Merge branch 'plugins/beta' into dev/plugin-deploy

.github/actions/setup-poetry/action.yml

@@ -8,7 +8,7 @@ inputs:
   poetry-version:
     description: Poetry version to set up
     required: true
-    default: '1.8.4'
+    default: '2.0.1'
   poetry-lockfile:
     description: Path to the Poetry lockfile to restore cache from
     required: true

.github/workflows/api-tests.yml

@@ -43,19 +43,17 @@ jobs:
         run: poetry install -C api --with dev
 
       - name: Check dependencies in pyproject.toml
-        run: poetry run -C api bash dev/pytest/pytest_artifacts.sh
+        run: poetry run -P api bash dev/pytest/pytest_artifacts.sh
 
       - name: Run Unit tests
-        run: poetry run -C api bash dev/pytest/pytest_unit_tests.sh
+        run: poetry run -P api bash dev/pytest/pytest_unit_tests.sh
 
       - name: Run dify config tests
-        run: poetry run -C api python dev/pytest/pytest_config_tests.py
+        run: poetry run -P api python dev/pytest/pytest_config_tests.py
 
       - name: Run mypy
         run: |
-          pushd api
-          poetry run python -m mypy --install-types --non-interactive .
-          popd
+          poetry run -C api python -m mypy --install-types --non-interactive .
 
       - name: Set up dotenvs
         run: |
@@ -75,4 +73,4 @@ jobs:
             ssrf_proxy
 
       - name: Run Workflow
-        run: poetry run -C api bash dev/pytest/pytest_workflow.sh
+        run: poetry run -P api bash dev/pytest/pytest_workflow.sh

.github/workflows/style.yml

@@ -39,12 +39,12 @@ jobs:
         if: steps.changed-files.outputs.any_changed == 'true'
         run: |
           poetry run -C api ruff --version
-          poetry run -C api ruff check ./api
-          poetry run -C api ruff format --check ./api
+          poetry run -C api ruff check ./
+          poetry run -C api ruff format --check ./
 
       - name: Dotenv check
         if: steps.changed-files.outputs.any_changed == 'true'
-        run: poetry run -C api dotenv-linter ./api/.env.example ./web/.env.example
+        run: poetry run -P api dotenv-linter ./api/.env.example ./web/.env.example
 
       - name: Lint hints
         if: failure()
@@ -87,7 +87,35 @@ jobs:
 
       - name: Web style check
         if: steps.changed-files.outputs.any_changed == 'true'
-        run: echo "${{ steps.changed-files.outputs.all_changed_files }}" | sed 's|web/||g' | xargs pnpm eslint # wait for next lint support eslint v9
+        run: yarn run lint
+
+  docker-compose-template:
+    name: Docker Compose Template
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Check changed files
+        id: changed-files
+        uses: tj-actions/changed-files@v45
+        with:
+          files: |
+            docker/generate_docker_compose
+            docker/.env.example
+            docker/docker-compose-template.yaml
+            docker/docker-compose.yaml
+
+      - name: Generate Docker Compose
+        if: steps.changed-files.outputs.any_changed == 'true'
+        run: |
+          cd docker
+          ./generate_docker_compose
+
+      - name: Check for changes
+        if: steps.changed-files.outputs.any_changed == 'true'
+        run: git diff --exit-code
 
 
   docker-compose-template:

.github/workflows/vdb-tests.yml

@@ -70,4 +70,4 @@ jobs:
             tidb
 
       - name: Test Vector Stores
-        run: poetry run -C api bash dev/pytest/pytest_vdb.sh
+        run: poetry run -P api bash dev/pytest/pytest_vdb.sh

.gitignore

@@ -197,3 +197,6 @@ api/.vscode
 
 # pnpm
 /.pnpm-store
+
+# plugin migrate
+plugins.jsonl

api/.env.example

@@ -422,8 +422,7 @@ POSITION_PROVIDER_INCLUDES=
 POSITION_PROVIDER_EXCLUDES=
 
 # Plugin configuration
-PLUGIN_API_KEY=lYkiYYT6owG+71oLerGzA7GXCgOT++6ovaezWAjpCjf+Sjc3ZtU+qUEi
-PLUGIN_API_URL=http://127.0.0.1:5002
+PLUGIN_DAEMON_KEY=lYkiYYT6owG+71oLerGzA7GXCgOT++6ovaezWAjpCjf+Sjc3ZtU+qUEi
 PLUGIN_DAEMON_URL=http://127.0.0.1:5002
 PLUGIN_REMOTE_INSTALL_PORT=5003
 PLUGIN_REMOTE_INSTALL_HOST=localhost
@@ -436,7 +435,7 @@ MARKETPLACE_ENABLED=true
 MARKETPLACE_API_URL=https://marketplace.dify.ai
 
 # Endpoint configuration
-ENDPOINT_URL_TEMPLATE=http://localhost/e/{hook_id}
+ENDPOINT_URL_TEMPLATE=http://localhost:5002/e/{hook_id}
 
