Merge branch 'feat/enhance-multi-modal-support' into release/0.10.0-beta

- Use more precise type annotations with Sequence and Mapping for task entities.
- Ensure raw_prompt is assigned properly after replacement in advanced prompt transform.
- Remove unused generator return type from _fetch_context method.
- Refactor tool node file handling to retrieve more comprehensive file attributes, ensuring file existence validation in the database.

.github/workflows/api-tests.yml

@@ -27,17 +27,18 @@ jobs:
       - name: Checkout code
         uses: actions/checkout@v4
 
+      - name: Install Poetry
+        uses: abatilo/actions-poetry@v3
+
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+          cache: 'poetry'
           cache-dependency-path: |
             api/pyproject.toml
             api/poetry.lock
 
-      - name: Install Poetry
-        uses: abatilo/actions-poetry@v3
-
       - name: Check Poetry lockfile
         run: |
           poetry check -C api --lock

.github/workflows/build-push.yml

@@ -5,6 +5,7 @@ on:
     branches:
       - "main"
       - "deploy/dev"
+      - "release/0.10.0-beta"
   release:
     types: [published]
 

.github/workflows/db-migration-test.yml

@@ -23,17 +23,18 @@ jobs:
       - name: Checkout code
         uses: actions/checkout@v4
 
+      - name: Install Poetry
+        uses: abatilo/actions-poetry@v3
+
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+          cache: 'poetry'
           cache-dependency-path: |
             api/pyproject.toml
             api/poetry.lock
 
-      - name: Install Poetry
-        uses: abatilo/actions-poetry@v3
-
       - name: Install dependencies
         run: poetry install -C api
 

.github/workflows/style.yml

@@ -24,16 +24,15 @@ jobs:
         with:
           files: api/**
 
+      - name: Install Poetry
+        uses: abatilo/actions-poetry@v3
+
       - name: Set up Python
         uses: actions/setup-python@v5
         if: steps.changed-files.outputs.any_changed == 'true'
         with:
           python-version: '3.10'
 
-      - name: Install Poetry
-        if: steps.changed-files.outputs.any_changed == 'true'
-        uses: abatilo/actions-poetry@v3
-
       - name: Python dependencies
         if: steps.changed-files.outputs.any_changed == 'true'
         run: poetry install -C api --only lint

.gitignore

@@ -175,8 +175,6 @@ docker/volumes/pgvector/data/*
 docker/volumes/pgvecto_rs/data/*
 
 docker/nginx/conf.d/default.conf
-docker/nginx/ssl/*
-!docker/nginx/ssl/.gitkeep
 docker/middleware.env
 
 sdks/python-client/build

LICENSE

@@ -6,9 +6,8 @@ Dify is licensed under the Apache License 2.0, with the following additional con
 
 a. Multi-tenant service: Unless explicitly authorized by Dify in writing, you may not use the Dify source code to operate a multi-tenant environment. 
     - Tenant Definition: Within the context of Dify, one tenant corresponds to one workspace. The workspace provides a separated area for each tenant's data and configurations.
-    
-b. LOGO and copyright information: In the process of using Dify's frontend, you may not remove or modify the LOGO or copyright information in the Dify console or applications. This restriction is inapplicable to uses of Dify that do not involve its frontend.
-    - Frontend Definition: For the purposes of this license, the "frontend" of Dify includes all components located in the `web/` directory when running Dify from the raw source code, or the "web" image when running Dify with Docker.
+
+b. LOGO and copyright information: In the process of using Dify's frontend components, you may not remove or modify the LOGO or copyright information in the Dify console or applications. This restriction is inapplicable to uses of Dify that do not involve its frontend components.
 
 Please contact business@dify.ai by email to inquire about licensing matters.
 

