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 @@ class InsertExploreAppListApi(Resource):
         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 controllers.console.wraps import account_initialization_required, setup_req
 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 @@ class ChatMessageTextApi(Resource):
                 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 @@ class DataSourceNotionListApi(Resource):
                         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 @@ class DatasetListApi(Resource):
         # 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 @@ class DatasetIndexingEstimateApi(Resource):
             )
         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 @@ class DatasetRetrievalSettingApi(Resource):
         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 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.TIDB_ON_QDRANT
                 | VectorType.LINDORM
                 | VectorType.COUCHBASE
+                | VectorType.MILVUS
             ):
                 return {
                     "retrieval_method": [

api/controllers/console/datasets/datasets_document.py

@@ -362,8 +362,7 @@ class DatasetInitApi(Resource):
                 )
             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 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
                 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 @@ class DatasetDocumentSegmentApi(Resource):
                 )
             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 @@ class DatasetDocumentSegmentAddApi(Resource):
                 )
             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 @@ class DatasetDocumentSegmentUpdateApi(Resource):
                 )
             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 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
             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 @@ class ChildChunkAddApi(Resource):
                 )
             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 @@ class ConversationListApi(InstalledAppResource):
 
         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 enterprise_inner_api_user_auth(view):
 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 @@ api = ExternalApi(bp)
 
 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 @@ class DatasetListApi(DatasetApiResource):
         # 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)

api/controllers/service_api/dataset/segment.py

@@ -53,8 +53,7 @@ class SegmentApi(DatasetApiResource):
                 )
             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)
@@ -95,8 +94,7 @@ class SegmentApi(DatasetApiResource):
                 )
             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)
@@ -175,8 +173,7 @@ class DatasetSegmentApi(DatasetApiResource):
                 )
             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/service_api/dataset/upload_file.py

@@ -0,0 +1,54 @@
+from werkzeug.exceptions import NotFound
+
+from controllers.service_api import api
+from controllers.service_api.wraps import (
+    DatasetApiResource,
+)
+from core.file import helpers as file_helpers
+from extensions.ext_database import db
+from models.dataset import Dataset
+from models.model import UploadFile
+from services.dataset_service import DocumentService
+
+
+class UploadFileApi(DatasetApiResource):
+    def get(self, tenant_id, dataset_id, document_id):
+        """Get upload file."""
+        # check dataset
+        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()
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset.id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+        # check upload file
+        if document.data_source_type != "upload_file":
+            raise ValueError(f"Document data source type ({document.data_source_type}) is not upload_file.")
+        data_source_info = document.data_source_info_dict
+        if data_source_info and "upload_file_id" in data_source_info:
+            file_id = data_source_info["upload_file_id"]
+            upload_file = db.session.query(UploadFile).filter(UploadFile.id == file_id).first()
+            if not upload_file:
+                raise NotFound("UploadFile not found.")
+        else:
+            raise ValueError("Upload file id not found in document data source info.")
+
+        url = file_helpers.get_signed_file_url(upload_file_id=upload_file.id)
+        return {
+            "id": upload_file.id,
+            "name": upload_file.name,
+            "size": upload_file.size,
+            "extension": upload_file.extension,
+            "url": url,
+            "download_url": f"{url}&as_attachment=true",
+            "mime_type": upload_file.mime_type,
+            "created_by": upload_file.created_by,
+            "created_at": upload_file.created_at.timestamp(),
+        }, 200
+
+
+api.add_resource(UploadFileApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/upload-file")

api/controllers/service_api/wraps.py

@@ -195,7 +195,11 @@ def validate_and_get_api_token(scope: str | None = None):
     with Session(db.engine, expire_on_commit=False) as session:
         update_stmt = (
             update(ApiToken)
-            .where(ApiToken.token == auth_token, ApiToken.last_used_at < cutoff_time, ApiToken.type == scope)
+            .where(
+                ApiToken.token == auth_token,
+                (ApiToken.last_used_at.is_(None) | (ApiToken.last_used_at < cutoff_time)),
+                ApiToken.type == scope,
+            )
             .values(last_used_at=current_time)
             .returning(ApiToken)
         )
@@ -236,7 +240,7 @@ def create_or_update_end_user_for_user_id(app_model: App, user_id: Optional[str]
             tenant_id=app_model.tenant_id,
             app_id=app_model.id,
             type="service_api",
-            is_anonymous=True if user_id == "DEFAULT-USER" else False,
+            is_anonymous=user_id == "DEFAULT-USER",
             session_id=user_id,
         )
         db.session.add(end_user)

api/controllers/web/conversation.py

@@ -39,7 +39,7 @@ class ConversationListApi(WebApiResource):
 
         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/core/agent/cot_agent_runner.py

@@ -168,7 +168,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):
 
             self.save_agent_thought(
                 agent_thought=agent_thought,
-                tool_name=scratchpad.action.action_name if scratchpad.action else "",
+                tool_name=(scratchpad.action.action_name if scratchpad.action and not scratchpad.is_final() else ""),
                 tool_input={scratchpad.action.action_name: scratchpad.action.action_input} if scratchpad.action else {},
                 tool_invoke_meta={},
                 thought=scratchpad.thought or "",

api/core/app/apps/base_app_queue_manager.py

@@ -167,8 +167,7 @@ class AppQueueManager:
         else:
             if isinstance(data, DeclarativeMeta) or hasattr(data, "_sa_instance_state"):
                 raise TypeError(
-                    "Critical Error: Passing SQLAlchemy Model instances "
-                    "that cause thread safety issues is not allowed."
+                    "Critical Error: Passing SQLAlchemy Model instances that cause thread safety issues is not allowed."
                 )
 
 

api/core/app/apps/message_based_app_generator.py

@@ -89,6 +89,7 @@ class MessageBasedAppGenerator(BaseAppGenerator):
             Conversation.id == conversation_id,
             Conversation.app_id == app_model.id,
             Conversation.status == "normal",
+            Conversation.is_deleted.is_(False),
         ]
 
         if isinstance(user, Account):

api/core/app/task_pipeline/message_cycle_manage.py

@@ -145,7 +145,7 @@ class MessageCycleManage:
 
             # get extension
             if "." in message_file.url:
-                extension = f'.{message_file.url.split(".")[-1]}'
+                extension = f".{message_file.url.split('.')[-1]}"
                 if len(extension) > 10:
                     extension = ".bin"
             else:

api/core/external_data_tool/api/api.py

@@ -62,8 +62,9 @@ class ApiExternalDataTool(ExternalDataTool):
 
         if not api_based_extension:
             raise ValueError(
-                "[External data tool] API query failed, variable: {}, "
-                "error: api_based_extension_id is invalid".format(self.variable)
+                "[External data tool] API query failed, variable: {}, error: api_based_extension_id is invalid".format(
+                    self.variable
+                )
             )
 
         # decrypt api_key

api/core/file/helpers.py

@@ -33,7 +33,7 @@ def get_signed_file_url_for_plugin(filename: str, mimetype: str, tenant_id: str,
     sign = hmac.new(key, msg.encode(), hashlib.sha256).digest()
     encoded_sign = base64.urlsafe_b64encode(sign).decode()
 
-    return f"{url}?timestamp={timestamp}&nonce={nonce}&sign={encoded_sign}&user_id={user_id}"
+    return f"{url}?timestamp={timestamp}&nonce={nonce}&sign={encoded_sign}&user_id={user_id}&tenant_id={tenant_id}"
 
 
 def verify_plugin_file_signature(

api/core/file/models.py

@@ -90,7 +90,7 @@ class File(BaseModel):
     def markdown(self) -> str:
         url = self.generate_url()
         if self.type == FileType.IMAGE:
-            text = f'![{self.filename or ""}]({url})'
+            text = f"![{self.filename or ''}]({url})"
         else:
             text = f"[{self.filename or url}]({url})"
 

api/core/indexing_runner.py

@@ -530,7 +530,6 @@ class IndexingRunner:
         # chunk nodes by chunk size
         indexing_start_at = time.perf_counter()
         tokens = 0
-        chunk_size = 10
         if dataset_document.doc_form != IndexType.PARENT_CHILD_INDEX:
             # create keyword index
             create_keyword_thread = threading.Thread(
@@ -539,11 +538,22 @@ class IndexingRunner:
             )
             create_keyword_thread.start()
 
+        max_workers = 10
         if dataset.indexing_technique == "high_quality":
-            with concurrent.futures.ThreadPoolExecutor(max_workers=10) as executor:
+            with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
                 futures = []
-                for i in range(0, len(documents), chunk_size):
-                    chunk_documents = documents[i : i + chunk_size]
+
+                # Distribute documents into multiple groups based on the hash values of page_content
+                # This is done to prevent multiple threads from processing the same document,
+                # Thereby avoiding potential database insertion deadlocks
+                document_groups: list[list[Document]] = [[] for _ in range(max_workers)]
+                for document in documents:
+                    hash = helper.generate_text_hash(document.page_content)
+                    group_index = int(hash, 16) % max_workers
+                    document_groups[group_index].append(document)
+                for chunk_documents in document_groups:
+                    if len(chunk_documents) == 0:
+                        continue
                     futures.append(
                         executor.submit(
                             self._process_chunk,

api/core/llm_generator/prompts.py

@@ -131,7 +131,7 @@ JAVASCRIPT_CODE_GENERATOR_PROMPT_TEMPLATE = (
 SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT = (
     "Please help me predict the three most likely questions that human would ask, "
     "and keeping each question under 20 characters.\n"
-    "MAKE SURE your output is the SAME language as the Assistant's latest response"
+    "MAKE SURE your output is the SAME language as the Assistant's latest response. "
     "The output must be an array in JSON format following the specified schema:\n"
     '["question1","question2","question3"]\n'
 )

api/core/model_runtime/model_providers/__base/tokenizers/gpt2_tokenzier.py

@@ -1,6 +1,9 @@
+import logging
 from threading import Lock
 from typing import Any
 
+logger = logging.getLogger(__name__)
+
 _tokenizer: Any = None
 _lock = Lock()
 
@@ -43,5 +46,6 @@ class GPT2Tokenizer:
                     base_path = abspath(__file__)
                     gpt2_tokenizer_path = join(dirname(base_path), "gpt2")
                     _tokenizer = TransformerGPT2Tokenizer.from_pretrained(gpt2_tokenizer_path)
+                    logger.info("Fallback to Transformers' GPT-2 tokenizer from tiktoken")
 
             return _tokenizer

api/core/model_runtime/model_providers/wenxin/llm/ernie-lite-pro-128k.yaml

@@ -1,42 +0,0 @@
-model: ernie-lite-pro-128k
-label:
-  en_US: Ernie-Lite-Pro-128K
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0.1
-    max: 1.0
-    default: 0.8
-  - name: top_p
-    use_template: top_p
-  - name: min_output_tokens
-    label:
-      en_US: "Min Output Tokens"
-      zh_Hans: "最小输出Token数"
-    use_template: max_tokens
-    min: 2
-    max: 2048
-    help:
-      zh_Hans: 指定模型最小输出token数
-      en_US: Specifies the lower limit on the length of generated results.
-  - name: max_output_tokens
-    label:
-      en_US: "Max Output Tokens"
-      zh_Hans: "最大输出Token数"
-    use_template: max_tokens
-    min: 2
-    max: 2048
-    default: 2048
-    help:
-      zh_Hans: 指定模型最大输出token数
-      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
-  - name: presence_penalty
-    use_template: presence_penalty
-  - name: frequency_penalty
-    use_template: frequency_penalty

api/core/model_runtime/schema_validators/common_validator.py

@@ -87,6 +87,6 @@ class CommonValidator:
             if value.lower() not in {"true", "false"}:
                 raise ValueError(f"Variable {credential_form_schema.variable} should be true or false")
 
-            value = True if value.lower() == "true" else False
+            value = value.lower() == "true"
 
         return value

api/core/ops/entities/config_entity.py

@@ -6,6 +6,7 @@ from pydantic import BaseModel, ValidationInfo, field_validator
 class TracingProviderEnum(Enum):
     LANGFUSE = "langfuse"
     LANGSMITH = "langsmith"
+    OPIK = "opik"
 
 
 class BaseTracingConfig(BaseModel):
@@ -56,5 +57,36 @@ class LangSmithConfig(BaseTracingConfig):
         return v
 
 
+class OpikConfig(BaseTracingConfig):
+    """
+    Model class for Opik tracing config.
+    """
+
+    api_key: str | None = None
+    project: str | None = None
+    workspace: str | None = None
+    url: str = "https://www.comet.com/opik/api/"
+
+    @field_validator("project")
+    @classmethod
+    def project_validator(cls, v, info: ValidationInfo):
+        if v is None or v == "":
+            v = "Default Project"
+
+        return v
+
+    @field_validator("url")
+    @classmethod
+    def url_validator(cls, v, info: ValidationInfo):
+        if v is None or v == "":
+            v = "https://www.comet.com/opik/api/"
+        if not v.startswith(("https://", "http://")):
+            raise ValueError("url must start with https:// or http://")
+        if not v.endswith("/api/"):
+            raise ValueError("url should ends with /api/")
+
+        return v
+
+
 OPS_FILE_PATH = "ops_trace/"
 OPS_TRACE_FAILED_KEY = "FAILED_OPS_TRACE"