 # Reset password token expiry minutes
 RESET_PASSWORD_TOKEN_EXPIRY_MINUTES=5

api/.ruff.toml

@@ -53,10 +53,12 @@ ignore = [
     "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

api/Dockerfile

@@ -4,7 +4,7 @@ FROM python:3.12-slim-bookworm AS base
 WORKDIR /app/api
 
 # Install Poetry
-ENV POETRY_VERSION=1.8.4
+ENV POETRY_VERSION=2.0.1
 
 # if you located in China, you can use aliyun mirror to speed up
 # RUN pip install --no-cache-dir poetry==${POETRY_VERSION} -i https://mirrors.aliyun.com/pypi/simple/
@@ -55,6 +55,7 @@ RUN apt-get update \
     && echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
     && apt-get update \
     # For Security
+    # && apt-get install -y --no-install-recommends expat=2.6.4-1 libldap-2.5-0=2.5.19+dfsg-1 perl=5.40.0-8 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
     # install a chinese font to support the use of tools like matplotlib
     && apt-get install -y fonts-noto-cjk \
     && apt-get autoremove -y \

api/README.md

@@ -79,5 +79,5 @@
 2. Run the tests locally with mocked system environment variables in `tool.pytest_env` section in `pyproject.toml`
 
    ```bash
-   poetry run -C api bash dev/pytest/pytest_all_tests.sh
+   poetry run -P api bash dev/pytest/pytest_all_tests.sh
    ```

api/configs/feature/__init__.py

@@ -141,10 +141,10 @@ class PluginConfig(BaseSettings):
 
     PLUGIN_DAEMON_URL: HttpUrl = Field(
         description="Plugin API URL",
-        default="http://plugin:5002",
+        default="http://localhost:5002",
     )
 
-    PLUGIN_API_KEY: str = Field(
+    PLUGIN_DAEMON_KEY: str = Field(
         description="Plugin API key",
         default="plugin-api-key",
     )
@@ -200,7 +200,7 @@ class EndpointConfig(BaseSettings):
     )
 
     CONSOLE_WEB_URL: str = Field(
-        description="Base URL for the console web interface," "used for frontend references and CORS configuration",
+        description="Base URL for the console web interface,used for frontend references and CORS configuration",
         default="",
     )
 

api/configs/feature/hosted_service/__init__.py

@@ -181,7 +181,7 @@ class HostedFetchAppTemplateConfig(BaseSettings):
     """
 
     HOSTED_FETCH_APP_TEMPLATES_MODE: str = Field(
-        description="Mode for fetching app templates: remote, db, or builtin" " default to remote,",
+        description="Mode for fetching app templates: remote, db, or builtin default to remote,",
         default="remote",
     )
 

api/controllers/console/admin.py

@@ -59,7 +59,7 @@ def post(self):
         with Session(db.engine) as session:
             app = session.execute(select(App).filter(App.id == args["app_id"])).scalar_one_or_none()
         if not app:
-            raise NotFound(f'App \'{args["app_id"]}\' is not found')
+            raise NotFound(f"App '{args['app_id']}' is not found")
 
         site = app.site
         if not site:

api/controllers/console/app/audio.py

@@ -22,7 +22,7 @@
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
 from libs.login import login_required
-from models.model import AppMode
+from models import App, AppMode
 from services.audio_service import AudioService
 from services.errors.audio import (
     AudioTooLargeServiceError,
@@ -79,7 +79,7 @@ class ChatMessageTextApi(Resource):
     @login_required
     @account_initialization_required
     @get_app_model
-    def post(self, app_model):
+    def post(self, app_model: App):
         from werkzeug.exceptions import InternalServerError
 
         try:
@@ -98,9 +98,13 @@ def post(self, app_model):
                 and app_model.workflow.features_dict
             ):
                 text_to_speech = app_model.workflow.features_dict.get("text_to_speech")
+                if text_to_speech is None:
+                    raise ValueError("TTS is not enabled")
                 voice = args.get("voice") or text_to_speech.get("voice")
             else:
                 try:
+                    if app_model.app_model_config is None:
+                        raise ValueError("AppModelConfig not found")
                     voice = args.get("voice") or app_model.app_model_config.text_to_speech_dict.get("voice")
                 except Exception:
                     voice = None

api/controllers/console/datasets/data_source.py

@@ -135,7 +135,7 @@ def get(self):
                         data_source_info = json.loads(document.data_source_info)
                         exist_page_ids.append(data_source_info["notion_page_id"])
             # get all authorized pages
-            data_source_bindings = session.execute(
+            data_source_bindings = session.scalars(
                 select(DataSourceOauthBinding).filter_by(
                     tenant_id=current_user.current_tenant_id, provider="notion", disabled=False
                 )

api/controllers/console/datasets/datasets.py

@@ -52,12 +52,12 @@ def get(self):
         # provider = request.args.get("provider", default="vendor")
         search = request.args.get("keyword", default=None, type=str)
         tag_ids = request.args.getlist("tag_ids")
-
+        include_all = request.args.get("include_all", default="false").lower() == "true"
         if ids:
             datasets, total = DatasetService.get_datasets_by_ids(ids, current_user.current_tenant_id)
         else:
             datasets, total = DatasetService.get_datasets(
-                page, limit, current_user.current_tenant_id, current_user, search, tag_ids
+                page, limit, current_user.current_tenant_id, current_user, search, tag_ids, include_all
             )
 