README.md

@@ -1,9 +1,5 @@
 ![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
 
-<p align="center">
-  📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">Introducing Dify Workflow File Upload: Recreate Google NotebookLM Podcast</a>
-</p>
-
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
   <a href="https://docs.dify.ai/getting-started/install-self-hosted">Self-hosting</a> ·
@@ -172,7 +168,7 @@ Star Dify on GitHub and be instantly notified of new releases.
 > Before installing Dify, make sure your machine meets the following minimum system requirements:
 > 
 >- CPU >= 2 Core
->- RAM >= 4 GiB
+>- RAM >= 4GB
 
 </br>
 

README_CN.md

@@ -154,7 +154,7 @@ Dify 是一个开源的 LLM 应用开发平台。其直观的界面结合了 AI
 我们提供[ Dify 云服务](https://dify.ai)，任何人都可以零设置尝试。它提供了自部署版本的所有功能，并在沙盒计划中包含 200 次免费的 GPT-4 调用。
 
 - **自托管 Dify 社区版</br>**
-使用这个[入门指南](#快速启动)快速在您的环境中运行 Dify。
+使用这个[入门指南](#quick-start)快速在您的环境中运行 Dify。
 使用我们的[文档](https://docs.dify.ai)进行进一步的参考和更深入的说明。
 
 - **面向企业/组织的 Dify</br>**
@@ -174,7 +174,7 @@ Dify 是一个开源的 LLM 应用开发平台。其直观的界面结合了 AI
 在安装 Dify 之前，请确保您的机器满足以下最低系统要求：
 
 - CPU >= 2 Core
-- RAM >= 4 GiB
+- RAM >= 4GB
 
 ### 快速启动
 

api/.env.example

@@ -31,17 +31,8 @@ REDIS_HOST=localhost
 REDIS_PORT=6379
 REDIS_USERNAME=
 REDIS_PASSWORD=difyai123456
-REDIS_USE_SSL=false
 REDIS_DB=0
 
-# redis Sentinel configuration.
-REDIS_USE_SENTINEL=false
-REDIS_SENTINELS=
-REDIS_SENTINEL_SERVICE_NAME=
-REDIS_SENTINEL_USERNAME=
-REDIS_SENTINEL_PASSWORD=
-REDIS_SENTINEL_SOCKET_TIMEOUT=0.1
-
 # PostgreSQL database configuration
 DB_USERNAME=postgres
 DB_PASSWORD=difyai123456
@@ -51,7 +42,7 @@ DB_DATABASE=dify
 
 # Storage configuration
 # use for store upload files, private keys...
-# storage type: local, s3, aliyun-oss, azure-blob, baidu-obs, google-storage, huawei-obs, oci-storage, tencent-cos, volcengine-tos, supabase
+# storage type: local, s3, azure-blob, google-storage, tencent-cos, huawei-obs, volcengine-tos, baidu-obs, supabase
 STORAGE_TYPE=local
 STORAGE_LOCAL_PATH=storage
 S3_USE_AWS_MANAGED_IAM=false
@@ -120,7 +111,7 @@ SUPABASE_URL=your-server-url
 WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 
-# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, vikingdb, upstash
+# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, vikingdb
 VECTOR_STORE=weaviate
 
 # Weaviate configuration
@@ -229,10 +220,6 @@ BAIDU_VECTOR_DB_DATABASE=dify
 BAIDU_VECTOR_DB_SHARD=1
 BAIDU_VECTOR_DB_REPLICAS=3
 
-# Upstash configuration
-UPSTASH_VECTOR_URL=your-server-url
-UPSTASH_VECTOR_TOKEN=your-access-token
-
 # ViKingDB configuration
 VIKINGDB_ACCESS_KEY=your-ak
 VIKINGDB_SECRET_KEY=your-sk
@@ -252,7 +239,6 @@ UPLOAD_AUDIO_FILE_SIZE_LIMIT=50
 # Model Configuration
 MULTIMODAL_SEND_IMAGE_FORMAT=base64
 PROMPT_GENERATION_MAX_TOKENS=512
-CODE_GENERATION_MAX_TOKENS=1024
 