api/core/ops/opik_trace/opik_trace.py

@@ -0,0 +1,469 @@
+import json
+import logging
+import os
+import uuid
+from datetime import datetime, timedelta
+from typing import Optional, cast
+
+from opik import Opik, Trace
+from opik.id_helpers import uuid4_to_uuid7
+
+from core.ops.base_trace_instance import BaseTraceInstance
+from core.ops.entities.config_entity import OpikConfig
+from core.ops.entities.trace_entity import (
+    BaseTraceInfo,
+    DatasetRetrievalTraceInfo,
+    GenerateNameTraceInfo,
+    MessageTraceInfo,
+    ModerationTraceInfo,
+    SuggestedQuestionTraceInfo,
+    ToolTraceInfo,
+    TraceTaskName,
+    WorkflowTraceInfo,
+)
+from extensions.ext_database import db
+from models.model import EndUser, MessageFile
+from models.workflow import WorkflowNodeExecution
+
+logger = logging.getLogger(__name__)
+
+
+def wrap_dict(key_name, data):
+    """Make sure that the input data is a dict"""
+    if not isinstance(data, dict):
+        return {key_name: data}
+
+    return data
+
+
+def wrap_metadata(metadata, **kwargs):
+    """Add common metatada to all Traces and Spans"""
+    metadata["created_from"] = "dify"
+
+    metadata.update(kwargs)
+
+    return metadata
+
+
+def prepare_opik_uuid(user_datetime: Optional[datetime], user_uuid: Optional[str]):
+    """Opik needs UUIDv7 while Dify uses UUIDv4 for identifier of most
+    messages and objects. The type-hints of BaseTraceInfo indicates that
+    objects start_time and message_id could be null which means we cannot map
+    it to a UUIDv7. Given that we have no way to identify that object
+    uniquely, generate a new random one UUIDv7 in that case.
+    """
+
+    if user_datetime is None:
+        user_datetime = datetime.now()
+
+    if user_uuid is None:
+        user_uuid = str(uuid.uuid4())
+
+    return uuid4_to_uuid7(user_datetime, user_uuid)
+
+
+class OpikDataTrace(BaseTraceInstance):
+    def __init__(
+        self,
+        opik_config: OpikConfig,
+    ):
+        super().__init__(opik_config)
+        self.opik_client = Opik(
+            project_name=opik_config.project,
+            workspace=opik_config.workspace,
+            host=opik_config.url,
+            api_key=opik_config.api_key,
+        )
+        self.project = opik_config.project
+        self.file_base_url = os.getenv("FILES_URL", "http://127.0.0.1:5001")
+
+    def trace(self, trace_info: BaseTraceInfo):
+        if isinstance(trace_info, WorkflowTraceInfo):
+            self.workflow_trace(trace_info)
+        if isinstance(trace_info, MessageTraceInfo):
+            self.message_trace(trace_info)
+        if isinstance(trace_info, ModerationTraceInfo):
+            self.moderation_trace(trace_info)
+        if isinstance(trace_info, SuggestedQuestionTraceInfo):
+            self.suggested_question_trace(trace_info)
+        if isinstance(trace_info, DatasetRetrievalTraceInfo):
+            self.dataset_retrieval_trace(trace_info)
+        if isinstance(trace_info, ToolTraceInfo):
+            self.tool_trace(trace_info)
+        if isinstance(trace_info, GenerateNameTraceInfo):
+            self.generate_name_trace(trace_info)
+
+    def workflow_trace(self, trace_info: WorkflowTraceInfo):
+        dify_trace_id = trace_info.workflow_run_id
+        opik_trace_id = prepare_opik_uuid(trace_info.start_time, dify_trace_id)
+        workflow_metadata = wrap_metadata(
+            trace_info.metadata, message_id=trace_info.message_id, workflow_app_log_id=trace_info.workflow_app_log_id
+        )
+        root_span_id = None
+
+        if trace_info.message_id:
+            dify_trace_id = trace_info.message_id
+            opik_trace_id = prepare_opik_uuid(trace_info.start_time, dify_trace_id)
+
+            trace_data = {
+                "id": opik_trace_id,
+                "name": TraceTaskName.MESSAGE_TRACE.value,
+                "start_time": trace_info.start_time,
+                "end_time": trace_info.end_time,
+                "metadata": workflow_metadata,
+                "input": wrap_dict("input", trace_info.workflow_run_inputs),
+                "output": wrap_dict("output", trace_info.workflow_run_outputs),
+                "tags": ["message", "workflow"],
+                "project_name": self.project,
+            }
+            self.add_trace(trace_data)
+
+            root_span_id = prepare_opik_uuid(trace_info.start_time, trace_info.workflow_run_id)
+            span_data = {
+                "id": root_span_id,
+                "parent_span_id": None,
+                "trace_id": opik_trace_id,
+                "name": TraceTaskName.WORKFLOW_TRACE.value,
+                "input": wrap_dict("input", trace_info.workflow_run_inputs),
+                "output": wrap_dict("output", trace_info.workflow_run_outputs),
+                "start_time": trace_info.start_time,
+                "end_time": trace_info.end_time,
+                "metadata": workflow_metadata,
+                "tags": ["workflow"],
+                "project_name": self.project,
+            }
+            self.add_span(span_data)
+        else:
+            trace_data = {
+                "id": opik_trace_id,
+                "name": TraceTaskName.MESSAGE_TRACE.value,
+                "start_time": trace_info.start_time,
+                "end_time": trace_info.end_time,
+                "metadata": workflow_metadata,
+                "input": wrap_dict("input", trace_info.workflow_run_inputs),
+                "output": wrap_dict("output", trace_info.workflow_run_outputs),
+                "tags": ["workflow"],
+                "project_name": self.project,
+            }
+            self.add_trace(trace_data)
+
+        # through workflow_run_id get all_nodes_execution
+        workflow_nodes_execution_id_records = (
+            db.session.query(WorkflowNodeExecution.id)
+            .filter(WorkflowNodeExecution.workflow_run_id == trace_info.workflow_run_id)
+            .all()
+        )
+
+        for node_execution_id_record in workflow_nodes_execution_id_records:
+            node_execution = (
+                db.session.query(
+                    WorkflowNodeExecution.id,
+                    WorkflowNodeExecution.tenant_id,
+                    WorkflowNodeExecution.app_id,
+                    WorkflowNodeExecution.title,
+                    WorkflowNodeExecution.node_type,
+                    WorkflowNodeExecution.status,
+                    WorkflowNodeExecution.inputs,
+                    WorkflowNodeExecution.outputs,
+                    WorkflowNodeExecution.created_at,
+                    WorkflowNodeExecution.elapsed_time,
+                    WorkflowNodeExecution.process_data,
+                    WorkflowNodeExecution.execution_metadata,
+                )
+                .filter(WorkflowNodeExecution.id == node_execution_id_record.id)
+                .first()
+            )
+
+            if not node_execution:
+                continue
+
+            node_execution_id = node_execution.id
+            tenant_id = node_execution.tenant_id
+            app_id = node_execution.app_id
+            node_name = node_execution.title
+            node_type = node_execution.node_type
+            status = node_execution.status
+            if node_type == "llm":
+                inputs = (
+                    json.loads(node_execution.process_data).get("prompts", {}) if node_execution.process_data else {}
+                )
+            else:
+                inputs = json.loads(node_execution.inputs) if node_execution.inputs else {}
+            outputs = json.loads(node_execution.outputs) if node_execution.outputs else {}
+            created_at = node_execution.created_at or datetime.now()
+            elapsed_time = node_execution.elapsed_time
+            finished_at = created_at + timedelta(seconds=elapsed_time)
+
+            execution_metadata = (
+                json.loads(node_execution.execution_metadata) if node_execution.execution_metadata else {}
+            )
+            metadata = execution_metadata.copy()
+            metadata.update(
+                {
+                    "workflow_run_id": trace_info.workflow_run_id,
+                    "node_execution_id": node_execution_id,
+                    "tenant_id": tenant_id,
+                    "app_id": app_id,
+                    "app_name": node_name,
+                    "node_type": node_type,
+                    "status": status,
+                }
+            )
+
+            process_data = json.loads(node_execution.process_data) if node_execution.process_data else {}
+
+            provider = None
+            model = None
+            total_tokens = 0
+            completion_tokens = 0
+            prompt_tokens = 0
+
+            if process_data and process_data.get("model_mode") == "chat":
+                run_type = "llm"
+                provider = process_data.get("model_provider", None)
+                model = process_data.get("model_name", "")
+                metadata.update(
+                    {
+                        "ls_provider": provider,
+                        "ls_model_name": model,
+                    }
+                )
+
+                try:
+                    if outputs.get("usage"):
+                        total_tokens = outputs["usage"].get("total_tokens", 0)
+                        prompt_tokens = outputs["usage"].get("prompt_tokens", 0)
+                        completion_tokens = outputs["usage"].get("completion_tokens", 0)
+                except Exception:
+                    logger.error("Failed to extract usage", exc_info=True)
+
+            else:
+                run_type = "tool"
+
+            parent_span_id = trace_info.workflow_app_log_id or trace_info.workflow_run_id
+
+            if not total_tokens:
+                total_tokens = execution_metadata.get("total_tokens", 0)
+
+            span_data = {
+                "trace_id": opik_trace_id,
+                "id": prepare_opik_uuid(created_at, node_execution_id),
+                "parent_span_id": prepare_opik_uuid(trace_info.start_time, parent_span_id),
+                "name": node_type,
+                "type": run_type,
+                "start_time": created_at,
+                "end_time": finished_at,
+                "metadata": wrap_metadata(metadata),
+                "input": wrap_dict("input", inputs),
+                "output": wrap_dict("output", outputs),
+                "tags": ["node_execution"],
+                "project_name": self.project,
+                "usage": {
+                    "total_tokens": total_tokens,
+                    "completion_tokens": completion_tokens,
+                    "prompt_tokens": prompt_tokens,
+                },
+                "model": model,
+                "provider": provider,
+            }
+
+            self.add_span(span_data)
+
+    def message_trace(self, trace_info: MessageTraceInfo):
+        # get message file data
+        file_list = cast(list[str], trace_info.file_list) or []
+        message_file_data: Optional[MessageFile] = trace_info.message_file_data
+
+        if message_file_data is not None:
+            file_url = f"{self.file_base_url}/{message_file_data.url}" if message_file_data else ""
+            file_list.append(file_url)
+
+        message_data = trace_info.message_data
+        if message_data is None:
+            return
+
+        metadata = trace_info.metadata
+        message_id = trace_info.message_id
+
+        user_id = message_data.from_account_id
+        metadata["user_id"] = user_id
+        metadata["file_list"] = file_list
+
+        if message_data.from_end_user_id:
+            end_user_data: Optional[EndUser] = (
+                db.session.query(EndUser).filter(EndUser.id == message_data.from_end_user_id).first()
+            )
+            if end_user_data is not None:
+                end_user_id = end_user_data.session_id
+                metadata["end_user_id"] = end_user_id
+
+        trace_data = {
+            "id": prepare_opik_uuid(trace_info.start_time, message_id),
+            "name": TraceTaskName.MESSAGE_TRACE.value,
+            "start_time": trace_info.start_time,
+            "end_time": trace_info.end_time,
+            "metadata": wrap_metadata(metadata),
+            "input": trace_info.inputs,
+            "output": message_data.answer,
+            "tags": ["message", str(trace_info.conversation_mode)],
+            "project_name": self.project,
+        }
+        trace = self.add_trace(trace_data)
+
+        span_data = {
+            "trace_id": trace.id,
+            "name": "llm",
+            "type": "llm",
+            "start_time": trace_info.start_time,
+            "end_time": trace_info.end_time,
+            "metadata": wrap_metadata(metadata),
+            "input": {"input": trace_info.inputs},
+            "output": {"output": message_data.answer},
+            "tags": ["llm", str(trace_info.conversation_mode)],
+            "usage": {
+                "completion_tokens": trace_info.answer_tokens,
+                "prompt_tokens": trace_info.message_tokens,
+                "total_tokens": trace_info.total_tokens,
+            },
+            "project_name": self.project,
+        }
+        self.add_span(span_data)
+
+    def moderation_trace(self, trace_info: ModerationTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        start_time = trace_info.start_time or trace_info.message_data.created_at
+
+        span_data = {
+            "trace_id": prepare_opik_uuid(start_time, trace_info.message_id),
+            "name": TraceTaskName.MODERATION_TRACE.value,
+            "type": "tool",
+            "start_time": start_time,
+            "end_time": trace_info.end_time or trace_info.message_data.updated_at,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": wrap_dict("input", trace_info.inputs),
+            "output": {
+                "action": trace_info.action,
+                "flagged": trace_info.flagged,
+                "preset_response": trace_info.preset_response,
+                "inputs": trace_info.inputs,
+            },
+            "tags": ["moderation"],
+        }
+
+        self.add_span(span_data)
+
+    def suggested_question_trace(self, trace_info: SuggestedQuestionTraceInfo):
+        message_data = trace_info.message_data
+        if message_data is None:
+            return
+
+        start_time = trace_info.start_time or message_data.created_at
+
+        span_data = {
+            "trace_id": prepare_opik_uuid(start_time, trace_info.message_id),
+            "name": TraceTaskName.SUGGESTED_QUESTION_TRACE.value,
+            "type": "tool",
+            "start_time": start_time,
+            "end_time": trace_info.end_time or message_data.updated_at,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": wrap_dict("input", trace_info.inputs),
+            "output": wrap_dict("output", trace_info.suggested_question),
+            "tags": ["suggested_question"],
+        }
+
+        self.add_span(span_data)
+
+    def dataset_retrieval_trace(self, trace_info: DatasetRetrievalTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        start_time = trace_info.start_time or trace_info.message_data.created_at
+
+        span_data = {
+            "trace_id": prepare_opik_uuid(start_time, trace_info.message_id),
+            "name": TraceTaskName.DATASET_RETRIEVAL_TRACE.value,
+            "type": "tool",
+            "start_time": start_time,
+            "end_time": trace_info.end_time or trace_info.message_data.updated_at,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": wrap_dict("input", trace_info.inputs),
+            "output": {"documents": trace_info.documents},
+            "tags": ["dataset_retrieval"],
+        }
+
+        self.add_span(span_data)
+
+    def tool_trace(self, trace_info: ToolTraceInfo):
+        span_data = {
+            "trace_id": prepare_opik_uuid(trace_info.start_time, trace_info.message_id),
+            "name": trace_info.tool_name,
+            "type": "tool",
+            "start_time": trace_info.start_time,
+            "end_time": trace_info.end_time,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": wrap_dict("input", trace_info.tool_inputs),
+            "output": wrap_dict("output", trace_info.tool_outputs),
+            "tags": ["tool", trace_info.tool_name],
+        }
+
+        self.add_span(span_data)
+
+    def generate_name_trace(self, trace_info: GenerateNameTraceInfo):
+        trace_data = {
+            "id": prepare_opik_uuid(trace_info.start_time, trace_info.message_id),
+            "name": TraceTaskName.GENERATE_NAME_TRACE.value,
+            "start_time": trace_info.start_time,
+            "end_time": trace_info.end_time,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": trace_info.inputs,
+            "output": trace_info.outputs,
+            "tags": ["generate_name"],
+            "project_name": self.project,
+        }
+
+        trace = self.add_trace(trace_data)
+
+        span_data = {
+            "trace_id": trace.id,
+            "name": TraceTaskName.GENERATE_NAME_TRACE.value,
+            "start_time": trace_info.start_time,
+            "end_time": trace_info.end_time,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": wrap_dict("input", trace_info.inputs),
+            "output": wrap_dict("output", trace_info.outputs),
+            "tags": ["generate_name"],
+        }
+
+        self.add_span(span_data)
+
+    def add_trace(self, opik_trace_data: dict) -> Trace:
+        try:
+            trace = self.opik_client.trace(**opik_trace_data)
+            logger.debug("Opik Trace created successfully")
+            return trace
+        except Exception as e:
+            raise ValueError(f"Opik Failed to create trace: {str(e)}")
+
+    def add_span(self, opik_span_data: dict):
+        try:
+            self.opik_client.span(**opik_span_data)
+            logger.debug("Opik Span created successfully")
+        except Exception as e:
+            raise ValueError(f"Opik Failed to create span: {str(e)}")
+
+    def api_check(self):
+        try:
+            self.opik_client.auth_check()
+            return True
+        except Exception as e:
+            logger.info(f"Opik API check failed: {str(e)}", exc_info=True)
+            raise ValueError(f"Opik API check failed: {str(e)}")
+
+    def get_project_url(self):
+        try:
+            return self.opik_client.get_project_url(project_name=self.project)
+        except Exception as e:
+            logger.info(f"Opik get run url failed: {str(e)}", exc_info=True)
+            raise ValueError(f"Opik get run url failed: {str(e)}")

api/core/ops/ops_trace_manager.py

@@ -17,6 +17,7 @@ from core.ops.entities.config_entity import (
     OPS_FILE_PATH,
     LangfuseConfig,
     LangSmithConfig,
+    OpikConfig,
     TracingProviderEnum,
 )
 from core.ops.entities.trace_entity import (
@@ -32,6 +33,7 @@ from core.ops.entities.trace_entity import (
 )
 from core.ops.langfuse_trace.langfuse_trace import LangFuseDataTrace
 from core.ops.langsmith_trace.langsmith_trace import LangSmithDataTrace
+from core.ops.opik_trace.opik_trace import OpikDataTrace
 from core.ops.utils import get_message_data
 from extensions.ext_database import db
 from extensions.ext_storage import storage
@@ -52,6 +54,12 @@ provider_config_map: dict[str, dict[str, Any]] = {
         "other_keys": ["project", "endpoint"],
         "trace_instance": LangSmithDataTrace,
     },
+    TracingProviderEnum.OPIK.value: {
+        "config_class": OpikConfig,
+        "secret_keys": ["api_key"],
+        "other_keys": ["project", "url", "workspace"],
+        "trace_instance": OpikDataTrace,
+    },
 }
 
 

api/core/plugin/manager/base.py

@@ -30,7 +30,7 @@ from core.plugin.manager.exc import (
 )
 
 plugin_daemon_inner_api_baseurl = dify_config.PLUGIN_DAEMON_URL
-plugin_daemon_inner_api_key = dify_config.PLUGIN_API_KEY
+plugin_daemon_inner_api_key = dify_config.PLUGIN_DAEMON_KEY
 
