opensource
/
dify
mirror of https://github.com/langgenius/dify.git
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'fix/explore-tabs-change-failed' into fix/e-300

This commit is contained in:
NFish 2025-06-30 17:45:59 +08:00
parent 745d67989b e979768949
commit 41f4eb044d
420 changed files with 17079 additions and 5010 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
.github/workflows/api-tests.yml vendored
View File

@ -83,9 +83,15 @@ jobs:
compose-file: |
docker/docker-compose.middleware.yaml
services: |
db
redis
sandbox
ssrf_proxy
- name: setup test config
run: |
cp api/tests/integration_tests/.env.example api/tests/integration_tests/.env
- name: Run Workflow
run: uv run --project api bash dev/pytest/pytest_workflow.sh

6
.github/workflows/vdb-tests.yml vendored
View File

@ -84,6 +84,12 @@ jobs:
elasticsearch
oceanbase
- name: setup test config
run: |
echo $(pwd)
ls -lah .
cp api/tests/integration_tests/.env.example api/tests/integration_tests/.env
- name: Check VDB Ready (TiDB)
run: uv run --project api python api/tests/integration_tests/vdb/tidb_vector/check_tiflash_ready.py

4
README.md
View File

@ -230,6 +230,10 @@ Deploy Dify to AWS with [CDK](https://aws.amazon.com/cdk/)
Quickly deploy Dify to Alibaba cloud with [Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
#### Using Alibaba Cloud Data Management
One-Click deploy Dify to Alibaba Cloud with [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
## Contributing

5
README_AR.md
View File

@ -211,6 +211,11 @@ docker compose up -d
#### استخدام Alibaba Cloud للنشر
[بسرعة نشر Dify إلى سحابة علي بابا مع عش الحوسبة السحابية علي بابا](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
#### استخدام Alibaba Cloud Data Management للنشر
انشر ​​Dify على علي بابا كلاود بنقرة واحدة باستخدام [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
## المساهمة

4
README_BN.md
View File

@ -229,6 +229,10 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন
[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
#### Alibaba Cloud Data Management ব্যবহার করে ডিপ্লয়
[Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
## Contributing

4
README_CN.md
View File

@ -225,6 +225,10 @@ docker compose up -d
使用 [阿里云计算巢](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88) 将 Dify 一键部署到 阿里云
#### 使用 阿里云数据管理DMS 部署
使用 [阿里云数据管理DMS](https://help.aliyun.com/zh/dms/dify-in-invitational-preview) 将 Dify 一键部署到 阿里云
## Star History

4
README_DE.md
View File

@ -225,6 +225,10 @@ Bereitstellung von Dify auf AWS mit [CDK](https://aws.amazon.com/cdk/)
[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
#### Alibaba Cloud Data Management
Ein-Klick-Bereitstellung von Dify in der Alibaba Cloud mit [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
## Contributing

5
README_ES.md
View File

@ -225,6 +225,11 @@ Despliegue Dify en AWS usando [CDK](https://aws.amazon.com/cdk/)
[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
#### Alibaba Cloud Data Management
Despliega Dify en Alibaba Cloud con un solo clic con [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
## Contribuir
Para aquellos que deseen contribuir con código, consulten nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).

4
README_FR.md
View File

@ -223,6 +223,10 @@ Déployez Dify sur AWS en utilisant [CDK](https://aws.amazon.com/cdk/)
[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
#### Alibaba Cloud Data Management
Déployez Dify en un clic sur Alibaba Cloud avec [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
## Contribuer

5
README_JA.md
View File

@ -155,7 +155,7 @@ DifyはオープンソースのLLMアプリケーション開発プラットフ
[こちら](https://dify.ai)のDify Cloudサービスを利用して、セットアップ不要で試すことができます。サンドボックスプランには、200回のGPT-4呼び出しが無料で含まれています。
- **Dify Community Editionのセルフホスティング</br>**
この[スタートガイド](#quick-start)を使用して、ローカル環境でDifyを簡単に実行できます。
この[スタートガイド](#クイックスタート)を使用して、ローカル環境でDifyを簡単に実行できます。
詳しくは[ドキュメント](https://docs.dify.ai)をご覧ください。
- **企業/組織向けのDify</br>**
@ -223,6 +223,9 @@ docker compose up -d
#### Alibaba Cloud
[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
#### Alibaba Cloud Data Management
[Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/) を利用して、DifyをAlibaba Cloudへワンクリックでデプロイできます
## 貢献

4
README_KL.md
View File

@ -223,6 +223,10 @@ wa'logh nIqHom neH ghun deployment toy'wI' [CDK](https://aws.amazon.com/cdk/) lo
[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
#### Alibaba Cloud Data Management
[Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
## Contributing

4
README_KR.md
View File

@ -217,6 +217,10 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
#### Alibaba Cloud Data Management
[Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)를 통해 원클릭으로 Dify를 Alibaba Cloud에 배포할 수 있습니다
## 기여

4
README_PT.md
View File

@ -222,6 +222,10 @@ Implante o Dify na AWS usando [CDK](https://aws.amazon.com/cdk/)
[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
#### Alibaba Cloud Data Management
Implante o Dify na Alibaba Cloud com um clique usando o [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
## Contribuindo

4
README_SI.md
View File

@ -223,6 +223,10 @@ Uvedite Dify v AWS z uporabo [CDK](https://aws.amazon.com/cdk/)
[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
#### Alibaba Cloud Data Management
Z enim klikom namestite Dify na Alibaba Cloud z [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
## Prispevam

4
README_TR.md
View File

@ -216,6 +216,10 @@ Dify'ı bulut platformuna tek tıklamayla dağıtın [terraform](https://www.ter
[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
#### Alibaba Cloud Data Management
[Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/) kullanarak Dify'ı tek tıkla Alibaba Cloud'a dağıtın
## Katkıda Bulunma

4
README_TW.md
View File

@ -228,6 +228,10 @@ Dify 的所有功能都提供相應的 API，因此您可以輕鬆地將 Dify
[阿里云](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
#### 使用 阿里雲數據管理DMS 進行部署
透過 [阿里雲數據管理DMS](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)，一鍵將 Dify 部署至阿里雲
## 貢獻

4
README_VI.md
View File

@ -219,6 +219,10 @@ Triển khai Dify trên AWS bằng [CDK](https://aws.amazon.com/cdk/)
[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
#### Alibaba Cloud Data Management
Triển khai Dify lên Alibaba Cloud chỉ với một cú nhấp chuột bằng [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
## Đóng góp

103
api/.ruff.toml
View File

@ -1,6 +1,4 @@
exclude = [
"migrations/*",
]
exclude = ["migrations/*"]
line-length = 120
[format]
@ -9,14 +7,14 @@ quote-style = "double"
[lint]
preview = false
select = [
"B", # flake8-bugbear rules
"C4", # flake8-comprehensions
"E", # pycodestyle E rules
"F", # pyflakes rules
"FURB", # refurb rules
"I", # isort rules
"N", # pep8-naming
"PT", # flake8-pytest-style rules
"B", # flake8-bugbear rules
"C4", # flake8-comprehensions
"E", # pycodestyle E rules
"F", # pyflakes rules
"FURB", # refurb rules
"I", # isort rules
"N", # pep8-naming
"PT", # flake8-pytest-style rules
"PLC0208", # iteration-over-set
"PLC0414", # useless-import-alias
"PLE0604", # invalid-all-object
@ -24,19 +22,19 @@ select = [
"PLR0402", # manual-from-import
"PLR1711", # useless-return
"PLR1714", # repeated-equality-comparison
"RUF013", # implicit-optional
"RUF019", # unnecessary-key-check
"RUF100", # unused-noqa
"RUF101", # redirected-noqa
"RUF200", # invalid-pyproject-toml
"RUF022", # unsorted-dunder-all
"S506", # unsafe-yaml-load
"SIM", # flake8-simplify rules
"TRY400", # error-instead-of-exception
"TRY401", # verbose-log-message
"UP", # pyupgrade rules
"W191", # tab-indentation
"W605", # invalid-escape-sequence
"RUF013", # implicit-optional
"RUF019", # unnecessary-key-check
"RUF100", # unused-noqa
"RUF101", # redirected-noqa
"RUF200", # invalid-pyproject-toml
"RUF022", # unsorted-dunder-all
"S506", # unsafe-yaml-load
"SIM", # flake8-simplify rules
"TRY400", # error-instead-of-exception
"TRY401", # verbose-log-message
"UP", # pyupgrade rules
"W191", # tab-indentation
"W605", # invalid-escape-sequence
# security related linting rules
# RCE proctection (sort of)
"S102", # exec-builtin, disallow use of `exec`
@ -47,36 +45,37 @@ select = [
]
ignore = [
"E402", # module-import-not-at-top-of-file
"E711", # none-comparison
"E712", # true-false-comparison
"E721", # type-comparison
"E722", # bare-except
"F821", # undefined-name
"F841", # unused-variable
"E402", # module-import-not-at-top-of-file
"E711", # none-comparison
"E712", # true-false-comparison
"E721", # type-comparison
"E722", # bare-except
"F821", # undefined-name
"F841", # unused-variable
"FURB113", # repeated-append
"FURB152", # math-constant
"UP007", # non-pep604-annotation
"UP032", # f-string
"UP045", # non-pep604-annotation-optional
"B005", # strip-with-multi-characters
"B006", # mutable-argument-default
"B007", # unused-loop-control-variable
"B026", # star-arg-unpacking-after-keyword-arg
"B903", # class-as-data-structure
"B904", # raise-without-from-inside-except
"B905", # zip-without-explicit-strict
"N806", # non-lowercase-variable-in-function
"N815", # mixed-case-variable-in-class-scope
"PT011", # pytest-raises-too-broad
"SIM102", # collapsible-if
"SIM103", # needless-bool
"SIM105", # suppressible-exception
"SIM107", # return-in-try-except-finally
"SIM108", # if-else-block-instead-of-if-exp
"SIM113", # enumerate-for-loop
"SIM117", # multiple-with-statements
"SIM210", # if-expr-with-true-false
"UP007", # non-pep604-annotation
"UP032", # f-string
"UP045", # non-pep604-annotation-optional
"B005", # strip-with-multi-characters
"B006", # mutable-argument-default
"B007", # unused-loop-control-variable
"B026", # star-arg-unpacking-after-keyword-arg
"B903", # class-as-data-structure
"B904", # raise-without-from-inside-except
"B905", # zip-without-explicit-strict
"N806", # non-lowercase-variable-in-function
"N815", # mixed-case-variable-in-class-scope
"PT011", # pytest-raises-too-broad
"SIM102", # collapsible-if
"SIM103", # needless-bool
"SIM105", # suppressible-exception
"SIM107", # return-in-try-except-finally
"SIM108", # if-else-block-instead-of-if-exp
"SIM113", # enumerate-for-loop
"SIM117", # multiple-with-statements
"SIM210", # if-expr-with-true-false
"UP038", # deprecated and not recommended by Ruff, https://docs.astral.sh/ruff/rules/non-pep604-isinstance/
]
[lint.per-file-ignores]

4
api/configs/middleware/__init__.py
View File

@ -223,6 +223,10 @@ class CeleryConfig(DatabaseConfig):
default=None,
)
CELERY_SENTINEL_PASSWORD: Optional[str] = Field(
description="Password of the Redis Sentinel master.",
default=None,
)
CELERY_SENTINEL_SOCKET_TIMEOUT: Optional[PositiveFloat] = Field(
description="Timeout for Redis Sentinel socket operations in seconds.",
default=0.1,

2
api/configs/packaging/__init__.py
View File

@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
CURRENT_VERSION: str = Field(
description="Dify version",
default="1.4.3",
default="1.5.0",
)
COMMIT_SHA: str = Field(

1
api/controllers/console/__init__.py
View File

@ -63,6 +63,7 @@ from .app import (
statistic,
workflow,
workflow_app_log,
workflow_draft_variable,
workflow_run,
workflow_statistic,
)

70
api/controllers/console/app/workflow.py
View File

@ -1,5 +1,6 @@
import json
import logging
from collections.abc import Sequence
from typing import cast
from flask import abort, request
@ -18,10 +19,12 @@ from controllers.console.app.error import (
from controllers.console.app.wraps import get_app_model
from controllers.console.wraps import account_initialization_required, setup_required
from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
from core.app.apps.base_app_queue_manager import AppQueueManager
from core.app.entities.app_invoke_entities import InvokeFrom
from core.file.models import File
from extensions.ext_database import db
from factories import variable_factory
from factories import file_factory, variable_factory
from fields.workflow_fields import workflow_fields, workflow_pagination_fields
from fields.workflow_run_fields import workflow_run_node_execution_fields
from libs import helper
@ -30,6 +33,7 @@ from libs.login import current_user, login_required
from models import App
from models.account import Account
from models.model import AppMode
from models.workflow import Workflow
from services.app_generate_service import AppGenerateService
from services.errors.app import WorkflowHashNotEqualError
from services.errors.llm import InvokeRateLimitError
@ -38,6 +42,24 @@ from services.workflow_service import DraftWorkflowDeletionError, WorkflowInUseE
logger = logging.getLogger(__name__)
# TODO(QuantumGhost): Refactor existing node run API to handle file parameter parsing
# at the controller level rather than in the workflow logic. This would improve separation
# of concerns and make the code more maintainable.
def _parse_file(workflow: Workflow, files: list[dict] | None = None) -> Sequence[File]:
files = files or []
file_extra_config = FileUploadConfigManager.convert(workflow.features_dict, is_vision=False)
file_objs: Sequence[File] = []
if file_extra_config is None:
return file_objs
file_objs = file_factory.build_from_mappings(
mappings=files,
tenant_id=workflow.tenant_id,
config=file_extra_config,
)
return file_objs
class DraftWorkflowApi(Resource):
@setup_required
@login_required
@ -402,15 +424,30 @@ class DraftWorkflowNodeRunApi(Resource):
parser = reqparse.RequestParser()
parser.add_argument("inputs", type=dict, required=True, nullable=False, location="json")
parser.add_argument("query", type=str, required=False, location="json", default="")
parser.add_argument("files", type=list, location="json", default=[])
args = parser.parse_args()
inputs = args.get("inputs")
if inputs == None:
user_inputs = args.get("inputs")
if user_inputs is None:
raise ValueError("missing inputs")
workflow_srv = WorkflowService()
# fetch draft workflow by app_model
draft_workflow = workflow_srv.get_draft_workflow(app_model=app_model)
if not draft_workflow:
raise ValueError("Workflow not initialized")
files = _parse_file(draft_workflow, args.get("files"))
workflow_service = WorkflowService()
workflow_node_execution = workflow_service.run_draft_workflow_node(
app_model=app_model, node_id=node_id, user_inputs=inputs, account=current_user
app_model=app_model,
draft_workflow=draft_workflow,
node_id=node_id,
user_inputs=user_inputs,
account=current_user,
query=args.get("query", ""),
files=files,
)
return workflow_node_execution
@ -731,6 +768,27 @@ class WorkflowByIdApi(Resource):
return None, 204
class DraftWorkflowNodeLastRunApi(Resource):
@setup_required
@login_required
@account_initialization_required
@get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
@marshal_with(workflow_run_node_execution_fields)
def get(self, app_model: App, node_id: str):
srv = WorkflowService()
workflow = srv.get_draft_workflow(app_model)
if not workflow:
raise NotFound("Workflow not found")
node_exec = srv.get_node_last_run(
app_model=app_model,
workflow=workflow,
node_id=node_id,
)
if node_exec is None:
raise NotFound("last run not found")
return node_exec
api.add_resource(
DraftWorkflowApi,
"/apps/<uuid:app_id>/workflows/draft",
@ -795,3 +853,7 @@ api.add_resource(
WorkflowByIdApi,
"/apps/<uuid:app_id>/workflows/<string:workflow_id>",
)
api.add_resource(
DraftWorkflowNodeLastRunApi,
"/apps/<uuid:app_id>/workflows/draft/nodes/<string:node_id>/last-run",
)