 # Mail configuration, support: resend, smtp
 MAIL_TYPE=
@@ -318,10 +304,6 @@ RESPECT_XFORWARD_HEADERS_ENABLED=false
 
 # Log file path
 LOG_FILE=
-# Log file max size, the unit is MB
-LOG_FILE_MAX_SIZE=20
-# Log file max backup count
-LOG_FILE_BACKUP_COUNT=5
 
 # Indexing configuration
 INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=1000
@@ -348,6 +330,3 @@ POSITION_TOOL_EXCLUDES=
 POSITION_PROVIDER_PINS=
 POSITION_PROVIDER_INCLUDES=
 POSITION_PROVIDER_EXCLUDES=
-
-# Reset password token expiry minutes
-RESET_PASSWORD_TOKEN_EXPIRY_MINUTES=5

api/Dockerfile

@@ -55,9 +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 zlib1g=1:1.3.dfsg+really1.3.1-1 expat=2.6.3-1 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-6 libsqlite3-0=3.46.1-1 \
-    # install a chinese font to support the use of tools like matplotlib
-    && apt-get install -y fonts-noto-cjk \
+    && apt-get install -y --no-install-recommends zlib1g=1:1.3.dfsg+really1.3.1-1 expat=2.6.3-1 libldap-2.5-0=2.5.18+dfsg-3 perl=5.38.2-5 libsqlite3-0=3.46.0-1 \
     && apt-get autoremove -y \
     && rm -rf /var/lib/apt/lists/*
 

api/README.md

@@ -85,4 +85,3 @@
    cd ../
    poetry run -C api bash dev/pytest/pytest_all_tests.sh
    ```
-

api/app.py

@@ -1,7 +1,5 @@
 import os
 
-from configs import dify_config
-
 if os.environ.get("DEBUG", "false").lower() != "true":
     from gevent import monkey
 
@@ -12,20 +10,44 @@ if os.environ.get("DEBUG", "false").lower() != "true":
     grpc.experimental.gevent.init_gevent()
 
 import json
+import logging
+import sys
 import threading
 import time
 import warnings
+from logging.handlers import RotatingFileHandler
 
-from flask import Response
+from flask import Flask, Response, request
+from flask_cors import CORS
+from werkzeug.exceptions import Unauthorized
 
-from app_factory import create_app
+import contexts
+from commands import register_commands
+from configs import dify_config
 
 # DO NOT REMOVE BELOW
 from events import event_handlers  # noqa: F401
+from extensions import (
+    ext_celery,
+    ext_code_based_extension,
+    ext_compress,
+    ext_database,
+    ext_hosting_provider,
+    ext_login,
+    ext_mail,
+    ext_migrate,
+    ext_proxy_fix,
+    ext_redis,
+    ext_sentry,
+    ext_storage,
+)
 from extensions.ext_database import db
+from extensions.ext_login import login_manager
+from libs.passport import PassportService
 
 # TODO: Find a way to avoid importing models here
 from models import account, dataset, model, source, task, tool, tools, web  # noqa: F401
+from services.account_service import AccountService
 
 # DO NOT REMOVE ABOVE
 
@@ -38,11 +60,194 @@ if hasattr(time, "tzset"):
     time.tzset()
 