 T = TypeVar("T", bound=(BaseModel | dict | list | bool | str))
 

api/core/plugin/manager/tool.py

@@ -48,8 +48,10 @@ class PluginToolManager(BasePluginManager):
         tool_provider_id = GenericProviderID(provider)
 
         def transformer(json_response: dict[str, Any]) -> dict:
-            for tool in json_response.get("data", {}).get("declaration", {}).get("tools", []):
-                tool["identity"]["provider"] = tool_provider_id.provider_name
+            data = json_response.get("data")
+            if data:
+                for tool in data.get("declaration", {}).get("tools", []):
+                    tool["identity"]["provider"] = tool_provider_id.provider_name
 
             return json_response
 

api/core/provider_manager.py

@@ -23,7 +23,12 @@ from core.helper import encrypter
 from core.helper.model_provider_cache import ProviderCredentialsCache, ProviderCredentialsCacheType
 from core.helper.position_helper import is_filtered
 from core.model_runtime.entities.model_entities import ModelType
-from core.model_runtime.entities.provider_entities import CredentialFormSchema, FormType, ProviderEntity
+from core.model_runtime.entities.provider_entities import (
+    ConfigurateMethod,
+    CredentialFormSchema,
+    FormType,
+    ProviderEntity,
+)
 from core.model_runtime.model_providers.model_provider_factory import ModelProviderFactory
 from extensions import ext_hosting_provider
 from extensions.ext_database import db
@@ -839,11 +844,18 @@ class ProviderManager:
         :return:
         """
         # Get provider model credential secret variables
-        model_credential_secret_variables = self._extract_secret_variables(
-            provider_entity.model_credential_schema.credential_form_schemas
-            if provider_entity.model_credential_schema
-            else []
-        )
+        if ConfigurateMethod.PREDEFINED_MODEL in provider_entity.configurate_methods:
+            model_credential_secret_variables = self._extract_secret_variables(
+                provider_entity.provider_credential_schema.credential_form_schemas
+                if provider_entity.provider_credential_schema
+                else []
+            )
+        else:
+            model_credential_secret_variables = self._extract_secret_variables(
+                provider_entity.model_credential_schema.credential_form_schemas
+                if provider_entity.model_credential_schema
+                else []
+            )
 
         model_settings: list[ModelSettings] = []
         if not provider_model_settings:

api/core/rag/datasource/vdb/lindorm/lindorm_vector.py

@@ -258,7 +258,7 @@ class LindormVectorStore(BaseVector):
             hnsw_ef_construction = kwargs.pop("hnsw_ef_construction", 500)
             ivfpq_m = kwargs.pop("ivfpq_m", dimension)
             nlist = kwargs.pop("nlist", 1000)
-            centroids_use_hnsw = kwargs.pop("centroids_use_hnsw", True if nlist >= 5000 else False)
+            centroids_use_hnsw = kwargs.pop("centroids_use_hnsw", nlist >= 5000)
             centroids_hnsw_m = kwargs.pop("centroids_hnsw_m", 24)
             centroids_hnsw_ef_construct = kwargs.pop("centroids_hnsw_ef_construct", 500)
             centroids_hnsw_ef_search = kwargs.pop("centroids_hnsw_ef_search", 100)
@@ -305,7 +305,7 @@ def default_text_mapping(dimension: int, method_name: str, **kwargs: Any) -> dic
     if method_name == "ivfpq":
         ivfpq_m = kwargs["ivfpq_m"]
         nlist = kwargs["nlist"]
-        centroids_use_hnsw = True if nlist > 10000 else False
+        centroids_use_hnsw = nlist > 10000
         centroids_hnsw_m = 24
         centroids_hnsw_ef_construct = 500
         centroids_hnsw_ef_search = 100

api/core/rag/datasource/vdb/pgvector/pgvector.py

@@ -57,6 +57,11 @@ CREATE TABLE IF NOT EXISTS {table_name} (
 ) using heap;
 """
 
+SQL_CREATE_INDEX = """
+CREATE INDEX IF NOT EXISTS embedding_cosine_v1_idx ON {table_name} 
+USING hnsw (embedding vector_cosine_ops) WITH (m = 16, ef_construction = 64);
+"""
+
 
 class PGVector(BaseVector):
     def __init__(self, collection_name: str, config: PGVectorConfig):
@@ -205,7 +210,10 @@ class PGVector(BaseVector):
             with self._get_cursor() as cur:
                 cur.execute("CREATE EXTENSION IF NOT EXISTS vector")
                 cur.execute(SQL_CREATE_TABLE.format(table_name=self.table_name, dimension=dimension))
-                # TODO: create index https://github.com/pgvector/pgvector?tab=readme-ov-file#indexing
+                # PG hnsw index only support 2000 dimension or less
+                # ref: https://github.com/pgvector/pgvector?tab=readme-ov-file#indexing
+                if dimension <= 2000:
+                    cur.execute(SQL_CREATE_INDEX.format(table_name=self.table_name))
             redis_client.set(collection_exist_cache_key, 1, ex=3600)
 
 

api/core/rag/embedding/cached_embedding.py

@@ -74,7 +74,7 @@ class CacheEmbedding(Embeddings):
                             embedding_queue_embeddings.append(normalized_embedding)
                         except IntegrityError:
                             db.session.rollback()
-                        except Exception as e:
+                        except Exception:
                             logging.exception("Failed transform embedding")
                 cache_embeddings = []
                 try:

api/core/rag/extractor/firecrawl/firecrawl_app.py

@@ -31,7 +31,7 @@ class FirecrawlApp:
                     "markdown": data.get("markdown"),
                 }
             else:
-                raise Exception(f'Failed to scrape URL. Error: {response_data["error"]}')
+                raise Exception(f"Failed to scrape URL. Error: {response_data['error']}")
 
         elif response.status_code in {402, 409, 500}:
             error_message = response.json().get("error", "Unknown error occurred")

api/core/rag/extractor/notion_extractor.py

@@ -358,8 +358,7 @@ class NotionExtractor(BaseExtractor):
 
         if not data_source_binding:
             raise Exception(
-                f"No notion data source binding found for tenant {tenant_id} "
-                f"and notion workspace {notion_workspace_id}"
+                f"No notion data source binding found for tenant {tenant_id} and notion workspace {notion_workspace_id}"
             )
 
         return cast(str, data_source_binding.access_token)

api/core/rag/index_processor/processor/qa_index_processor.py

@@ -112,7 +112,7 @@ class QAIndexProcessor(BaseIndexProcessor):
             df = pd.read_csv(file)
             text_docs = []
             for index, row in df.iterrows():
-                data = Document(page_content=row[0], metadata={"answer": row[1]})
+                data = Document(page_content=row.iloc[0], metadata={"answer": row.iloc[1]})
                 text_docs.append(data)
             if len(text_docs) == 0:
                 raise ValueError("The CSV file is empty.")

api/core/tools/custom_tool/tool.py

@@ -94,9 +94,9 @@ class ApiTool(Tool):
             if "api_key_header_prefix" in credentials:
                 api_key_header_prefix = credentials["api_key_header_prefix"]
                 if api_key_header_prefix == "basic" and credentials["api_key_value"]:
-                    credentials["api_key_value"] = f'Basic {credentials["api_key_value"]}'
+                    credentials["api_key_value"] = f"Basic {credentials['api_key_value']}"
                 elif api_key_header_prefix == "bearer" and credentials["api_key_value"]:
-                    credentials["api_key_value"] = f'Bearer {credentials["api_key_value"]}'
+                    credentials["api_key_value"] = f"Bearer {credentials['api_key_value']}"
                 elif api_key_header_prefix == "custom":
                     pass
 

api/core/tools/plugin_tool/provider.py

@@ -48,7 +48,9 @@ class PluginToolProviderController(BuiltinToolProviderController):
         """
         return tool with given name
         """
-        tool_entity = next(tool_entity for tool_entity in self.entity.tools if tool_entity.identity.name == tool_name)
+        tool_entity = next(
+            (tool_entity for tool_entity in self.entity.tools if tool_entity.identity.name == tool_name), None
+        )
 
         if not tool_entity:
             raise ValueError(f"Tool with name {tool_name} not found")

api/core/tools/utils/message_transformer.py

@@ -39,7 +39,7 @@ class ToolFileMessageTransformer:
                         conversation_id=conversation_id,
                     )
 
-                    url = f'/files/tools/{file.id}{guess_extension(file.mimetype) or ".png"}'
+                    url = f"/files/tools/{file.id}{guess_extension(file.mimetype) or '.png'}"
 
                     yield ToolInvokeMessage(
                         type=ToolInvokeMessage.MessageType.IMAGE_LINK,
@@ -115,4 +115,4 @@ class ToolFileMessageTransformer:
 
     @classmethod
     def get_tool_file_url(cls, tool_file_id: str, extension: Optional[str]) -> str:
-        return f'/files/tools/{tool_file_id}{extension or ".bin"}'
+        return f"/files/tools/{tool_file_id}{extension or '.bin'}"

api/core/tools/utils/parser.py

@@ -5,6 +5,7 @@ from json import loads as json_loads
 from json.decoder import JSONDecodeError
 from typing import Optional
 
+from flask import request
 from requests import get
 from yaml import YAMLError, safe_load  # type: ignore
 
@@ -29,6 +30,10 @@ class ApiBasedToolSchemaParser:
             raise ToolProviderNotFoundError("No server found in the openapi yaml.")
 
         server_url = openapi["servers"][0]["url"]
+        request_env = request.headers.get("X-Request-Env")
+        if request_env:
+            matched_servers = [server["url"] for server in openapi["servers"] if server["env"] == request_env]
+            server_url = matched_servers[0] if matched_servers else server_url
 
         # list all interfaces
         interfaces = []
@@ -112,7 +117,7 @@ class ApiBasedToolSchemaParser:
                                 llm_description=property.get("description", ""),
                                 default=property.get("default", None),
                                 placeholder=I18nObject(
-                                    en_US=parameter.get("description", ""), zh_Hans=parameter.get("description", "")
+                                    en_US=property.get("description", ""), zh_Hans=property.get("description", "")
                                 ),
                             )
 
@@ -144,7 +149,7 @@ class ApiBasedToolSchemaParser:
                 if not path:
                     path = str(uuid.uuid4())
 
-                interface["operation"]["operationId"] = f'{path}_{interface["method"]}'
+                interface["operation"]["operationId"] = f"{path}_{interface['method']}"
 
             bundles.append(
                 ApiToolBundle(

api/core/variables/segments.py

@@ -134,6 +134,10 @@ class ArrayStringSegment(ArraySegment):
     value_type: SegmentType = SegmentType.ARRAY_STRING
     value: Sequence[str]
 
+    @property
+    def text(self) -> str:
+        return json.dumps(self.value)
+
 
 class ArrayNumberSegment(ArraySegment):
     value_type: SegmentType = SegmentType.ARRAY_NUMBER

api/core/workflow/nodes/answer/base_stream_processor.py

@@ -1,6 +1,7 @@
 import logging
 from abc import ABC, abstractmethod
 from collections.abc import Generator
+from typing import Optional
 
 from core.workflow.entities.variable_pool import VariablePool
 from core.workflow.graph_engine.entities.event import GraphEngineEvent, NodeRunExceptionEvent, NodeRunSucceededEvent
@@ -48,25 +49,35 @@ class StreamProcessor(ABC):
                     # we remove the node maybe shortcut the answer node, so comment this code for now
                     # there is not effect on the answer node and the workflow, when we have a better solution
                     # we can open this code. Issues: #11542 #9560 #10638 #10564
-                    ids = self._fetch_node_ids_in_reachable_branch(edge.target_node_id)
-                    if "answer" in ids:
-                        continue
-                    else:
-                        reachable_node_ids.extend(ids)
+                    # ids = self._fetch_node_ids_in_reachable_branch(edge.target_node_id)
+                    # if "answer" in ids:
+                    #     continue
+                    # else:
+                    #     reachable_node_ids.extend(ids)
+
+                    # The branch_identify parameter is added to ensure that
+                    # only nodes in the correct logical branch are included.
+                    ids = self._fetch_node_ids_in_reachable_branch(edge.target_node_id, run_result.edge_source_handle)
+                    reachable_node_ids.extend(ids)
                 else:
                     unreachable_first_node_ids.append(edge.target_node_id)
 
             for node_id in unreachable_first_node_ids:
                 self._remove_node_ids_in_unreachable_branch(node_id, reachable_node_ids)
 
-    def _fetch_node_ids_in_reachable_branch(self, node_id: str) -> list[str]:
+    def _fetch_node_ids_in_reachable_branch(self, node_id: str, branch_identify: Optional[str] = None) -> list[str]:
         node_ids = []
         for edge in self.graph.edge_mapping.get(node_id, []):
             if edge.target_node_id == self.graph.root_node_id:
                 continue
 
+            # Only follow edges that match the branch_identify or have no run_condition
+            if edge.run_condition and edge.run_condition.branch_identify:
+                if not branch_identify or edge.run_condition.branch_identify != branch_identify:
+                    continue
+
             node_ids.append(edge.target_node_id)
-            node_ids.extend(self._fetch_node_ids_in_reachable_branch(edge.target_node_id))
+            node_ids.extend(self._fetch_node_ids_in_reachable_branch(edge.target_node_id, branch_identify))
         return node_ids
 
     def _remove_node_ids_in_unreachable_branch(self, node_id: str, reachable_node_ids: list[str]) -> None:

api/core/workflow/nodes/http_request/executor.py

@@ -253,9 +253,9 @@ class Executor:
         )
         if executor_response.size > threshold_size:
             raise ResponseSizeError(
-                f'{"File" if executor_response.is_file else "Text"} size is too large,'
-                f' max size is {threshold_size / 1024 / 1024:.2f} MB,'
-                f' but current size is {executor_response.readable_size}.'
+                f"{'File' if executor_response.is_file else 'Text'} size is too large,"
+                f" max size is {threshold_size / 1024 / 1024:.2f} MB,"
+                f" but current size is {executor_response.readable_size}."
             )
 
         return executor_response
@@ -338,7 +338,7 @@ class Executor:
                 if self.auth.config and self.auth.config.header:
                     authorization_header = self.auth.config.header
                 if k.lower() == authorization_header.lower():
-                    raw += f'{k}: {"*" * len(v)}\r\n'
+                    raw += f"{k}: {'*' * len(v)}\r\n"
                     continue
             raw += f"{k}: {v}\r\n"
 

api/core/workflow/nodes/variable_assigner/v2/node.py

@@ -1,4 +1,5 @@
 import json
+from collections.abc import Sequence
 from typing import Any, cast
 
 from core.variables import SegmentType, Variable
@@ -31,7 +32,7 @@ class VariableAssignerNode(BaseNode[VariableAssignerNodeData]):
         inputs = self.node_data.model_dump()
         process_data: dict[str, Any] = {}
         # NOTE: This node has no outputs
-        updated_variables: list[Variable] = []
+        updated_variable_selectors: list[Sequence[str]] = []
 
         try:
             for item in self.node_data.items:
@@ -98,7 +99,8 @@ class VariableAssignerNode(BaseNode[VariableAssignerNodeData]):
                     value=item.value,
                 )
                 variable = variable.model_copy(update={"value": updated_value})
-                updated_variables.append(variable)
+                self.graph_runtime_state.variable_pool.add(variable.selector, variable)
+                updated_variable_selectors.append(variable.selector)
         except VariableOperatorNodeError as e:
             return NodeRunResult(
                 status=WorkflowNodeExecutionStatus.FAILED,
@@ -107,9 +109,15 @@ class VariableAssignerNode(BaseNode[VariableAssignerNodeData]):
                 error=str(e),
             )
 
+        # The `updated_variable_selectors` is a list contains list[str] which not hashable,
+        # remove the duplicated items first.
+        updated_variable_selectors = list(set(map(tuple, updated_variable_selectors)))
+
         # Update variables
-        for variable in updated_variables:
-            self.graph_runtime_state.variable_pool.add(variable.selector, variable)
+        for selector in updated_variable_selectors:
+            variable = self.graph_runtime_state.variable_pool.get(selector)
+            if not isinstance(variable, Variable):
+                raise VariableNotFoundError(variable_selector=selector)
             process_data[variable.name] = variable.value
 
             if variable.selector[0] == CONVERSATION_VARIABLE_NODE_ID:

api/events/event_handlers/delete_tool_parameters_cache_when_sync_draft_workflow.py

@@ -26,7 +26,7 @@ def handle(sender, **kwargs):
                     tool_runtime=tool_runtime,
                     provider_name=tool_entity.provider_name,
                     provider_type=tool_entity.provider_type,
-                    identity_id=f'WORKFLOW.{app.id}.{node_data.get("id")}',
+                    identity_id=f"WORKFLOW.{app.id}.{node_data.get('id')}",
                 )
                 manager.delete_tool_parameters_cache()
             except:

api/extensions/storage/opendal_storage.py

@@ -34,7 +34,7 @@ class OpenDALStorage(BaseStorage):
             root = kwargs.get("root", "storage")
             Path(root).mkdir(parents=True, exist_ok=True)
 
-        self.op = opendal.Operator(scheme=scheme, **kwargs)
+        self.op = opendal.Operator(scheme=scheme, **kwargs)  # type: ignore
         logger.debug(f"opendal operator created with scheme {scheme}")
         retry_layer = opendal.layers.RetryLayer(max_times=3, factor=2.0, jitter=True)
         self.op = self.op.layer(retry_layer)

api/fields/member_fields.py

@@ -1,6 +1,6 @@
 from flask_restful import fields  # type: ignore
 
-from libs.helper import TimestampField
+from libs.helper import AvatarUrlField, TimestampField
 
 simple_account_fields = {"id": fields.String, "name": fields.String, "email": fields.String}
 