421
api/controllers/console/app/workflow_draft_variable.py Normal file
View File

@ -0,0 +1,421 @@
import logging
from typing import Any, NoReturn
from flask import Response
from flask_restful import Resource, fields, inputs, marshal, marshal_with, reqparse
from sqlalchemy.orm import Session
from werkzeug.exceptions import Forbidden
from controllers.console import api
from controllers.console.app.error import (
DraftWorkflowNotExist,
)
from controllers.console.app.wraps import get_app_model
from controllers.console.wraps import account_initialization_required, setup_required
from controllers.web.error import InvalidArgumentError, NotFoundError
from core.variables.segment_group import SegmentGroup
from core.variables.segments import ArrayFileSegment, FileSegment, Segment
from core.variables.types import SegmentType
from core.workflow.constants import CONVERSATION_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
from factories.file_factory import build_from_mapping, build_from_mappings
from factories.variable_factory import build_segment_with_type
from libs.login import current_user, login_required
from models import App, AppMode, db
from models.workflow import WorkflowDraftVariable
from services.workflow_draft_variable_service import WorkflowDraftVariableList, WorkflowDraftVariableService
from services.workflow_service import WorkflowService
logger = logging.getLogger(__name__)
def _convert_values_to_json_serializable_object(value: Segment) -> Any:
if isinstance(value, FileSegment):
return value.value.model_dump()
elif isinstance(value, ArrayFileSegment):
return [i.model_dump() for i in value.value]
elif isinstance(value, SegmentGroup):
return [_convert_values_to_json_serializable_object(i) for i in value.value]
else:
return value.value
def _serialize_var_value(variable: WorkflowDraftVariable) -> Any:
value = variable.get_value()
# create a copy of the value to avoid affecting the model cache.
value = value.model_copy(deep=True)
# Refresh the url signature before returning it to client.
if isinstance(value, FileSegment):
file = value.value
file.remote_url = file.generate_url()
elif isinstance(value, ArrayFileSegment):
files = value.value
for file in files:
file.remote_url = file.generate_url()
return _convert_values_to_json_serializable_object(value)
def _create_pagination_parser():
parser = reqparse.RequestParser()
parser.add_argument(
"page",
type=inputs.int_range(1, 100_000),
required=False,
default=1,
location="args",
help="the page of data requested",
)
parser.add_argument("limit", type=inputs.int_range(1, 100), required=False, default=20, location="args")
return parser
_WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS = {
"id": fields.String,
"type": fields.String(attribute=lambda model: model.get_variable_type()),
"name": fields.String,
"description": fields.String,
"selector": fields.List(fields.String, attribute=lambda model: model.get_selector()),
"value_type": fields.String,
"edited": fields.Boolean(attribute=lambda model: model.edited),
"visible": fields.Boolean,
}
_WORKFLOW_DRAFT_VARIABLE_FIELDS = dict(
_WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS,
value=fields.Raw(attribute=_serialize_var_value),
)
_WORKFLOW_DRAFT_ENV_VARIABLE_FIELDS = {
"id": fields.String,
"type": fields.String(attribute=lambda _: "env"),
"name": fields.String,
"description": fields.String,
"selector": fields.List(fields.String, attribute=lambda model: model.get_selector()),
"value_type": fields.String,
"edited": fields.Boolean(attribute=lambda model: model.edited),
"visible": fields.Boolean,
}
_WORKFLOW_DRAFT_ENV_VARIABLE_LIST_FIELDS = {
"items": fields.List(fields.Nested(_WORKFLOW_DRAFT_ENV_VARIABLE_FIELDS)),
}
def _get_items(var_list: WorkflowDraftVariableList) -> list[WorkflowDraftVariable]:
return var_list.variables
_WORKFLOW_DRAFT_VARIABLE_LIST_WITHOUT_VALUE_FIELDS = {
"items": fields.List(fields.Nested(_WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS), attribute=_get_items),
"total": fields.Raw(),
}
_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS = {
"items": fields.List(fields.Nested(_WORKFLOW_DRAFT_VARIABLE_FIELDS), attribute=_get_items),
}
def _api_prerequisite(f):
"""Common prerequisites for all draft workflow variable APIs.
It ensures the following conditions are satisfied:
- Dify has been property setup.
- The request user has logged in and initialized.
- The requested app is a workflow or a chat flow.
- The request user has the edit permission for the app.
"""
@setup_required
@login_required
@account_initialization_required
@get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
def wrapper(*args, **kwargs):
if not current_user.is_editor:
raise Forbidden()
return f(*args, **kwargs)
return wrapper
class WorkflowVariableCollectionApi(Resource):
@_api_prerequisite
@marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_WITHOUT_VALUE_FIELDS)
def get(self, app_model: App):
"""
Get draft workflow
"""
parser = _create_pagination_parser()
args = parser.parse_args()
# fetch draft workflow by app_model
workflow_service = WorkflowService()
workflow_exist = workflow_service.is_workflow_exist(app_model=app_model)
if not workflow_exist:
raise DraftWorkflowNotExist()
# fetch draft workflow by app_model
with Session(bind=db.engine, expire_on_commit=False) as session:
draft_var_srv = WorkflowDraftVariableService(
session=session,
)
workflow_vars = draft_var_srv.list_variables_without_values(
app_id=app_model.id,
page=args.page,
limit=args.limit,
)
return workflow_vars
@_api_prerequisite
def delete(self, app_model: App):
draft_var_srv = WorkflowDraftVariableService(
session=db.session(),
)
draft_var_srv.delete_workflow_variables(app_model.id)
db.session.commit()
return Response("", 204)
def validate_node_id(node_id: str) -> NoReturn | None:
if node_id in [
CONVERSATION_VARIABLE_NODE_ID,
SYSTEM_VARIABLE_NODE_ID,
]:
# NOTE(QuantumGhost): While we store the system and conversation variables as node variables
# with specific `node_id` in database, we still want to make the API separated. By disallowing
# accessing system and conversation variables in `WorkflowDraftNodeVariableListApi`,
# we mitigate the risk that user of the API depending on the implementation detail of the API.
#
# ref: [Hyrum's Law](https://www.hyrumslaw.com/)
raise InvalidArgumentError(
f"invalid node_id, please use correspond api for conversation and system variables, node_id={node_id}",
)
return None
class NodeVariableCollectionApi(Resource):
@_api_prerequisite
@marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
def get(self, app_model: App, node_id: str):
validate_node_id(node_id)
with Session(bind=db.engine, expire_on_commit=False) as session:
draft_var_srv = WorkflowDraftVariableService(
session=session,
)
node_vars = draft_var_srv.list_node_variables(app_model.id, node_id)
return node_vars
@_api_prerequisite
def delete(self, app_model: App, node_id: str):
validate_node_id(node_id)
srv = WorkflowDraftVariableService(db.session())
srv.delete_node_variables(app_model.id, node_id)
db.session.commit()
return Response("", 204)
class VariableApi(Resource):
_PATCH_NAME_FIELD = "name"
_PATCH_VALUE_FIELD = "value"
@_api_prerequisite
@marshal_with(_WORKFLOW_DRAFT_VARIABLE_FIELDS)
def get(self, app_model: App, variable_id: str):
draft_var_srv = WorkflowDraftVariableService(
session=db.session(),
)
variable = draft_var_srv.get_variable(variable_id=variable_id)
if variable is None:
raise NotFoundError(description=f"variable not found, id={variable_id}")
if variable.app_id != app_model.id:
raise NotFoundError(description=f"variable not found, id={variable_id}")
return variable
@_api_prerequisite
@marshal_with(_WORKFLOW_DRAFT_VARIABLE_FIELDS)
def patch(self, app_model: App, variable_id: str):
# Request payload for file types:
#
# Local File:
#
# {
# "type": "image",
# "transfer_method": "local_file",
# "url": "",
# "upload_file_id": "daded54f-72c7-4f8e-9d18-9b0abdd9f190"
# }
#
# Remote File:
#
#
# {
# "type": "image",
# "transfer_method": "remote_url",
# "url": "http://127.0.0.1:5001/files/1602650a-4fe4-423c-85a2-af76c083e3c4/file-preview?timestamp=1750041099&nonce=...&sign=...=",
# "upload_file_id": "1602650a-4fe4-423c-85a2-af76c083e3c4"
# }
parser = reqparse.RequestParser()
parser.add_argument(self._PATCH_NAME_FIELD, type=str, required=False, nullable=True, location="json")
# Parse 'value' field as-is to maintain its original data structure
parser.add_argument(self._PATCH_VALUE_FIELD, type=lambda x: x, required=False, nullable=True, location="json")
draft_var_srv = WorkflowDraftVariableService(
session=db.session(),
)
args = parser.parse_args(strict=True)
variable = draft_var_srv.get_variable(variable_id=variable_id)
if variable is None:
raise NotFoundError(description=f"variable not found, id={variable_id}")
if variable.app_id != app_model.id:
raise NotFoundError(description=f"variable not found, id={variable_id}")
new_name = args.get(self._PATCH_NAME_FIELD, None)
raw_value = args.get(self._PATCH_VALUE_FIELD, None)
if new_name is None and raw_value is None:
return variable
new_value = None
if raw_value is not None:
if variable.value_type == SegmentType.FILE:
if not isinstance(raw_value, dict):
raise InvalidArgumentError(description=f"expected dict for file, got {type(raw_value)}")
raw_value = build_from_mapping(mapping=raw_value, tenant_id=app_model.tenant_id)
elif variable.value_type == SegmentType.ARRAY_FILE:
if not isinstance(raw_value, list):
raise InvalidArgumentError(description=f"expected list for files, got {type(raw_value)}")
if len(raw_value) > 0 and not isinstance(raw_value[0], dict):
raise InvalidArgumentError(description=f"expected dict for files[0], got {type(raw_value)}")
raw_value = build_from_mappings(mappings=raw_value, tenant_id=app_model.tenant_id)
new_value = build_segment_with_type(variable.value_type, raw_value)
draft_var_srv.update_variable(variable, name=new_name, value=new_value)
db.session.commit()
return variable
@_api_prerequisite
def delete(self, app_model: App, variable_id: str):
draft_var_srv = WorkflowDraftVariableService(
session=db.session(),
)
variable = draft_var_srv.get_variable(variable_id=variable_id)
if variable is None:
raise NotFoundError(description=f"variable not found, id={variable_id}")
if variable.app_id != app_model.id:
raise NotFoundError(description=f"variable not found, id={variable_id}")
draft_var_srv.delete_variable(variable)
db.session.commit()
return Response("", 204)
class VariableResetApi(Resource):
@_api_prerequisite
def put(self, app_model: App, variable_id: str):
draft_var_srv = WorkflowDraftVariableService(
session=db.session(),
)
workflow_srv = WorkflowService()
draft_workflow = workflow_srv.get_draft_workflow(app_model)
if draft_workflow is None:
raise NotFoundError(
f"Draft workflow not found, app_id={app_model.id}",
)
variable = draft_var_srv.get_variable(variable_id=variable_id)
if variable is None:
raise NotFoundError(description=f"variable not found, id={variable_id}")
if variable.app_id != app_model.id:
raise NotFoundError(description=f"variable not found, id={variable_id}")
resetted = draft_var_srv.reset_variable(draft_workflow, variable)
db.session.commit()
if resetted is None:
return Response("", 204)
else:
return marshal(resetted, _WORKFLOW_DRAFT_VARIABLE_FIELDS)
def _get_variable_list(app_model: App, node_id) -> WorkflowDraftVariableList:
with Session(bind=db.engine, expire_on_commit=False) as session:
draft_var_srv = WorkflowDraftVariableService(
session=session,
)
if node_id == CONVERSATION_VARIABLE_NODE_ID:
draft_vars = draft_var_srv.list_conversation_variables(app_model.id)
elif node_id == SYSTEM_VARIABLE_NODE_ID:
draft_vars = draft_var_srv.list_system_variables(app_model.id)
else:
draft_vars = draft_var_srv.list_node_variables(app_id=app_model.id, node_id=node_id)
return draft_vars
class ConversationVariableCollectionApi(Resource):
@_api_prerequisite
@marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
def get(self, app_model: App):
# NOTE(QuantumGhost): Prefill conversation variables into the draft variables table
# so their IDs can be returned to the caller.
workflow_srv = WorkflowService()
draft_workflow = workflow_srv.get_draft_workflow(app_model)
if draft_workflow is None:
raise NotFoundError(description=f"draft workflow not found, id={app_model.id}")
draft_var_srv = WorkflowDraftVariableService(db.session())
draft_var_srv.prefill_conversation_variable_default_values(draft_workflow)
db.session.commit()
return _get_variable_list(app_model, CONVERSATION_VARIABLE_NODE_ID)
class SystemVariableCollectionApi(Resource):
@_api_prerequisite
@marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
def get(self, app_model: App):
return _get_variable_list(app_model, SYSTEM_VARIABLE_NODE_ID)
class EnvironmentVariableCollectionApi(Resource):
@_api_prerequisite
def get(self, app_model: App):
"""
Get draft workflow
"""
# fetch draft workflow by app_model
workflow_service = WorkflowService()
workflow = workflow_service.get_draft_workflow(app_model=app_model)
if workflow is None:
raise DraftWorkflowNotExist()
env_vars = workflow.environment_variables
env_vars_list = []
for v in env_vars:
env_vars_list.append(
{
"id": v.id,
"type": "env",
"name": v.name,
"description": v.description,
"selector": v.selector,
"value_type": v.value_type.value,
"value": v.value,
# Do not track edited for env vars.
"edited": False,
"visible": True,
"editable": True,
}
)
return {"items": env_vars_list}
api.add_resource(
WorkflowVariableCollectionApi,
"/apps/<uuid:app_id>/workflows/draft/variables",
)
api.add_resource(NodeVariableCollectionApi, "/apps/<uuid:app_id>/workflows/draft/nodes/<string:node_id>/variables")
api.add_resource(VariableApi, "/apps/<uuid:app_id>/workflows/draft/variables/<uuid:variable_id>")
api.add_resource(VariableResetApi, "/apps/<uuid:app_id>/workflows/draft/variables/<uuid:variable_id>/reset")
api.add_resource(ConversationVariableCollectionApi, "/apps/<uuid:app_id>/workflows/draft/conversation-variables")
api.add_resource(SystemVariableCollectionApi, "/apps/<uuid:app_id>/workflows/draft/system-variables")
api.add_resource(EnvironmentVariableCollectionApi, "/apps/<uuid:app_id>/workflows/draft/environment-variables")

15
api/controllers/console/app/wraps.py
View File

@ -8,6 +8,15 @@ from libs.login import current_user
from models import App, AppMode
def _load_app_model(app_id: str) -> Optional[App]:
app_model = (
db.session.query(App)
.filter(App.id == app_id, App.tenant_id == current_user.current_tenant_id, App.status == "normal")
.first()
)
return app_model
def get_app_model(view: Optional[Callable] = None, *, mode: Union[AppMode, list[AppMode], None] = None):
def decorator(view_func):
@wraps(view_func)
@ -20,11 +29,7 @@ def get_app_model(view: Optional[Callable] = None, *, mode: Union[AppMode, list[
del kwargs["app_id"]
app_model = (
db.session.query(App)
.filter(App.id == app_id, App.tenant_id == current_user.current_tenant_id, App.status == "normal")
.first()
)
app_model = _load_app_model(app_id)
if not app_model:
raise AppNotFoundError()

10
api/controllers/console/datasets/datasets_document.py
View File

@ -5,7 +5,7 @@ from typing import cast
from flask import request
from flask_login import current_user
from flask_restful import Resource, fields, marshal, marshal_with, reqparse
from flask_restful import Resource, marshal, marshal_with, reqparse
from sqlalchemy import asc, desc, select
from werkzeug.exceptions import Forbidden, NotFound
@ -239,12 +239,10 @@ class DatasetDocumentListApi(Resource):
return response
documents_and_batch_fields = {"documents": fields.List(fields.Nested(document_fields)), "batch": fields.String}
@setup_required
@login_required
@account_initialization_required
@marshal_with(documents_and_batch_fields)
@marshal_with(dataset_and_document_fields)
@cloud_edition_billing_resource_check("vector_space")
@cloud_edition_billing_rate_limit_check("knowledge")
def post(self, dataset_id):
@ -290,6 +288,8 @@ class DatasetDocumentListApi(Resource):
try:
documents, batch = DocumentService.save_document_with_dataset_id(dataset, knowledge_config, current_user)
dataset = DatasetService.get_dataset(dataset_id)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
except QuotaExceededError:
@ -297,7 +297,7 @@ class DatasetDocumentListApi(Resource):
except ModelCurrentlyNotSupportError:
raise ProviderModelCurrentlyNotSupportError()
return {"documents": documents, "batch": batch}
return {"dataset": dataset, "documents": documents, "batch": batch}
@setup_required
@login_required

3
api/controllers/console/workspace/members.py
View File

@ -85,6 +85,7 @@ class MemberInviteEmailApi(Resource):
return {
"result": "success",
"invitation_results": invitation_results,
"tenant_id": str(current_user.current_tenant.id),
}, 201
@ -110,7 +111,7 @@ class MemberCancelInviteApi(Resource):
except Exception as e:
raise ValueError(str(e))
return {"result": "success"}, 204
return {"result": "success", "tenant_id": str(current_user.current_tenant.id)}, 200
class MemberUpdateRoleApi(Resource):

39
api/controllers/console/workspace/plugin.py
View File

@ -13,6 +13,7 @@ from core.model_runtime.utils.encoders import jsonable_encoder
from core.plugin.impl.exc import PluginDaemonClientSideError
from libs.login import login_required
from models.account import TenantPluginPermission
from services.plugin.plugin_parameter_service import PluginParameterService
from services.plugin.plugin_permission_service import PluginPermissionService
from services.plugin.plugin_service import PluginService
@ -497,6 +498,42 @@ class PluginFetchPermissionApi(Resource):
)
class PluginFetchDynamicSelectOptionsApi(Resource):
@setup_required
@login_required
@account_initialization_required
def get(self):
# check if the user is admin or owner
if not current_user.is_admin_or_owner:
raise Forbidden()
tenant_id = current_user.current_tenant_id
user_id = current_user.id
parser = reqparse.RequestParser()
parser.add_argument("plugin_id", type=str, required=True, location="args")
parser.add_argument("provider", type=str, required=True, location="args")
parser.add_argument("action", type=str, required=True, location="args")
parser.add_argument("parameter", type=str, required=True, location="args")
parser.add_argument("provider_type", type=str, required=True, location="args")
args = parser.parse_args()
try:
options = PluginParameterService.get_dynamic_select_options(
tenant_id,
user_id,
args["plugin_id"],
args["provider"],
args["action"],
args["parameter"],
args["provider_type"],
)
except PluginDaemonClientSideError as e:
raise ValueError(e)
return jsonable_encoder({"options": options})
api.add_resource(PluginDebuggingKeyApi, "/workspaces/current/plugin/debugging-key")
api.add_resource(PluginListApi, "/workspaces/current/plugin/list")
api.add_resource(PluginListLatestVersionsApi, "/workspaces/current/plugin/list/latest-versions")
@ -521,3 +558,5 @@ api.add_resource(PluginFetchMarketplacePkgApi, "/workspaces/current/plugin/marke
api.add_resource(PluginChangePermissionApi, "/workspaces/current/plugin/permission/change")
api.add_resource(PluginFetchPermissionApi, "/workspaces/current/plugin/permission/fetch")
api.add_resource(PluginFetchDynamicSelectOptionsApi, "/workspaces/current/plugin/parameters/dynamic-options")

17
api/controllers/inner_api/plugin/plugin.py
View File

@ -17,6 +17,7 @@ from core.plugin.entities.request import (
RequestInvokeApp,
RequestInvokeEncrypt,
RequestInvokeLLM,
RequestInvokeLLMWithStructuredOutput,
RequestInvokeModeration,
RequestInvokeParameterExtractorNode,
RequestInvokeQuestionClassifierNode,
@ -47,6 +48,21 @@ class PluginInvokeLLMApi(Resource):
return length_prefixed_response(0xF, generator())
class PluginInvokeLLMWithStructuredOutputApi(Resource):
@setup_required
@plugin_inner_api_only
@get_user_tenant
@plugin_data(payload_type=RequestInvokeLLMWithStructuredOutput)
def post(self, user_model: Account | EndUser, tenant_model: Tenant, payload: RequestInvokeLLMWithStructuredOutput):
def generator():
response = PluginModelBackwardsInvocation.invoke_llm_with_structured_output(
user_model.id, tenant_model, payload
)
return PluginModelBackwardsInvocation.convert_to_event_stream(response)
return length_prefixed_response(0xF, generator())
class PluginInvokeTextEmbeddingApi(Resource):
@setup_required
@plugin_inner_api_only
@ -291,6 +307,7 @@ class PluginFetchAppInfoApi(Resource):
api.add_resource(PluginInvokeLLMApi, "/invoke/llm")
api.add_resource(PluginInvokeLLMWithStructuredOutputApi, "/invoke/llm/structured-output")
api.add_resource(PluginInvokeTextEmbeddingApi, "/invoke/text-embedding")
api.add_resource(PluginInvokeRerankApi, "/invoke/rerank")
api.add_resource(PluginInvokeTTSApi, "/invoke/tts")

14
api/controllers/inner_api/workspace/workspace.py
View File

@ -29,7 +29,19 @@ class EnterpriseWorkspace(Resource):
tenant_was_created.send(tenant)
return {"message": "enterprise workspace created."}
resp = {
"id": tenant.id,
"name": tenant.name,
"plan": tenant.plan,
"status": tenant.status,
"created_at": tenant.created_at.isoformat() + "Z" if tenant.created_at else None,
"updated_at": tenant.updated_at.isoformat() + "Z" if tenant.updated_at else None,
}
return {
"message": "enterprise workspace created.",
"tenant": resp,
}
class EnterpriseWorkspaceNoOwnerEmail(Resource):

28
api/controllers/service_api/dataset/dataset.py
View File

@ -133,6 +133,22 @@ class DatasetListApi(DatasetApiResource):
parser.add_argument("embedding_model_provider", type=str, required=False, nullable=True, location="json")
args = parser.parse_args()
if args.get("embedding_model_provider"):
DatasetService.check_embedding_model_setting(
tenant_id, args.get("embedding_model_provider"), args.get("embedding_model")
)
if (
args.get("retrieval_model")
and args.get("retrieval_model").get("reranking_model")
and args.get("retrieval_model").get("reranking_model").get("reranking_provider_name")
):
DatasetService.check_reranking_model_setting(
tenant_id,
args.get("retrieval_model").get("reranking_model").get("reranking_provider_name"),
args.get("retrieval_model").get("reranking_model").get("reranking_model_name"),
)
try:
dataset = DatasetService.create_empty_dataset(
tenant_id=tenant_id,
@ -265,10 +281,20 @@ class DatasetApi(DatasetApiResource):
data = request.get_json()
# check embedding model setting
if data.get("indexing_technique") == "high_quality":
if data.get("indexing_technique") == "high_quality" or data.get("embedding_model_provider"):
DatasetService.check_embedding_model_setting(
dataset.tenant_id, data.get("embedding_model_provider"), data.get("embedding_model")
)
if (
data.get("retrieval_model")
and data.get("retrieval_model").get("reranking_model")
and data.get("retrieval_model").get("reranking_model").get("reranking_provider_name")
):
DatasetService.check_reranking_model_setting(
dataset.tenant_id,
data.get("retrieval_model").get("reranking_model").get("reranking_provider_name"),
data.get("retrieval_model").get("reranking_model").get("reranking_model_name"),
)
# The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
DatasetPermissionService.check_permission(

