Merge branch 'langgenius:main' into main

.github/workflows/api-tests.yml

@@ -50,9 +50,18 @@ jobs:
       - name: Run ModelRuntime
         run: poetry run -C api bash dev/pytest/pytest_model_runtime.sh
 
+      - name: Run dify config tests
+        run: poetry run -C api python dev/pytest/pytest_config_tests.py
+
       - name: Run Tool
         run: poetry run -C api bash dev/pytest/pytest_tools.sh
 
+      - name: Run mypy
+        run: |
+          pushd api
+          poetry run python -m mypy --install-types --non-interactive .
+          popd
+
       - name: Set up dotenvs
         run: |
           cp docker/.env.example docker/.env

api/.env.example

@@ -60,21 +60,12 @@ DB_DATABASE=dify
 STORAGE_TYPE=opendal
 
 # Apache OpenDAL storage configuration, refer to https://github.com/apache/opendal
-STORAGE_OPENDAL_SCHEME=fs
-# OpenDAL FS
+OPENDAL_SCHEME=fs
 OPENDAL_FS_ROOT=storage
-# OpenDAL S3
-OPENDAL_S3_ROOT=/
-OPENDAL_S3_BUCKET=your-bucket-name
-OPENDAL_S3_ENDPOINT=https://s3.amazonaws.com
-OPENDAL_S3_ACCESS_KEY_ID=your-access-key
-OPENDAL_S3_SECRET_ACCESS_KEY=your-secret-key
-OPENDAL_S3_REGION=your-region
-OPENDAL_S3_SERVER_SIDE_ENCRYPTION=
 
 # S3 Storage configuration
 S3_USE_AWS_MANAGED_IAM=false
-S3_ENDPOINT=https://your-bucket-name.storage.s3.clooudflare.com
+S3_ENDPOINT=https://your-bucket-name.storage.s3.cloudflare.com
 S3_BUCKET_NAME=your-bucket-name
 S3_ACCESS_KEY=your-access-key
 S3_SECRET_KEY=your-secret-key
@@ -83,7 +74,7 @@ S3_REGION=your-region
 # Azure Blob Storage configuration
 AZURE_BLOB_ACCOUNT_NAME=your-account-name
 AZURE_BLOB_ACCOUNT_KEY=your-account-key
-AZURE_BLOB_CONTAINER_NAME=yout-container-name
+AZURE_BLOB_CONTAINER_NAME=your-container-name
 AZURE_BLOB_ACCOUNT_URL=https://<your_account_name>.blob.core.windows.net
 
 # Aliyun oss Storage configuration
@@ -97,7 +88,7 @@ ALIYUN_OSS_REGION=your-region
 ALIYUN_OSS_PATH=your-path
 
 # Google Storage configuration
-GOOGLE_STORAGE_BUCKET_NAME=yout-bucket-name
+GOOGLE_STORAGE_BUCKET_NAME=your-bucket-name
 GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64=your-google-service-account-json-base64-string
 
 # Tencent COS Storage configuration
@@ -408,6 +399,7 @@ INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=4000
 WORKFLOW_MAX_EXECUTION_STEPS=500
 WORKFLOW_MAX_EXECUTION_TIME=1200
 WORKFLOW_CALL_MAX_DEPTH=5
+WORKFLOW_PARALLEL_DEPTH_LIMIT=3
 MAX_VARIABLE_SIZE=204800
 
 # App configuration

api/.ruff.toml

@@ -67,10 +67,9 @@ ignore = [
     "SIM105", # suppressible-exception
     "SIM107", # return-in-try-except-finally
     "SIM108", # if-else-block-instead-of-if-exp
-    "SIM113", # eumerate-for-loop
+    "SIM113", # enumerate-for-loop
     "SIM117", # multiple-with-statements
     "SIM210", # if-expr-with-true-false
-    "SIM300", # yoda-conditions,
 ]
 
 [lint.per-file-ignores]
@@ -86,11 +85,11 @@ ignore = [
 ]
 "tests/*" = [
     "F811", # redefined-while-unused
-    "F401", # unused-import
 ]
 
 [lint.pyflakes]
-extend-generics = [
+allowed-unused-imports = [
     "_pytest.monkeypatch",
     "tests.integration_tests",
+    "tests.unit_tests",
 ]

api/Dockerfile

@@ -55,7 +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=2.5.18+dfsg-3+b1 perl=5.40.0-8 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
+    && 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/app.py