@@ -8,6 +8,7 @@ account_fields = {
     "id": fields.String,
     "name": fields.String,
     "avatar": fields.String,
+    "avatar_url": AvatarUrlField,
     "email": fields.String,
     "is_password_set": fields.Boolean,
     "interface_language": fields.String,
@@ -22,6 +23,7 @@ account_with_role_fields = {
     "id": fields.String,
     "name": fields.String,
     "avatar": fields.String,
+    "avatar_url": AvatarUrlField,
     "email": fields.String,
     "last_login_at": TimestampField,
     "last_active_at": TimestampField,

api/libs/helper.py

@@ -43,6 +43,18 @@ class AppIconUrlField(fields.Raw):
         return None
 
 
+class AvatarUrlField(fields.Raw):
+    def output(self, key, obj):
+        if obj is None:
+            return None
+
+        from models.account import Account
+
+        if isinstance(obj, Account) and obj.avatar is not None:
+            return file_helpers.get_signed_file_url(obj.avatar)
+        return None
+
+
 class TimestampField(fields.Raw):
     def format(self, value) -> int:
         return int(value.timestamp())

api/models/dataset.py

@@ -13,6 +13,7 @@ from typing import Any, cast
 
 from sqlalchemy import func
 from sqlalchemy.dialects.postgresql import JSONB
+from sqlalchemy.orm import Mapped
 
 from configs import dify_config
 from core.rag.retrieval.retrieval_methods import RetrievalMethod
@@ -515,7 +516,7 @@ class DocumentSegment(db.Model):  # type: ignore[name-defined]
     tenant_id = db.Column(StringUUID, nullable=False)
     dataset_id = db.Column(StringUUID, nullable=False)
     document_id = db.Column(StringUUID, nullable=False)
-    position = db.Column(db.Integer, nullable=False)
+    position: Mapped[int]
     content = db.Column(db.Text, nullable=False)
     answer = db.Column(db.Text, nullable=True)
     word_count = db.Column(db.Integer, nullable=False)
@@ -582,7 +583,7 @@ class DocumentSegment(db.Model):  # type: ignore[name-defined]
                 return []
         else:
             return []
-    
+
     @property
     def sign_content(self):
         return self.get_sign_content()
@@ -747,7 +748,7 @@ class DatasetKeywordTable(db.Model):  # type: ignore[name-defined]
                 if keyword_table_text:
                     return json.loads(keyword_table_text.decode("utf-8"), cls=SetDecoder)
                 return None
-            except Exception as e:
+            except Exception:
                 logging.exception(f"Failed to load keyword table from file: {file_key}")
                 return None
 

api/models/model.py

@@ -1486,9 +1486,8 @@ class ApiToken(Base):
     def generate_api_key(prefix, n):
         while True:
             result = prefix + generate_string(n)
-            while db.session.query(ApiToken).filter(ApiToken.token == result).count() > 0:
-                result = prefix + generate_string(n)
-
+            if db.session.query(ApiToken).filter(ApiToken.token == result).count() > 0:
+                continue
             return result
 
 

api/pyproject.toml

@@ -1,9 +1,10 @@
 [project]
 name = "dify-api"
 requires-python = ">=3.11,<3.13"
+dynamic = [ "dependencies" ]
 
 [build-system]
-requires = ["poetry-core"]
+requires = ["poetry-core>=2.0.0"]
 build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
@@ -48,6 +49,7 @@ numpy = "~1.26.4"
 oci = "~2.135.1"
 openai = "~1.52.0"
 openpyxl = "~3.1.5"
+opik = "~1.3.4"
 pandas = { version = "~2.2.2", extras = ["performance", "excel"] }
 pandas-stubs = "~2.2.3.241009"
 psycogreen = "~1.0.2"
@@ -157,4 +159,4 @@ pytest-mock = "~3.14.0"
 optional = true
 [tool.poetry.group.lint.dependencies]
 dotenv-linter = "~0.5.0"
-ruff = "~0.8.1"
+ruff = "~0.9.2"

api/pytest.ini

@@ -7,7 +7,7 @@ env =
     CODE_EXECUTION_API_KEY = dify-sandbox
     CODE_EXECUTION_ENDPOINT = http://127.0.0.1:8194
     CODE_MAX_STRING_LENGTH = 80000
-    PLUGIN_API_KEY=lYkiYYT6owG+71oLerGzA7GXCgOT++6ovaezWAjpCjf+Sjc3ZtU+qUEi
+    PLUGIN_DAEMON_KEY=lYkiYYT6owG+71oLerGzA7GXCgOT++6ovaezWAjpCjf+Sjc3ZtU+qUEi
     PLUGIN_DAEMON_URL=http://127.0.0.1:5002
     PLUGIN_MAX_PACKAGE_SIZE=15728640
     INNER_API_KEY_FOR_PLUGIN=QaHbTe77CtuXmsfyhR7+vRjI/+XbV1AaFy691iy+kGDv2Jvy0/eAh8Y1

api/services/annotation_service.py

@@ -286,7 +286,7 @@ class AppAnnotationService:
             df = pd.read_csv(file)
             result = []
             for index, row in df.iterrows():
-                content = {"question": row[0], "answer": row[1]}
+                content = {"question": row.iloc[0], "answer": row.iloc[1]}
                 result.append(content)
             if len(result) == 0:
                 raise ValueError("The CSV file is empty.")

api/services/app_dsl_service.py

@@ -1,7 +1,7 @@
 import logging
 import uuid
 from enum import StrEnum
-from typing import Optional, cast
+from typing import Optional
 from urllib.parse import urlparse
 from uuid import uuid4
 
@@ -159,15 +159,6 @@ class AppDslService:
                         status=ImportStatus.FAILED,
                         error="Empty content from url",
                     )
-
-                try:
-                    content = cast(bytes, content).decode("utf-8")
-                except UnicodeDecodeError as e:
-                    return Import(
-                        id=import_id,
-                        status=ImportStatus.FAILED,
-                        error=f"Error decoding content: {e}",
-                    )
             except Exception as e:
                 return Import(
                     id=import_id,

api/services/audio_service.py

@@ -82,7 +82,7 @@ class AudioService:
         from app import app
         from extensions.ext_database import db
 
-        def invoke_tts(text_content: str, app_model, voice: Optional[str] = None):
+        def invoke_tts(text_content: str, app_model: App, voice: Optional[str] = None):
             with app.app_context():
                 if app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}:
                     workflow = app_model.workflow
@@ -95,6 +95,8 @@ class AudioService:
 
                     voice = features_dict["text_to_speech"].get("voice") if voice is None else voice
                 else:
+                    if app_model.app_model_config is None:
+                        raise ValueError("AppModelConfig not found")
                     text_to_speech_dict = app_model.app_model_config.text_to_speech_dict
 
                     if not text_to_speech_dict.get("enabled"):

api/services/dataset_service.py

@@ -4,13 +4,16 @@ import logging
 import random
 import time
 import uuid
+from collections import Counter
 from typing import Any, Optional
 
 from flask_login import current_user  # type: ignore
 from sqlalchemy import func
+from sqlalchemy.orm import Session
 from werkzeug.exceptions import NotFound
 
 from configs import dify_config
+from core.entities import DEFAULT_PLUGIN_ID
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.model_manager import ModelManager
 from core.model_runtime.entities.model_entities import ModelType
@@ -71,7 +74,7 @@ from tasks.sync_website_document_indexing_task import sync_website_document_inde
 
 class DatasetService:
     @staticmethod
-    def get_datasets(page, per_page, tenant_id=None, user=None, search=None, tag_ids=None):
+    def get_datasets(page, per_page, tenant_id=None, user=None, search=None, tag_ids=None, include_all=False):
         query = Dataset.query.filter(Dataset.tenant_id == tenant_id).order_by(Dataset.created_at.desc())
 
         if user:
@@ -86,7 +89,7 @@ class DatasetService:
                 else:
                     return [], 0
             else:
-                if user.current_role != TenantAccountRole.OWNER:
+                if user.current_role != TenantAccountRole.OWNER or not include_all:
                     # show all datasets that the user has permission to access
                     if permitted_dataset_ids:
                         query = query.filter(
@@ -221,8 +224,7 @@ class DatasetService:
                 )
             except LLMBadRequestError:
                 raise ValueError(
-                    "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 ValueError(f"The dataset in unavailable, due to: {ex.description}")
@@ -267,7 +269,15 @@ class DatasetService:
             external_knowledge_api_id = data.get("external_knowledge_api_id", None)
             if not external_knowledge_api_id:
                 raise ValueError("External knowledge api id is required.")
-            external_knowledge_binding = ExternalKnowledgeBindings.query.filter_by(dataset_id=dataset_id).first()
+
+            with Session(db.engine) as session:
+                external_knowledge_binding = (
+                    session.query(ExternalKnowledgeBindings).filter_by(dataset_id=dataset_id).first()
+                )
+
+                if not external_knowledge_binding:
+                    raise ValueError("External knowledge binding not found.")
+
             if (
                 external_knowledge_binding.external_knowledge_id != external_knowledge_id
                 or external_knowledge_binding.external_knowledge_api_id != external_knowledge_api_id
@@ -315,8 +325,19 @@ class DatasetService:
                     except ProviderTokenNotInitError as ex:
                         raise ValueError(ex.description)
             else:
+                # add default plugin id to both setting sets, to make sure the plugin model provider is consistent
+                plugin_model_provider = dataset.embedding_model_provider
+                if "/" not in plugin_model_provider:
+                    plugin_model_provider = f"{DEFAULT_PLUGIN_ID}/{plugin_model_provider}/{plugin_model_provider}"
+
+                new_plugin_model_provider = data["embedding_model_provider"]
+                if "/" not in new_plugin_model_provider:
+                    new_plugin_model_provider = (
+                        f"{DEFAULT_PLUGIN_ID}/{new_plugin_model_provider}/{new_plugin_model_provider}"
+                    )
+
                 if (
-                    data["embedding_model_provider"] != dataset.embedding_model_provider
+                    new_plugin_model_provider != plugin_model_provider
                     or data["embedding_model"] != dataset.embedding_model
                 ):
                     action = "update"
@@ -859,7 +880,7 @@ class DocumentService:
                 position = DocumentService.get_documents_position(dataset.id)
                 document_ids = []
                 duplicate_document_ids = []
-                if knowledge_config.data_source.info_list.data_source_type == "upload_file":
+                if knowledge_config.data_source.info_list.data_source_type == "upload_file":  # type: ignore
                     upload_file_list = knowledge_config.data_source.info_list.file_info_list.file_ids  # type: ignore
                     for file_id in upload_file_list:
                         file = (
@@ -901,7 +922,7 @@ class DocumentService:
                         document = DocumentService.build_document(
                             dataset,
                             dataset_process_rule.id,  # type: ignore
-                            knowledge_config.data_source.info_list.data_source_type,
+                            knowledge_config.data_source.info_list.data_source_type,  # type: ignore
                             knowledge_config.doc_form,
                             knowledge_config.doc_language,
                             data_source_info,
@@ -916,8 +937,8 @@ class DocumentService:
                         document_ids.append(document.id)
                         documents.append(document)
                         position += 1
-                elif knowledge_config.data_source.info_list.data_source_type == "notion_import":
-                    notion_info_list = knowledge_config.data_source.info_list.notion_info_list
+                elif knowledge_config.data_source.info_list.data_source_type == "notion_import":  # type: ignore
+                    notion_info_list = knowledge_config.data_source.info_list.notion_info_list  # type: ignore
                     if not notion_info_list:
                         raise ValueError("No notion info list found.")
                     exist_page_ids = []
@@ -956,7 +977,7 @@ class DocumentService:
                                 document = DocumentService.build_document(
                                     dataset,
                                     dataset_process_rule.id,  # type: ignore
-                                    knowledge_config.data_source.info_list.data_source_type,
+                                    knowledge_config.data_source.info_list.data_source_type,  # type: ignore
                                     knowledge_config.doc_form,
                                     knowledge_config.doc_language,
                                     data_source_info,
@@ -976,8 +997,8 @@ class DocumentService:
                     # delete not selected documents
                     if len(exist_document) > 0:
                         clean_notion_document_task.delay(list(exist_document.values()), dataset.id)
-                elif knowledge_config.data_source.info_list.data_source_type == "website_crawl":
-                    website_info = knowledge_config.data_source.info_list.website_info_list
+                elif knowledge_config.data_source.info_list.data_source_type == "website_crawl":  # type: ignore
+                    website_info = knowledge_config.data_source.info_list.website_info_list  # type: ignore
                     if not website_info:
                         raise ValueError("No website info list found.")
                     urls = website_info.urls
@@ -996,7 +1017,7 @@ class DocumentService:
                         document = DocumentService.build_document(
                             dataset,
                             dataset_process_rule.id,  # type: ignore
-                            knowledge_config.data_source.info_list.data_source_type,
+                            knowledge_config.data_source.info_list.data_source_type,  # type: ignore
                             knowledge_config.doc_form,
                             knowledge_config.doc_language,
                             data_source_info,
@@ -1195,20 +1216,20 @@ class DocumentService:
 
         if features.billing.enabled:
             count = 0
-            if knowledge_config.data_source.info_list.data_source_type == "upload_file":
+            if knowledge_config.data_source.info_list.data_source_type == "upload_file":  # type: ignore
                 upload_file_list = (
-                    knowledge_config.data_source.info_list.file_info_list.file_ids
-                    if knowledge_config.data_source.info_list.file_info_list
+                    knowledge_config.data_source.info_list.file_info_list.file_ids  # type: ignore
+                    if knowledge_config.data_source.info_list.file_info_list  # type: ignore
                     else []
                 )
                 count = len(upload_file_list)
-            elif knowledge_config.data_source.info_list.data_source_type == "notion_import":
-                notion_info_list = knowledge_config.data_source.info_list.notion_info_list
+            elif knowledge_config.data_source.info_list.data_source_type == "notion_import":  # type: ignore
+                notion_info_list = knowledge_config.data_source.info_list.notion_info_list  # type: ignore
                 if notion_info_list:
                     for notion_info in notion_info_list:
                         count = count + len(notion_info.pages)
-            elif knowledge_config.data_source.info_list.data_source_type == "website_crawl":
-                website_info = knowledge_config.data_source.info_list.website_info_list
+            elif knowledge_config.data_source.info_list.data_source_type == "website_crawl":  # type: ignore
+                website_info = knowledge_config.data_source.info_list.website_info_list  # type: ignore
                 if website_info:
                     count = len(website_info.urls)
             batch_upload_limit = int(dify_config.BATCH_UPLOAD_LIMIT)
@@ -1239,7 +1260,7 @@ class DocumentService:
         dataset = Dataset(
             tenant_id=tenant_id,
             name="",
-            data_source_type=knowledge_config.data_source.info_list.data_source_type,
+            data_source_type=knowledge_config.data_source.info_list.data_source_type,  # type: ignore
             indexing_technique=knowledge_config.indexing_technique,
             created_by=account.id,
             embedding_model=knowledge_config.embedding_model,
@@ -1614,8 +1635,11 @@ class SegmentService:
                     segment.answer = args.answer
                     segment.word_count += len(args.answer) if args.answer else 0
                 word_count_change = segment.word_count - word_count_change
+                keyword_changed = False
                 if args.keywords:
-                    segment.keywords = args.keywords
+                    if Counter(segment.keywords) != Counter(args.keywords):
+                        segment.keywords = args.keywords
+                        keyword_changed = True
                 segment.enabled = True
                 segment.disabled_at = None
                 segment.disabled_by = None
@@ -1626,13 +1650,6 @@ class SegmentService:
                     document.word_count = max(0, document.word_count + word_count_change)
                     db.session.add(document)
                 # update segment index task
-                if args.enabled:
-                    VectorService.create_segments_vector(
-                        [args.keywords] if args.keywords else None,
-                        [segment],
-                        dataset,
-                        document.doc_form,
-                    )
                 if document.doc_form == IndexType.PARENT_CHILD_INDEX and args.regenerate_child_chunks:
                     # regenerate child chunks
                     # get embedding model instance
@@ -1665,6 +1682,14 @@ class SegmentService:
                     VectorService.generate_child_chunks(
                         segment, document, dataset, embedding_model_instance, processing_rule, True
                     )
+                elif document.doc_form in (IndexType.PARAGRAPH_INDEX, IndexType.QA_INDEX):
+                    if args.enabled or keyword_changed:
+                        VectorService.create_segments_vector(
+                            [args.keywords] if args.keywords else None,
+                            [segment],
+                            dataset,
+                            document.doc_form,
+                        )
             else:
                 segment_hash = helper.generate_text_hash(content)
                 tokens = 0

api/services/entities/knowledge_entities/knowledge_entities.py

@@ -97,7 +97,7 @@ class KnowledgeConfig(BaseModel):
     original_document_id: Optional[str] = None
     duplicate: bool = True
     indexing_technique: Literal["high_quality", "economy"]
-    data_source: DataSource
+    data_source: Optional[DataSource] = None
     process_rule: Optional[ProcessRule] = None
     retrieval_model: Optional[RetrievalModel] = None
     doc_form: str = "text_model"

api/services/external_knowledge_service.py

@@ -155,7 +155,7 @@ class ExternalDatasetService:
             if custom_parameters:
                 for parameter in custom_parameters:
                     if parameter.get("required", False) and not process_parameter.get(parameter.get("name")):
-                        raise ValueError(f'{parameter.get("name")} is required')
+                        raise ValueError(f"{parameter.get('name')} is required")
 