44
api/controllers/service_api/dataset/document.py
View File

@ -29,7 +29,7 @@ from extensions.ext_database import db
from fields.document_fields import document_fields, document_status_fields
from libs.login import current_user
from models.dataset import Dataset, Document, DocumentSegment
from services.dataset_service import DocumentService
from services.dataset_service import DatasetService, DocumentService
from services.entities.knowledge_entities.knowledge_entities import KnowledgeConfig
from services.file_service import FileService
@ -59,6 +59,7 @@ class DocumentAddByTextApi(DatasetApiResource):
parser.add_argument("embedding_model_provider", type=str, required=False, nullable=True, location="json")
args = parser.parse_args()
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
@ -74,6 +75,21 @@ class DocumentAddByTextApi(DatasetApiResource):
if text is None or name is None:
raise ValueError("Both 'text' and 'name' must be non-null values.")
if args.get("embedding_model_provider"):
DatasetService.check_embedding_model_setting(
tenant_id, args.get("embedding_model_provider"), args.get("embedding_model")
)
if (
args.get("retrieval_model")
and args.get("retrieval_model").get("reranking_model")
and args.get("retrieval_model").get("reranking_model").get("reranking_provider_name")
):
DatasetService.check_reranking_model_setting(
tenant_id,
args.get("retrieval_model").get("reranking_model").get("reranking_provider_name"),
args.get("retrieval_model").get("reranking_model").get("reranking_model_name"),
)
upload_file = FileService.upload_text(text=str(text), text_name=str(name))
data_source = {
"type": "upload_file",
@ -124,6 +140,17 @@ class DocumentUpdateByTextApi(DatasetApiResource):
if not dataset:
raise ValueError("Dataset does not exist.")
if (
args.get("retrieval_model")
and args.get("retrieval_model").get("reranking_model")
and args.get("retrieval_model").get("reranking_model").get("reranking_provider_name")
):
DatasetService.check_reranking_model_setting(
tenant_id,
args.get("retrieval_model").get("reranking_model").get("reranking_provider_name"),
args.get("retrieval_model").get("reranking_model").get("reranking_model_name"),
)
# indexing_technique is already set in dataset since this is an update
args["indexing_technique"] = dataset.indexing_technique
@ -188,6 +215,21 @@ class DocumentAddByFileApi(DatasetApiResource):
raise ValueError("indexing_technique is required.")
args["indexing_technique"] = indexing_technique
if "embedding_model_provider" in args:
DatasetService.check_embedding_model_setting(
tenant_id, args["embedding_model_provider"], args["embedding_model"]
)
if (
"retrieval_model" in args
and args["retrieval_model"].get("reranking_model")
and args["retrieval_model"].get("reranking_model").get("reranking_provider_name")
):
DatasetService.check_reranking_model_setting(
tenant_id,
args["retrieval_model"].get("reranking_model").get("reranking_provider_name"),
args["retrieval_model"].get("reranking_model").get("reranking_model_name"),
)
# save file info
file = request.files["file"]
# check file

10
api/controllers/web/error.py
View File

@ -139,3 +139,13 @@ class InvokeRateLimitError(BaseHTTPException):
error_code = "rate_limit_error"
description = "Rate Limit Error"
code = 429
class NotFoundError(BaseHTTPException):
error_code = "not_found"
code = 404
class InvalidArgumentError(BaseHTTPException):
error_code = "invalid_param"
code = 400

1
api/core/app/app_config/entities.py
View File

@ -104,6 +104,7 @@ class VariableEntity(BaseModel):
Variable Entity.
"""
# `variable` records the name of the variable in user inputs.
variable: str
label: str
description: str = ""

30
api/core/app/apps/advanced_chat/app_generator.py
View File

@ -29,13 +29,14 @@ from core.repositories import SQLAlchemyWorkflowNodeExecutionRepository
from core.repositories.sqlalchemy_workflow_execution_repository import SQLAlchemyWorkflowExecutionRepository
from core.workflow.repositories.workflow_execution_repository import WorkflowExecutionRepository
from core.workflow.repositories.workflow_node_execution_repository import WorkflowNodeExecutionRepository
from core.workflow.variable_loader import DUMMY_VARIABLE_LOADER, VariableLoader
from extensions.ext_database import db
from factories import file_factory
from libs.flask_utils import preserve_flask_contexts
from models import Account, App, Conversation, EndUser, Message, Workflow, WorkflowNodeExecutionTriggeredFrom
from models.enums import WorkflowRunTriggeredFrom
from services.conversation_service import ConversationService
from services.errors.message import MessageNotExistsError
from services.workflow_draft_variable_service import DraftVarLoader, WorkflowDraftVariableService
logger = logging.getLogger(__name__)
@ -116,6 +117,11 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
)
# parse files
# TODO(QuantumGhost): Move file parsing logic to the API controller layer
# for better separation of concerns.
#
# For implementation reference, see the `_parse_file` function and
# `DraftWorkflowNodeRunApi` class which handle this properly.
files = args["files"] if args.get("files") else []
file_extra_config = FileUploadConfigManager.convert(workflow.features_dict, is_vision=False)
if file_extra_config:
@ -261,6 +267,13 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
app_id=application_generate_entity.app_config.app_id,
triggered_from=WorkflowNodeExecutionTriggeredFrom.SINGLE_STEP,
)
var_loader = DraftVarLoader(
engine=db.engine,
app_id=application_generate_entity.app_config.app_id,
tenant_id=application_generate_entity.app_config.tenant_id,
)
draft_var_srv = WorkflowDraftVariableService(db.session())
draft_var_srv.prefill_conversation_variable_default_values(workflow)
return self._generate(
workflow=workflow,
@ -271,6 +284,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
workflow_node_execution_repository=workflow_node_execution_repository,
conversation=None,
stream=streaming,
variable_loader=var_loader,
)
def single_loop_generate(
@ -336,6 +350,13 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
app_id=application_generate_entity.app_config.app_id,
triggered_from=WorkflowNodeExecutionTriggeredFrom.SINGLE_STEP,
)
var_loader = DraftVarLoader(
engine=db.engine,
app_id=application_generate_entity.app_config.app_id,
tenant_id=application_generate_entity.app_config.tenant_id,
)
draft_var_srv = WorkflowDraftVariableService(db.session())
draft_var_srv.prefill_conversation_variable_default_values(workflow)
return self._generate(
workflow=workflow,
@ -346,6 +367,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
workflow_node_execution_repository=workflow_node_execution_repository,
conversation=None,
stream=streaming,
variable_loader=var_loader,
)
def _generate(
@ -359,6 +381,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
workflow_node_execution_repository: WorkflowNodeExecutionRepository,
conversation: Optional[Conversation] = None,
stream: bool = True,
variable_loader: VariableLoader = DUMMY_VARIABLE_LOADER,
) -> Mapping[str, Any] | Generator[str | Mapping[str, Any], Any, None]:
"""
Generate App response.
@ -410,6 +433,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
"conversation_id": conversation.id,
"message_id": message.id,
"context": context,
"variable_loader": variable_loader,
},
)
@ -438,6 +462,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
conversation_id: str,
message_id: str,
context: contextvars.Context,
variable_loader: VariableLoader,
) -> None:
"""
Generate worker in a new thread.
@ -454,8 +479,6 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
# get conversation and message
conversation = self._get_conversation(conversation_id)
message = self._get_message(message_id)
if message is None:
raise MessageNotExistsError("Message not exists")
# chatbot app
runner = AdvancedChatAppRunner(
@ -464,6 +487,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
conversation=conversation,
message=message,
dialogue_count=self._dialogue_count,
variable_loader=variable_loader,
)
runner.run()

8
api/core/app/apps/advanced_chat/app_runner.py
View File

@ -19,6 +19,7 @@ from core.moderation.base import ModerationError
from core.workflow.callbacks import WorkflowCallback, WorkflowLoggingCallback
from core.workflow.entities.variable_pool import VariablePool
from core.workflow.enums import SystemVariableKey
from core.workflow.variable_loader import VariableLoader
from core.workflow.workflow_entry import WorkflowEntry
from extensions.ext_database import db
from models.enums import UserFrom
@ -40,14 +41,17 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
conversation: Conversation,
message: Message,
dialogue_count: int,
variable_loader: VariableLoader,
) -> None:
super().__init__(queue_manager)
super().__init__(queue_manager, variable_loader)
self.application_generate_entity = application_generate_entity
self.conversation = conversation
self.message = message
self._dialogue_count = dialogue_count
def _get_app_id(self) -> str:
return self.application_generate_entity.app_config.app_id
def run(self) -> None:
app_config = self.application_generate_entity.app_config
app_config = cast(AdvancedChatAppConfig, app_config)

8
api/core/app/apps/agent_chat/app_generator.py
View File

@ -26,7 +26,6 @@ from factories import file_factory
from libs.flask_utils import preserve_flask_contexts
from models import Account, App, EndUser
from services.conversation_service import ConversationService
from services.errors.message import MessageNotExistsError
logger = logging.getLogger(__name__)
@ -124,6 +123,11 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
override_model_config_dict["retriever_resource"] = {"enabled": True}
# parse files
# TODO(QuantumGhost): Move file parsing logic to the API controller layer
# for better separation of concerns.
#
# For implementation reference, see the `_parse_file` function and
# `DraftWorkflowNodeRunApi` class which handle this properly.
files = args.get("files") or []
file_extra_config = FileUploadConfigManager.convert(override_model_config_dict or app_model_config.to_dict())
if file_extra_config:
@ -233,8 +237,6 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
# get conversation and message
conversation = self._get_conversation(conversation_id)
message = self._get_message(message_id)
if message is None:
raise MessageNotExistsError("Message not exists")
# chatbot app
runner = AgentChatAppRunner()

8
api/core/app/apps/chat/app_generator.py
View File

@ -25,7 +25,6 @@ from factories import file_factory
from models.account import Account
from models.model import App, EndUser
from services.conversation_service import ConversationService
from services.errors.message import MessageNotExistsError
logger = logging.getLogger(__name__)
@ -115,6 +114,11 @@ class ChatAppGenerator(MessageBasedAppGenerator):
override_model_config_dict["retriever_resource"] = {"enabled": True}
# parse files
# TODO(QuantumGhost): Move file parsing logic to the API controller layer
# for better separation of concerns.
#
# For implementation reference, see the `_parse_file` function and
# `DraftWorkflowNodeRunApi` class which handle this properly.
files = args["files"] if args.get("files") else []
file_extra_config = FileUploadConfigManager.convert(override_model_config_dict or app_model_config.to_dict())
if file_extra_config:
@ -219,8 +223,6 @@ class ChatAppGenerator(MessageBasedAppGenerator):
# get conversation and message
conversation = self._get_conversation(conversation_id)
message = self._get_message(message_id)
if message is None:
raise MessageNotExistsError("Message not exists")
# chatbot app
runner = ChatAppRunner()

16
api/core/app/apps/common/workflow_response_converter.py
View File

@ -48,6 +48,7 @@ from core.workflow.entities.workflow_execution import WorkflowExecution
from core.workflow.entities.workflow_node_execution import WorkflowNodeExecution, WorkflowNodeExecutionStatus
from core.workflow.nodes import NodeType
from core.workflow.nodes.tool.entities import ToolNodeData
from core.workflow.workflow_type_encoder import WorkflowRuntimeTypeConverter
from models import (
Account,
CreatorUserRole,
@ -125,7 +126,7 @@ class WorkflowResponseConverter:
id=workflow_execution.id_,
workflow_id=workflow_execution.workflow_id,
status=workflow_execution.status,
outputs=workflow_execution.outputs,
outputs=WorkflowRuntimeTypeConverter().to_json_encodable(workflow_execution.outputs),
error=workflow_execution.error_message,
elapsed_time=workflow_execution.elapsed_time,
total_tokens=workflow_execution.total_tokens,
@ -202,6 +203,8 @@ class WorkflowResponseConverter:
if not workflow_node_execution.finished_at:
return None
json_converter = WorkflowRuntimeTypeConverter()
return NodeFinishStreamResponse(
task_id=task_id,
workflow_run_id=workflow_node_execution.workflow_execution_id,
@ -214,7 +217,7 @@ class WorkflowResponseConverter:
predecessor_node_id=workflow_node_execution.predecessor_node_id,
inputs=workflow_node_execution.inputs,
process_data=workflow_node_execution.process_data,
outputs=workflow_node_execution.outputs,
outputs=json_converter.to_json_encodable(workflow_node_execution.outputs),
status=workflow_node_execution.status,
error=workflow_node_execution.error,
elapsed_time=workflow_node_execution.elapsed_time,
@ -245,6 +248,8 @@ class WorkflowResponseConverter:
if not workflow_node_execution.finished_at:
return None
json_converter = WorkflowRuntimeTypeConverter()
return NodeRetryStreamResponse(
task_id=task_id,
workflow_run_id=workflow_node_execution.workflow_execution_id,
@ -257,7 +262,7 @@ class WorkflowResponseConverter:
predecessor_node_id=workflow_node_execution.predecessor_node_id,
inputs=workflow_node_execution.inputs,
process_data=workflow_node_execution.process_data,
outputs=workflow_node_execution.outputs,
outputs=json_converter.to_json_encodable(workflow_node_execution.outputs),
status=workflow_node_execution.status,
error=workflow_node_execution.error,
elapsed_time=workflow_node_execution.elapsed_time,
@ -376,6 +381,7 @@ class WorkflowResponseConverter:
workflow_execution_id: str,
event: QueueIterationCompletedEvent,
) -> IterationNodeCompletedStreamResponse:
json_converter = WorkflowRuntimeTypeConverter()
return IterationNodeCompletedStreamResponse(
task_id=task_id,
workflow_run_id=workflow_execution_id,
@ -384,7 +390,7 @@ class WorkflowResponseConverter:
node_id=event.node_id,
node_type=event.node_type.value,
title=event.node_data.title,
outputs=event.outputs,
outputs=json_converter.to_json_encodable(event.outputs),
created_at=int(time.time()),
extras={},
inputs=event.inputs or {},
@ -463,7 +469,7 @@ class WorkflowResponseConverter:
node_id=event.node_id,
node_type=event.node_type.value,
title=event.node_data.title,
outputs=event.outputs,
outputs=WorkflowRuntimeTypeConverter().to_json_encodable(event.outputs),
created_at=int(time.time()),
extras={},
inputs=event.inputs or {},

7
api/core/app/apps/completion/app_generator.py
View File

@ -101,6 +101,11 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
)
# parse files
# TODO(QuantumGhost): Move file parsing logic to the API controller layer
# for better separation of concerns.
#
# For implementation reference, see the `_parse_file` function and
# `DraftWorkflowNodeRunApi` class which handle this properly.
files = args["files"] if args.get("files") else []
file_extra_config = FileUploadConfigManager.convert(override_model_config_dict or app_model_config.to_dict())
if file_extra_config:
@ -196,8 +201,6 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
try:
# get message
message = self._get_message(message_id)
if message is None:
raise MessageNotExistsError()
# chatbot app
runner = CompletionAppRunner()

10
api/core/app/apps/message_based_app_generator.py
View File

@ -29,6 +29,7 @@ from models.enums import CreatorUserRole
from models.model import App, AppMode, AppModelConfig, Conversation, EndUser, Message, MessageFile
from services.errors.app_model_config import AppModelConfigBrokenError
from services.errors.conversation import ConversationNotExistsError
from services.errors.message import MessageNotExistsError
logger = logging.getLogger(__name__)
@ -251,7 +252,7 @@ class MessageBasedAppGenerator(BaseAppGenerator):
return introduction or ""
def _get_conversation(self, conversation_id: str):
def _get_conversation(self, conversation_id: str) -> Conversation:
"""
Get conversation by conversation id
:param conversation_id: conversation id
@ -260,11 +261,11 @@ class MessageBasedAppGenerator(BaseAppGenerator):
conversation = db.session.query(Conversation).filter(Conversation.id == conversation_id).first()
if not conversation:
raise ConversationNotExistsError()
raise ConversationNotExistsError("Conversation not exists")
return conversation
def _get_message(self, message_id: str) -> Optional[Message]:
def _get_message(self, message_id: str) -> Message:
"""
Get message by message id
:param message_id: message id
@ -272,4 +273,7 @@ class MessageBasedAppGenerator(BaseAppGenerator):
"""
message = db.session.query(Message).filter(Message.id == message_id).first()
if message is None:
raise MessageNotExistsError("Message not exists")
return message

28
api/core/app/apps/workflow/app_generator.py
View File

@ -27,11 +27,13 @@ from core.repositories import SQLAlchemyWorkflowNodeExecutionRepository
from core.repositories.sqlalchemy_workflow_execution_repository import SQLAlchemyWorkflowExecutionRepository
from core.workflow.repositories.workflow_execution_repository import WorkflowExecutionRepository
from core.workflow.repositories.workflow_node_execution_repository import WorkflowNodeExecutionRepository
from core.workflow.variable_loader import DUMMY_VARIABLE_LOADER, VariableLoader
from extensions.ext_database import db
from factories import file_factory
from libs.flask_utils import preserve_flask_contexts
from models import Account, App, EndUser, Workflow, WorkflowNodeExecutionTriggeredFrom
from models.enums import WorkflowRunTriggeredFrom
from services.workflow_draft_variable_service import DraftVarLoader, WorkflowDraftVariableService
logger = logging.getLogger(__name__)
@ -94,6 +96,11 @@ class WorkflowAppGenerator(BaseAppGenerator):
files: Sequence[Mapping[str, Any]] = args.get("files") or []
# parse files
# TODO(QuantumGhost): Move file parsing logic to the API controller layer
# for better separation of concerns.
#
# For implementation reference, see the `_parse_file` function and
# `DraftWorkflowNodeRunApi` class which handle this properly.
file_extra_config = FileUploadConfigManager.convert(workflow.features_dict, is_vision=False)
system_files = file_factory.build_from_mappings(
mappings=files,
@ -186,6 +193,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
workflow_node_execution_repository: WorkflowNodeExecutionRepository,
streaming: bool = True,
workflow_thread_pool_id: Optional[str] = None,
variable_loader: VariableLoader = DUMMY_VARIABLE_LOADER,
) -> Union[Mapping[str, Any], Generator[str | Mapping[str, Any], None, None]]:
"""
Generate App response.
@ -219,6 +227,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
"queue_manager": queue_manager,
"context": context,
"workflow_thread_pool_id": workflow_thread_pool_id,
"variable_loader": variable_loader,
},
)
@ -303,6 +312,13 @@ class WorkflowAppGenerator(BaseAppGenerator):
app_id=application_generate_entity.app_config.app_id,
triggered_from=WorkflowNodeExecutionTriggeredFrom.SINGLE_STEP,
)
draft_var_srv = WorkflowDraftVariableService(db.session())
draft_var_srv.prefill_conversation_variable_default_values(workflow)
var_loader = DraftVarLoader(
engine=db.engine,
app_id=application_generate_entity.app_config.app_id,
tenant_id=application_generate_entity.app_config.tenant_id,
)
return self._generate(
app_model=app_model,
@ -313,6 +329,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
workflow_execution_repository=workflow_execution_repository,
workflow_node_execution_repository=workflow_node_execution_repository,
streaming=streaming,
variable_loader=var_loader,
)
def single_loop_generate(
@ -379,7 +396,13 @@ class WorkflowAppGenerator(BaseAppGenerator):
app_id=application_generate_entity.app_config.app_id,
triggered_from=WorkflowNodeExecutionTriggeredFrom.SINGLE_STEP,
)
draft_var_srv = WorkflowDraftVariableService(db.session())
draft_var_srv.prefill_conversation_variable_default_values(workflow)
var_loader = DraftVarLoader(
engine=db.engine,
app_id=application_generate_entity.app_config.app_id,
tenant_id=application_generate_entity.app_config.tenant_id,
)
return self._generate(
app_model=app_model,
workflow=workflow,
@ -389,6 +412,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
workflow_execution_repository=workflow_execution_repository,
workflow_node_execution_repository=workflow_node_execution_repository,
streaming=streaming,
variable_loader=var_loader,
)
def _generate_worker(
@ -397,6 +421,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
application_generate_entity: WorkflowAppGenerateEntity,
queue_manager: AppQueueManager,
context: contextvars.Context,
variable_loader: VariableLoader,
workflow_thread_pool_id: Optional[str] = None,
) -> None:
"""
@ -415,6 +440,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
application_generate_entity=application_generate_entity,
queue_manager=queue_manager,
workflow_thread_pool_id=workflow_thread_pool_id,
variable_loader=variable_loader,
)
runner.run()