@@ -1,13 +1,41 @@
-from app_factory import create_app
-from libs import threadings_utils, version_utils
+import os
+import sys
+
+
+def is_db_command():
+    if len(sys.argv) > 1 and sys.argv[0].endswith("flask") and sys.argv[1] == "db":
+        return True
+    return False
 
-# preparation before creating app
-version_utils.check_supported_python_version()
-threadings_utils.apply_gevent_threading_patch()
 
 # create app
-app = create_app()
-celery = app.extensions["celery"]
+if is_db_command():
+    from app_factory import create_migrations_app
+
+    app = create_migrations_app()
+else:
+    # It seems that JetBrains Python debugger does not work well with gevent,
+    # so we need to disable gevent in debug mode.
+    # If you are using debugpy and set GEVENT_SUPPORT=True, you can debug with gevent.
+    if (flask_debug := os.environ.get("FLASK_DEBUG", "0")) and flask_debug.lower() in {"false", "0", "no"}:
+        from gevent import monkey  # type: ignore
+
+        # gevent
+        monkey.patch_all()
+
+        from grpc.experimental import gevent as grpc_gevent  # type: ignore
+
+        # grpc gevent
+        grpc_gevent.init_gevent()
+
+        import psycogreen.gevent  # type: ignore
+
+        psycogreen.gevent.patch_psycopg()
+
+    from app_factory import create_app
+
+    app = create_app()
+    celery = app.extensions["celery"]
 
 if __name__ == "__main__":
     app.run(host="0.0.0.0", port=5001)

api/app_factory.py

@@ -1,5 +1,4 @@
 import logging
-import os
 import time
 
 from configs import dify_config
@@ -17,15 +16,6 @@ def create_flask_app_with_configs() -> DifyApp:
     dify_app = DifyApp(__name__)
     dify_app.config.from_mapping(dify_config.model_dump())
 
-    # populate configs into system environment variables
-    for key, value in dify_app.config.items():
-        if isinstance(value, str):
-            os.environ[key] = value
-        elif isinstance(value, int | float | bool):
-            os.environ[key] = str(value)
-        elif value is None:
-            os.environ[key] = ""
-
     return dify_app
 
 
@@ -98,3 +88,14 @@ def initialize_extensions(app: DifyApp):
         end_time = time.perf_counter()
         if dify_config.DEBUG:
             logging.info(f"Loaded {short_name} ({round((end_time - start_time) * 1000, 2)} ms)")
+
+
+def create_migrations_app():
+    app = create_flask_app_with_configs()
+    from extensions import ext_database, ext_migrate
+
+    # Initialize only required extensions
+    ext_database.init_app(app)
+    ext_migrate.init_app(app)
+
+    return app

api/commands.py

@@ -159,8 +159,7 @@ def migrate_annotation_vector_database():
         try:
             # get apps info
             apps = (
-                db.session.query(App)
-                .filter(App.status == "normal")
+                App.query.filter(App.status == "normal")
                 .order_by(App.created_at.desc())
                 .paginate(page=page, per_page=50)
             )
@@ -285,8 +284,7 @@ def migrate_knowledge_vector_database():
     while True:
         try:
             datasets = (
-                db.session.query(Dataset)
-                .filter(Dataset.indexing_technique == "high_quality")
+                Dataset.query.filter(Dataset.indexing_technique == "high_quality")
                 .order_by(Dataset.created_at.desc())
                 .paginate(page=page, per_page=50)
             )
@@ -450,7 +448,8 @@ def convert_to_agent_apps():
                 if app_id not in proceeded_app_ids:
                     proceeded_app_ids.append(app_id)
                     app = db.session.query(App).filter(App.id == app_id).first()
-                    apps.append(app)
+                    if app is not None:
+                        apps.append(app)
 
             if len(apps) == 0:
                 break
@@ -555,14 +554,20 @@ def create_tenant(email: str, language: Optional[str] = None, name: Optional[str
     if language not in languages:
         language = "en-US"
 
-    name = name.strip()
+    # Validates name encoding for non-Latin characters.
+    name = name.strip().encode("utf-8").decode("utf-8") if name else None
 
     # generate random password
     new_password = secrets.token_urlsafe(16)
 
     # register account
-    account = RegisterService.register(email=email, name=account_name, password=new_password, language=language)
-
+    account = RegisterService.register(
+        email=email,
+        name=account_name,
+        password=new_password,
+        language=language,
+        create_workspace_required=False,
+    )
     TenantService.create_owner_tenant_if_not_exist(account, name)
 
     click.echo(
@@ -582,7 +587,7 @@ def upgrade_db():
             click.echo(click.style("Starting database migration.", fg="green"))
 