     @staticmethod
     def process_external_api(

api/services/ops_service.py

@@ -59,6 +59,15 @@ class OpsService:
             except Exception:
                 new_decrypt_tracing_config.update({"project_url": "https://smith.langchain.com/"})
 
+        if tracing_provider == "opik" and (
+            "project_url" not in decrypt_tracing_config or not decrypt_tracing_config.get("project_url")
+        ):
+            try:
+                project_url = OpsTraceManager.get_trace_config_project_url(decrypt_tracing_config, tracing_provider)
+                new_decrypt_tracing_config.update({"project_url": project_url})
+            except Exception:
+                new_decrypt_tracing_config.update({"project_url": "https://www.comet.com/opik/"})
+
         trace_config_data.tracing_config = new_decrypt_tracing_config
         return trace_config_data.to_dict()
 
@@ -92,7 +101,7 @@ class OpsService:
         if tracing_provider == "langfuse":
             project_key = OpsTraceManager.get_trace_config_project_key(tracing_config, tracing_provider)
             project_url = "{host}/project/{key}".format(host=tracing_config.get("host"), key=project_key)
-        elif tracing_provider == "langsmith":
+        elif tracing_provider in ("langsmith", "opik"):
             project_url = OpsTraceManager.get_trace_config_project_url(tracing_config, tracing_provider)
         else:
             project_url = None

api/tasks/batch_create_segment_to_index_task.py

@@ -5,7 +5,8 @@ import uuid
 
 import click
 from celery import shared_task  # type: ignore
-from sqlalchemy import func
+from sqlalchemy import func, select
+from sqlalchemy.orm import Session
 
 from core.model_manager import ModelManager
 from core.model_runtime.entities.model_entities import ModelType
@@ -18,7 +19,12 @@ from services.vector_service import VectorService
 
 @shared_task(queue="dataset")
 def batch_create_segment_to_index_task(
-    job_id: str, content: list, dataset_id: str, document_id: str, tenant_id: str, user_id: str
+    job_id: str,
+    content: list,
+    dataset_id: str,
+    document_id: str,
+    tenant_id: str,
+    user_id: str,
 ):
     """
     Async batch create segment to index
@@ -37,25 +43,35 @@ def batch_create_segment_to_index_task(
     indexing_cache_key = "segment_batch_import_{}".format(job_id)
 
     try:
-        dataset = db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
-        if not dataset:
-            raise ValueError("Dataset not exist.")
+        with Session(db.engine) as session:
+            dataset = session.get(Dataset, dataset_id)
+            if not dataset:
+                raise ValueError("Dataset not exist.")
 
-        dataset_document = db.session.query(Document).filter(Document.id == document_id).first()
-        if not dataset_document:
-            raise ValueError("Document not exist.")
+            dataset_document = session.get(Document, document_id)
+            if not dataset_document:
+                raise ValueError("Document not exist.")
 
-        if not dataset_document.enabled or dataset_document.archived or dataset_document.indexing_status != "completed":
-            raise ValueError("Document is not available.")
-        document_segments = []
-        embedding_model = None
-        if dataset.indexing_technique == "high_quality":
-            model_manager = ModelManager()
-            embedding_model = model_manager.get_model_instance(
-                tenant_id=dataset.tenant_id,
-                provider=dataset.embedding_model_provider,
-                model_type=ModelType.TEXT_EMBEDDING,
-                model=dataset.embedding_model,
+            if (
+                not dataset_document.enabled
+                or dataset_document.archived
+                or dataset_document.indexing_status != "completed"
+            ):
+                raise ValueError("Document is not available.")
+            document_segments = []
+            embedding_model = None
+            if dataset.indexing_technique == "high_quality":
+                model_manager = ModelManager()
+                embedding_model = model_manager.get_model_instance(
+                    tenant_id=dataset.tenant_id,
+                    provider=dataset.embedding_model_provider,
+                    model_type=ModelType.TEXT_EMBEDDING,
+                    model=dataset.embedding_model,
+                )
+            word_count_change = 0
+            segments_to_insert: list[str] = []
+            max_position_stmt = select(func.max(DocumentSegment.position)).where(
+                DocumentSegment.document_id == dataset_document.id
             )
         word_count_change = 0
         if embedding_model:
@@ -103,7 +119,10 @@ def batch_create_segment_to_index_task(
         redis_client.setex(indexing_cache_key, 600, "completed")
         end_at = time.perf_counter()
         logging.info(
-            click.style("Segment batch created job: {} latency: {}".format(job_id, end_at - start_at), fg="green")
+            click.style(
+                "Segment batch created job: {} latency: {}".format(job_id, end_at - start_at),
+                fg="green",
+            )
         )
     except Exception:
         logging.exception("Segments batch created index failed")

api/tests/artifact_tests/dependencies/test_dependencies_sorted.py

@@ -44,6 +44,6 @@ def test_duplicated_dependency_crossing_groups() -> None:
         dependency_names = list(dependencies.keys())
         all_dependency_names.extend(dependency_names)
     expected_all_dependency_names = set(all_dependency_names)
-    assert sorted(expected_all_dependency_names) == sorted(
-        all_dependency_names
-    ), "Duplicated dependencies crossing groups are found"
+    assert sorted(expected_all_dependency_names) == sorted(all_dependency_names), (
+        "Duplicated dependencies crossing groups are found"
+    )

api/tests/integration_tests/.env.example

@@ -85,7 +85,7 @@ VOLC_EMBEDDING_ENDPOINT_ID=
 ZHINAO_API_KEY=
 
 # Plugin configuration
-PLUGIN_API_KEY=
+PLUGIN_DAEMON_KEY=
 PLUGIN_DAEMON_URL=
 INNER_API_KEY=
 

api/tests/integration_tests/controllers/test_controllers.py

@@ -4,7 +4,6 @@ from app_fixture import mock_user  # type: ignore
 
 
 def test_post_requires_login(app):
-    with app.test_client() as client:
-        with patch("flask_login.utils._get_user", mock_user):
-            response = client.get("/console/api/data-source/integrates")
-            assert response.status_code == 200
+    with app.test_client() as client, patch("flask_login.utils._get_user", mock_user):
+        response = client.get("/console/api/data-source/integrates")
+        assert response.status_code == 200

api/tests/integration_tests/vdb/opensearch/test_opensearch.py

@@ -89,9 +89,9 @@ class TestOpenSearchVector:
         print("Actual document ID:", hits_by_vector[0].metadata["document_id"] if hits_by_vector else "No hits")
 
         assert len(hits_by_vector) > 0, f"Expected at least one hit, got {len(hits_by_vector)}"
-        assert (
-            hits_by_vector[0].metadata["document_id"] == self.example_doc_id
-        ), f"Expected document ID {self.example_doc_id}, got {hits_by_vector[0].metadata['document_id']}"
+        assert hits_by_vector[0].metadata["document_id"] == self.example_doc_id, (
+            f"Expected document ID {self.example_doc_id}, got {hits_by_vector[0].metadata['document_id']}"
+        )
 
     def test_get_ids_by_metadata_field(self):
         mock_response = {"hits": {"total": {"value": 1}, "hits": [{"_id": "mock_id"}]}}

api/tests/unit_tests/core/workflow/nodes/llm/test_node.py

@@ -434,11 +434,11 @@ def test_fetch_files_with_non_existent_variable(llm_node):
 #         jinja2_variables=[],
 #     )
 
-#     # Verify the result
-#     assert len(prompt_messages) == len(scenario.expected_messages), f"Scenario failed: {scenario.description}"
-#     assert (
-#         prompt_messages == scenario.expected_messages
-#     ), f"Message content mismatch in scenario: {scenario.description}"
+# # Verify the result
+# assert len(prompt_messages) == len(scenario.expected_messages), f"Scenario failed: {scenario.description}"
+# assert prompt_messages == scenario.expected_messages, (
+#     f"Message content mismatch in scenario: {scenario.description}"
+# )
 
 
 def test_handle_list_messages_basic(llm_node):

api/tests/unit_tests/services/workflow/test_workflow_converter.py

@@ -401,8 +401,7 @@ def test__convert_to_llm_node_for_workflow_advanced_completion_model(default_var
     prompt_template = PromptTemplateEntity(
         prompt_type=PromptTemplateEntity.PromptType.ADVANCED,
         advanced_completion_prompt_template=AdvancedCompletionPromptTemplateEntity(
-            prompt="You are a helpful assistant named {{name}}.\n\nContext:\n{{#context#}}\n\n"
-            "Human: hi\nAssistant: ",
+            prompt="You are a helpful assistant named {{name}}.\n\nContext:\n{{#context#}}\n\nHuman: hi\nAssistant: ",
             role_prefix=AdvancedCompletionPromptTemplateEntity.RolePrefixEntity(user="Human", assistant="Assistant"),
         ),
     )

dev/pytest/pytest_config_tests.py

@@ -20,8 +20,8 @@ BASE_API_AND_DOCKER_CONFIG_SET_DIFF = {
     "OCI_ENDPOINT",
     "OCI_REGION",
     "OCI_SECRET_KEY",
-    "PLUGIN_API_KEY",
-    "PLUGIN_API_URL",
+    "PLUGIN_DAEMON_KEY",
+    "PLUGIN_DAEMON_URL",
     "PLUGIN_REMOTE_INSTALL_HOST",
     "PLUGIN_REMOTE_INSTALL_PORT",
     "REDIS_DB",
@@ -66,8 +66,8 @@ BASE_API_AND_DOCKER_COMPOSE_CONFIG_SET_DIFF = {
     "PGVECTO_RS_PASSWORD",
     "PGVECTO_RS_PORT",
     "PGVECTO_RS_USER",
-    "PLUGIN_API_KEY",
-    "PLUGIN_API_URL",
+    "PLUGIN_DAEMON_KEY",
+    "PLUGIN_DAEMON_URL",
     "PLUGIN_REMOTE_INSTALL_HOST",
     "PLUGIN_REMOTE_INSTALL_PORT",
     "RESPECT_XFORWARD_HEADERS_ENABLED",

dev/reformat

@@ -9,10 +9,10 @@ if ! command -v ruff &> /dev/null || ! command -v dotenv-linter &> /dev/null; th
 fi
 
 # run ruff linter
-poetry run -C api ruff check --fix ./api
+poetry run -C api ruff check --fix ./
 
 # run ruff formatter
-poetry run -C api ruff format ./api
+poetry run -C api ruff format ./
 
 # run dotenv-linter linter
-poetry run -C api dotenv-linter ./api/.env.example ./web/.env.example
+poetry run -P api dotenv-linter ./api/.env.example ./web/.env.example

dev/sync-poetry

@@ -12,7 +12,7 @@ if [ $? -ne 0 ]; then
     # update poetry.lock
     # refreshing lockfile only without updating locked versions
     echo "poetry.lock is outdated, refreshing without updating locked versions ..."
-    poetry lock -C api --no-update
+    poetry lock -C api
 else
   echo "poetry.lock is ready."
 fi

docker-legacy/docker-compose.chroma.yaml

@@ -1,13 +0,0 @@
-services:
-  # Chroma vector store.
-  chroma:
-    image: ghcr.io/chroma-core/chroma:0.5.20
-    restart: always
-    volumes:
-      - ./volumes/chroma:/chroma/chroma
-    environment:
-      CHROMA_SERVER_AUTHN_CREDENTIALS: difyai123456
-      CHROMA_SERVER_AUTHN_PROVIDER: chromadb.auth.token_authn.TokenAuthenticationServerProvider
-      IS_PERSISTENT: TRUE
-    ports:
-      - "8000:8000"

docker-legacy/docker-compose.middleware.yaml

@@ -1,109 +0,0 @@
-version: '3'
-services:
-  # The postgres database.
-  db:
-    image: postgres:15-alpine
-    restart: always
-    environment:
-      # The password for the default postgres user.
-      POSTGRES_PASSWORD: difyai123456
-      # The name of the default postgres database.
-      POSTGRES_DB: dify
-      # postgres data directory
-      PGDATA: /var/lib/postgresql/data/pgdata
-    volumes:
-      - ./volumes/db/data:/var/lib/postgresql/data
-    ports:
-      - "5432:5432"
-
-  # The redis cache.
-  redis:
-    image: redis:6-alpine
-    restart: always
-    volumes:
-      # Mount the redis data directory to the container.
-      - ./volumes/redis/data:/data
-    # Set the redis password when startup redis server.
-    command: redis-server --requirepass difyai123456
-    ports:
-      - "6379:6379"
-
-  # The Weaviate vector store.
-  weaviate:
-    image: semitechnologies/weaviate:1.19.0
-    restart: always
-    volumes:
-      # Mount the Weaviate data directory to the container.
-      - ./volumes/weaviate:/var/lib/weaviate
-    environment:
-      # The Weaviate configurations
-      # You can refer to the [Weaviate](https://weaviate.io/developers/weaviate/config-refs/env-vars) documentation for more information.
-      QUERY_DEFAULTS_LIMIT: 25
-      AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: 'false'
-      PERSISTENCE_DATA_PATH: '/var/lib/weaviate'
-      DEFAULT_VECTORIZER_MODULE: 'none'
-      CLUSTER_HOSTNAME: 'node1'
-      AUTHENTICATION_APIKEY_ENABLED: 'true'
-      AUTHENTICATION_APIKEY_ALLOWED_KEYS: 'WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih'
-      AUTHENTICATION_APIKEY_USERS: 'hello@dify.ai'
-      AUTHORIZATION_ADMINLIST_ENABLED: 'true'
-      AUTHORIZATION_ADMINLIST_USERS: 'hello@dify.ai'
-    ports:
-      - "8080:8080"
-
-  # The DifySandbox
-  sandbox:
-    image: langgenius/dify-sandbox:0.2.1
-    restart: always
-    environment:
-      # The DifySandbox configurations
-      # Make sure you are changing this key for your deployment with a strong key.
-      # You can generate a strong key using `openssl rand -base64 42`.
-      API_KEY: dify-sandbox
-      GIN_MODE: 'release'
-      WORKER_TIMEOUT: 15
-      ENABLE_NETWORK: 'true'
-      HTTP_PROXY: 'http://ssrf_proxy:3128'
-      HTTPS_PROXY: 'http://ssrf_proxy:3128'
-      SANDBOX_PORT: 8194
-    volumes:
-      - ./volumes/sandbox/dependencies:/dependencies
-    networks:
-      - ssrf_proxy_network
-
-  # ssrf_proxy server
-  # for more information, please refer to
-  # https://docs.dify.ai/learn-more/faq/install-faq#id-18.-why-is-ssrf_proxy-needed
-  ssrf_proxy:
-    image: ubuntu/squid:latest
-    restart: always
-    ports:
-      - "3128:3128"
-      - "8194:8194"
-    volumes:
-      # pls clearly modify the squid.conf file to fit your network environment.
-      - ./volumes/ssrf_proxy/squid.conf:/etc/squid/squid.conf
-    networks:
-      - ssrf_proxy_network
-      - default
-  # Qdrant vector store.
-  # uncomment to use qdrant as vector store.
-  # (if uncommented, you need to comment out the weaviate service above,
-  # and set VECTOR_STORE to qdrant in the api & worker service.)
-  # qdrant:
-  #   image: qdrant/qdrant:1.7.3
-  #   restart: always
-  #   volumes:
-  #     - ./volumes/qdrant:/qdrant/storage
-  #   environment:
-  #     QDRANT_API_KEY: 'difyai123456'
-  #   ports:
-  #     - "6333:6333"
-  #     - "6334:6334"
-
-
-networks:
-  # create a network between sandbox, api and ssrf_proxy, and can not access outside.
-  ssrf_proxy_network:
-    driver: bridge
-    internal: true