7
api/core/app/apps/workflow/app_runner.py
View File

@ -12,6 +12,7 @@ from core.app.entities.app_invoke_entities import (
from core.workflow.callbacks import WorkflowCallback, WorkflowLoggingCallback
from core.workflow.entities.variable_pool import VariablePool
from core.workflow.enums import SystemVariableKey
from core.workflow.variable_loader import VariableLoader
from core.workflow.workflow_entry import WorkflowEntry
from extensions.ext_database import db
from models.enums import UserFrom
@ -30,6 +31,7 @@ class WorkflowAppRunner(WorkflowBasedAppRunner):
self,
application_generate_entity: WorkflowAppGenerateEntity,
queue_manager: AppQueueManager,
variable_loader: VariableLoader,
workflow_thread_pool_id: Optional[str] = None,
) -> None:
"""
@ -37,10 +39,13 @@ class WorkflowAppRunner(WorkflowBasedAppRunner):
:param queue_manager: application queue manager
:param workflow_thread_pool_id: workflow thread pool id
"""
super().__init__(queue_manager, variable_loader)
self.application_generate_entity = application_generate_entity
self.queue_manager = queue_manager
self.workflow_thread_pool_id = workflow_thread_pool_id
def _get_app_id(self) -> str:
return self.application_generate_entity.app_config.app_id
def run(self) -> None:
"""
Run application

57
api/core/app/apps/workflow_app_runner.py
View File

@ -1,6 +1,8 @@
from collections.abc import Mapping
from typing import Any, Optional, cast
from sqlalchemy.orm import Session
from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom
from core.app.apps.base_app_runner import AppRunner
from core.app.entities.queue_entities import (
@ -33,6 +35,7 @@ from core.workflow.entities.variable_pool import VariablePool
from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionMetadataKey
from core.workflow.graph_engine.entities.event import (
AgentLogEvent,
BaseNodeEvent,
GraphEngineEvent,
GraphRunFailedEvent,
GraphRunPartialSucceededEvent,
@ -62,15 +65,23 @@ from core.workflow.graph_engine.entities.event import (
from core.workflow.graph_engine.entities.graph import Graph
from core.workflow.nodes import NodeType
from core.workflow.nodes.node_mapping import NODE_TYPE_CLASSES_MAPPING
from core.workflow.variable_loader import DUMMY_VARIABLE_LOADER, VariableLoader, load_into_variable_pool
from core.workflow.workflow_entry import WorkflowEntry
from extensions.ext_database import db
from models.model import App
from models.workflow import Workflow
from services.workflow_draft_variable_service import (
DraftVariableSaver,
)
class WorkflowBasedAppRunner(AppRunner):
def __init__(self, queue_manager: AppQueueManager):
def __init__(self, queue_manager: AppQueueManager, variable_loader: VariableLoader = DUMMY_VARIABLE_LOADER) -> None:
self.queue_manager = queue_manager
self._variable_loader = variable_loader
def _get_app_id(self) -> str:
raise NotImplementedError("not implemented")
def _init_graph(self, graph_config: Mapping[str, Any]) -> Graph:
"""
@ -173,6 +184,13 @@ class WorkflowBasedAppRunner(AppRunner):
except NotImplementedError:
variable_mapping = {}
load_into_variable_pool(
variable_loader=self._variable_loader,
variable_pool=variable_pool,
variable_mapping=variable_mapping,
user_inputs=user_inputs,
)
WorkflowEntry.mapping_user_inputs_to_variable_pool(
variable_mapping=variable_mapping,
user_inputs=user_inputs,
@ -262,6 +280,12 @@ class WorkflowBasedAppRunner(AppRunner):
)
except NotImplementedError:
variable_mapping = {}
load_into_variable_pool(
self._variable_loader,
variable_pool=variable_pool,
variable_mapping=variable_mapping,
user_inputs=user_inputs,
)
WorkflowEntry.mapping_user_inputs_to_variable_pool(
variable_mapping=variable_mapping,
@ -376,6 +400,8 @@ class WorkflowBasedAppRunner(AppRunner):
in_loop_id=event.in_loop_id,
)
)
self._save_draft_var_for_event(event)
elif isinstance(event, NodeRunFailedEvent):
self._publish_event(
QueueNodeFailedEvent(
@ -438,6 +464,8 @@ class WorkflowBasedAppRunner(AppRunner):
in_loop_id=event.in_loop_id,
)
)
self._save_draft_var_for_event(event)
elif isinstance(event, NodeInIterationFailedEvent):
self._publish_event(
QueueNodeInIterationFailedEvent(
@ -690,3 +718,30 @@ class WorkflowBasedAppRunner(AppRunner):
def _publish_event(self, event: AppQueueEvent) -> None:
self.queue_manager.publish(event, PublishFrom.APPLICATION_MANAGER)
def _save_draft_var_for_event(self, event: BaseNodeEvent):
run_result = event.route_node_state.node_run_result
if run_result is None:
return
process_data = run_result.process_data
outputs = run_result.outputs
with Session(bind=db.engine) as session, session.begin():
draft_var_saver = DraftVariableSaver(
session=session,
app_id=self._get_app_id(),
node_id=event.node_id,
node_type=event.node_type,
# FIXME(QuantumGhost): rely on private state of queue_manager is not ideal.
invoke_from=self.queue_manager._invoke_from,
node_execution_id=event.id,
enclosing_node_id=event.in_loop_id or event.in_iteration_id or None,
)
draft_var_saver.save(process_data=process_data, outputs=outputs)
def _remove_first_element_from_variable_string(key: str) -> str:
"""
Remove the first element from the prefix.
"""
prefix, remaining = key.split(".", maxsplit=1)
return remaining

15
api/core/app/entities/app_invoke_entities.py
View File

@ -17,9 +17,24 @@ class InvokeFrom(Enum):
Invoke From.
"""
# SERVICE_API indicates that this invocation is from an API call to Dify app.
#
# Description of service api in Dify docs:
# https://docs.dify.ai/en/guides/application-publishing/developing-with-apis
SERVICE_API = "service-api"
# WEB_APP indicates that this invocation is from
# the web app of the workflow (or chatflow).
#
# Description of web app in Dify docs:
# https://docs.dify.ai/en/guides/application-publishing/launch-your-webapp-quickly/README
WEB_APP = "web-app"
# EXPLORE indicates that this invocation is from
# the workflow (or chatflow) explore page.
EXPLORE = "explore"
# DEBUGGER indicates that this invocation is from
# the workflow (or chatflow) edit page.
DEBUGGER = "debugger"
@classmethod

5
api/core/entities/parameter_entities.py
View File

@ -15,6 +15,11 @@ class CommonParameterType(StrEnum):
MODEL_SELECTOR = "model-selector"
TOOLS_SELECTOR = "array[tools]"
# Dynamic select parameter
# Once you are not sure about the available options until authorization is done
# eg: Select a Slack channel from a Slack workspace
DYNAMIC_SELECT = "dynamic-select"
# TOOL_SELECTOR = "tool-selector"

10
api/core/file/constants.py
View File

@ -1 +1,11 @@
from typing import Any
# TODO(QuantumGhost): Refactor variable type identification. Instead of directly
# comparing `dify_model_identity` with constants throughout the codebase, extract
# this logic into a dedicated function. This would encapsulate the implementation
# details of how different variable types are identified.
FILE_MODEL_IDENTITY = "__dify__file__"
def maybe_file_object(o: Any) -> bool:
return isinstance(o, dict) and o.get("dify_model_identity") == FILE_MODEL_IDENTITY

4
api/core/indexing_runner.py
View File

@ -534,7 +534,7 @@ class IndexingRunner:
# chunk nodes by chunk size
indexing_start_at = time.perf_counter()
tokens = 0
if dataset_document.doc_form != IndexType.PARENT_CHILD_INDEX:
if dataset_document.doc_form != IndexType.PARENT_CHILD_INDEX and dataset.indexing_technique == "economy":
# create keyword index
create_keyword_thread = threading.Thread(
target=self._process_keyword_index,
@ -572,7 +572,7 @@ class IndexingRunner:
for future in futures:
tokens += future.result()
if dataset_document.doc_form != IndexType.PARENT_CHILD_INDEX:
if dataset_document.doc_form != IndexType.PARENT_CHILD_INDEX and dataset.indexing_technique == "economy":
create_keyword_thread.join()
indexing_end_at = time.perf_counter()

374
api/core/llm_generator/output_parser/structured_output.py Normal file
View File

@ -0,0 +1,374 @@
import json
from collections.abc import Generator, Mapping, Sequence
from copy import deepcopy
from enum import StrEnum
from typing import Any, Literal, Optional, cast, overload
import json_repair
from pydantic import TypeAdapter, ValidationError
from core.llm_generator.output_parser.errors import OutputParserError
from core.llm_generator.prompts import STRUCTURED_OUTPUT_PROMPT
from core.model_manager import ModelInstance
from core.model_runtime.callbacks.base_callback import Callback
from core.model_runtime.entities.llm_entities import (
LLMResult,
LLMResultChunk,
LLMResultChunkDelta,
LLMResultChunkWithStructuredOutput,
LLMResultWithStructuredOutput,
)
from core.model_runtime.entities.message_entities import (
AssistantPromptMessage,
PromptMessage,
PromptMessageTool,
SystemPromptMessage,
)
from core.model_runtime.entities.model_entities import AIModelEntity, ParameterRule
class ResponseFormat(StrEnum):
"""Constants for model response formats"""
JSON_SCHEMA = "json_schema" # model's structured output mode. some model like gemini, gpt-4o, support this mode.
JSON = "JSON" # model's json mode. some model like claude support this mode.
JSON_OBJECT = "json_object" # json mode's another alias. some model like deepseek-chat, qwen use this alias.
class SpecialModelType(StrEnum):
"""Constants for identifying model types"""
GEMINI = "gemini"
OLLAMA = "ollama"
@overload
def invoke_llm_with_structured_output(
provider: str,
model_schema: AIModelEntity,
model_instance: ModelInstance,
prompt_messages: Sequence[PromptMessage],
json_schema: Mapping[str, Any],
model_parameters: Optional[Mapping] = None,
tools: Sequence[PromptMessageTool] | None = None,
stop: Optional[list[str]] = None,
stream: Literal[True] = True,
user: Optional[str] = None,
callbacks: Optional[list[Callback]] = None,
) -> Generator[LLMResultChunkWithStructuredOutput, None, None]: ...
@overload
def invoke_llm_with_structured_output(
provider: str,
model_schema: AIModelEntity,
model_instance: ModelInstance,
prompt_messages: Sequence[PromptMessage],
json_schema: Mapping[str, Any],
model_parameters: Optional[Mapping] = None,
tools: Sequence[PromptMessageTool] | None = None,
stop: Optional[list[str]] = None,
stream: Literal[False] = False,
user: Optional[str] = None,
callbacks: Optional[list[Callback]] = None,
) -> LLMResultWithStructuredOutput: ...
@overload
def invoke_llm_with_structured_output(
provider: str,
model_schema: AIModelEntity,
model_instance: ModelInstance,
prompt_messages: Sequence[PromptMessage],
json_schema: Mapping[str, Any],
model_parameters: Optional[Mapping] = None,
tools: Sequence[PromptMessageTool] | None = None,
stop: Optional[list[str]] = None,
stream: bool = True,
user: Optional[str] = None,
callbacks: Optional[list[Callback]] = None,
) -> LLMResultWithStructuredOutput | Generator[LLMResultChunkWithStructuredOutput, None, None]: ...
def invoke_llm_with_structured_output(
provider: str,
model_schema: AIModelEntity,
model_instance: ModelInstance,
prompt_messages: Sequence[PromptMessage],
json_schema: Mapping[str, Any],
model_parameters: Optional[Mapping] = None,
tools: Sequence[PromptMessageTool] | None = None,
stop: Optional[list[str]] = None,
stream: bool = True,
user: Optional[str] = None,
callbacks: Optional[list[Callback]] = None,
) -> LLMResultWithStructuredOutput | Generator[LLMResultChunkWithStructuredOutput, None, None]:
"""
Invoke large language model with structured output
1. This method invokes model_instance.invoke_llm with json_schema
2. Try to parse the result as structured output
:param prompt_messages: prompt messages
:param json_schema: json schema
:param model_parameters: model parameters
:param tools: tools for tool calling
:param stop: stop words
:param stream: is stream response
:param user: unique user id
:param callbacks: callbacks
:return: full response or stream response chunk generator result
"""
# handle native json schema
model_parameters_with_json_schema: dict[str, Any] = {
**(model_parameters or {}),
}
if model_schema.support_structure_output:
model_parameters = _handle_native_json_schema(
provider, model_schema, json_schema, model_parameters_with_json_schema, model_schema.parameter_rules
)
else:
# Set appropriate response format based on model capabilities
_set_response_format(model_parameters_with_json_schema, model_schema.parameter_rules)
# handle prompt based schema
prompt_messages = _handle_prompt_based_schema(
prompt_messages=prompt_messages,
structured_output_schema=json_schema,
)
llm_result = model_instance.invoke_llm(
prompt_messages=list(prompt_messages),
model_parameters=model_parameters_with_json_schema,
tools=tools,
stop=stop,
stream=stream,
user=user,
callbacks=callbacks,
)
if isinstance(llm_result, LLMResult):
if not isinstance(llm_result.message.content, str):
raise OutputParserError(
f"Failed to parse structured output, LLM result is not a string: {llm_result.message.content}"
)
return LLMResultWithStructuredOutput(
structured_output=_parse_structured_output(llm_result.message.content),
model=llm_result.model,
message=llm_result.message,
usage=llm_result.usage,
system_fingerprint=llm_result.system_fingerprint,
prompt_messages=llm_result.prompt_messages,
)
else:
def generator() -> Generator[LLMResultChunkWithStructuredOutput, None, None]:
result_text: str = ""
prompt_messages: Sequence[PromptMessage] = []
system_fingerprint: Optional[str] = None
for event in llm_result:
if isinstance(event, LLMResultChunk):
if isinstance(event.delta.message.content, str):
result_text += event.delta.message.content
prompt_messages = event.prompt_messages
system_fingerprint = event.system_fingerprint
yield LLMResultChunkWithStructuredOutput(
model=model_schema.model,
prompt_messages=prompt_messages,
system_fingerprint=system_fingerprint,
delta=event.delta,
)
yield LLMResultChunkWithStructuredOutput(
structured_output=_parse_structured_output(result_text),
model=model_schema.model,
prompt_messages=prompt_messages,
system_fingerprint=system_fingerprint,
delta=LLMResultChunkDelta(
index=0,
message=AssistantPromptMessage(content=""),
usage=None,
finish_reason=None,
),
)
return generator()
def _handle_native_json_schema(
provider: str,
model_schema: AIModelEntity,
structured_output_schema: Mapping,
model_parameters: dict,
rules: list[ParameterRule],
) -> dict:
"""
Handle structured output for models with native JSON schema support.
:param model_parameters: Model parameters to update
:param rules: Model parameter rules
:return: Updated model parameters with JSON schema configuration
"""
# Process schema according to model requirements
schema_json = _prepare_schema_for_model(provider, model_schema, structured_output_schema)
# Set JSON schema in parameters
model_parameters["json_schema"] = json.dumps(schema_json, ensure_ascii=False)
# Set appropriate response format if required by the model
for rule in rules:
if rule.name == "response_format" and ResponseFormat.JSON_SCHEMA.value in rule.options:
model_parameters["response_format"] = ResponseFormat.JSON_SCHEMA.value
return model_parameters
def _set_response_format(model_parameters: dict, rules: list) -> None:
"""
Set the appropriate response format parameter based on model rules.
:param model_parameters: Model parameters to update
:param rules: Model parameter rules
"""
for rule in rules:
if rule.name == "response_format":
if ResponseFormat.JSON.value in rule.options:
model_parameters["response_format"] = ResponseFormat.JSON.value
elif ResponseFormat.JSON_OBJECT.value in rule.options:
model_parameters["response_format"] = ResponseFormat.JSON_OBJECT.value
def _handle_prompt_based_schema(
prompt_messages: Sequence[PromptMessage], structured_output_schema: Mapping
) -> list[PromptMessage]:
"""
Handle structured output for models without native JSON schema support.
This function modifies the prompt messages to include schema-based output requirements.
Args:
prompt_messages: Original sequence of prompt messages
Returns:
list[PromptMessage]: Updated prompt messages with structured output requirements
"""
# Convert schema to string format
schema_str = json.dumps(structured_output_schema, ensure_ascii=False)
# Find existing system prompt with schema placeholder
system_prompt = next(
(prompt for prompt in prompt_messages if isinstance(prompt, SystemPromptMessage)),
None,
)
structured_output_prompt = STRUCTURED_OUTPUT_PROMPT.replace("{{schema}}", schema_str)
# Prepare system prompt content
system_prompt_content = (
structured_output_prompt + "\n\n" + system_prompt.content
if system_prompt and isinstance(system_prompt.content, str)
else structured_output_prompt
)
system_prompt = SystemPromptMessage(content=system_prompt_content)
# Extract content from the last user message
filtered_prompts = [prompt for prompt in prompt_messages if not isinstance(prompt, SystemPromptMessage)]
updated_prompt = [system_prompt] + filtered_prompts
return updated_prompt
def _parse_structured_output(result_text: str) -> Mapping[str, Any]:
structured_output: Mapping[str, Any] = {}
parsed: Mapping[str, Any] = {}
try:
parsed = TypeAdapter(Mapping).validate_json(result_text)
if not isinstance(parsed, dict):
raise OutputParserError(f"Failed to parse structured output: {result_text}")
structured_output = parsed
except ValidationError:
# if the result_text is not a valid json, try to repair it
temp_parsed = json_repair.loads(result_text)
if not isinstance(temp_parsed, dict):
# handle reasoning model like deepseek-r1 got '<think>\n\n</think>\n' prefix
if isinstance(temp_parsed, list):
temp_parsed = next((item for item in temp_parsed if isinstance(item, dict)), {})
else:
raise OutputParserError(f"Failed to parse structured output: {result_text}")
structured_output = cast(dict, temp_parsed)
return structured_output
def _prepare_schema_for_model(provider: str, model_schema: AIModelEntity, schema: Mapping) -> dict:
"""
Prepare JSON schema based on model requirements.
Different models have different requirements for JSON schema formatting.
This function handles these differences.
:param schema: The original JSON schema
:return: Processed schema compatible with the current model
"""
# Deep copy to avoid modifying the original schema
processed_schema = dict(deepcopy(schema))
# Convert boolean types to string types (common requirement)
convert_boolean_to_string(processed_schema)
# Apply model-specific transformations
if SpecialModelType.GEMINI in model_schema.model:
remove_additional_properties(processed_schema)
return processed_schema
elif SpecialModelType.OLLAMA in provider:
return processed_schema
else:
# Default format with name field
return {"schema": processed_schema, "name": "llm_response"}
def remove_additional_properties(schema: dict) -> None:
"""
Remove additionalProperties fields from JSON schema.
Used for models like Gemini that don't support this property.
:param schema: JSON schema to modify in-place
"""
if not isinstance(schema, dict):
return
# Remove additionalProperties at current level
schema.pop("additionalProperties", None)
# Process nested structures recursively
for value in schema.values():
if isinstance(value, dict):
remove_additional_properties(value)
elif isinstance(value, list):
for item in value:
if isinstance(item, dict):
remove_additional_properties(item)
def convert_boolean_to_string(schema: dict) -> None:
"""
Convert boolean type specifications to string in JSON schema.
:param schema: JSON schema to modify in-place
"""
if not isinstance(schema, dict):
return
# Check for boolean type at current level
if schema.get("type") == "boolean":
schema["type"] = "string"
# Process nested dictionaries and lists recursively
for value in schema.values():
if isinstance(value, dict):
convert_boolean_to_string(value)
elif isinstance(value, list):
for item in value:
if isinstance(item, dict):
convert_boolean_to_string(item)

18
api/core/llm_generator/prompts.py
View File

@ -291,3 +291,21 @@ Your task is to convert simple user descriptions into properly formatted JSON Sc
Now, generate a JSON Schema based on my description
""" # noqa: E501
STRUCTURED_OUTPUT_PROMPT = """You’re a helpful AI assistant. You could answer questions and output in JSON format.
constraints:
- You must output in JSON format.
- Do not output boolean value, use string type instead.
- Do not output integer or float value, use number type instead.
eg:
Here is the JSON schema:
{"additionalProperties": false, "properties": {"age": {"type": "number"}, "name": {"type": "string"}}, "required": ["name", "age"], "type": "object"}
Here is the user's question:
My name is John Doe and I am 30 years old.
output:
{"name": "John Doe", "age": 30}
Here is the JSON schema:
{{schema}}
""" # noqa: E501

24
api/core/model_runtime/entities/llm_entities.py
View File

@ -1,7 +1,7 @@
from collections.abc import Sequence
from collections.abc import Mapping, Sequence
from decimal import Decimal
from enum import StrEnum
from typing import Optional
from typing import Any, Optional
from pydantic import BaseModel, Field
@ -101,6 +101,20 @@ class LLMResult(BaseModel):
system_fingerprint: Optional[str] = None
class LLMStructuredOutput(BaseModel):
"""
Model class for llm structured output.
"""
structured_output: Optional[Mapping[str, Any]] = None
class LLMResultWithStructuredOutput(LLMResult, LLMStructuredOutput):
"""
Model class for llm result with structured output.
"""
class LLMResultChunkDelta(BaseModel):
"""
Model class for llm result chunk delta.
@ -123,6 +137,12 @@ class LLMResultChunk(BaseModel):
delta: LLMResultChunkDelta
class LLMResultChunkWithStructuredOutput(LLMResultChunk, LLMStructuredOutput):
"""
Model class for llm result chunk with structured output.
"""
class NumTokensResult(PriceInfo):
"""
Model class for number of tokens result.