         # check embedding setting
@@ -457,7 +457,7 @@ def post(self):
             )
         except LLMBadRequestError:
             raise ProviderNotInitializeError(
-                "No Embedding Model available. Please configure a valid provider " "in the Settings -> Model Provider."
+                "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
             )
         except ProviderTokenNotInitError as ex:
             raise ProviderNotInitializeError(ex.description)
@@ -619,8 +619,7 @@ def get(self):
         vector_type = dify_config.VECTOR_STORE
         match vector_type:
             case (
-                VectorType.MILVUS
-                | VectorType.RELYT
+                VectorType.RELYT
                 | VectorType.PGVECTOR
                 | VectorType.TIDB_VECTOR
                 | VectorType.CHROMA
@@ -645,6 +644,7 @@ def get(self):
                 | VectorType.TIDB_ON_QDRANT
                 | VectorType.LINDORM
                 | VectorType.COUCHBASE
+                | VectorType.MILVUS
             ):
                 return {
                     "retrieval_method": [

api/controllers/console/datasets/datasets_document.py

@@ -362,8 +362,7 @@ def post(self):
                 )
             except InvokeAuthorizationError:
                 raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                 )
             except ProviderTokenNotInitError as ex:
                 raise ProviderNotInitializeError(ex.description)
@@ -540,8 +539,7 @@ def get(self, dataset_id, batch):
                 return response.model_dump(), 200
             except LLMBadRequestError:
                 raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                 )
             except ProviderTokenNotInitError as ex:
                 raise ProviderNotInitializeError(ex.description)

api/controllers/console/datasets/datasets_segments.py

@@ -168,8 +168,7 @@ def patch(self, dataset_id, document_id, action):
                 )
             except LLMBadRequestError:
                 raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                 )
             except ProviderTokenNotInitError as ex:
                 raise ProviderNotInitializeError(ex.description)
@@ -217,8 +216,7 @@ def post(self, dataset_id, document_id):
                 )
             except LLMBadRequestError:
                 raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                 )
             except ProviderTokenNotInitError as ex:
                 raise ProviderNotInitializeError(ex.description)
@@ -267,8 +265,7 @@ def patch(self, dataset_id, document_id, segment_id):
                 )
             except LLMBadRequestError:
                 raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                 )
             except ProviderTokenNotInitError as ex:
                 raise ProviderNotInitializeError(ex.description)
@@ -368,9 +365,9 @@ def post(self, dataset_id, document_id):
             result = []
             for index, row in df.iterrows():
                 if document.doc_form == "qa_model":
-                    data = {"content": row[0], "answer": row[1]}
+                    data = {"content": row.iloc[0], "answer": row.iloc[1]}
                 else:
-                    data = {"content": row[0]}
+                    data = {"content": row.iloc[0]}
                 result.append(data)
             if len(result) == 0:
                 raise ValueError("The CSV file is empty.")
@@ -437,8 +434,7 @@ def post(self, dataset_id, document_id, segment_id):
                 )
             except LLMBadRequestError:
                 raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                 )
             except ProviderTokenNotInitError as ex:
                 raise ProviderNotInitializeError(ex.description)

api/controllers/console/explore/conversation.py

@@ -32,7 +32,7 @@ def get(self, installed_app):
 
         pinned = None
         if "pinned" in args and args["pinned"] is not None:
-            pinned = True if args["pinned"] == "true" else False
+            pinned = args["pinned"] == "true"
 
         try:
             with Session(db.engine) as session:

api/controllers/inner_api/wraps.py

@@ -65,7 +65,7 @@ def decorated(*args, **kwargs):
 def plugin_inner_api_only(view):
     @wraps(view)
     def decorated(*args, **kwargs):
-        if not dify_config.PLUGIN_API_KEY:
+        if not dify_config.PLUGIN_DAEMON_KEY:
             abort(404)
 
         # get header 'X-Inner-Api-Key'

api/controllers/service_api/__init__.py

@@ -7,4 +7,4 @@
 
 from . import index
 from .app import app, audio, completion, conversation, file, message, workflow
-from .dataset import dataset, document, hit_testing, segment
+from .dataset import dataset, document, hit_testing, segment, upload_file

api/controllers/service_api/dataset/dataset.py

@@ -31,8 +31,11 @@ def get(self, tenant_id):
         # provider = request.args.get("provider", default="vendor")
         search = request.args.get("keyword", default=None, type=str)
         tag_ids = request.args.getlist("tag_ids")
+        include_all = request.args.get("include_all", default="false").lower() == "true"
 
-        datasets, total = DatasetService.get_datasets(page, limit, tenant_id, current_user, search, tag_ids)
+        datasets, total = DatasetService.get_datasets(
+            page, limit, tenant_id, current_user, search, tag_ids, include_all
+        )
         # check embedding setting
         provider_manager = ProviderManager()
         configurations = provider_manager.get_configurations(tenant_id=current_user.current_tenant_id)