docker-legacy/docker-compose.milvus.yaml

@@ -1,64 +0,0 @@
-version: '3.5'
-
-services:
-  etcd:
-    container_name: milvus-etcd
-    image: quay.io/coreos/etcd:v3.5.5
-    environment:
-      - ETCD_AUTO_COMPACTION_MODE=revision
-      - ETCD_AUTO_COMPACTION_RETENTION=1000
-      - ETCD_QUOTA_BACKEND_BYTES=4294967296
-      - ETCD_SNAPSHOT_COUNT=50000
-    volumes:
-      - ${DOCKER_VOLUME_DIRECTORY:-.}/volumes/etcd:/etcd
-    command: etcd -advertise-client-urls=http://127.0.0.1:2379 -listen-client-urls http://0.0.0.0:2379 --data-dir /etcd
-    healthcheck:
-      test: ["CMD", "etcdctl", "endpoint", "health"]
-      interval: 30s
-      timeout: 20s
-      retries: 3
-
-  minio:
-    container_name: milvus-minio
-    image: minio/minio:RELEASE.2023-03-20T20-16-18Z
-    environment:
-      MINIO_ACCESS_KEY: minioadmin
-      MINIO_SECRET_KEY: minioadmin
-    ports:
-      - "9001:9001"
-      - "9000:9000"
-    volumes:
-      - ${DOCKER_VOLUME_DIRECTORY:-.}/volumes/minio:/minio_data
-    command: minio server /minio_data --console-address ":9001"
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
-      interval: 30s
-      timeout: 20s
-      retries: 3
-
-  milvus-standalone:
-    container_name: milvus-standalone
-    image: milvusdb/milvus:v2.4.6
-    command: ["milvus", "run", "standalone"]
-    environment:
-      ETCD_ENDPOINTS: etcd:2379
-      MINIO_ADDRESS: minio:9000
-      common.security.authorizationEnabled: true
-    volumes:
-      - ${DOCKER_VOLUME_DIRECTORY:-.}/volumes/milvus:/var/lib/milvus
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:9091/healthz"]
-      interval: 30s
-      start_period: 90s
-      timeout: 20s
-      retries: 3
-    ports:
-      - "19530:19530"
-      - "9091:9091"
-    depends_on:
-      - "etcd"
-      - "minio"
-
-networks:
-  default:
-    name: milvus

docker-legacy/docker-compose.opensearch.yml

@@ -1,40 +0,0 @@
-services:
-  opensearch: # This is also the hostname of the container within the Docker network (i.e. https://opensearch/)
-    image: opensearchproject/opensearch:latest # Specifying the latest available image - modify if you want a specific version
-    container_name: opensearch
-    environment:
-      - discovery.type=single-node
-      - bootstrap.memory_lock=true # Disable JVM heap memory swapping
-      - "OPENSEARCH_JAVA_OPTS=-Xms512m -Xmx1024m" # Set min and max JVM heap sizes to at least 50% of system RAM
-      - OPENSEARCH_INITIAL_ADMIN_PASSWORD=Qazwsxedc!@#123    # Sets the demo admin user password when using demo configuration, required for OpenSearch 2.12 and later
-    ulimits:
-      memlock:
-        soft: -1 # Set memlock to unlimited (no soft or hard limit)
-        hard: -1
-      nofile:
-        soft: 65536 # Maximum number of open files for the opensearch user - set to at least 65536
-        hard: 65536
-    volumes:
-      - ./volumes/opensearch/data:/usr/share/opensearch/data # Creates volume called opensearch-data1 and mounts it to the container
-    ports:
-      - 9200:9200 # REST API
-      - 9600:9600 # Performance Analyzer
-    networks:
-      - opensearch-net # All of the containers will join the same Docker bridge network
-  opensearch-dashboards:
-    image: opensearchproject/opensearch-dashboards:latest # Make sure the version of opensearch-dashboards matches the version of opensearch installed on other nodes
-    container_name: opensearch-dashboards
-    ports:
-      - 5601:5601 # Map host port 5601 to container port 5601
-    expose:
-      - "5601" # Expose port 5601 for web access to OpenSearch Dashboards
-    environment:
-      OPENSEARCH_HOSTS: '["https://opensearch:9200"]' # Define the OpenSearch nodes that OpenSearch Dashboards will query
-    volumes:
-      - ./volumes/opensearch/opensearch_dashboards.yml:/usr/share/opensearch-dashboards/config/opensearch_dashboards.yml
-    networks:
-      - opensearch-net
-
-networks:
-  opensearch-net:
-    driver: bridge

docker-legacy/docker-compose.oracle.yaml

@@ -1,17 +0,0 @@
-services:
-  # oracle 23 ai vector store.
-  oracle:
-    image: container-registry.oracle.com/database/free:latest
-    restart: always
-    ports:
-      - 1521:1521
-    volumes:
-      - type: volume
-        source: oradata_vector
-        target: /opt/oracle/oradata
-      - ./startupscripts:/opt/oracle/scripts/startup
-    environment:
-      - ORACLE_PWD=Dify123456
-      - ORACLE_CHARACTERSET=AL32UTF8
-volumes:
-  oradata_vector:

docker-legacy/docker-compose.pgvecto-rs.yaml

@@ -1,23 +0,0 @@
-services:
-  # The pgvecto—rs database.
-  pgvecto-rs:
-    image: tensorchord/pgvecto-rs:pg16-v0.2.0
-    restart: always
-    environment:
-      PGUSER: postgres
-      # The password for the default postgres user.
-      POSTGRES_PASSWORD: difyai123456
-      # The name of the default postgres database.
-      POSTGRES_DB: dify
-      # postgres data directory
-      PGDATA: /var/lib/postgresql/data/pgdata
-    volumes:
-      - ./volumes/pgvectors/data:/var/lib/postgresql/data
-    # uncomment to expose db(postgresql) port to host
-    ports:
-      - "5431:5432"
-    healthcheck:
-      test: [ "CMD", "pg_isready" ]
-      interval: 1s
-      timeout: 3s
-      retries: 30

docker-legacy/docker-compose.pgvector.yaml

@@ -1,23 +0,0 @@
-services:
-  # Qdrant vector store.
-  pgvector:
-    image: pgvector/pgvector:pg16
-    restart: always
-    environment:
-      PGUSER: postgres
-      # The password for the default postgres user.
-      POSTGRES_PASSWORD: difyai123456
-      # The name of the default postgres database.
-      POSTGRES_DB: dify
-      # postgres data directory
-      PGDATA: /var/lib/postgresql/data/pgdata
-    volumes:
-      - ./volumes/pgvector/data:/var/lib/postgresql/data
-    # uncomment to expose db(postgresql) port to host
-    ports:
-      - "5433:5432"
-    healthcheck:
-      test: [ "CMD", "pg_isready" ]
-      interval: 1s
-      timeout: 3s
-      retries: 30

docker-legacy/docker-compose.qdrant.yaml

@@ -1,12 +0,0 @@
-services:
-  # Qdrant vector store.
-  qdrant:
-    image: langgenius/qdrant:v1.7.3
-    restart: always
-    volumes:
-      - ./volumes/qdrant:/qdrant/storage
-    environment:
-      QDRANT_API_KEY: 'difyai123456'
-    ports:
-      - "6333:6333"
-      - "6334:6334"

