/api/core/model_runtime/model_providers/novita/llm/mistral-nemo.yaml new file mode 100644 index 0000000000..cb11ebbf94 --- /dev/null +++ b/api/core/model_runtime/model_providers/novita/llm/mistral-nemo.yaml @@ -0,0 +1,41 @@ +model: mistralai/mistral-nemo +label: + zh_Hans: mistralai/mistral-nemo + en_US: mistralai/mistral-nemo +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 131072 +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: '0.0017' + output: '0.0017' + 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 7e4ac3ffe0..fd859dcb39 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 @@ -35,7 +35,7 @@ parameter_rules: max: 2 default: 0 pricing: - input: '0.00119' - output: '0.00119' + input: '0.0009' + output: '0.0009' 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/openchat-7b.yaml similarity index 83% rename from api/core/model_runtime/model_providers/novita/llm/lzlv_70b.yaml rename to api/core/model_runtime/model_providers/novita/llm/openchat-7b.yaml index 0cc68a8c45..cad52a4408 100644 --- a/api/core/model_runtime/model_providers/novita/llm/lzlv_70b.yaml +++ b/api/core/model_runtime/model_providers/novita/llm/openchat-7b.yaml @@ -1,7 +1,7 @@ -model: lzlv_70b +model: openchat/openchat-7b label: - zh_Hans: lzlv_70b - en_US: lzlv_70b + zh_Hans: openchat/openchat-7b + en_US: openchat/openchat-7b model_type: llm features: - agent-thought @@ -35,7 +35,7 @@ parameter_rules: max: 2 default: 0 pricing: - input: '0.0058' - output: '0.0078' + input: '0.0006' + output: '0.0006' unit: '0.0001' currency: USD 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/qwen-2-72b-instruct.yaml similarity index 79% rename from api/core/model_runtime/model_providers/novita/llm/Nous-Hermes-2-Mixtral-8x7B-DPO.yaml rename to api/core/model_runtime/model_providers/novita/llm/qwen-2-72b-instruct.yaml index 7ff30458e2..bb2e935c01 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/qwen-2-72b-instruct.yaml @@ -1,7 +1,7 @@ -model: Nous-Hermes-2-Mixtral-8x7B-DPO +model: qwen/qwen-2-72b-instruct label: - zh_Hans: Nous-Hermes-2-Mixtral-8x7B-DPO - en_US: Nous-Hermes-2-Mixtral-8x7B-DPO + zh_Hans: qwen/qwen-2-72b-instruct + en_US: qwen/qwen-2-72b-instruct model_type: llm features: - agent-thought @@ -35,7 +35,7 @@ parameter_rules: max: 2 default: 0 pricing: - input: '0.0027' - output: '0.0027' + input: '0.0034' + output: '0.0039' unit: '0.0001' currency: USD diff --git a/api/core/model_runtime/model_providers/novita/llm/qwen-2-7b-instruct.yaml b/api/core/model_runtime/model_providers/novita/llm/qwen-2-7b-instruct.yaml new file mode 100644 index 0000000000..ff93d2eb11 --- /dev/null +++ b/api/core/model_runtime/model_providers/novita/llm/qwen-2-7b-instruct.yaml @@ -0,0 +1,41 @@ +model: qwen/qwen-2-7b-instruct +label: + zh_Hans: qwen/qwen-2-7b-instruct + en_US: qwen/qwen-2-7b-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: '0.00054' + output: '0.00054' + unit: '0.0001' + currency: USD diff --git a/api/core/model_runtime/model_providers/novita/llm/qwen-2-vl-72b-instruct.yaml b/api/core/model_runtime/model_providers/novita/llm/qwen-2-vl-72b-instruct.yaml new file mode 100644 index 0000000000..97097778c3 --- /dev/null +++ b/api/core/model_runtime/model_providers/novita/llm/qwen-2-vl-72b-instruct.yaml @@ -0,0 +1,41 @@ +model: qwen/qwen-2-vl-72b-instruct +label: + zh_Hans: qwen/qwen-2-vl-72b-instruct + en_US: qwen/qwen-2-vl-72b-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: '0.0045' + output: '0.0045' + unit: '0.0001' + currency: USD diff --git a/api/core/model_runtime/model_providers/novita/llm/qwen-2.5-72b-instruct.yaml b/api/core/model_runtime/model_providers/novita/llm/qwen-2.5-72b-instruct.yaml new file mode 100644 index 0000000000..729fac1da9 --- /dev/null +++ b/api/core/model_runtime/model_providers/novita/llm/qwen-2.5-72b-instruct.yaml @@ -0,0 +1,41 @@ +model: qwen/qwen-2.5-72b-instruct +label: + zh_Hans: qwen/qwen-2.5-72b-instruct + en_US: qwen/qwen-2.5-72b-instruct +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 32000 +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: '0.0038' + output: '0.004' + 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 ef42568e8f..6da4c7eca0 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 @@ -35,7 +35,7 @@ parameter_rules: max: 2 default: 0 pricing: - input: '0.0064' - output: '0.0064' + input: '0.0062' + output: '0.0062' 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 f634197989..b90d64c951 100644 --- a/api/core/model_runtime/model_providers/novita/novita.yaml +++ b/api/core/model_runtime/model_providers/novita/novita.yaml @@ -1,6 +1,6 @@ provider: novita label: - en_US: novita.ai + 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 @@ -11,10 +11,10 @@ icon_large: background: "#eadeff" help: title: - en_US: Get your API key from novita.ai - zh_Hans: 从 novita.ai 获取 API Key + en_US: Get your API key from Novita AI + zh_Hans: 从 Novita AI 获取 API Key url: - en_US: https://novita.ai/settings#key-management?utm_source=dify&utm_medium=ch&utm_campaign=api + en_US: https://novita.ai/settings/key-management?utm_source=dify&utm_medium=ch&utm_campaign=api supported_model_types: - llm configurate_methods: From d1fc65fabc12a2fb53b0be3e41610024e3874b52 Mon Sep 17 00:00:00 2001 From: NFish Date: Sun, 26 Jan 2025 11:19:41 +0800 Subject: [PATCH 10/75] fix: adjust iteration node dark style (#13051) --- .../workflow/nodes/_base/components/node-control.tsx | 4 ++-- .../nodes/_base/components/panel-operator/index.tsx | 6 +++--- .../nodes/_base/components/title-description-input.tsx | 10 ++++------ .../_base/components/variable/var-reference-picker.tsx | 2 +- web/app/components/workflow/nodes/_base/node.tsx | 4 ++-- .../workflow/nodes/iteration-start/index.tsx | 2 +- .../components/workflow/nodes/iteration/add-block.tsx | 6 +++--- web/app/components/workflow/nodes/iteration/node.tsx | 4 ++-- web/app/components/workflow/nodes/iteration/panel.tsx | 7 +++---- 9 files changed, 21 insertions(+), 24 deletions(-) diff --git a/web/app/components/workflow/nodes/_base/components/node-control.tsx b/web/app/components/workflow/nodes/_base/components/node-control.tsx index 1ce78220a1..781b66af6b 100644 --- a/web/app/components/workflow/nodes/_base/components/node-control.tsx +++ b/web/app/components/workflow/nodes/_base/components/node-control.tsx @@ -45,13 +45,13 @@ const NodeControl: FC = ({ `} >
e.stopPropagation()} > { canRunBySingle(data.type) && (
{ handleNodeDataUpdate({ id, diff --git a/web/app/components/workflow/nodes/_base/components/panel-operator/index.tsx b/web/app/components/workflow/nodes/_base/components/panel-operator/index.tsx index 4c19236716..43d65d3439 100644 --- a/web/app/components/workflow/nodes/_base/components/panel-operator/index.tsx +++ b/web/app/components/workflow/nodes/_base/components/panel-operator/index.tsx @@ -54,12 +54,12 @@ const PanelOperator = ({
- +
diff --git a/web/app/components/workflow/nodes/_base/components/title-description-input.tsx b/web/app/components/workflow/nodes/_base/components/title-description-input.tsx index a5718ba2b6..f17d34af8a 100644 --- a/web/app/components/workflow/nodes/_base/components/title-description-input.tsx +++ b/web/app/components/workflow/nodes/_base/components/title-description-input.tsx @@ -33,10 +33,8 @@ export const TitleInput = memo(({ value={localValue} onChange={e => setLocalValue(e.target.value)} className={` - grow mr-2 px-1 h-6 text-base text-gray-900 font-semibold rounded-lg border border-transparent appearance-none outline-none - hover:bg-gray-50 - focus:border-gray-300 focus:shadow-xs focus:bg-white caret-[#295EFF] - min-w-0 + grow mr-2 px-1 h-7 text-text-primary system-xl-semibold rounded-md border border-transparent appearance-none outline-none + focus:shadow-xs min-w-0 `} placeholder={t('workflow.common.addTitle') || ''} onBlur={handleBlur} @@ -66,8 +64,8 @@ export const DescriptionInput = memo(({