Merge branch 'langgenius:main' into main

.github/workflows/api-tests.yml

@@ -56,6 +56,12 @@ jobs:
       - 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

.github/workflows/style.yml

@@ -82,6 +82,33 @@ jobs:
         if: steps.changed-files.outputs.any_changed == 'true'
         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
 
   superlinter:
     name: SuperLinter

api/.env.example

@@ -23,6 +23,9 @@ FILES_ACCESS_TIMEOUT=300
 # Access token expiration time in minutes
 ACCESS_TOKEN_EXPIRE_MINUTES=60
 
+# Refresh token expiration time in days
+REFRESH_TOKEN_EXPIRE_DAYS=30
+
 # celery configuration
 CELERY_BROKER_URL=redis://:difyai123456@localhost:6379/1
 
@@ -65,7 +68,7 @@ OPENDAL_FS_ROOT=storage
 
 # 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
@@ -74,7 +77,7 @@ 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
@@ -88,7 +91,7 @@ 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
@@ -399,6 +402,7 @@ 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

@@ -1,12 +1,8 @@
-from libs import version_utils
-
-# preparation before creating app
-version_utils.check_supported_python_version()
+import os
+import sys
 
 
 def is_db_command():
-    import sys
-
     if len(sys.argv) > 1 and sys.argv[0].endswith("flask") and sys.argv[1] == "db":
         return True
     return False
@@ -18,10 +14,25 @@ def is_db_command():
 
     app = create_migrations_app()
 else:
-    from app_factory import create_app
-    from libs import threadings_utils
+    # 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
 
-    threadings_utils.apply_gevent_threading_patch()
+        # 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"]

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,
@@ -485,6 +488,11 @@ class AuthConfig(BaseSettings):
         default=60,
     )
 
+    REFRESH_TOKEN_EXPIRE_DAYS: PositiveFloat = Field(
+        description="Expiration time for refresh tokens in days",
+        default=30,
+    )
+
     LOGIN_LOCKOUT_DURATION: PositiveInt = Field(
         description="Time (in seconds) a user must wait before retrying login after exceeding the rate limit.",
         default=86400,
@@ -598,7 +606,7 @@ 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 +672,11 @@ 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 +723,27 @@ 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 +775,13 @@ 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 +809,7 @@ class FeatureConfig(
     WorkflowNodeExecutionConfig,
     WorkspaceConfig,
     LoginConfig,
+    AccountConfig,
     # hosted services config
     HostedServiceConfig,
     CeleryBeatConfig,

api/configs/middleware/__init__.py

@@ -130,7 +130,6 @@ class DatabaseConfig(BaseSettings):
     )
 
     @computed_field
-    @property
     def SQLALCHEMY_DATABASE_URI(self) -> str:
         db_extras = (
             f"{self.DB_EXTRAS}&client_encoding={self.DB_CHARSET}" if self.DB_CHARSET else self.DB_EXTRAS
@@ -168,7 +167,6 @@ def SQLALCHEMY_DATABASE_URI(self) -> str:
     )
 
     @computed_field
-    @property
     def SQLALCHEMY_ENGINE_OPTIONS(self) -> dict[str, Any]:
         return {
             "pool_size": self.SQLALCHEMY_POOL_SIZE,
@@ -206,15 +204,13 @@ class CeleryConfig(DatabaseConfig):
     )
 
     @computed_field
-    @property
     def CELERY_RESULT_BACKEND(self) -> str | None:
         return (
             "db+{}".format(self.SQLALCHEMY_DATABASE_URI)
             if self.CELERY_BACKEND == "database"
             else self.CELERY_BROKER_URL
         )
 
-    @computed_field
     @property
     def BROKER_USE_SSL(self) -> bool:
         return self.CELERY_BROKER_URL.startswith("rediss://") if self.CELERY_BROKER_URL else False