docker-legacy/docker-compose.yaml

@@ -1,597 +0,0 @@
-version: '3'
-services:
-  # API service
-  api:
-    image: langgenius/dify-api:1.0.0-beta.1
-    restart: always
-    environment:
-      # Startup mode, 'api' starts the API server.
-      MODE: api
-      # The log level for the application. Supported values are `DEBUG`, `INFO`, `WARNING`, `ERROR`, `CRITICAL`
-      LOG_LEVEL: INFO
-      # enable DEBUG mode to output more logs
-      # DEBUG : true
-      # A secret key that is used for securely signing the session cookie and encrypting sensitive information on the database. You can generate a strong key using `openssl rand -base64 42`.
-      SECRET_KEY: sk-9f73s3ljTXVcMT3Blb3ljTqtsKiGHXVcMT3BlbkFJLK7U
-      # The base URL of console application web frontend, refers to the Console base URL of WEB service if console domain is
-      # different from api or web app domain.
-      # example: http://cloud.dify.ai
-      CONSOLE_WEB_URL: ''
-      # Password for admin user initialization.
-      # If left unset, admin user will not be prompted for a password when creating the initial admin account.
-      INIT_PASSWORD: ''
-      # The base URL of console application api server, refers to the Console base URL of WEB service if console domain is
-      # different from api or web app domain.
-      # example: http://cloud.dify.ai
-      CONSOLE_API_URL: ''
-      # The URL prefix for Service API endpoints, refers to the base URL of the current API service if api domain is
-      # different from console domain.
-      # example: http://api.dify.ai
-      SERVICE_API_URL: ''
-      # The URL prefix for Web APP frontend, refers to the Web App base URL of WEB service if web app domain is different from
-      # console or api domain.
-      # example: http://udify.app
-      APP_WEB_URL: ''
-      # File preview or download Url prefix.
-      # used to display File preview or download Url to the front-end or as Multi-model inputs;
-      # Url is signed and has expiration time.
-      FILES_URL: ''
-      # File Access Time specifies a time interval in seconds for the file to be accessed.
-      # The default value is 300 seconds.
-      FILES_ACCESS_TIMEOUT: 300
-      # The maximum number of active requests for the application, where 0 means unlimited, should be a non-negative integer.
-      APP_MAX_ACTIVE_REQUESTS: 0
-      # When enabled, migrations will be executed prior to application startup and the application will start after the migrations have completed.
-      MIGRATION_ENABLED: 'true'
-      # The configurations of postgres database connection.
-      # It is consistent with the configuration in the 'db' service below.
-      DB_USERNAME: postgres
-      DB_PASSWORD: difyai123456
-      DB_HOST: db
-      DB_PORT: 5432
-      DB_DATABASE: dify
-      # The configurations of redis connection.
-      # It is consistent with the configuration in the 'redis' service below.
-      REDIS_HOST: redis
-      REDIS_PORT: 6379
-      REDIS_USERNAME: ''
-      REDIS_PASSWORD: difyai123456
-      REDIS_USE_SSL: 'false'
-      # use redis db 0 for redis cache
-      REDIS_DB: 0
-      # The configurations of celery broker.
-      # Use redis as the broker, and redis db 1 for celery broker.
-      CELERY_BROKER_URL: redis://:difyai123456@redis:6379/1
-      # Specifies the allowed origins for cross-origin requests to the Web API, e.g. https://dify.app or * for all origins.
-      WEB_API_CORS_ALLOW_ORIGINS: '*'
-      # Specifies the allowed origins for cross-origin requests to the console API, e.g. https://cloud.dify.ai or * for all origins.
-      CONSOLE_CORS_ALLOW_ORIGINS: '*'
-      # CSRF Cookie settings
-      # Controls whether a cookie is sent with cross-site requests,
-      # providing some protection against cross-site request forgery attacks
-      #
-      # Default: `SameSite=Lax, Secure=false, HttpOnly=true`
-      # This default configuration supports same-origin requests using either HTTP or HTTPS,
-      # but does not support cross-origin requests. It is suitable for local debugging purposes.
-      #
-      # If you want to enable cross-origin support,
-      # you must use the HTTPS protocol and set the configuration to `SameSite=None, Secure=true, HttpOnly=true`.
-      #
-      # The type of storage to use for storing user files. Supported values are `local` and `s3` and `azure-blob` and `google-storage`, Default: `local`
-      STORAGE_TYPE: local
-      # The path to the local storage directory, the directory relative the root path of API service codes or absolute path. Default: `storage` or `/home/john/storage`.
-      # only available when STORAGE_TYPE is `local`.
-      STORAGE_LOCAL_PATH: storage
-      # The S3 storage configurations, only available when STORAGE_TYPE is `s3`.
-      S3_USE_AWS_MANAGED_IAM: 'false'
-      S3_ENDPOINT: 'https://xxx.r2.cloudflarestorage.com'
-      S3_BUCKET_NAME: 'difyai'
-      S3_ACCESS_KEY: 'ak-difyai'
-      S3_SECRET_KEY: 'sk-difyai'
-      S3_REGION: 'us-east-1'
-      # The Azure Blob storage configurations, only available when STORAGE_TYPE is `azure-blob`.
-      AZURE_BLOB_ACCOUNT_NAME: 'difyai'
-      AZURE_BLOB_ACCOUNT_KEY: 'difyai'
-      AZURE_BLOB_CONTAINER_NAME: 'difyai-container'
-      AZURE_BLOB_ACCOUNT_URL: 'https://<your_account_name>.blob.core.windows.net'
-      # The Google storage configurations, only available when STORAGE_TYPE is `google-storage`.
-      GOOGLE_STORAGE_BUCKET_NAME: 'yout-bucket-name'
-      # if you want to use Application Default Credentials, you can leave GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64 empty.
-      GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64: 'your-google-service-account-json-base64-string'
-      # The Alibaba Cloud OSS configurations, only available when STORAGE_TYPE is `aliyun-oss`
-      ALIYUN_OSS_BUCKET_NAME: 'your-bucket-name'
-      ALIYUN_OSS_ACCESS_KEY: 'your-access-key'
-      ALIYUN_OSS_SECRET_KEY: 'your-secret-key'
-      ALIYUN_OSS_ENDPOINT: 'https://oss-ap-southeast-1-internal.aliyuncs.com'
-      ALIYUN_OSS_REGION: 'ap-southeast-1'
-      ALIYUN_OSS_AUTH_VERSION: 'v4'
-      # The Tencent COS storage configurations, only available when STORAGE_TYPE is `tencent-cos`.
-      TENCENT_COS_BUCKET_NAME: 'your-bucket-name'
-      TENCENT_COS_SECRET_KEY: 'your-secret-key'
-      TENCENT_COS_SECRET_ID: 'your-secret-id'
-      TENCENT_COS_REGION: 'your-region'
-      TENCENT_COS_SCHEME: 'your-scheme'
-      # The type of vector store to use. Supported values are `weaviate`, `qdrant`, `milvus`, `relyt`,`pgvector`, `chroma`, 'opensearch', 'tidb_vector'.
-      VECTOR_STORE: weaviate
-      # The Weaviate endpoint URL. Only available when VECTOR_STORE is `weaviate`.
-      WEAVIATE_ENDPOINT: http://weaviate:8080
-      # The Weaviate API key.
-      WEAVIATE_API_KEY: WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih
-      # The Qdrant endpoint URL. Only available when VECTOR_STORE is `qdrant`.
-      QDRANT_URL: http://qdrant:6333
-      # The Qdrant API key.
-      QDRANT_API_KEY: difyai123456
-      # The Qdrant client timeout setting.
-      QDRANT_CLIENT_TIMEOUT: 20
-      # The Qdrant client enable gRPC mode.
-      QDRANT_GRPC_ENABLED: 'false'
-      # The Qdrant server gRPC mode PORT.
-      QDRANT_GRPC_PORT: 6334
-      # Milvus configuration Only available when VECTOR_STORE is `milvus`.
-      # The milvus uri.
-      MILVUS_URI: http://127.0.0.1:19530
-      # The milvus token.
-      MILVUS_TOKEN: ''
-      # The milvus username.
-      MILVUS_USER: root
-      # The milvus password.
-      MILVUS_PASSWORD: Milvus
-      # relyt configurations
-      RELYT_HOST: db
-      RELYT_PORT: 5432
-      RELYT_USER: postgres
-      RELYT_PASSWORD: difyai123456
-      RELYT_DATABASE: postgres
-      # pgvector configurations
-      PGVECTOR_HOST: pgvector
-      PGVECTOR_PORT: 5432
-      PGVECTOR_USER: postgres
-      PGVECTOR_PASSWORD: difyai123456
-      PGVECTOR_DATABASE: dify
-      # tidb vector configurations
-      TIDB_VECTOR_HOST: tidb
-      TIDB_VECTOR_PORT: 4000
-      TIDB_VECTOR_USER: xxx.root
-      TIDB_VECTOR_PASSWORD: xxxxxx
-      TIDB_VECTOR_DATABASE: dify
-      # oracle configurations
-      ORACLE_HOST: oracle
-      ORACLE_PORT: 1521
-      ORACLE_USER: dify
-      ORACLE_PASSWORD: dify
-      ORACLE_DATABASE: FREEPDB1
-      # Chroma configuration
-      CHROMA_HOST: 127.0.0.1
-      CHROMA_PORT: 8000
-      CHROMA_TENANT: default_tenant
-      CHROMA_DATABASE: default_database
-      CHROMA_AUTH_PROVIDER: chromadb.auth.token_authn.TokenAuthClientProvider
-      CHROMA_AUTH_CREDENTIALS: xxxxxx
-      # ElasticSearch Config
-      ELASTICSEARCH_HOST: 127.0.0.1
-      ELASTICSEARCH_PORT: 9200
-      ELASTICSEARCH_USERNAME: elastic
-      ELASTICSEARCH_PASSWORD: elastic
-      # Mail configuration, support: resend, smtp
-      MAIL_TYPE: ''
-      # default send from email address, if not specified
-      MAIL_DEFAULT_SEND_FROM: 'YOUR EMAIL FROM (eg: no-reply <no-reply@dify.ai>)'
-      SMTP_SERVER: ''
-      SMTP_PORT: 465
-      SMTP_USERNAME: ''
-      SMTP_PASSWORD: ''
-      SMTP_USE_TLS: 'true'
-      SMTP_OPPORTUNISTIC_TLS: 'false'
-      # the api-key for resend (https://resend.com)
-      RESEND_API_KEY: ''
-      RESEND_API_URL: https://api.resend.com
-      # The DSN for Sentry error reporting. If not set, Sentry error reporting will be disabled.
-      SENTRY_DSN: ''
-      # The sample rate for Sentry events. Default: `1.0`
-      SENTRY_TRACES_SAMPLE_RATE: 1.0
-      # The sample rate for Sentry profiles. Default: `1.0`
-      SENTRY_PROFILES_SAMPLE_RATE: 1.0
-      # Notion import configuration, support public and internal
-      NOTION_INTEGRATION_TYPE: public
-      NOTION_CLIENT_SECRET: you-client-secret
-      NOTION_CLIENT_ID: you-client-id
-      NOTION_INTERNAL_SECRET: you-internal-secret
-      # The sandbox service endpoint.
-      CODE_EXECUTION_ENDPOINT: "http://sandbox:8194"
-      CODE_EXECUTION_API_KEY: dify-sandbox
-      CODE_MAX_NUMBER: 9223372036854775807
-      CODE_MIN_NUMBER: -9223372036854775808
-      CODE_MAX_STRING_LENGTH: 80000
-      TEMPLATE_TRANSFORM_MAX_LENGTH: 80000
-      CODE_MAX_STRING_ARRAY_LENGTH: 30
-      CODE_MAX_OBJECT_ARRAY_LENGTH: 30
-      CODE_MAX_NUMBER_ARRAY_LENGTH: 1000
-      # SSRF Proxy server
-      SSRF_PROXY_HTTP_URL: 'http://ssrf_proxy:3128'
-      SSRF_PROXY_HTTPS_URL: 'http://ssrf_proxy:3128'
-      # Indexing configuration
-      INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH: 4000
-    depends_on:
-      - db
-      - redis
-    volumes:
-      # Mount the storage directory to the container, for storing user files.
-      - ./volumes/app/storage:/app/api/storage
-    # uncomment to expose dify-api port to host
-    # ports:
-    #   - "5001:5001"
-    networks:
-      - ssrf_proxy_network
-      - default
-
-  # worker service
-  # The Celery worker for processing the queue.
-  worker:
-    image: langgenius/dify-api:1.0.0-beta.1
-    restart: always
-    environment:
-      CONSOLE_WEB_URL: ''
-      # Startup mode, 'worker' starts the Celery worker for processing the queue.
-      MODE: worker
-
-      # --- All the configurations below are the same as those in the 'api' service. ---
-
-      # The log level for the application. Supported values are `DEBUG`, `INFO`, `WARNING`, `ERROR`, `CRITICAL`
-      LOG_LEVEL: INFO
-      # A secret key that is used for securely signing the session cookie and encrypting sensitive information on the database. You can generate a strong key using `openssl rand -base64 42`.
-      # same as the API service
-      SECRET_KEY: sk-9f73s3ljTXVcMT3Blb3ljTqtsKiGHXVcMT3BlbkFJLK7U
-      # The configurations of postgres database connection.
-      # It is consistent with the configuration in the 'db' service below.
-      DB_USERNAME: postgres
-      DB_PASSWORD: difyai123456
-      DB_HOST: db
-      DB_PORT: 5432
-      DB_DATABASE: dify
-      # The configurations of redis cache connection.
-      REDIS_HOST: redis
-      REDIS_PORT: 6379
-      REDIS_USERNAME: ''
-      REDIS_PASSWORD: difyai123456
-      REDIS_DB: 0
-      REDIS_USE_SSL: 'false'
-      # The configurations of celery broker.
-      CELERY_BROKER_URL: redis://:difyai123456@redis:6379/1
-      # The type of storage to use for storing user files. Supported values are `local` and `s3` and `azure-blob` and `google-storage`, Default: `local`
-      STORAGE_TYPE: local
-      STORAGE_LOCAL_PATH: storage
-      # The S3 storage configurations, only available when STORAGE_TYPE is `s3`.
-      S3_USE_AWS_MANAGED_IAM: 'false'
-      S3_ENDPOINT: 'https://xxx.r2.cloudflarestorage.com'
-      S3_BUCKET_NAME: 'difyai'
-      S3_ACCESS_KEY: 'ak-difyai'
-      S3_SECRET_KEY: 'sk-difyai'
-      S3_REGION: 'us-east-1'
-      # The Azure Blob storage configurations, only available when STORAGE_TYPE is `azure-blob`.
-      AZURE_BLOB_ACCOUNT_NAME: 'difyai'
-      AZURE_BLOB_ACCOUNT_KEY: 'difyai'
-      AZURE_BLOB_CONTAINER_NAME: 'difyai-container'
-      AZURE_BLOB_ACCOUNT_URL: 'https://<your_account_name>.blob.core.windows.net'
-      # The Google storage configurations, only available when STORAGE_TYPE is `google-storage`.
-      GOOGLE_STORAGE_BUCKET_NAME: 'yout-bucket-name'
-      # if you want to use Application Default Credentials, you can leave GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64 empty.
-      GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64: 'your-google-service-account-json-base64-string'
-      # The Alibaba Cloud OSS configurations, only available when STORAGE_TYPE is `aliyun-oss`
-      ALIYUN_OSS_BUCKET_NAME: 'your-bucket-name'
-      ALIYUN_OSS_ACCESS_KEY: 'your-access-key'
-      ALIYUN_OSS_SECRET_KEY: 'your-secret-key'
-      ALIYUN_OSS_ENDPOINT: 'https://oss-ap-southeast-1-internal.aliyuncs.com'
-      ALIYUN_OSS_REGION: 'ap-southeast-1'
-      ALIYUN_OSS_AUTH_VERSION: 'v4'
-      # The Tencent COS storage configurations, only available when STORAGE_TYPE is `tencent-cos`.
-      TENCENT_COS_BUCKET_NAME: 'your-bucket-name'
-      TENCENT_COS_SECRET_KEY: 'your-secret-key'
-      TENCENT_COS_SECRET_ID: 'your-secret-id'
-      TENCENT_COS_REGION: 'your-region'
-      TENCENT_COS_SCHEME: 'your-scheme'
-      # The type of vector store to use. Supported values are `weaviate`, `qdrant`, `milvus`, `relyt`, `pgvector`, `chroma`, 'opensearch', 'tidb_vector'.
-      VECTOR_STORE: weaviate
-      # The Weaviate endpoint URL. Only available when VECTOR_STORE is `weaviate`.
-      WEAVIATE_ENDPOINT: http://weaviate:8080
-      # The Weaviate API key.
-      WEAVIATE_API_KEY: WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih
-      # The Qdrant endpoint URL. Only available when VECTOR_STORE is `qdrant`.
-      QDRANT_URL: http://qdrant:6333
-      # The Qdrant API key.
-      QDRANT_API_KEY: difyai123456
-      # The Qdrant client timeout setting.
-      QDRANT_CLIENT_TIMEOUT: 20
-      # The Qdrant client enable gRPC mode.
-      QDRANT_GRPC_ENABLED: 'false'
-      # The Qdrant server gRPC mode PORT.
-      QDRANT_GRPC_PORT: 6334
-      # Milvus configuration Only available when VECTOR_STORE is `milvus`.
-      # The milvus uri.
-      MILVUS_URI: http://127.0.0.1:19530
-      # The milvus token.
-      MILVUS_PORT: ''
-      # The milvus username.
-      MILVUS_USER: root
-      # The milvus password.
-      MILVUS_PASSWORD: Milvus
-      # Mail configuration, support: resend
-      MAIL_TYPE: ''
-      # default send from email address, if not specified
-      MAIL_DEFAULT_SEND_FROM: 'YOUR EMAIL FROM (eg: no-reply <no-reply@dify.ai>)'
-      SMTP_SERVER: ''
-      SMTP_PORT: 465
-      SMTP_USERNAME: ''
-      SMTP_PASSWORD: ''
-      SMTP_USE_TLS: 'true'
-      SMTP_OPPORTUNISTIC_TLS: 'false'
-      # the api-key for resend (https://resend.com)
-      RESEND_API_KEY: ''
-      RESEND_API_URL: https://api.resend.com
-      # relyt configurations
-      RELYT_HOST: db
-      RELYT_PORT: 5432
-      RELYT_USER: postgres
-      RELYT_PASSWORD: difyai123456
-      RELYT_DATABASE: postgres
-      # tencent configurations
-      TENCENT_VECTOR_DB_URL: http://127.0.0.1
-      TENCENT_VECTOR_DB_API_KEY: dify
-      TENCENT_VECTOR_DB_TIMEOUT: 30
-      TENCENT_VECTOR_DB_USERNAME: dify
-      TENCENT_VECTOR_DB_DATABASE: dify
-      TENCENT_VECTOR_DB_SHARD: 1
-      TENCENT_VECTOR_DB_REPLICAS: 2
-      # OpenSearch configuration
-      OPENSEARCH_HOST: 127.0.0.1
-      OPENSEARCH_PORT: 9200
-      OPENSEARCH_USER: admin
-      OPENSEARCH_PASSWORD: admin
-      OPENSEARCH_SECURE: 'true'
-      # pgvector configurations
-      PGVECTOR_HOST: pgvector
-      PGVECTOR_PORT: 5432
-      PGVECTOR_USER: postgres
-      PGVECTOR_PASSWORD: difyai123456
-      PGVECTOR_DATABASE: dify
-      # tidb vector configurations
-      TIDB_VECTOR_HOST: tidb
-      TIDB_VECTOR_PORT: 4000
-      TIDB_VECTOR_USER: xxx.root
-      TIDB_VECTOR_PASSWORD: xxxxxx
-      TIDB_VECTOR_DATABASE: dify
-      # oracle configurations
-      ORACLE_HOST: oracle
-      ORACLE_PORT: 1521
-      ORACLE_USER: dify
-      ORACLE_PASSWORD: dify
-      ORACLE_DATABASE: FREEPDB1
-      # Chroma configuration
-      CHROMA_HOST: 127.0.0.1
-      CHROMA_PORT: 8000
-      CHROMA_TENANT: default_tenant
-      CHROMA_DATABASE: default_database
-      CHROMA_AUTH_PROVIDER: chromadb.auth.token_authn.TokenAuthClientProvider
-      CHROMA_AUTH_CREDENTIALS: xxxxxx
-      # ElasticSearch Config
-      ELASTICSEARCH_HOST: 127.0.0.1
-      ELASTICSEARCH_PORT: 9200
-      ELASTICSEARCH_USERNAME: elastic
-      ELASTICSEARCH_PASSWORD: elastic
-      # Notion import configuration, support public and internal
-      NOTION_INTEGRATION_TYPE: public
-      NOTION_CLIENT_SECRET: you-client-secret
-      NOTION_CLIENT_ID: you-client-id
-      NOTION_INTERNAL_SECRET: you-internal-secret
-      # Indexing configuration
-      INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH: 1000
-      CREATE_TIDB_SERVICE_JOB_ENABLED: false
-    depends_on:
-      - db
-      - redis
-    volumes:
-      # Mount the storage directory to the container, for storing user files.
-      - ./volumes/app/storage:/app/api/storage
-    networks:
-      - ssrf_proxy_network
-      - default
-
-  # Frontend web application.
-  web:
-    image: langgenius/dify-web:1.0.0-beta.1
-    restart: always
-    environment:
-      # The base URL of console application api server, refers to the Console base URL of WEB service if console domain is
-      # different from api or web app domain.
-      # example: http://cloud.dify.ai
-      CONSOLE_API_URL: ''
-      # The URL for Web APP api server, refers to the Web App base URL of WEB service if web app domain is different from
-      # console or api domain.
-      # example: http://udify.app
-      APP_API_URL: ''
-      # The DSN for Sentry error reporting. If not set, Sentry error reporting will be disabled.
-      SENTRY_DSN: ''
-    # uncomment to expose dify-web port to host
-    # ports:
-    #   - "3000:3000"
-
-  # The postgres database.
-  db:
-    image: postgres:15-alpine
-    restart: always
-    environment:
-      PGUSER: postgres
-      # The password for the default postgres user.
-      POSTGRES_PASSWORD: difyai123456
-      # The name of the default postgres database.
-      POSTGRES_DB: dify
-      # postgres data directory
-      PGDATA: /var/lib/postgresql/data/pgdata
-    volumes:
-      - ./volumes/db/data:/var/lib/postgresql/data
-      # notice!: if you use windows-wsl2, postgres may not work properly due to the ntfs issue.you can use volumes to mount the data directory to the host.
-      # if you use the following config, you need to uncomment the volumes configuration below at the end of the file.
-      # - postgres:/var/lib/postgresql/data
-    # uncomment to expose db(postgresql) port to host
-    # ports:
-    #   - "5432:5432"
-    healthcheck:
-      test: [ "CMD", "pg_isready" ]
-      interval: 1s
-      timeout: 3s
-      retries: 30
-
-  # The redis cache.
-  redis:
-    image: redis:6-alpine
-    restart: always
-    volumes:
-      # Mount the redis data directory to the container.
-      - ./volumes/redis/data:/data
-    # Set the redis password when startup redis server.
-    command: redis-server --requirepass difyai123456
-    healthcheck:
-      test: [ "CMD", "redis-cli", "ping" ]
-    # uncomment to expose redis port to host
-    # ports:
-    #   - "6379:6379"
-
-  # The Weaviate vector store.
-  weaviate:
-    image: semitechnologies/weaviate:1.19.0
-    restart: always
-    volumes:
-      # Mount the Weaviate data directory to the container.
-      - ./volumes/weaviate:/var/lib/weaviate
-    environment:
-      # The Weaviate configurations
-      # You can refer to the [Weaviate](https://weaviate.io/developers/weaviate/config-refs/env-vars) documentation for more information.
-      QUERY_DEFAULTS_LIMIT: 25
-      AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: 'false'
-      PERSISTENCE_DATA_PATH: '/var/lib/weaviate'
-      DEFAULT_VECTORIZER_MODULE: 'none'
-      CLUSTER_HOSTNAME: 'node1'
-      AUTHENTICATION_APIKEY_ENABLED: 'true'
-      AUTHENTICATION_APIKEY_ALLOWED_KEYS: 'WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih'
-      AUTHENTICATION_APIKEY_USERS: 'hello@dify.ai'
-      AUTHORIZATION_ADMINLIST_ENABLED: 'true'
-      AUTHORIZATION_ADMINLIST_USERS: 'hello@dify.ai'
-    # uncomment to expose weaviate port to host
-    # ports:
-    #  - "8080:8080"
-
-  # The DifySandbox
-  sandbox:
-    image: langgenius/dify-sandbox:0.2.1
-    restart: always
-    environment:
-      # The DifySandbox configurations
-      # Make sure you are changing this key for your deployment with a strong key.
-      # You can generate a strong key using `openssl rand -base64 42`.
-      API_KEY: dify-sandbox
-      GIN_MODE: 'release'
-      WORKER_TIMEOUT: 15
-      ENABLE_NETWORK: 'true'
-      HTTP_PROXY: 'http://ssrf_proxy:3128'
-      HTTPS_PROXY: 'http://ssrf_proxy:3128'
-      SANDBOX_PORT: 8194
-    volumes:
-      - ./volumes/sandbox/dependencies:/dependencies
-    networks:
-      - ssrf_proxy_network
-
-  # ssrf_proxy server
-  # for more information, please refer to
-  # https://docs.dify.ai/learn-more/faq/install-faq#id-18.-why-is-ssrf_proxy-needed
-  ssrf_proxy:
-    image: ubuntu/squid:latest
-    restart: always
-    volumes:
-      # pls clearly modify the squid.conf file to fit your network environment.
-      - ./volumes/ssrf_proxy/squid.conf:/etc/squid/squid.conf
-    networks:
-      - ssrf_proxy_network
-      - default
-  # Qdrant vector store.
-  # uncomment to use qdrant as vector store.
-  # (if uncommented, you need to comment out the weaviate service above,
-  # and set VECTOR_STORE to qdrant in the api & worker service.)
-  # qdrant:
-  #   image: langgenius/qdrant:v1.7.3
-  #   restart: always
-  #   volumes:
-  #     - ./volumes/qdrant:/qdrant/storage
-  #   environment:
-  #     QDRANT_API_KEY: 'difyai123456'
-  #   # uncomment to expose qdrant port to host
-  #   # ports:
-  #   #  - "6333:6333"
-  #   #  - "6334:6334"
-
-  # The pgvector vector database.
-  # Uncomment to use qdrant as vector store.
-  # pgvector:
-  #   image: pgvector/pgvector:pg16
-  #   restart: always
-  #   environment:
-  #     PGUSER: postgres
-  #     # The password for the default postgres user.
-  #     POSTGRES_PASSWORD: difyai123456
-  #     # The name of the default postgres database.
-  #     POSTGRES_DB: dify
-  #     # postgres data directory
-  #     PGDATA: /var/lib/postgresql/data/pgdata
-  #   volumes:
-  #     - ./volumes/pgvector/data:/var/lib/postgresql/data
-  #   # uncomment to expose db(postgresql) port to host
-  #   # ports:
-  #   #   - "5433:5432"
-  #   healthcheck:
-  #     test: [ "CMD", "pg_isready" ]
-  #     interval: 1s
-  #     timeout: 3s
-  #     retries: 30
-
-  # The oracle vector database.
-  # Uncomment to use oracle23ai as vector store. Also need to Uncomment volumes block
-  # oracle:
-  #   image: container-registry.oracle.com/database/free:latest
-  #   restart: always
-  #   ports:
-  #     - 1521:1521
-  #   volumes:
-  #     - type: volume
-  #       source: oradata
-  #       target: /opt/oracle/oradata
-  #     - ./startupscripts:/opt/oracle/scripts/startup
-  #   environment:
-  #     - ORACLE_PWD=Dify123456
-  #     - ORACLE_CHARACTERSET=AL32UTF8
-
-
-  # The nginx reverse proxy.
-  # used for reverse proxying the API service and Web service.
-  nginx:
-    image: nginx:latest
-    restart: always
-    volumes:
-      - ./nginx/nginx.conf:/etc/nginx/nginx.conf
-      - ./nginx/proxy.conf:/etc/nginx/proxy.conf
-      - ./nginx/conf.d:/etc/nginx/conf.d
-      #- ./nginx/ssl:/etc/ssl
-    depends_on:
-      - api
-      - web
-    ports:
-      - "80:80"
-      #- "443:443"
-# notice: if you use windows-wsl2, postgres may not work properly due to the ntfs issue.you can use volumes to mount the data directory to the host.
-# volumes:
-#   postgres:
-networks:
-  # create a network between sandbox, api and ssrf_proxy, and can not access outside.
-  ssrf_proxy_network:
-    driver: bridge
-    internal: true
-
-#volumes:
-#  oradata:

docker-legacy/nginx/conf.d/default.conf

@@ -1,38 +0,0 @@
-server {
-    listen 80;
-    server_name _;
-
-    location /console/api {
-      proxy_pass http://api:5001;
-      include proxy.conf;
-    }
-
-    location /api {
-      proxy_pass http://api:5001;
-      include proxy.conf;
-    }
-
-    location /v1 {
-      proxy_pass http://api:5001;
-      include proxy.conf;
-    }
-
-    location /files {
-      proxy_pass http://api:5001;
-      include proxy.conf;
-    }
-
-    location / {
-      proxy_pass http://web:3000;
-      include proxy.conf;
-    }
-
-    # If you want to support HTTPS, please uncomment the code snippet below
-    #listen 443 ssl;
-    #ssl_certificate ./../ssl/your_cert_file.cer;
-    #ssl_certificate_key ./../ssl/your_cert_key.key;
-    #ssl_protocols TLSv1.1 TLSv1.2 TLSv1.3;
-    #ssl_prefer_server_ciphers on;
-    #ssl_session_cache shared:SSL:10m;
-    #ssl_session_timeout 10m;
-}

docker-legacy/nginx/nginx.conf

@@ -1,32 +0,0 @@
-user  nginx;
-worker_processes  auto;
-
-error_log  /var/log/nginx/error.log notice;
-pid        /var/run/nginx.pid;
-
-
-events {
-    worker_connections  1024;
-}
-
-
-http {
-    include       /etc/nginx/mime.types;
-    default_type  application/octet-stream;
-
-    log_format  main  '$remote_addr - $remote_user [$time_local] "$request" '
-                      '$status $body_bytes_sent "$http_referer" '
-                      '"$http_user_agent" "$http_x_forwarded_for"';
-
-    access_log  /var/log/nginx/access.log  main;
-
-    sendfile        on;
-    #tcp_nopush     on;
-
-    keepalive_timeout  65;
-
-    #gzip  on;
-    client_max_body_size 15M;
-
-    include /etc/nginx/conf.d/*.conf;
-}

docker-legacy/nginx/proxy.conf

@@ -1,8 +0,0 @@
-proxy_set_header Host $host;
-proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-proxy_set_header X-Forwarded-Proto $scheme;
-proxy_http_version 1.1;
-proxy_set_header Connection "";
-proxy_buffering off;
-proxy_read_timeout 3600s;
-proxy_send_timeout 3600s;

docker-legacy/nginx/ssl/.gitkeep

@@ -1 +0,0 @@
-

docker-legacy/startupscripts/create_user.sql

@@ -1,5 +0,0 @@
-show pdbs;
-ALTER SYSTEM SET PROCESSES=500 SCOPE=SPFILE; 
-alter session set container= freepdb1;
-create user dify identified by dify DEFAULT TABLESPACE users quota unlimited on users;
-grant DB_DEVELOPER_ROLE to dify;

docker-legacy/volumes/opensearch/opensearch_dashboards.yml

@@ -1,222 +0,0 @@
----
-# Copyright OpenSearch Contributors
-# SPDX-License-Identifier: Apache-2.0
-
-# Description:
-# Default configuration for OpenSearch Dashboards
-
-# OpenSearch Dashboards is served by a back end server. This setting specifies the port to use.
-# server.port: 5601
-
-# Specifies the address to which the OpenSearch Dashboards server will bind. IP addresses and host names are both valid values.
-# The default is 'localhost', which usually means remote machines will not be able to connect.
-# To allow connections from remote users, set this parameter to a non-loopback address.
-# server.host: "localhost"
-
-# Enables you to specify a path to mount OpenSearch Dashboards at if you are running behind a proxy.
-# Use the `server.rewriteBasePath` setting to tell OpenSearch Dashboards if it should remove the basePath
-# from requests it receives, and to prevent a deprecation warning at startup.
-# This setting cannot end in a slash.
-# server.basePath: ""
-
-# Specifies whether OpenSearch Dashboards should rewrite requests that are prefixed with
-# `server.basePath` or require that they are rewritten by your reverse proxy.
-# server.rewriteBasePath: false
-
-# The maximum payload size in bytes for incoming server requests.
-# server.maxPayloadBytes: 1048576
-
-# The OpenSearch Dashboards server's name.  This is used for display purposes.
-# server.name: "your-hostname"
-
-# The URLs of the OpenSearch instances to use for all your queries.
-# opensearch.hosts: ["http://localhost:9200"]
-
-# OpenSearch Dashboards uses an index in OpenSearch to store saved searches, visualizations and
-# dashboards. OpenSearch Dashboards creates a new index if the index doesn't already exist.
-# opensearchDashboards.index: ".opensearch_dashboards"
-
-# The default application to load.
-# opensearchDashboards.defaultAppId: "home"
-
-# Setting for an optimized healthcheck that only uses the local OpenSearch node to do Dashboards healthcheck.
-# This settings should be used for large clusters or for clusters with ingest heavy nodes.
-# It allows Dashboards to only healthcheck using the local OpenSearch node rather than fan out requests across all nodes.
-#
-# It requires the user to create an OpenSearch node attribute with the same name as the value used in the setting
-# This node attribute should assign all nodes of the same cluster an integer value that increments with each new cluster that is spun up
-# e.g. in opensearch.yml file you would set the value to a setting using node.attr.cluster_id:
-# Should only be enabled if there is a corresponding node attribute created in your OpenSearch config that matches the value here
-# opensearch.optimizedHealthcheckId: "cluster_id"
-
-# If your OpenSearch is protected with basic authentication, these settings provide
-# the username and password that the OpenSearch Dashboards server uses to perform maintenance on the OpenSearch Dashboards
-# index at startup. Your OpenSearch Dashboards users still need to authenticate with OpenSearch, which
-# is proxied through the OpenSearch Dashboards server.
-# opensearch.username: "opensearch_dashboards_system"
-# opensearch.password: "pass"
-
-# Enables SSL and paths to the PEM-format SSL certificate and SSL key files, respectively.
-# These settings enable SSL for outgoing requests from the OpenSearch Dashboards server to the browser.
-# server.ssl.enabled: false
-# server.ssl.certificate: /path/to/your/server.crt
-# server.ssl.key: /path/to/your/server.key
-
-# Optional settings that provide the paths to the PEM-format SSL certificate and key files.
-# These files are used to verify the identity of OpenSearch Dashboards to OpenSearch and are required when
-# xpack.security.http.ssl.client_authentication in OpenSearch is set to required.
-# opensearch.ssl.certificate: /path/to/your/client.crt
-# opensearch.ssl.key: /path/to/your/client.key
-
-# Optional setting that enables you to specify a path to the PEM file for the certificate
-# authority for your OpenSearch instance.
-# opensearch.ssl.certificateAuthorities: [ "/path/to/your/CA.pem" ]
-
-# To disregard the validity of SSL certificates, change this setting's value to 'none'.
-# opensearch.ssl.verificationMode: full
-
-# Time in milliseconds to wait for OpenSearch to respond to pings. Defaults to the value of
-# the opensearch.requestTimeout setting.
-# opensearch.pingTimeout: 1500
-
-# Time in milliseconds to wait for responses from the back end or OpenSearch. This value
-# must be a positive integer.
-# opensearch.requestTimeout: 30000
-
-# List of OpenSearch Dashboards client-side headers to send to OpenSearch. To send *no* client-side
-# headers, set this value to [] (an empty list).
-# opensearch.requestHeadersWhitelist: [ authorization ]
-
-# Header names and values that are sent to OpenSearch. Any custom headers cannot be overwritten
-# by client-side headers, regardless of the opensearch.requestHeadersWhitelist configuration.
-# opensearch.customHeaders: {}
-
-# Time in milliseconds for OpenSearch to wait for responses from shards. Set to 0 to disable.
-# opensearch.shardTimeout: 30000
-
-# Logs queries sent to OpenSearch. Requires logging.verbose set to true.
-# opensearch.logQueries: false
-
-# Specifies the path where OpenSearch Dashboards creates the process ID file.
-# pid.file: /var/run/opensearchDashboards.pid
-
-# Enables you to specify a file where OpenSearch Dashboards stores log output.
-# logging.dest: stdout
-
-# Set the value of this setting to true to suppress all logging output.
-# logging.silent: false
-
-# Set the value of this setting to true to suppress all logging output other than error messages.
-# logging.quiet: false
-
-# Set the value of this setting to true to log all events, including system usage information
-# and all requests.
-# logging.verbose: false
-
-# Set the interval in milliseconds to sample system and process performance
-# metrics. Minimum is 100ms. Defaults to 5000.
-# ops.interval: 5000
-
-# Specifies locale to be used for all localizable strings, dates and number formats.
-# Supported languages are the following: English - en , by default , Chinese - zh-CN .
-# i18n.locale: "en"
-
-# Set the allowlist to check input graphite Url. Allowlist is the default check list.
-# vis_type_timeline.graphiteAllowedUrls: ['https://www.hostedgraphite.com/UID/ACCESS_KEY/graphite']
-
-# Set the blocklist to check input graphite Url. Blocklist is an IP list.
-# Below is an example for reference
-# vis_type_timeline.graphiteBlockedIPs: [
-#  //Loopback
-#  '127.0.0.0/8',
-#  '::1/128',
-#  //Link-local Address for IPv6
-#  'fe80::/10',
-#  //Private IP address for IPv4
-#  '10.0.0.0/8',
-#  '172.16.0.0/12',
-#  '192.168.0.0/16',
-#  //Unique local address (ULA)
-#  'fc00::/7',
-#  //Reserved IP address
-#  '0.0.0.0/8',
-#  '100.64.0.0/10',
-#  '192.0.0.0/24',
-#  '192.0.2.0/24',
-#  '198.18.0.0/15',
-#  '192.88.99.0/24',
-#  '198.51.100.0/24',
-#  '203.0.113.0/24',
-#  '224.0.0.0/4',
-#  '240.0.0.0/4',
-#  '255.255.255.255/32',
-#  '::/128',
-#  '2001:db8::/32',
-#  'ff00::/8',
-# ]
-# vis_type_timeline.graphiteBlockedIPs: []
-
-# opensearchDashboards.branding:
-#   logo:
-#     defaultUrl: ""
-#     darkModeUrl: ""
-#   mark:
-#     defaultUrl: ""
-#     darkModeUrl: ""
-#   loadingLogo:
-#     defaultUrl: ""
-#     darkModeUrl: ""
-#   faviconUrl: ""
-#   applicationTitle: ""
-
-# Set the value of this setting to true to capture region blocked warnings and errors
-# for your map rendering services.
-# map.showRegionBlockedWarning: false%
-
-# Set the value of this setting to false to suppress search usage telemetry
-# for reducing the load of OpenSearch cluster.
-# data.search.usageTelemetry.enabled: false
-
-# 2.4 renames 'wizard.enabled: false' to 'vis_builder.enabled: false'
-# Set the value of this setting to false to disable VisBuilder
-# functionality in Visualization.
-# vis_builder.enabled: false
-
-# 2.4 New Experimental Feature
-# Set the value of this setting to true to enable the experimental multiple data source
-# support feature. Use with caution.
-# data_source.enabled: false
-# Set the value of these settings to customize crypto materials to encryption saved credentials
-# in data sources.
-# data_source.encryption.wrappingKeyName: 'changeme'
-# data_source.encryption.wrappingKeyNamespace: 'changeme'
-# data_source.encryption.wrappingKey: [0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
-
-# 2.6 New ML Commons Dashboards Feature
-# Set the value of this setting to true to enable the ml commons dashboards
-# ml_commons_dashboards.enabled: false
-
-# 2.12 New experimental Assistant Dashboards Feature
-# Set the value of this setting to true to enable the assistant dashboards
-# assistant.chat.enabled: false
-
-# 2.13 New Query Assistant Feature
-# Set the value of this setting to false to disable the query assistant
-# observability.query_assist.enabled: false
-
-# 2.14 Enable Ui Metric Collectors in Usage Collector
-# Set the value of this setting to true to enable UI Metric collections
-# usageCollection.uiMetric.enabled: false
-
-opensearch.hosts: [https://localhost:9200]
-opensearch.ssl.verificationMode: none
-opensearch.username: admin
-opensearch.password: 'Qazwsxedc!@#123'
-opensearch.requestHeadersWhitelist: [authorization, securitytenant]
-
-opensearch_security.multitenancy.enabled: true
-opensearch_security.multitenancy.tenants.preferred: [Private, Global]
-opensearch_security.readonly_mode.roles: [kibana_read_only]
-# Use this setting if you are running opensearch-dashboards without https
-opensearch_security.cookie.secure: false
-server.host: '0.0.0.0'