76
api/core/plugin/backwards_invocation/model.py
View File

@ -2,8 +2,15 @@ import tempfile
from binascii import hexlify, unhexlify
from collections.abc import Generator
from core.llm_generator.output_parser.structured_output import invoke_llm_with_structured_output
from core.model_manager import ModelManager
from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta
from core.model_runtime.entities.llm_entities import (
LLMResult,
LLMResultChunk,
LLMResultChunkDelta,
LLMResultChunkWithStructuredOutput,
LLMResultWithStructuredOutput,
)
from core.model_runtime.entities.message_entities import (
PromptMessage,
SystemPromptMessage,
@ -12,6 +19,7 @@ from core.model_runtime.entities.message_entities import (
from core.plugin.backwards_invocation.base import BaseBackwardsInvocation
from core.plugin.entities.request import (
RequestInvokeLLM,
RequestInvokeLLMWithStructuredOutput,
RequestInvokeModeration,
RequestInvokeRerank,
RequestInvokeSpeech2Text,
@ -81,6 +89,72 @@ class PluginModelBackwardsInvocation(BaseBackwardsInvocation):
return handle_non_streaming(response)
@classmethod
def invoke_llm_with_structured_output(
cls, user_id: str, tenant: Tenant, payload: RequestInvokeLLMWithStructuredOutput
):
"""
invoke llm with structured output
"""
model_instance = ModelManager().get_model_instance(
tenant_id=tenant.id,
provider=payload.provider,
model_type=payload.model_type,
model=payload.model,
)
model_schema = model_instance.model_type_instance.get_model_schema(payload.model, model_instance.credentials)
if not model_schema:
raise ValueError(f"Model schema not found for {payload.model}")
response = invoke_llm_with_structured_output(
provider=payload.provider,
model_schema=model_schema,
model_instance=model_instance,
prompt_messages=payload.prompt_messages,
json_schema=payload.structured_output_schema,
tools=payload.tools,
stop=payload.stop,
stream=True if payload.stream is None else payload.stream,
user=user_id,
model_parameters=payload.completion_params,
)
if isinstance(response, Generator):
def handle() -> Generator[LLMResultChunkWithStructuredOutput, None, None]:
for chunk in response:
if chunk.delta.usage:
llm_utils.deduct_llm_quota(
tenant_id=tenant.id, model_instance=model_instance, usage=chunk.delta.usage
)
chunk.prompt_messages = []
yield chunk
return handle()
else:
if response.usage:
llm_utils.deduct_llm_quota(tenant_id=tenant.id, model_instance=model_instance, usage=response.usage)
def handle_non_streaming(
response: LLMResultWithStructuredOutput,
) -> Generator[LLMResultChunkWithStructuredOutput, None, None]:
yield LLMResultChunkWithStructuredOutput(
model=response.model,
prompt_messages=[],
system_fingerprint=response.system_fingerprint,
structured_output=response.structured_output,
delta=LLMResultChunkDelta(
index=0,
message=response.message,
usage=response.usage,
finish_reason="",
),
)
return handle_non_streaming(response)
@classmethod
def invoke_text_embedding(cls, user_id: str, tenant: Tenant, payload: RequestInvokeTextEmbedding):
"""

4
api/core/plugin/entities/parameters.py
View File

@ -10,6 +10,9 @@ from core.tools.entities.common_entities import I18nObject
class PluginParameterOption(BaseModel):
value: str = Field(..., description="The value of the option")
label: I18nObject = Field(..., description="The label of the option")
icon: Optional[str] = Field(
default=None, description="The icon of the option, can be a url or a base64 encoded image"
)
@field_validator("value", mode="before")
@classmethod
@ -35,6 +38,7 @@ class PluginParameterType(enum.StrEnum):
APP_SELECTOR = CommonParameterType.APP_SELECTOR.value
MODEL_SELECTOR = CommonParameterType.MODEL_SELECTOR.value
TOOLS_SELECTOR = CommonParameterType.TOOLS_SELECTOR.value
DYNAMIC_SELECT = CommonParameterType.DYNAMIC_SELECT.value
# deprecated, should not use.
SYSTEM_FILES = CommonParameterType.SYSTEM_FILES.value

7
api/core/plugin/entities/plugin_daemon.py
View File

@ -1,4 +1,4 @@
from collections.abc import Mapping
from collections.abc import Mapping, Sequence
from datetime import datetime
from enum import StrEnum
from typing import Any, Generic, Optional, TypeVar
@ -9,6 +9,7 @@ from core.agent.plugin_entities import AgentProviderEntityWithPlugin
from core.model_runtime.entities.model_entities import AIModelEntity
from core.model_runtime.entities.provider_entities import ProviderEntity
from core.plugin.entities.base import BasePluginEntity
from core.plugin.entities.parameters import PluginParameterOption
from core.plugin.entities.plugin import PluginDeclaration, PluginEntity
from core.tools.entities.common_entities import I18nObject
from core.tools.entities.tool_entities import ToolProviderEntityWithPlugin
@ -186,3 +187,7 @@ class PluginOAuthCredentialsResponse(BaseModel):
class PluginListResponse(BaseModel):
list: list[PluginEntity]
total: int
class PluginDynamicSelectOptionsResponse(BaseModel):
options: Sequence[PluginParameterOption] = Field(description="The options of the dynamic select.")

10
api/core/plugin/entities/request.py
View File

@ -82,6 +82,16 @@ class RequestInvokeLLM(BaseRequestInvokeModel):
return v
class RequestInvokeLLMWithStructuredOutput(RequestInvokeLLM):
"""
Request to invoke LLM with structured output
"""
structured_output_schema: dict[str, Any] = Field(
default_factory=dict, description="The schema of the structured output in JSON schema format"
)
class RequestInvokeTextEmbedding(BaseRequestInvokeModel):
"""
Request to invoke text embedding

45
api/core/plugin/impl/dynamic_select.py Normal file
View File

@ -0,0 +1,45 @@
from collections.abc import Mapping
from typing import Any
from core.plugin.entities.plugin import GenericProviderID
from core.plugin.entities.plugin_daemon import PluginDynamicSelectOptionsResponse
from core.plugin.impl.base import BasePluginClient
class DynamicSelectClient(BasePluginClient):
def fetch_dynamic_select_options(
self,
tenant_id: str,
user_id: str,
plugin_id: str,
provider: str,
action: str,
credentials: Mapping[str, Any],
parameter: str,
) -> PluginDynamicSelectOptionsResponse:
"""
Fetch dynamic select options for a plugin parameter.
"""
response = self._request_with_plugin_daemon_response_stream(
"POST",
f"plugin/{tenant_id}/dispatch/dynamic_select/fetch_parameter_options",
PluginDynamicSelectOptionsResponse,
data={
"user_id": user_id,
"data": {
"provider": GenericProviderID(provider).provider_name,
"credentials": credentials,
"provider_action": action,
"parameter": parameter,
},
},
headers={
"X-Plugin-ID": plugin_id,
"Content-Type": "application/json",
},
)
for options in response:
return options
raise ValueError("Plugin service returned no options")

16
api/core/plugin/impl/oauth.py
View File

@ -1,3 +1,4 @@
import binascii
from collections.abc import Mapping
from typing import Any
@ -16,7 +17,7 @@ class OAuthHandler(BasePluginClient):
provider: str,
system_credentials: Mapping[str, Any],
) -> PluginOAuthAuthorizationUrlResponse:
return self._request_with_plugin_daemon_response(
response = self._request_with_plugin_daemon_response_stream(
"POST",
f"plugin/{tenant_id}/dispatch/oauth/get_authorization_url",
PluginOAuthAuthorizationUrlResponse,
@ -32,6 +33,9 @@ class OAuthHandler(BasePluginClient):
"Content-Type": "application/json",
},
)
for resp in response:
return resp
raise ValueError("No response received from plugin daemon for authorization URL request.")
def get_credentials(
self,
@ -49,7 +53,7 @@ class OAuthHandler(BasePluginClient):
# encode request to raw http request
raw_request_bytes = self._convert_request_to_raw_data(request)
return self._request_with_plugin_daemon_response(
response = self._request_with_plugin_daemon_response_stream(
"POST",
f"plugin/{tenant_id}/dispatch/oauth/get_credentials",
PluginOAuthCredentialsResponse,
@ -58,7 +62,8 @@ class OAuthHandler(BasePluginClient):
"data": {
"provider": provider,
"system_credentials": system_credentials,
"raw_request_bytes": raw_request_bytes,
# for json serialization
"raw_http_request": binascii.hexlify(raw_request_bytes).decode(),
},
},
headers={
@ -66,6 +71,9 @@ class OAuthHandler(BasePluginClient):
"Content-Type": "application/json",
},
)
for resp in response:
return resp
raise ValueError("No response received from plugin daemon for authorization URL request.")
def _convert_request_to_raw_data(self, request: Request) -> bytes:
"""
@ -79,7 +87,7 @@ class OAuthHandler(BasePluginClient):
"""
# Start with the request line
method = request.method
path = request.path
path = request.full_path
protocol = request.headers.get("HTTP_VERSION", "HTTP/1.1")
raw_data = f"{method} {path} {protocol}\r\n".encode()

2
api/core/rag/index_processor/processor/paragraph_index_processor.py
View File

@ -76,6 +76,7 @@ class ParagraphIndexProcessor(BaseIndexProcessor):
if dataset.indexing_technique == "high_quality":
vector = Vector(dataset)
vector.create(documents)
with_keywords = False
if with_keywords:
keywords_list = kwargs.get("keywords_list")
keyword = Keyword(dataset)
@ -91,6 +92,7 @@ class ParagraphIndexProcessor(BaseIndexProcessor):
vector.delete_by_ids(node_ids)
else:
vector.delete()
with_keywords = False
if with_keywords:
keyword = Keyword(dataset)
if node_ids:

7
api/core/repositories/sqlalchemy_workflow_execution_repository.py
View File

@ -16,6 +16,7 @@ from core.workflow.entities.workflow_execution import (
WorkflowType,
)
from core.workflow.repositories.workflow_execution_repository import WorkflowExecutionRepository
from core.workflow.workflow_type_encoder import WorkflowRuntimeTypeConverter
from models import (
Account,
CreatorUserRole,
@ -152,7 +153,11 @@ class SQLAlchemyWorkflowExecutionRepository(WorkflowExecutionRepository):
db_model.version = domain_model.workflow_version
db_model.graph = json.dumps(domain_model.graph) if domain_model.graph else None
db_model.inputs = json.dumps(domain_model.inputs) if domain_model.inputs else None
db_model.outputs = json.dumps(domain_model.outputs) if domain_model.outputs else None
db_model.outputs = (
json.dumps(WorkflowRuntimeTypeConverter().to_json_encodable(domain_model.outputs))
if domain_model.outputs
else None
)
db_model.status = domain_model.status
db_model.error = domain_model.error_message if domain_model.error_message else None
db_model.total_tokens = domain_model.total_tokens

16
api/core/repositories/sqlalchemy_workflow_node_execution_repository.py
View File

@ -19,6 +19,7 @@ from core.workflow.entities.workflow_node_execution import (
)
from core.workflow.nodes.enums import NodeType
from core.workflow.repositories.workflow_node_execution_repository import OrderConfig, WorkflowNodeExecutionRepository
from core.workflow.workflow_type_encoder import WorkflowRuntimeTypeConverter
from models import (
Account,
CreatorUserRole,
@ -146,6 +147,7 @@ class SQLAlchemyWorkflowNodeExecutionRepository(WorkflowNodeExecutionRepository)
if not self._creator_user_role:
raise ValueError("created_by_role is required in repository constructor")
json_converter = WorkflowRuntimeTypeConverter()
db_model = WorkflowNodeExecutionModel()
db_model.id = domain_model.id
db_model.tenant_id = self._tenant_id
@ -160,9 +162,17 @@ class SQLAlchemyWorkflowNodeExecutionRepository(WorkflowNodeExecutionRepository)
db_model.node_id = domain_model.node_id
db_model.node_type = domain_model.node_type
db_model.title = domain_model.title
db_model.inputs = json.dumps(domain_model.inputs) if domain_model.inputs else None
db_model.process_data = json.dumps(domain_model.process_data) if domain_model.process_data else None
db_model.outputs = json.dumps(domain_model.outputs) if domain_model.outputs else None
db_model.inputs = (
json.dumps(json_converter.to_json_encodable(domain_model.inputs)) if domain_model.inputs else None
)
db_model.process_data = (
json.dumps(json_converter.to_json_encodable(domain_model.process_data))
if domain_model.process_data
else None
)
db_model.outputs = (
json.dumps(json_converter.to_json_encodable(domain_model.outputs)) if domain_model.outputs else None
)
db_model.status = domain_model.status
db_model.error = domain_model.error
db_model.elapsed_time = domain_model.elapsed_time

1
api/core/tools/entities/tool_entities.py
View File

@ -240,6 +240,7 @@ class ToolParameter(PluginParameter):
FILES = PluginParameterType.FILES.value
APP_SELECTOR = PluginParameterType.APP_SELECTOR.value
MODEL_SELECTOR = PluginParameterType.MODEL_SELECTOR.value
DYNAMIC_SELECT = PluginParameterType.DYNAMIC_SELECT.value
# deprecated, should not use.
SYSTEM_FILES = PluginParameterType.SYSTEM_FILES.value

1
api/core/tools/utils/configuration.py
View File

@ -86,6 +86,7 @@ class ProviderConfigEncrypter(BaseModel):
cached_credentials = cache.get()
if cached_credentials:
return cached_credentials
data = self._deep_copy(data)
# get fields need to be decrypted
fields = dict[str, BasicProviderConfig]()

14
api/core/variables/segments.py
View File

@ -75,6 +75,20 @@ class StringSegment(Segment):
class FloatSegment(Segment):
value_type: SegmentType = SegmentType.NUMBER
value: float
# NOTE(QuantumGhost): seems that the equality for FloatSegment with `NaN` value has some problems.
# The following tests cannot pass.
#
# def test_float_segment_and_nan():
# nan = float("nan")
# assert nan != nan
#
# f1 = FloatSegment(value=float("nan"))
# f2 = FloatSegment(value=float("nan"))
# assert f1 != f2
#
# f3 = FloatSegment(value=nan)
# f4 = FloatSegment(value=nan)
# assert f3 != f4
class IntegerSegment(Segment):

14
api/core/variables/types.py
View File

@ -18,3 +18,17 @@ class SegmentType(StrEnum):
NONE = "none"
GROUP = "group"
def is_array_type(self):
return self in _ARRAY_TYPES
_ARRAY_TYPES = frozenset(
[
SegmentType.ARRAY_ANY,
SegmentType.ARRAY_STRING,
SegmentType.ARRAY_NUMBER,
SegmentType.ARRAY_OBJECT,
SegmentType.ARRAY_FILE,
]
)

18
api/core/variables/utils.py
View File

@ -1,8 +1,26 @@
import json
from collections.abc import Iterable, Sequence
from .segment_group import SegmentGroup
from .segments import ArrayFileSegment, FileSegment, Segment
def to_selector(node_id: str, name: str, paths: Iterable[str] = ()) -> Sequence[str]:
selectors = [node_id, name]
if paths:
selectors.extend(paths)
return selectors
class SegmentJSONEncoder(json.JSONEncoder):
def default(self, o):
if isinstance(o, ArrayFileSegment):
return [v.model_dump() for v in o.value]
elif isinstance(o, FileSegment):
return o.value.model_dump()
elif isinstance(o, SegmentGroup):
return [self.default(seg) for seg in o.value]
elif isinstance(o, Segment):
return o.value
else:
super().default(o)

39
api/core/workflow/conversation_variable_updater.py Normal file
View File

@ -0,0 +1,39 @@
import abc
from typing import Protocol
from core.variables import Variable
class ConversationVariableUpdater(Protocol):
"""
ConversationVariableUpdater defines an abstraction for updating conversation variable values.
It is intended for use by `v1.VariableAssignerNode` and `v2.VariableAssignerNode` when updating
conversation variables.
Implementations may choose to batch updates. If batching is used, the `flush` method
should be implemented to persist buffered changes, and `update`
should handle buffering accordingly.
Note: Since implementations may buffer updates, instances of ConversationVariableUpdater
are not thread-safe. Each VariableAssignerNode should create its own instance during execution.
"""
@abc.abstractmethod
def update(self, conversation_id: str, variable: "Variable") -> None:
"""
Updates the value of the specified conversation variable in the underlying storage.
:param conversation_id: The ID of the conversation to update. Typically references `ConversationVariable.id`.
:param variable: The `Variable` instance containing the updated value.
"""
pass
@abc.abstractmethod
def flush(self):
"""
Flushes all pending updates to the underlying storage system.
If the implementation does not buffer updates, this method can be a no-op.
"""
pass