 
+class DifyApp(Flask):
+    pass
+
+
+# -------------
+# Configuration
+# -------------
+
+
+config_type = os.getenv("EDITION", default="SELF_HOSTED")  # ce edition first
+
+
+# ----------------------------
+# Application Factory Function
+# ----------------------------
+
+
+def create_flask_app_with_configs() -> Flask:
+    """
+    create a raw flask app
+    with configs loaded from .env file
+    """
+    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
+
+
+def create_app() -> Flask:
+    app = create_flask_app_with_configs()
+
+    app.secret_key = app.config["SECRET_KEY"]
+
+    log_handlers = None
+    log_file = app.config.get("LOG_FILE")
+    if log_file:
+        log_dir = os.path.dirname(log_file)
+        os.makedirs(log_dir, exist_ok=True)
+        log_handlers = [
+            RotatingFileHandler(
+                filename=log_file,
+                maxBytes=1024 * 1024 * 1024,
+                backupCount=5,
+            ),
+            logging.StreamHandler(sys.stdout),
+        ]
+
+    logging.basicConfig(
+        level=app.config.get("LOG_LEVEL"),
+        format=app.config["LOG_FORMAT"],
+        datefmt=app.config.get("LOG_DATEFORMAT"),
+        handlers=log_handlers,
+        force=True,
+    )
+    log_tz = app.config.get("LOG_TZ")
+    if log_tz:
+        from datetime import datetime
+
+        import pytz
+
+        timezone = pytz.timezone(log_tz)
+
+        def time_converter(seconds):
+            return datetime.utcfromtimestamp(seconds).astimezone(timezone).timetuple()
+
+        for handler in logging.root.handlers:
+            assert handler.formatter
+            handler.formatter.converter = time_converter
+    initialize_extensions(app)
+    register_blueprints(app)
+    register_commands(app)
+
+    return app
+
+
+def initialize_extensions(app):
+    # Since the application instance is now created, pass it to each Flask
+    # extension instance to bind it to the Flask application instance (app)
+    ext_compress.init_app(app)
+    ext_code_based_extension.init()
+    ext_database.init_app(app)
+    ext_migrate.init(app, db)
+    ext_redis.init_app(app)
+    ext_storage.init_app(app)
+    ext_celery.init_app(app)
+    ext_login.init_app(app)
+    ext_mail.init_app(app)
+    ext_hosting_provider.init_app(app)
+    ext_sentry.init_app(app)
+    ext_proxy_fix.init_app(app)
+
+
+# Flask-Login configuration
+@login_manager.request_loader
+def load_user_from_request(request_from_flask_login):
+    """Load user based on the request."""
+    if request.blueprint not in {"console", "inner_api"}:
+        return None
+    # Check if the user_id contains a dot, indicating the old format
+    auth_header = request.headers.get("Authorization", "")
+    if not auth_header:
+        auth_token = request.args.get("_token")
+        if not auth_token:
+            raise Unauthorized("Invalid Authorization token.")
+    else:
+        if " " not in auth_header:
+            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
+        auth_scheme, auth_token = auth_header.split(None, 1)
+        auth_scheme = auth_scheme.lower()
+        if auth_scheme != "bearer":
+            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
+
+    decoded = PassportService().verify(auth_token)
+    user_id = decoded.get("user_id")
+
+    logged_in_account = AccountService.load_logged_in_account(account_id=user_id)
+    if logged_in_account:
+        contexts.tenant_id.set(logged_in_account.current_tenant_id)
+    return logged_in_account
+
+
+@login_manager.unauthorized_handler
+def unauthorized_handler():
+    """Handle unauthorized requests."""
+    return Response(
+        json.dumps({"code": "unauthorized", "message": "Unauthorized."}),
+        status=401,
+        content_type="application/json",
+    )
+
+
+# register blueprint routers
+def register_blueprints(app):
+    from controllers.console import bp as console_app_bp
+    from controllers.files import bp as files_bp
+    from controllers.inner_api import bp as inner_api_bp
+    from controllers.service_api import bp as service_api_bp
+    from controllers.web import bp as web_bp
+
+    CORS(
+        service_api_bp,
+        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
+        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
+    )
+    app.register_blueprint(service_api_bp)
+
+    CORS(
+        web_bp,
+        resources={r"/*": {"origins": app.config["WEB_API_CORS_ALLOW_ORIGINS"]}},
+        supports_credentials=True,
+        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
+        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
+        expose_headers=["X-Version", "X-Env"],
+    )
+
+    app.register_blueprint(web_bp)
+
+    CORS(
+        console_app_bp,
+        resources={r"/*": {"origins": app.config["CONSOLE_CORS_ALLOW_ORIGINS"]}},
+        supports_credentials=True,
+        allow_headers=["Content-Type", "Authorization"],
+        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
+        expose_headers=["X-Version", "X-Env"],
+    )
+
+    app.register_blueprint(console_app_bp)
+
+    CORS(files_bp, allow_headers=["Content-Type"], methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"])
+    app.register_blueprint(files_bp)
+
+    app.register_blueprint(inner_api_bp)
+
+
 # create app
 app = create_app()
 celery = app.extensions["celery"]
 