             # run db migration
-            import flask_migrate
+            import flask_migrate  # type: ignore
 
             flask_migrate.upgrade()
 
@@ -620,6 +625,10 @@ def fix_app_site_missing():
 
                 try:
                     app = db.session.query(App).filter(App.id == app_id).first()
+                    if not app:
+                        print(f"App {app_id} not found")
+                        continue
+
                     tenant = app.tenant
                     if tenant:
                         accounts = tenant.get_accounts()

api/configs/feature/__init__.py

@@ -239,7 +239,6 @@ class HttpConfig(BaseSettings):
     )
 
     @computed_field
-    @property
     def CONSOLE_CORS_ALLOW_ORIGINS(self) -> list[str]:
         return self.inner_CONSOLE_CORS_ALLOW_ORIGINS.split(",")
 
@@ -250,7 +249,6 @@ def CONSOLE_CORS_ALLOW_ORIGINS(self) -> list[str]:
     )
 
     @computed_field
-    @property
     def WEB_API_CORS_ALLOW_ORIGINS(self) -> list[str]:
         return self.inner_WEB_API_CORS_ALLOW_ORIGINS.split(",")
 
@@ -433,6 +431,11 @@ class WorkflowConfig(BaseSettings):
         default=5,
     )
 
+    WORKFLOW_PARALLEL_DEPTH_LIMIT: PositiveInt = Field(
+        description="Maximum allowed depth for nested parallel executions",
+        default=3,
+    )
+
     MAX_VARIABLE_SIZE: PositiveInt = Field(
         description="Maximum size in bytes for a single variable in workflows. Default to 200 KB.",
         default=200 * 1024,
@@ -598,7 +601,7 @@ class RagEtlConfig(BaseSettings):
 
     UNSTRUCTURED_API_KEY: Optional[str] = Field(
         description="API key for Unstructured.io service",
-        default=None,
+        default="",
     )
 
     SCARF_NO_ANALYTICS: Optional[str] = Field(
@@ -664,6 +667,11 @@ class IndexingConfig(BaseSettings):
         default=4000,
     )
 
+    CHILD_CHUNKS_PREVIEW_NUMBER: PositiveInt = Field(
+        description="Maximum number of child chunks to preview",
+        default=50,
+    )
+
 
 class MultiModalTransferConfig(BaseSettings):
     MULTIMODAL_SEND_FORMAT: Literal["base64", "url"] = Field(
@@ -710,27 +718,27 @@ class PositionConfig(BaseSettings):
         default="",
     )
 
-    @computed_field
+    @property
     def POSITION_PROVIDER_PINS_LIST(self) -> list[str]:
         return [item.strip() for item in self.POSITION_PROVIDER_PINS.split(",") if item.strip() != ""]
 
-    @computed_field
+    @property
     def POSITION_PROVIDER_INCLUDES_SET(self) -> set[str]:
         return {item.strip() for item in self.POSITION_PROVIDER_INCLUDES.split(",") if item.strip() != ""}
 
-    @computed_field
+    @property
     def POSITION_PROVIDER_EXCLUDES_SET(self) -> set[str]:
         return {item.strip() for item in self.POSITION_PROVIDER_EXCLUDES.split(",") if item.strip() != ""}
 
-    @computed_field
+    @property
     def POSITION_TOOL_PINS_LIST(self) -> list[str]:
         return [item.strip() for item in self.POSITION_TOOL_PINS.split(",") if item.strip() != ""]
 
-    @computed_field
+    @property
     def POSITION_TOOL_INCLUDES_SET(self) -> set[str]:
         return {item.strip() for item in self.POSITION_TOOL_INCLUDES.split(",") if item.strip() != ""}
 
-    @computed_field
+    @property
     def POSITION_TOOL_EXCLUDES_SET(self) -> set[str]:
         return {item.strip() for item in self.POSITION_TOOL_EXCLUDES.split(",") if item.strip() != ""}
 
@@ -762,6 +770,13 @@ class LoginConfig(BaseSettings):
     )
 
 
+class AccountConfig(BaseSettings):
+    ACCOUNT_DELETION_TOKEN_EXPIRY_MINUTES: PositiveInt = Field(
+        description="Duration in minutes for which a account deletion token remains valid",
+        default=5,
+    )
+
+
 class FeatureConfig(
     # place the configs in alphabet order
     AppExecutionConfig,
@@ -789,6 +804,7 @@ class FeatureConfig(
     WorkflowNodeExecutionConfig,
     WorkspaceConfig,
     LoginConfig,
+    AccountConfig,
     # hosted services config
     HostedServiceConfig,
     CeleryBeatConfig,