37
api/core/workflow/entities/variable_pool.py
View File

@ -7,12 +7,12 @@ from pydantic import BaseModel, Field
from core.file import File, FileAttribute, file_manager
from core.variables import Segment, SegmentGroup, Variable
from core.variables.consts import MIN_SELECTORS_LENGTH
from core.variables.segments import FileSegment, NoneSegment
from core.workflow.constants import CONVERSATION_VARIABLE_NODE_ID, ENVIRONMENT_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
from core.workflow.enums import SystemVariableKey
from factories import variable_factory
from ..constants import CONVERSATION_VARIABLE_NODE_ID, ENVIRONMENT_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
from ..enums import SystemVariableKey
VariableValue = Union[str, int, float, dict, list, File]
VARIABLE_PATTERN = re.compile(r"\{\{#([a-zA-Z0-9_]{1,50}(?:\.[a-zA-Z_][a-zA-Z0-9_]{0,29}){1,10})#\}\}")
@ -30,9 +30,11 @@ class VariablePool(BaseModel):
# TODO: This user inputs is not used for pool.
user_inputs: Mapping[str, Any] = Field(
description="User inputs",
default_factory=dict,
)
system_variables: Mapping[SystemVariableKey, Any] = Field(
description="System variables",
default_factory=dict,
)
environment_variables: Sequence[Variable] = Field(
description="Environment variables.",
@ -43,28 +45,7 @@ class VariablePool(BaseModel):
default_factory=list,
)
def __init__(
self,
*,
system_variables: Mapping[SystemVariableKey, Any] | None = None,
user_inputs: Mapping[str, Any] | None = None,
environment_variables: Sequence[Variable] | None = None,
conversation_variables: Sequence[Variable] | None = None,
**kwargs,
):
environment_variables = environment_variables or []
conversation_variables = conversation_variables or []
user_inputs = user_inputs or {}
system_variables = system_variables or {}
super().__init__(
system_variables=system_variables,
user_inputs=user_inputs,
environment_variables=environment_variables,
conversation_variables=conversation_variables,
**kwargs,
)
def model_post_init(self, context: Any, /) -> None:
for key, value in self.system_variables.items():
self.add((SYSTEM_VARIABLE_NODE_ID, key.value), value)
# Add environment variables to the variable pool
@ -91,12 +72,12 @@ class VariablePool(BaseModel):
Returns:
None
"""
if len(selector) < 2:
if len(selector) < MIN_SELECTORS_LENGTH:
raise ValueError("Invalid selector")
if isinstance(value, Variable):
variable = value
if isinstance(value, Segment):
elif isinstance(value, Segment):
variable = variable_factory.segment_to_variable(segment=value, selector=selector)
else:
segment = variable_factory.build_segment(value)
@ -118,7 +99,7 @@ class VariablePool(BaseModel):
Raises:
ValueError: If the selector is invalid.
"""
if len(selector) < 2:
if len(selector) < MIN_SELECTORS_LENGTH:
return None
hash_key = hash(tuple(selector[1:]))

2
api/core/workflow/graph_engine/entities/event.py
View File

@ -66,6 +66,8 @@ class BaseNodeEvent(GraphEngineEvent):
"""iteration id if node is in iteration"""
in_loop_id: Optional[str] = None
"""loop id if node is in loop"""
# The version of the node, or "1" if not specified.
node_version: str = "1"
class NodeRunStartedEvent(BaseNodeEvent):

26
api/core/workflow/graph_engine/graph_engine.py
View File

@ -53,6 +53,7 @@ from core.workflow.nodes.end.end_stream_processor import EndStreamProcessor
from core.workflow.nodes.enums import ErrorStrategy, FailBranchSourceHandle
from core.workflow.nodes.event import RunCompletedEvent, RunRetrieverResourceEvent, RunStreamChunkEvent
from core.workflow.nodes.node_mapping import NODE_TYPE_CLASSES_MAPPING
from core.workflow.utils import variable_utils
from libs.flask_utils import preserve_flask_contexts
from models.enums import UserFrom
from models.workflow import WorkflowType
@ -314,6 +315,7 @@ class GraphEngine:
parallel_start_node_id=parallel_start_node_id,
parent_parallel_id=parent_parallel_id,
parent_parallel_start_node_id=parent_parallel_start_node_id,
node_version=node_instance.version(),
)
raise e
@ -627,6 +629,7 @@ class GraphEngine:
parent_parallel_id=parent_parallel_id,
parent_parallel_start_node_id=parent_parallel_start_node_id,
agent_strategy=agent_strategy,
node_version=node_instance.version(),
)
max_retries = node_instance.node_data.retry_config.max_retries
@ -677,6 +680,7 @@ class GraphEngine:
error=run_result.error or "Unknown error",
retry_index=retries,
start_at=retry_start_at,
node_version=node_instance.version(),
)
time.sleep(retry_interval)
break
@ -712,6 +716,7 @@ class GraphEngine:
parallel_start_node_id=parallel_start_node_id,
parent_parallel_id=parent_parallel_id,
parent_parallel_start_node_id=parent_parallel_start_node_id,
node_version=node_instance.version(),
)
should_continue_retry = False
else:
@ -726,6 +731,7 @@ class GraphEngine:
parallel_start_node_id=parallel_start_node_id,
parent_parallel_id=parent_parallel_id,
parent_parallel_start_node_id=parent_parallel_start_node_id,
node_version=node_instance.version(),
)
should_continue_retry = False
elif run_result.status == WorkflowNodeExecutionStatus.SUCCEEDED:
@ -786,6 +792,7 @@ class GraphEngine:
parallel_start_node_id=parallel_start_node_id,
parent_parallel_id=parent_parallel_id,
parent_parallel_start_node_id=parent_parallel_start_node_id,
node_version=node_instance.version(),
)
should_continue_retry = False
@ -803,6 +810,7 @@ class GraphEngine:
parallel_start_node_id=parallel_start_node_id,
parent_parallel_id=parent_parallel_id,
parent_parallel_start_node_id=parent_parallel_start_node_id,
node_version=node_instance.version(),
)
elif isinstance(event, RunRetrieverResourceEvent):
yield NodeRunRetrieverResourceEvent(
@ -817,6 +825,7 @@ class GraphEngine:
parallel_start_node_id=parallel_start_node_id,
parent_parallel_id=parent_parallel_id,
parent_parallel_start_node_id=parent_parallel_start_node_id,
node_version=node_instance.version(),
)
except GenerateTaskStoppedError:
# trigger node run failed event
@ -833,6 +842,7 @@ class GraphEngine:
parallel_start_node_id=parallel_start_node_id,
parent_parallel_id=parent_parallel_id,
parent_parallel_start_node_id=parent_parallel_start_node_id,
node_version=node_instance.version(),
)
return
except Exception as e:
@ -847,16 +857,12 @@ class GraphEngine:
:param variable_value: variable value
:return:
"""
self.graph_runtime_state.variable_pool.add([node_id] + variable_key_list, variable_value)
# if variable_value is a dict, then recursively append variables
if isinstance(variable_value, dict):
for key, value in variable_value.items():
# construct new key list
new_key_list = variable_key_list + [key]
self._append_variables_recursively(
node_id=node_id, variable_key_list=new_key_list, variable_value=value
)
variable_utils.append_variables_recursively(
self.graph_runtime_state.variable_pool,
node_id,
variable_key_list,
variable_value,
)
def _is_timed_out(self, start_at: float, max_execution_time: int) -> bool:
"""

4
api/core/workflow/nodes/agent/agent_node.py
View File

@ -39,6 +39,10 @@ class AgentNode(ToolNode):
_node_data_cls = AgentNodeData # type: ignore
_node_type = NodeType.AGENT
@classmethod
def version(cls) -> str:
return "1"
def _run(self) -> Generator:
"""
Run the agent node

11
api/core/workflow/nodes/answer/answer_node.py
View File

@ -18,7 +18,11 @@ from core.workflow.utils.variable_template_parser import VariableTemplateParser
class AnswerNode(BaseNode[AnswerNodeData]):
_node_data_cls = AnswerNodeData
_node_type: NodeType = NodeType.ANSWER
_node_type = NodeType.ANSWER
@classmethod
def version(cls) -> str:
return "1"
def _run(self) -> NodeRunResult:
"""
@ -45,7 +49,10 @@ class AnswerNode(BaseNode[AnswerNodeData]):
part = cast(TextGenerateRouteChunk, part)
answer += part.text
return NodeRunResult(status=WorkflowNodeExecutionStatus.SUCCEEDED, outputs={"answer": answer, "files": files})
return NodeRunResult(
status=WorkflowNodeExecutionStatus.SUCCEEDED,
outputs={"answer": answer, "files": ArrayFileSegment(value=files)},
)
@classmethod
def _extract_variable_selector_to_variable_mapping(

2
api/core/workflow/nodes/answer/answer_stream_processor.py
View File

@ -109,6 +109,7 @@ class AnswerStreamProcessor(StreamProcessor):
parallel_id=event.parallel_id,
parallel_start_node_id=event.parallel_start_node_id,
from_variable_selector=[answer_node_id, "answer"],
node_version=event.node_version,
)
else:
route_chunk = cast(VarGenerateRouteChunk, route_chunk)
@ -134,6 +135,7 @@ class AnswerStreamProcessor(StreamProcessor):
route_node_state=event.route_node_state,
parallel_id=event.parallel_id,
parallel_start_node_id=event.parallel_start_node_id,
node_version=event.node_version,
)
self.route_position[answer_node_id] += 1

51
api/core/workflow/nodes/base/node.py
View File

@ -1,7 +1,7 @@
import logging
from abc import abstractmethod
from collections.abc import Generator, Mapping, Sequence
from typing import TYPE_CHECKING, Any, Generic, Optional, TypeVar, Union, cast
from typing import TYPE_CHECKING, Any, ClassVar, Generic, Optional, TypeVar, Union, cast
from core.workflow.entities.node_entities import NodeRunResult
from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionStatus
@ -23,7 +23,7 @@ GenericNodeData = TypeVar("GenericNodeData", bound=BaseNodeData)
class BaseNode(Generic[GenericNodeData]):
_node_data_cls: type[GenericNodeData]
_node_type: NodeType
_node_type: ClassVar[NodeType]
def __init__(
self,
@ -90,8 +90,38 @@ class BaseNode(Generic[GenericNodeData]):
graph_config: Mapping[str, Any],
config: Mapping[str, Any],
) -> Mapping[str, Sequence[str]]:
"""
Extract variable selector to variable mapping
"""Extracts references variable selectors from node configuration.
The `config` parameter represents the configuration for a specific node type and corresponds
to the `data` field in the node definition object.
The returned mapping has the following structure:
{'1747829548239.#1747829667553.result#': ['1747829667553', 'result']}
For loop and iteration nodes, the mapping may look like this:
{
"1748332301644.input_selector": ["1748332363630", "result"],
"1748332325079.1748332325079.#sys.workflow_id#": ["sys", "workflow_id"],
}
where `1748332301644` is the ID of the loop / iteration node,
and `1748332325079` is the ID of the node inside the loop or iteration node.
Here, the key consists of two parts: the current node ID (provided as the `node_id`
parameter to `_extract_variable_selector_to_variable_mapping`) and the variable selector,
enclosed in `#` symbols. These two parts are separated by a dot (`.`).
The value is a list of string representing the variable selector, where the first element is the node ID
of the referenced variable, and the second element is the variable name within that node.
The meaning of the above response is:
The node with ID `1747829548239` references the variable `result` from the node with
ID `1747829667553`. For example, if `1747829548239` is a LLM node, its prompt may contain a
reference to the `result` output variable of node `1747829667553`.
:param graph_config: graph config
:param config: node config
:return:
@ -101,9 +131,10 @@ class BaseNode(Generic[GenericNodeData]):
raise ValueError("Node ID is required when extracting variable selector to variable mapping.")
node_data = cls._node_data_cls(**config.get("data", {}))
return cls._extract_variable_selector_to_variable_mapping(
data = cls._extract_variable_selector_to_variable_mapping(
graph_config=graph_config, node_id=node_id, node_data=cast(GenericNodeData, node_data)
)
return data
@classmethod
def _extract_variable_selector_to_variable_mapping(
@ -139,6 +170,16 @@ class BaseNode(Generic[GenericNodeData]):
"""
return self._node_type
@classmethod
@abstractmethod
def version(cls) -> str:
"""`node_version` returns the version of current node type."""
# NOTE(QuantumGhost): This should be in sync with `NODE_TYPE_CLASSES_MAPPING`.
#
# If you have introduced a new node type, please add it to `NODE_TYPE_CLASSES_MAPPING`
# in `api/core/workflow/nodes/__init__.py`.
raise NotImplementedError("subclasses of BaseNode must implement `version` method.")
@property
def should_continue_on_error(self) -> bool:
"""judge if should continue on error

7
api/core/workflow/nodes/code/code_node.py
View File

@ -40,6 +40,10 @@ class CodeNode(BaseNode[CodeNodeData]):
return code_provider.get_default_config()
@classmethod
def version(cls) -> str:
return "1"
def _run(self) -> NodeRunResult:
# Get code language
code_language = self.node_data.code_language
@ -126,6 +130,9 @@ class CodeNode(BaseNode[CodeNodeData]):
prefix: str = "",
depth: int = 1,
):
# TODO(QuantumGhost): Replace native Python lists with `Array*Segment` classes.
# Note that `_transform_result` may produce lists containing `None` values,
# which don't conform to the type requirements of `Array*Segment` classes.
if depth > dify_config.CODE_MAX_DEPTH:
raise DepthLimitError(f"Depth limit {dify_config.CODE_MAX_DEPTH} reached, object too deep.")

10
api/core/workflow/nodes/document_extractor/node.py
View File

@ -24,7 +24,7 @@ from configs import dify_config
from core.file import File, FileTransferMethod, file_manager
from core.helper import ssrf_proxy
from core.variables import ArrayFileSegment
from core.variables.segments import FileSegment
from core.variables.segments import ArrayStringSegment, FileSegment
from core.workflow.entities.node_entities import NodeRunResult
from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionStatus
from core.workflow.nodes.base import BaseNode
@ -45,6 +45,10 @@ class DocumentExtractorNode(BaseNode[DocumentExtractorNodeData]):
_node_data_cls = DocumentExtractorNodeData
_node_type = NodeType.DOCUMENT_EXTRACTOR
@classmethod
def version(cls) -> str:
return "1"
def _run(self):
variable_selector = self.node_data.variable_selector
variable = self.graph_runtime_state.variable_pool.get(variable_selector)
@ -67,7 +71,7 @@ class DocumentExtractorNode(BaseNode[DocumentExtractorNodeData]):
status=WorkflowNodeExecutionStatus.SUCCEEDED,
inputs=inputs,
process_data=process_data,
outputs={"text": extracted_text_list},
outputs={"text": ArrayStringSegment(value=extracted_text_list)},
)
elif isinstance(value, File):
extracted_text = _extract_text_from_file(value)
@ -447,7 +451,7 @@ def _extract_text_from_excel(file_content: bytes) -> str:
df = df.applymap(lambda x: " ".join(str(x).splitlines()) if isinstance(x, str) else x) # type: ignore
# Combine multi-line text in column names into a single line
df.columns = pd.Index([" ".join(col.splitlines()) for col in df.columns])
df.columns = pd.Index([" ".join(str(col).splitlines()) for col in df.columns])
# Manually construct the Markdown table
markdown_table += _construct_markdown_table(df) + "\n\n"

4
api/core/workflow/nodes/end/end_node.py
View File

@ -9,6 +9,10 @@ class EndNode(BaseNode[EndNodeData]):
_node_data_cls = EndNodeData
_node_type = NodeType.END
@classmethod
def version(cls) -> str:
return "1"
def _run(self) -> NodeRunResult:
"""
Run node

1
api/core/workflow/nodes/end/end_stream_processor.py
View File

@ -139,6 +139,7 @@ class EndStreamProcessor(StreamProcessor):
route_node_state=event.route_node_state,
parallel_id=event.parallel_id,
parallel_start_node_id=event.parallel_start_node_id,
node_version=event.node_version,
)
self.route_position[end_node_id] += 1

13
api/core/workflow/nodes/http_request/node.py
View File

@ -6,6 +6,7 @@ from typing import Any, Optional
from configs import dify_config
from core.file import File, FileTransferMethod
from core.tools.tool_file_manager import ToolFileManager
from core.variables.segments import ArrayFileSegment
from core.workflow.entities.node_entities import NodeRunResult
from core.workflow.entities.variable_entities import VariableSelector
from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionStatus
@ -60,6 +61,10 @@ class HttpRequestNode(BaseNode[HttpRequestNodeData]):
},
}
@classmethod
def version(cls) -> str:
return "1"
def _run(self) -> NodeRunResult:
process_data = {}
try:
@ -92,7 +97,7 @@ class HttpRequestNode(BaseNode[HttpRequestNodeData]):
status=WorkflowNodeExecutionStatus.SUCCEEDED,
outputs={
"status_code": response.status_code,
"body": response.text if not files else "",
"body": response.text if not files.value else "",
"headers": response.headers,
"files": files,
},
@ -166,7 +171,7 @@ class HttpRequestNode(BaseNode[HttpRequestNodeData]):
return mapping
def extract_files(self, url: str, response: Response) -> list[File]:
def extract_files(self, url: str, response: Response) -> ArrayFileSegment:
"""
Extract files from response by checking both Content-Type header and URL
"""
@ -178,7 +183,7 @@ class HttpRequestNode(BaseNode[HttpRequestNodeData]):
content_disposition_type = None
if not is_file:
return files
return ArrayFileSegment(value=[])
if parsed_content_disposition:
content_disposition_filename = parsed_content_disposition.get_filename()
@ -211,4 +216,4 @@ class HttpRequestNode(BaseNode[HttpRequestNodeData]):
)
files.append(file)
return files
return ArrayFileSegment(value=files)

23
api/core/workflow/nodes/if_else/if_else_node.py
View File

@ -1,4 +1,5 @@
from typing import Literal
from collections.abc import Mapping, Sequence
from typing import Any, Literal
from typing_extensions import deprecated
@ -16,6 +17,10 @@ class IfElseNode(BaseNode[IfElseNodeData]):
_node_data_cls = IfElseNodeData
_node_type = NodeType.IF_ELSE
@classmethod
def version(cls) -> str:
return "1"
def _run(self) -> NodeRunResult:
"""
Run node
@ -87,6 +92,22 @@ class IfElseNode(BaseNode[IfElseNodeData]):
return data
@classmethod
def _extract_variable_selector_to_variable_mapping(
cls,
*,
graph_config: Mapping[str, Any],
node_id: str,
node_data: IfElseNodeData,
) -> Mapping[str, Sequence[str]]:
var_mapping: dict[str, list[str]] = {}
for case in node_data.cases or []:
for condition in case.conditions:
key = "{}.#{}#".format(node_id, ".".join(condition.variable_selector))
var_mapping[key] = condition.variable_selector
return var_mapping
@deprecated("This function is deprecated. You should use the new cases structure.")
def _should_not_use_old_function(

18
api/core/workflow/nodes/iteration/iteration_node.py
View File

@ -11,6 +11,7 @@ from flask import Flask, current_app
from configs import dify_config
from core.variables import ArrayVariable, IntegerVariable, NoneVariable
from core.variables.segments import ArrayAnySegment, ArraySegment
from core.workflow.entities.node_entities import (
NodeRunResult,
)
@ -37,6 +38,7 @@ from core.workflow.nodes.base import BaseNode
from core.workflow.nodes.enums import NodeType
from core.workflow.nodes.event import NodeEvent, RunCompletedEvent
from core.workflow.nodes.iteration.entities import ErrorHandleMode, IterationNodeData
from factories.variable_factory import build_segment
from libs.flask_utils import preserve_flask_contexts
from .exc import (
@ -72,6 +74,10 @@ class IterationNode(BaseNode[IterationNodeData]):
},
}
@classmethod
def version(cls) -> str:
return "1"
def _run(self) -> Generator[NodeEvent | InNodeEvent, None, None]:
"""
Run the node.
@ -85,10 +91,17 @@ class IterationNode(BaseNode[IterationNodeData]):
raise InvalidIteratorValueError(f"invalid iterator value: {variable}, please provide a list.")
if isinstance(variable, NoneVariable) or len(variable.value) == 0:
# Try our best to preserve the type informat.
if isinstance(variable, ArraySegment):
output = variable.model_copy(update={"value": []})
else:
output = ArrayAnySegment(value=[])
yield RunCompletedEvent(
run_result=NodeRunResult(
status=WorkflowNodeExecutionStatus.SUCCEEDED,
outputs={"output": []},
# TODO(QuantumGhost): is it possible to compute the type of `output`
# from graph definition?
outputs={"output": output},
)
)
return
@ -231,6 +244,7 @@ class IterationNode(BaseNode[IterationNodeData]):
# Flatten the list of lists
if isinstance(outputs, list) and all(isinstance(output, list) for output in outputs):
outputs = [item for sublist in outputs for item in sublist]
output_segment = build_segment(outputs)
yield IterationRunSucceededEvent(
iteration_id=self.id,
@ -247,7 +261,7 @@ class IterationNode(BaseNode[IterationNodeData]):
yield RunCompletedEvent(
run_result=NodeRunResult(
status=WorkflowNodeExecutionStatus.SUCCEEDED,
outputs={"output": outputs},
outputs={"output": output_segment},
metadata={
WorkflowNodeExecutionMetadataKey.ITERATION_DURATION_MAP: iter_run_map,
WorkflowNodeExecutionMetadataKey.TOTAL_TOKENS: graph_engine.graph_runtime_state.total_tokens,

4
api/core/workflow/nodes/iteration/iteration_start_node.py
View File

@ -13,6 +13,10 @@ class IterationStartNode(BaseNode[IterationStartNodeData]):
_node_data_cls = IterationStartNodeData
_node_type = NodeType.ITERATION_START
@classmethod
def version(cls) -> str:
return "1"
def _run(self) -> NodeRunResult:
"""
Run the node.