-if dify_config.TESTING:
+if app.config.get("TESTING"):
     print("App is running in TESTING mode")
 
 
@@ -50,15 +255,15 @@ if dify_config.TESTING:
 def after_request(response):
     """Add Version headers to the response."""
     response.set_cookie("remember_token", "", expires=0)
-    response.headers.add("X-Version", dify_config.CURRENT_VERSION)
-    response.headers.add("X-Env", dify_config.DEPLOY_ENV)
+    response.headers.add("X-Version", app.config["CURRENT_VERSION"])
+    response.headers.add("X-Env", app.config["DEPLOY_ENV"])
     return response
 
 
 @app.route("/health")
 def health():
     return Response(
-        json.dumps({"pid": os.getpid(), "status": "ok", "version": dify_config.CURRENT_VERSION}),
+        json.dumps({"pid": os.getpid(), "status": "ok", "version": app.config["CURRENT_VERSION"]}),
         status=200,
         content_type="application/json",
     )

api/app_factory.py

@@ -1,176 +0,0 @@
-import os
-
-if os.environ.get("DEBUG", "false").lower() != "true":
-    from gevent import monkey
-
-    monkey.patch_all()
-
-    import grpc.experimental.gevent
-
-    grpc.experimental.gevent.init_gevent()
-
-import json
-
-from flask import Flask, Response, request
-from flask_cors import CORS
-from werkzeug.exceptions import Unauthorized
-
-import contexts
-from commands import register_commands
-from configs import dify_config
-from extensions import (
-    ext_celery,
-    ext_code_based_extension,
-    ext_compress,
-    ext_database,
-    ext_hosting_provider,
-    ext_logging,
-    ext_login,
-    ext_mail,
-    ext_migrate,
-    ext_proxy_fix,
-    ext_redis,
-    ext_sentry,
-    ext_storage,
-)
-from extensions.ext_database import db
-from extensions.ext_login import login_manager
-from libs.passport import PassportService
-from services.account_service import AccountService
-
-
-class DifyApp(Flask):
-    pass
-
-
-# ----------------------------
-# Application Factory Function
-# ----------------------------
-def create_flask_app_with_configs() -> Flask:
-    """
-    create a raw flask app
-    with configs loaded from .env file
-    """
-    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
-
-
-def create_app() -> Flask:
-    app = create_flask_app_with_configs()
-    app.secret_key = dify_config.SECRET_KEY
-    initialize_extensions(app)
-    register_blueprints(app)
-    register_commands(app)
-
-    return app
-
-
-def initialize_extensions(app):
-    # Since the application instance is now created, pass it to each Flask
-    # extension instance to bind it to the Flask application instance (app)
-    ext_logging.init_app(app)
-    ext_compress.init_app(app)
-    ext_code_based_extension.init()
-    ext_database.init_app(app)
-    ext_migrate.init(app, db)
-    ext_redis.init_app(app)
-    ext_storage.init_app(app)
-    ext_celery.init_app(app)
-    ext_login.init_app(app)
-    ext_mail.init_app(app)
-    ext_hosting_provider.init_app(app)
-    ext_sentry.init_app(app)
-    ext_proxy_fix.init_app(app)
-
-
-# Flask-Login configuration
-@login_manager.request_loader
-def load_user_from_request(request_from_flask_login):
-    """Load user based on the request."""
-    if request.blueprint not in {"console", "inner_api"}:
-        return None
-    # Check if the user_id contains a dot, indicating the old format
-    auth_header = request.headers.get("Authorization", "")
-    if not auth_header:
-        auth_token = request.args.get("_token")
-        if not auth_token:
-            raise Unauthorized("Invalid Authorization token.")
-    else:
-        if " " not in auth_header:
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
-        auth_scheme, auth_token = auth_header.split(None, 1)
-        auth_scheme = auth_scheme.lower()
-        if auth_scheme != "bearer":
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
-
-    decoded = PassportService().verify(auth_token)
-    user_id = decoded.get("user_id")
-
-    logged_in_account = AccountService.load_logged_in_account(account_id=user_id)
-    if logged_in_account:
-        contexts.tenant_id.set(logged_in_account.current_tenant_id)
-    return logged_in_account
-
-
-@login_manager.unauthorized_handler
-def unauthorized_handler():
-    """Handle unauthorized requests."""
-    return Response(
-        json.dumps({"code": "unauthorized", "message": "Unauthorized."}),
-        status=401,
-        content_type="application/json",
-    )
-
-
-# register blueprint routers
-def register_blueprints(app):
-    from controllers.console import bp as console_app_bp
-    from controllers.files import bp as files_bp
-    from controllers.inner_api import bp as inner_api_bp
-    from controllers.service_api import bp as service_api_bp
-    from controllers.web import bp as web_bp
-
-    CORS(
-        service_api_bp,
-        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-    )
-    app.register_blueprint(service_api_bp)
-
-    CORS(
-        web_bp,
-        resources={r"/*": {"origins": dify_config.WEB_API_CORS_ALLOW_ORIGINS}},
-        supports_credentials=True,
-        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-        expose_headers=["X-Version", "X-Env"],
-    )
-
-    app.register_blueprint(web_bp)
-
-    CORS(
-        console_app_bp,
-        resources={r"/*": {"origins": dify_config.CONSOLE_CORS_ALLOW_ORIGINS}},
-        supports_credentials=True,
-        allow_headers=["Content-Type", "Authorization"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-        expose_headers=["X-Version", "X-Env"],
-    )
-
-    app.register_blueprint(console_app_bp)
-
-    CORS(files_bp, allow_headers=["Content-Type"], methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"])
-    app.register_blueprint(files_bp)
-
-    app.register_blueprint(inner_api_bp)

api/commands.py

@@ -259,26 +259,6 @@ def migrate_knowledge_vector_database():
     skipped_count = 0
     total_count = 0
     vector_type = dify_config.VECTOR_STORE
-    upper_colletion_vector_types = {
-        VectorType.MILVUS,
-        VectorType.PGVECTOR,
-        VectorType.RELYT,
-        VectorType.WEAVIATE,
-        VectorType.ORACLE,
-        VectorType.ELASTICSEARCH,
-    }
-    lower_colletion_vector_types = {
-        VectorType.ANALYTICDB,
-        VectorType.CHROMA,
-        VectorType.MYSCALE,
-        VectorType.PGVECTO_RS,
-        VectorType.TIDB_VECTOR,
-        VectorType.OPENSEARCH,
-        VectorType.TENCENT,
-        VectorType.BAIDU,
-        VectorType.VIKINGDB,
-        VectorType.UPSTASH,
-    }
     page = 1
     while True:
         try:
@@ -304,9 +284,11 @@ def migrate_knowledge_vector_database():
                         skipped_count = skipped_count + 1
                         continue
                 collection_name = ""
-                dataset_id = dataset.id
-                if vector_type in upper_colletion_vector_types:
+                if vector_type == VectorType.WEAVIATE:
+                    dataset_id = dataset.id
                     collection_name = Dataset.gen_collection_name_by_id(dataset_id)
+                    index_struct_dict = {"type": VectorType.WEAVIATE, "vector_store": {"class_prefix": collection_name}}
+                    dataset.index_struct = json.dumps(index_struct_dict)
                 elif vector_type == VectorType.QDRANT:
                     if dataset.collection_binding_id:
                         dataset_collection_binding = (
@@ -319,15 +301,63 @@ def migrate_knowledge_vector_database():
                         else:
                             raise ValueError("Dataset Collection Binding not found")
                     else:
+                        dataset_id = dataset.id
                         collection_name = Dataset.gen_collection_name_by_id(dataset_id)
+                    index_struct_dict = {"type": VectorType.QDRANT, "vector_store": {"class_prefix": collection_name}}
+                    dataset.index_struct = json.dumps(index_struct_dict)
 