12
api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py
View File

@ -24,6 +24,7 @@ from core.rag.entities.metadata_entities import Condition, MetadataCondition
from core.rag.retrieval.dataset_retrieval import DatasetRetrieval
from core.rag.retrieval.retrieval_methods import RetrievalMethod
from core.variables import StringSegment
from core.variables.segments import ArrayObjectSegment
from core.workflow.entities.node_entities import NodeRunResult
from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionStatus
from core.workflow.nodes.enums import NodeType
@ -70,6 +71,10 @@ class KnowledgeRetrievalNode(LLMNode):
_node_data_cls = KnowledgeRetrievalNodeData # type: ignore
_node_type = NodeType.KNOWLEDGE_RETRIEVAL
@classmethod
def version(cls):
return "1"
def _run(self) -> NodeRunResult: # type: ignore
node_data = cast(KnowledgeRetrievalNodeData, self.node_data)
# extract variables
@ -115,9 +120,12 @@ class KnowledgeRetrievalNode(LLMNode):
# retrieve knowledge
try:
results = self._fetch_dataset_retriever(node_data=node_data, query=query)
outputs = {"result": results}
outputs = {"result": ArrayObjectSegment(value=results)}
return NodeRunResult(
status=WorkflowNodeExecutionStatus.SUCCEEDED, inputs=variables, process_data=None, outputs=outputs
status=WorkflowNodeExecutionStatus.SUCCEEDED,
inputs=variables,
process_data=None,
outputs=outputs, # type: ignore
)
except KnowledgeRetrievalNodeError as e:

13
api/core/workflow/nodes/list_operator/node.py
View File

@ -3,6 +3,7 @@ from typing import Any, Literal, Union
from core.file import File
from core.variables import ArrayFileSegment, ArrayNumberSegment, ArrayStringSegment
from core.variables.segments import ArrayAnySegment, ArraySegment
from core.workflow.entities.node_entities import NodeRunResult
from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionStatus
from core.workflow.nodes.base import BaseNode
@ -16,6 +17,10 @@ class ListOperatorNode(BaseNode[ListOperatorNodeData]):
_node_data_cls = ListOperatorNodeData
_node_type = NodeType.LIST_OPERATOR
@classmethod
def version(cls) -> str:
return "1"
def _run(self):
inputs: dict[str, list] = {}
process_data: dict[str, list] = {}
@ -30,7 +35,11 @@ class ListOperatorNode(BaseNode[ListOperatorNodeData]):
if not variable.value:
inputs = {"variable": []}
process_data = {"variable": []}
outputs = {"result": [], "first_record": None, "last_record": None}
if isinstance(variable, ArraySegment):
result = variable.model_copy(update={"value": []})
else:
result = ArrayAnySegment(value=[])
outputs = {"result": result, "first_record": None, "last_record": None}
return NodeRunResult(
status=WorkflowNodeExecutionStatus.SUCCEEDED,
inputs=inputs,
@ -71,7 +80,7 @@ class ListOperatorNode(BaseNode[ListOperatorNodeData]):
variable = self._apply_slice(variable)
outputs = {
"result": variable.value,
"result": variable,
"first_record": variable.value[0] if variable.value else None,
"last_record": variable.value[-1] if variable.value else None,
}

3
api/core/workflow/nodes/llm/file_saver.py
View File

@ -119,9 +119,6 @@ class FileSaverImpl(LLMFileSaver):
size=len(data),
related_id=tool_file.id,
url=url,
# TODO(QuantumGhost): how should I set the following key?
# What's the difference between `remote_url` and `url`?
# What's the purpose of `storage_key` and `dify_model_identity`?
storage_key=tool_file.file_key,
)

291
api/core/workflow/nodes/llm/node.py
View File

@ -5,11 +5,11 @@ import logging
from collections.abc import Generator, Mapping, Sequence
from typing import TYPE_CHECKING, Any, Optional, cast
import json_repair
from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEntity
from core.file import FileType, file_manager
from core.helper.code_executor import CodeExecutor, CodeLanguage
from core.llm_generator.output_parser.errors import OutputParserError
from core.llm_generator.output_parser.structured_output import invoke_llm_with_structured_output
from core.memory.token_buffer_memory import TokenBufferMemory
from core.model_manager import ModelInstance, ModelManager
from core.model_runtime.entities import (
@ -18,7 +18,13 @@ from core.model_runtime.entities import (
PromptMessageContentType,
TextPromptMessageContent,
)
from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMUsage
from core.model_runtime.entities.llm_entities import (
LLMResult,
LLMResultChunk,
LLMResultChunkWithStructuredOutput,
LLMStructuredOutput,
LLMUsage,
)
from core.model_runtime.entities.message_entities import (
AssistantPromptMessage,
PromptMessageContentUnionTypes,
@ -31,7 +37,6 @@ from core.model_runtime.entities.model_entities import (
ModelFeature,
ModelPropertyKey,
ModelType,
ParameterRule,
)
from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
from core.model_runtime.utils.encoders import jsonable_encoder
@ -62,11 +67,6 @@ from core.workflow.nodes.event import (
RunRetrieverResourceEvent,
RunStreamChunkEvent,
)
from core.workflow.utils.structured_output.entities import (
ResponseFormat,
SpecialModelType,
)
from core.workflow.utils.structured_output.prompt import STRUCTURED_OUTPUT_PROMPT
from core.workflow.utils.variable_template_parser import VariableTemplateParser
from . import llm_utils
@ -138,13 +138,11 @@ class LLMNode(BaseNode[LLMNodeData]):
)
self._llm_file_saver = llm_file_saver
def _run(self) -> Generator[NodeEvent | InNodeEvent, None, None]:
def process_structured_output(text: str) -> Optional[dict[str, Any]]:
"""Process structured output if enabled"""
if not self.node_data.structured_output_enabled or not self.node_data.structured_output:
return None
return self._parse_structured_output(text)
@classmethod
def version(cls) -> str:
return "1"
def _run(self) -> Generator[NodeEvent | InNodeEvent, None, None]:
node_inputs: Optional[dict[str, Any]] = None
process_data = None
result_text = ""
@ -240,6 +238,8 @@ class LLMNode(BaseNode[LLMNodeData]):
stop=stop,
)
structured_output: LLMStructuredOutput | None = None
for event in generator:
if isinstance(event, RunStreamChunkEvent):
yield event
@ -250,12 +250,14 @@ class LLMNode(BaseNode[LLMNodeData]):
# deduct quota
llm_utils.deduct_llm_quota(tenant_id=self.tenant_id, model_instance=model_instance, usage=usage)
break
elif isinstance(event, LLMStructuredOutput):
structured_output = event
outputs = {"text": result_text, "usage": jsonable_encoder(usage), "finish_reason": finish_reason}
structured_output = process_structured_output(result_text)
if structured_output:
outputs["structured_output"] = structured_output
outputs["structured_output"] = structured_output.structured_output
if self._file_outputs is not None:
outputs["files"] = self._file_outputs
outputs["files"] = ArrayFileSegment(value=self._file_outputs)
yield RunCompletedEvent(
run_result=NodeRunResult(
@ -298,20 +300,40 @@ class LLMNode(BaseNode[LLMNodeData]):
model_instance: ModelInstance,
prompt_messages: Sequence[PromptMessage],
stop: Optional[Sequence[str]] = None,
) -> Generator[NodeEvent, None, None]:
invoke_result = model_instance.invoke_llm(
prompt_messages=list(prompt_messages),
model_parameters=node_data_model.completion_params,
stop=list(stop or []),
stream=True,
user=self.user_id,
) -> Generator[NodeEvent | LLMStructuredOutput, None, None]:
model_schema = model_instance.model_type_instance.get_model_schema(
node_data_model.name, model_instance.credentials
)
if not model_schema:
raise ValueError(f"Model schema not found for {node_data_model.name}")
if self.node_data.structured_output_enabled:
output_schema = self._fetch_structured_output_schema()
invoke_result = invoke_llm_with_structured_output(
provider=model_instance.provider,
model_schema=model_schema,
model_instance=model_instance,
prompt_messages=prompt_messages,
json_schema=output_schema,
model_parameters=node_data_model.completion_params,
stop=list(stop or []),
stream=True,
user=self.user_id,
)
else:
invoke_result = model_instance.invoke_llm(
prompt_messages=list(prompt_messages),
model_parameters=node_data_model.completion_params,
stop=list(stop or []),
stream=True,
user=self.user_id,
)
return self._handle_invoke_result(invoke_result=invoke_result)
def _handle_invoke_result(
self, invoke_result: LLMResult | Generator[LLMResultChunk, None, None]
) -> Generator[NodeEvent, None, None]:
self, invoke_result: LLMResult | Generator[LLMResultChunk | LLMStructuredOutput, None, None]
) -> Generator[NodeEvent | LLMStructuredOutput, None, None]:
# For blocking mode
if isinstance(invoke_result, LLMResult):
event = self._handle_blocking_result(invoke_result=invoke_result)
@ -325,23 +347,32 @@ class LLMNode(BaseNode[LLMNodeData]):
usage = LLMUsage.empty_usage()
finish_reason = None
full_text_buffer = io.StringIO()
for result in invoke_result:
contents = result.delta.message.content
for text_part in self._save_multimodal_output_and_convert_result_to_markdown(contents):
full_text_buffer.write(text_part)
yield RunStreamChunkEvent(chunk_content=text_part, from_variable_selector=[self.node_id, "text"])
# Consume the invoke result and handle generator exception
try:
for result in invoke_result:
if isinstance(result, LLMResultChunkWithStructuredOutput):
yield result
if isinstance(result, LLMResultChunk):
contents = result.delta.message.content
for text_part in self._save_multimodal_output_and_convert_result_to_markdown(contents):
full_text_buffer.write(text_part)
yield RunStreamChunkEvent(
chunk_content=text_part, from_variable_selector=[self.node_id, "text"]
)
# Update the whole metadata
if not model and result.model:
model = result.model
if len(prompt_messages) == 0:
# TODO(QuantumGhost): it seems that this update has no visable effect.
# What's the purpose of the line below?
prompt_messages = list(result.prompt_messages)
if usage.prompt_tokens == 0 and result.delta.usage:
usage = result.delta.usage
if finish_reason is None and result.delta.finish_reason:
finish_reason = result.delta.finish_reason
# Update the whole metadata
if not model and result.model:
model = result.model
if len(prompt_messages) == 0:
# TODO(QuantumGhost): it seems that this update has no visable effect.
# What's the purpose of the line below?
prompt_messages = list(result.prompt_messages)
if usage.prompt_tokens == 0 and result.delta.usage:
usage = result.delta.usage
if finish_reason is None and result.delta.finish_reason:
finish_reason = result.delta.finish_reason
except OutputParserError as e:
raise LLMNodeError(f"Failed to parse structured output: {e}")
yield ModelInvokeCompletedEvent(text=full_text_buffer.getvalue(), usage=usage, finish_reason=finish_reason)
@ -518,12 +549,6 @@ class LLMNode(BaseNode[LLMNodeData]):
if not model_schema:
raise ModelNotExistError(f"Model {node_data_model.name} not exist.")
if self.node_data.structured_output_enabled:
if model_schema.support_structure_output:
completion_params = self._handle_native_json_schema(completion_params, model_schema.parameter_rules)
else:
# Set appropriate response format based on model capabilities
self._set_response_format(completion_params, model_schema.parameter_rules)
model_config_with_cred.parameters = completion_params
# NOTE(-LAN-): This line modify the `self.node_data.model`, which is used in `_invoke_llm()`.
node_data_model.completion_params = completion_params
@ -715,32 +740,8 @@ class LLMNode(BaseNode[LLMNodeData]):
)
if not model_schema:
raise ModelNotExistError(f"Model {model_config.model} not exist.")
if self.node_data.structured_output_enabled:
if not model_schema.support_structure_output:
filtered_prompt_messages = self._handle_prompt_based_schema(
prompt_messages=filtered_prompt_messages,
)
return filtered_prompt_messages, model_config.stop
def _parse_structured_output(self, result_text: str) -> dict[str, Any]:
structured_output: dict[str, Any] = {}
try:
parsed = json.loads(result_text)
if not isinstance(parsed, dict):
raise LLMNodeError(f"Failed to parse structured output: {result_text}")
structured_output = parsed
except json.JSONDecodeError as e:
# if the result_text is not a valid json, try to repair it
parsed = json_repair.loads(result_text)
if not isinstance(parsed, dict):
# handle reasoning model like deepseek-r1 got '<think>\n\n</think>\n' prefix
if isinstance(parsed, list):
parsed = next((item for item in parsed if isinstance(item, dict)), {})
else:
raise LLMNodeError(f"Failed to parse structured output: {result_text}")
structured_output = parsed
return structured_output
@classmethod
def _extract_variable_selector_to_variable_mapping(
cls,
@ -930,104 +931,6 @@ class LLMNode(BaseNode[LLMNodeData]):
self._file_outputs.append(saved_file)
return saved_file
def _handle_native_json_schema(self, model_parameters: dict, rules: list[ParameterRule]) -> dict:
"""
Handle structured output for models with native JSON schema support.
:param model_parameters: Model parameters to update
:param rules: Model parameter rules
:return: Updated model parameters with JSON schema configuration
"""
# Process schema according to model requirements
schema = self._fetch_structured_output_schema()
schema_json = self._prepare_schema_for_model(schema)
# Set JSON schema in parameters
model_parameters["json_schema"] = json.dumps(schema_json, ensure_ascii=False)
# Set appropriate response format if required by the model
for rule in rules:
if rule.name == "response_format" and ResponseFormat.JSON_SCHEMA.value in rule.options:
model_parameters["response_format"] = ResponseFormat.JSON_SCHEMA.value
return model_parameters
def _handle_prompt_based_schema(self, prompt_messages: Sequence[PromptMessage]) -> list[PromptMessage]:
"""
Handle structured output for models without native JSON schema support.
This function modifies the prompt messages to include schema-based output requirements.
Args:
prompt_messages: Original sequence of prompt messages
Returns:
list[PromptMessage]: Updated prompt messages with structured output requirements
"""
# Convert schema to string format
schema_str = json.dumps(self._fetch_structured_output_schema(), ensure_ascii=False)
# Find existing system prompt with schema placeholder
system_prompt = next(
(prompt for prompt in prompt_messages if isinstance(prompt, SystemPromptMessage)),
None,
)
structured_output_prompt = STRUCTURED_OUTPUT_PROMPT.replace("{{schema}}", schema_str)
# Prepare system prompt content
system_prompt_content = (
structured_output_prompt + "\n\n" + system_prompt.content
if system_prompt and isinstance(system_prompt.content, str)
else structured_output_prompt
)
system_prompt = SystemPromptMessage(content=system_prompt_content)
# Extract content from the last user message
filtered_prompts = [prompt for prompt in prompt_messages if not isinstance(prompt, SystemPromptMessage)]
updated_prompt = [system_prompt] + filtered_prompts
return updated_prompt
def _set_response_format(self, model_parameters: dict, rules: list) -> None:
"""
Set the appropriate response format parameter based on model rules.
:param model_parameters: Model parameters to update
:param rules: Model parameter rules
"""
for rule in rules:
if rule.name == "response_format":
if ResponseFormat.JSON.value in rule.options:
model_parameters["response_format"] = ResponseFormat.JSON.value
elif ResponseFormat.JSON_OBJECT.value in rule.options:
model_parameters["response_format"] = ResponseFormat.JSON_OBJECT.value
def _prepare_schema_for_model(self, schema: dict) -> dict:
"""
Prepare JSON schema based on model requirements.
Different models have different requirements for JSON schema formatting.
This function handles these differences.
:param schema: The original JSON schema
:return: Processed schema compatible with the current model
"""
# Deep copy to avoid modifying the original schema
processed_schema = schema.copy()
# Convert boolean types to string types (common requirement)
convert_boolean_to_string(processed_schema)
# Apply model-specific transformations
if SpecialModelType.GEMINI in self.node_data.model.name:
remove_additional_properties(processed_schema)
return processed_schema
elif SpecialModelType.OLLAMA in self.node_data.model.provider:
return processed_schema
else:
# Default format with name field
return {"schema": processed_schema, "name": "llm_response"}
def _fetch_model_schema(self, provider: str) -> AIModelEntity | None:
"""
Fetch model schema
@ -1239,49 +1142,3 @@ def _handle_completion_template(
)
prompt_messages.append(prompt_message)
return prompt_messages
def remove_additional_properties(schema: dict) -> None:
"""
Remove additionalProperties fields from JSON schema.
Used for models like Gemini that don't support this property.
:param schema: JSON schema to modify in-place
"""
if not isinstance(schema, dict):
return
# Remove additionalProperties at current level
schema.pop("additionalProperties", None)
# Process nested structures recursively
for value in schema.values():
if isinstance(value, dict):
remove_additional_properties(value)
elif isinstance(value, list):
for item in value:
if isinstance(item, dict):
remove_additional_properties(item)
def convert_boolean_to_string(schema: dict) -> None:
"""
Convert boolean type specifications to string in JSON schema.
:param schema: JSON schema to modify in-place
"""
if not isinstance(schema, dict):
return
# Check for boolean type at current level
if schema.get("type") == "boolean":
schema["type"] = "string"
# Process nested dictionaries and lists recursively
for value in schema.values():
if isinstance(value, dict):
convert_boolean_to_string(value)
elif isinstance(value, list):
for item in value:
if isinstance(item, dict):
convert_boolean_to_string(item)

4
api/core/workflow/nodes/loop/loop_end_node.py
View File

@ -13,6 +13,10 @@ class LoopEndNode(BaseNode[LoopEndNodeData]):
_node_data_cls = LoopEndNodeData
_node_type = NodeType.LOOP_END
@classmethod
def version(cls) -> str:
return "1"
def _run(self) -> NodeRunResult:
"""
Run the node.

11
api/core/workflow/nodes/loop/loop_node.py
View File

@ -54,6 +54,10 @@ class LoopNode(BaseNode[LoopNodeData]):
_node_data_cls = LoopNodeData
_node_type = NodeType.LOOP
@classmethod
def version(cls) -> str:
return "1"
def _run(self) -> Generator[NodeEvent | InNodeEvent, None, None]:
"""Run the node."""
# Get inputs
@ -482,6 +486,13 @@ class LoopNode(BaseNode[LoopNodeData]):
variable_mapping.update(sub_node_variable_mapping)
for loop_variable in node_data.loop_variables or []:
if loop_variable.value_type == "variable":
assert loop_variable.value is not None, "Loop variable value must be provided for variable type"
# add loop variable to variable mapping
selector = loop_variable.value
variable_mapping[f"{node_id}.{loop_variable.label}"] = selector
# remove variable out from loop
variable_mapping = {
key: value for key, value in variable_mapping.items() if value[0] not in loop_graph.node_ids

4
api/core/workflow/nodes/loop/loop_start_node.py
View File

@ -13,6 +13,10 @@ class LoopStartNode(BaseNode[LoopStartNodeData]):
_node_data_cls = LoopStartNodeData
_node_type = NodeType.LOOP_START
@classmethod
def version(cls) -> str:
return "1"
def _run(self) -> NodeRunResult:
"""
Run the node.

5
api/core/workflow/nodes/node_mapping.py
View File

@ -25,6 +25,11 @@ from core.workflow.nodes.variable_assigner.v2 import VariableAssignerNode as Var
LATEST_VERSION = "latest"
# NOTE(QuantumGhost): This should be in sync with subclasses of BaseNode.
# Specifically, if you have introduced new node types, you should add them here.
#
# TODO(QuantumGhost): This could be automated with either metaclass or `__init_subclass__`
# hook. Try to avoid duplication of node information.
NODE_TYPE_CLASSES_MAPPING: Mapping[NodeType, Mapping[str, type[BaseNode]]] = {
NodeType.START: {
LATEST_VERSION: StartNode,

17
api/core/workflow/nodes/parameter_extractor/entities.py
View File

@ -7,6 +7,10 @@ from core.workflow.nodes.base import BaseNodeData
from core.workflow.nodes.llm import ModelConfig, VisionConfig
class _ParameterConfigError(Exception):
pass
class ParameterConfig(BaseModel):
"""
Parameter Config.
@ -27,6 +31,19 @@ class ParameterConfig(BaseModel):
raise ValueError("Invalid parameter name, __reason and __is_success are reserved")
return str(value)
def is_array_type(self) -> bool:
return self.type in ("array[string]", "array[number]", "array[object]")
def element_type(self) -> Literal["string", "number", "object"]:
if self.type == "array[number]":
return "number"
elif self.type == "array[string]":
return "string"
elif self.type == "array[object]":
return "object"
else:
raise _ParameterConfigError(f"{self.type} is not array type.")
class ParameterExtractorNodeData(BaseNodeData):
"""

28
api/core/workflow/nodes/parameter_extractor/parameter_extractor_node.py
View File

@ -25,6 +25,7 @@ from core.prompt.advanced_prompt_transform import AdvancedPromptTransform
from core.prompt.entities.advanced_prompt_entities import ChatModelMessage, CompletionModelPromptTemplate
from core.prompt.simple_prompt_transform import ModelMode
from core.prompt.utils.prompt_message_util import PromptMessageUtil
from core.variables.types import SegmentType
from core.workflow.entities.node_entities import NodeRunResult
from core.workflow.entities.variable_pool import VariablePool
from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionMetadataKey, WorkflowNodeExecutionStatus
@ -32,6 +33,7 @@ from core.workflow.nodes.base.node import BaseNode
from core.workflow.nodes.enums import NodeType
from core.workflow.nodes.llm import ModelConfig, llm_utils
from core.workflow.utils import variable_template_parser
from factories.variable_factory import build_segment_with_type
from .entities import ParameterExtractorNodeData
from .exc import (
@ -109,6 +111,10 @@ class ParameterExtractorNode(BaseNode):
}
}
@classmethod
def version(cls) -> str:
return "1"
def _run(self):
"""
Run the node.
@ -584,28 +590,30 @@ class ParameterExtractorNode(BaseNode):
elif parameter.type in {"string", "select"}:
if isinstance(result[parameter.name], str):
transformed_result[parameter.name] = result[parameter.name]
elif parameter.type.startswith("array"):
elif parameter.is_array_type():
if isinstance(result[parameter.name], list):
nested_type = parameter.type[6:-1]
transformed_result[parameter.name] = []
nested_type = parameter.element_type()
assert nested_type is not None
segment_value = build_segment_with_type(segment_type=SegmentType(parameter.type), value=[])
transformed_result[parameter.name] = segment_value
for item in result[parameter.name]:
if nested_type == "number":
if isinstance(item, int | float):
transformed_result[parameter.name].append(item)
segment_value.value.append(item)
elif isinstance(item, str):
try:
if "." in item:
transformed_result[parameter.name].append(float(item))
segment_value.value.append(float(item))
else:
transformed_result[parameter.name].append(int(item))
segment_value.value.append(int(item))
except ValueError:
pass
elif nested_type == "string":
if isinstance(item, str):
transformed_result[parameter.name].append(item)
segment_value.value.append(item)
elif nested_type == "object":
if isinstance(item, dict):
transformed_result[parameter.name].append(item)
segment_value.value.append(item)
if parameter.name not in transformed_result:
if parameter.type == "number":
@ -615,7 +623,9 @@ class ParameterExtractorNode(BaseNode):
elif parameter.type in {"string", "select"}:
transformed_result[parameter.name] = ""
elif parameter.type.startswith("array"):
transformed_result[parameter.name] = []
transformed_result[parameter.name] = build_segment_with_type(
segment_type=SegmentType(parameter.type), value=[]
)
return transformed_result

4
api/core/workflow/nodes/question_classifier/question_classifier_node.py
View File

@ -40,6 +40,10 @@ class QuestionClassifierNode(LLMNode):
_node_data_cls = QuestionClassifierNodeData # type: ignore
_node_type = NodeType.QUESTION_CLASSIFIER
@classmethod
def version(cls):
return "1"
def _run(self):
node_data = cast(QuestionClassifierNodeData, self.node_data)
variable_pool = self.graph_runtime_state.variable_pool

7
api/core/workflow/nodes/start/start_node.py
View File

@ -10,6 +10,10 @@ class StartNode(BaseNode[StartNodeData]):
_node_data_cls = StartNodeData
_node_type = NodeType.START
@classmethod
def version(cls) -> str:
return "1"
def _run(self) -> NodeRunResult:
node_inputs = dict(self.graph_runtime_state.variable_pool.user_inputs)
system_inputs = self.graph_runtime_state.variable_pool.system_variables
@ -18,5 +22,6 @@ class StartNode(BaseNode[StartNodeData]):
# Set system variables as node outputs.
for var in system_inputs:
node_inputs[SYSTEM_VARIABLE_NODE_ID + "." + var] = system_inputs[var]
outputs = dict(node_inputs)
return NodeRunResult(status=WorkflowNodeExecutionStatus.SUCCEEDED, inputs=node_inputs, outputs=node_inputs)
return NodeRunResult(status=WorkflowNodeExecutionStatus.SUCCEEDED, inputs=node_inputs, outputs=outputs)

4
api/core/workflow/nodes/template_transform/template_transform_node.py
View File

@ -28,6 +28,10 @@ class TemplateTransformNode(BaseNode[TemplateTransformNodeData]):
"config": {"variables": [{"variable": "arg1", "value_selector": []}], "template": "{{ arg1 }}"},
}
@classmethod
def version(cls) -> str:
return "1"
def _run(self) -> NodeRunResult:
# Get variables
variables = {}

9
api/core/workflow/nodes/tool/tool_node.py
View File

@ -12,7 +12,7 @@ from core.tools.entities.tool_entities import ToolInvokeMessage, ToolParameter
from core.tools.errors import ToolInvokeError
from core.tools.tool_engine import ToolEngine
from core.tools.utils.message_transformer import ToolFileMessageTransformer
from core.variables.segments import ArrayAnySegment
from core.variables.segments import ArrayAnySegment, ArrayFileSegment
from core.variables.variables import ArrayAnyVariable
from core.workflow.entities.node_entities import NodeRunResult
from core.workflow.entities.variable_pool import VariablePool
@ -44,6 +44,10 @@ class ToolNode(BaseNode[ToolNodeData]):
_node_data_cls = ToolNodeData
_node_type = NodeType.TOOL
@classmethod
def version(cls) -> str:
return "1"
def _run(self) -> Generator:
"""
Run the tool node
@ -300,6 +304,7 @@ class ToolNode(BaseNode[ToolNodeData]):
variables[variable_name] = variable_value
elif message.type == ToolInvokeMessage.MessageType.FILE:
assert message.meta is not None
assert isinstance(message.meta, File)
files.append(message.meta["file"])
elif message.type == ToolInvokeMessage.MessageType.LOG:
assert isinstance(message.message, ToolInvokeMessage.LogMessage)
@ -363,7 +368,7 @@ class ToolNode(BaseNode[ToolNodeData]):
yield RunCompletedEvent(
run_result=NodeRunResult(
status=WorkflowNodeExecutionStatus.SUCCEEDED,
outputs={"text": text, "files": files, "json": json, **variables},
outputs={"text": text, "files": ArrayFileSegment(value=files), "json": json, **variables},
metadata={
**agent_execution_metadata,
WorkflowNodeExecutionMetadataKey.TOOL_INFO: tool_info,

13
api/core/workflow/nodes/variable_aggregator/variable_aggregator_node.py
View File

@ -1,3 +1,6 @@
from collections.abc import Mapping
from core.variables.segments import Segment
from core.workflow.entities.node_entities import NodeRunResult
from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionStatus
from core.workflow.nodes.base import BaseNode
@ -9,16 +12,20 @@ class VariableAggregatorNode(BaseNode[VariableAssignerNodeData]):
_node_data_cls = VariableAssignerNodeData
_node_type = NodeType.VARIABLE_AGGREGATOR
@classmethod
def version(cls) -> str:
return "1"
def _run(self) -> NodeRunResult:
# Get variables
outputs = {}
outputs: dict[str, Segment | Mapping[str, Segment]] = {}
inputs = {}
if not self.node_data.advanced_settings or not self.node_data.advanced_settings.group_enabled:
for selector in self.node_data.variables:
variable = self.graph_runtime_state.variable_pool.get(selector)
if variable is not None:
outputs = {"output": variable.to_object()}
outputs = {"output": variable}
inputs = {".".join(selector[1:]): variable.to_object()}
break
@ -28,7 +35,7 @@ class VariableAggregatorNode(BaseNode[VariableAssignerNodeData]):
variable = self.graph_runtime_state.variable_pool.get(selector)
if variable is not None:
outputs[group.group_name] = {"output": variable.to_object()}
outputs[group.group_name] = {"output": variable}
inputs[".".join(selector[1:])] = variable.to_object()
break

66
api/core/workflow/nodes/variable_assigner/common/helpers.py
View File

@ -1,19 +1,55 @@
from sqlalchemy import select
from sqlalchemy.orm import Session
from collections.abc import Mapping, MutableMapping, Sequence
from typing import Any, TypeVar
from core.variables import Variable
from core.workflow.nodes.variable_assigner.common.exc import VariableOperatorNodeError
from extensions.ext_database import db
from models import ConversationVariable
from pydantic import BaseModel
from core.variables import Segment
from core.variables.consts import MIN_SELECTORS_LENGTH
from core.variables.types import SegmentType
# Use double underscore (`__`) prefix for internal variables
# to minimize risk of collision with user-defined variable names.
_UPDATED_VARIABLES_KEY = "__updated_variables"
def update_conversation_variable(conversation_id: str, variable: Variable):
stmt = select(ConversationVariable).where(
ConversationVariable.id == variable.id, ConversationVariable.conversation_id == conversation_id
class UpdatedVariable(BaseModel):
name: str
selector: Sequence[str]
value_type: SegmentType
new_value: Any
_T = TypeVar("_T", bound=MutableMapping[str, Any])
def variable_to_processed_data(selector: Sequence[str], seg: Segment) -> UpdatedVariable:
if len(selector) < MIN_SELECTORS_LENGTH:
raise Exception("selector too short")
node_id, var_name = selector[:2]
return UpdatedVariable(
name=var_name,
selector=list(selector[:2]),
value_type=seg.value_type,
new_value=seg.value,
)
with Session(db.engine) as session:
row = session.scalar(stmt)
if not row:
raise VariableOperatorNodeError("conversation variable not found in the database")
row.data = variable.model_dump_json()
session.commit()
def set_updated_variables(m: _T, updates: Sequence[UpdatedVariable]) -> _T:
m[_UPDATED_VARIABLES_KEY] = updates
return m
def get_updated_variables(m: Mapping[str, Any]) -> Sequence[UpdatedVariable] | None:
updated_values = m.get(_UPDATED_VARIABLES_KEY, None)
if updated_values is None:
return None
result = []
for items in updated_values:
if isinstance(items, UpdatedVariable):
result.append(items)
elif isinstance(items, dict):
items = UpdatedVariable.model_validate(items)
result.append(items)
else:
raise TypeError(f"Invalid updated variable: {items}, type={type(items)}")
return result

38
api/core/workflow/nodes/variable_assigner/common/impl.py Normal file
View File

@ -0,0 +1,38 @@
from sqlalchemy import Engine, select
from sqlalchemy.orm import Session
from core.variables.variables import Variable
from models.engine import db
from models.workflow import ConversationVariable
from .exc import VariableOperatorNodeError
class ConversationVariableUpdaterImpl:
_engine: Engine | None
def __init__(self, engine: Engine | None = None) -> None:
self._engine = engine
def _get_engine(self) -> Engine:
if self._engine:
return self._engine
return db.engine
def update(self, conversation_id: str, variable: Variable):
stmt = select(ConversationVariable).where(
ConversationVariable.id == variable.id, ConversationVariable.conversation_id == conversation_id
)
with Session(self._get_engine()) as session:
row = session.scalar(stmt)
if not row:
raise VariableOperatorNodeError("conversation variable not found in the database")
row.data = variable.model_dump_json()
session.commit()
def flush(self):
pass
def conversation_variable_updater_factory() -> ConversationVariableUpdaterImpl:
return ConversationVariableUpdaterImpl()

74
api/core/workflow/nodes/variable_assigner/v1/node.py
View File

@ -1,4 +1,9 @@
from collections.abc import Callable, Mapping, Sequence
from typing import TYPE_CHECKING, Any, Optional, TypeAlias
from core.variables import SegmentType, Variable
from core.workflow.constants import CONVERSATION_VARIABLE_NODE_ID
from core.workflow.conversation_variable_updater import ConversationVariableUpdater
from core.workflow.entities.node_entities import NodeRunResult
from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionStatus
from core.workflow.nodes.base import BaseNode
@ -7,16 +12,71 @@ from core.workflow.nodes.variable_assigner.common import helpers as common_helpe
from core.workflow.nodes.variable_assigner.common.exc import VariableOperatorNodeError
from factories import variable_factory
from ..common.impl import conversation_variable_updater_factory
from .node_data import VariableAssignerData, WriteMode
if TYPE_CHECKING:
from core.workflow.graph_engine import Graph, GraphInitParams, GraphRuntimeState
_CONV_VAR_UPDATER_FACTORY: TypeAlias = Callable[[], ConversationVariableUpdater]
class VariableAssignerNode(BaseNode[VariableAssignerData]):
_node_data_cls = VariableAssignerData
_node_type = NodeType.VARIABLE_ASSIGNER
_conv_var_updater_factory: _CONV_VAR_UPDATER_FACTORY
def __init__(
self,
id: str,
config: Mapping[str, Any],
graph_init_params: "GraphInitParams",
graph: "Graph",
graph_runtime_state: "GraphRuntimeState",
previous_node_id: Optional[str] = None,
thread_pool_id: Optional[str] = None,
conv_var_updater_factory: _CONV_VAR_UPDATER_FACTORY = conversation_variable_updater_factory,
) -> None:
super().__init__(
id=id,
config=config,
graph_init_params=graph_init_params,
graph=graph,
graph_runtime_state=graph_runtime_state,
previous_node_id=previous_node_id,
thread_pool_id=thread_pool_id,
)
self._conv_var_updater_factory = conv_var_updater_factory
@classmethod
def version(cls) -> str:
return "1"
@classmethod
def _extract_variable_selector_to_variable_mapping(
cls,
*,
graph_config: Mapping[str, Any],
node_id: str,
node_data: VariableAssignerData,
) -> Mapping[str, Sequence[str]]:
mapping = {}
assigned_variable_node_id = node_data.assigned_variable_selector[0]
if assigned_variable_node_id == CONVERSATION_VARIABLE_NODE_ID:
selector_key = ".".join(node_data.assigned_variable_selector)
key = f"{node_id}.#{selector_key}#"
mapping[key] = node_data.assigned_variable_selector
selector_key = ".".join(node_data.input_variable_selector)
key = f"{node_id}.#{selector_key}#"
mapping[key] = node_data.input_variable_selector
return mapping
def _run(self) -> NodeRunResult:
assigned_variable_selector = self.node_data.assigned_variable_selector
# Should be String, Number, Object, ArrayString, ArrayNumber, ArrayObject
original_variable = self.graph_runtime_state.variable_pool.get(self.node_data.assigned_variable_selector)
original_variable = self.graph_runtime_state.variable_pool.get(assigned_variable_selector)
if not isinstance(original_variable, Variable):
raise VariableOperatorNodeError("assigned variable not found")
@ -44,20 +104,28 @@ class VariableAssignerNode(BaseNode[VariableAssignerData]):
raise VariableOperatorNodeError(f"unsupported write mode: {self.node_data.write_mode}")
# Over write the variable.
self.graph_runtime_state.variable_pool.add(self.node_data.assigned_variable_selector, updated_variable)
self.graph_runtime_state.variable_pool.add(assigned_variable_selector, updated_variable)
# TODO: Move database operation to the pipeline.
# Update conversation variable.
conversation_id = self.graph_runtime_state.variable_pool.get(["sys", "conversation_id"])
if not conversation_id:
raise VariableOperatorNodeError("conversation_id not found")
common_helpers.update_conversation_variable(conversation_id=conversation_id.text, variable=updated_variable)
conv_var_updater = self._conv_var_updater_factory()
conv_var_updater.update(conversation_id=conversation_id.text, variable=updated_variable)
conv_var_updater.flush()
updated_variables = [common_helpers.variable_to_processed_data(assigned_variable_selector, updated_variable)]
return NodeRunResult(
status=WorkflowNodeExecutionStatus.SUCCEEDED,
inputs={
"value": income_value.to_object(),
},
# NOTE(QuantumGhost): although only one variable is updated in `v1.VariableAssignerNode`,
# we still set `output_variables` as a list to ensure the schema of output is
# compatible with `v2.VariableAssignerNode`.
process_data=common_helpers.set_updated_variables({}, updated_variables),
outputs={},
)

6
api/core/workflow/nodes/variable_assigner/v2/entities.py
View File

@ -12,6 +12,12 @@ class VariableOperationItem(BaseModel):
variable_selector: Sequence[str]
input_type: InputType
operation: Operation
# NOTE(QuantumGhost): The `value` field serves multiple purposes depending on context:
#
# 1. For CONSTANT input_type: Contains the literal value to be used in the operation.
# 2. For VARIABLE input_type: Initially contains the selector of the source variable.
# 3. During the variable updating procedure: The `value` field is reassigned to hold
# the resolved actual value that will be applied to the target variable.
value: Any | None = None

5
api/core/workflow/nodes/variable_assigner/v2/exc.py
View File

@ -29,3 +29,8 @@ class InvalidInputValueError(VariableOperatorNodeError):
class ConversationIDNotFoundError(VariableOperatorNodeError):
def __init__(self):
super().__init__("conversation_id not found")
class InvalidDataError(VariableOperatorNodeError):
def __init__(self, message: str) -> None:
super().__init__(message)

Some files were not shown because too many files have changed in this diff Show More