-                elif vector_type in lower_colletion_vector_types:
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id).lower()
+                elif vector_type == VectorType.MILVUS:
+                    dataset_id = dataset.id
+                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
+                    index_struct_dict = {"type": VectorType.MILVUS, "vector_store": {"class_prefix": collection_name}}
+                    dataset.index_struct = json.dumps(index_struct_dict)
+                elif vector_type == VectorType.RELYT:
+                    dataset_id = dataset.id
+                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
+                    index_struct_dict = {"type": "relyt", "vector_store": {"class_prefix": collection_name}}
+                    dataset.index_struct = json.dumps(index_struct_dict)
+                elif vector_type == VectorType.TENCENT:
+                    dataset_id = dataset.id
+                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
+                    index_struct_dict = {"type": VectorType.TENCENT, "vector_store": {"class_prefix": collection_name}}
+                    dataset.index_struct = json.dumps(index_struct_dict)
+                elif vector_type == VectorType.PGVECTOR:
+                    dataset_id = dataset.id
+                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
+                    index_struct_dict = {"type": VectorType.PGVECTOR, "vector_store": {"class_prefix": collection_name}}
+                    dataset.index_struct = json.dumps(index_struct_dict)
+                elif vector_type == VectorType.OPENSEARCH:
+                    dataset_id = dataset.id
+                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
+                    index_struct_dict = {
+                        "type": VectorType.OPENSEARCH,
+                        "vector_store": {"class_prefix": collection_name},
+                    }
+                    dataset.index_struct = json.dumps(index_struct_dict)
+                elif vector_type == VectorType.ANALYTICDB:
+                    dataset_id = dataset.id
+                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
+                    index_struct_dict = {
+                        "type": VectorType.ANALYTICDB,
+                        "vector_store": {"class_prefix": collection_name},
+                    }
+                    dataset.index_struct = json.dumps(index_struct_dict)
+                elif vector_type == VectorType.ELASTICSEARCH:
+                    dataset_id = dataset.id
+                    index_name = Dataset.gen_collection_name_by_id(dataset_id)
+                    index_struct_dict = {"type": "elasticsearch", "vector_store": {"class_prefix": index_name}}
+                    dataset.index_struct = json.dumps(index_struct_dict)
+                elif vector_type == VectorType.BAIDU:
+                    dataset_id = dataset.id
+                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
+                    index_struct_dict = {
+                        "type": VectorType.BAIDU,
+                        "vector_store": {"class_prefix": collection_name},
+                    }
+                    dataset.index_struct = json.dumps(index_struct_dict)
                 else:
                     raise ValueError(f"Vector store {vector_type} is not supported.")
 
-                index_struct_dict = {"type": vector_type, "vector_store": {"class_prefix": collection_name}}
-                dataset.index_struct = json.dumps(index_struct_dict)
                 vector = Vector(dataset)
                 click.echo(f"Migrating dataset {dataset.id}.")
 

api/configs/feature/__init__.py

@@ -1,15 +1,6 @@
 from typing import Annotated, Literal, Optional
 
-from pydantic import (
-    AliasChoices,
-    Field,
-    HttpUrl,
-    NegativeInt,
-    NonNegativeInt,
-    PositiveFloat,
-    PositiveInt,
-    computed_field,
-)
+from pydantic import AliasChoices, Field, HttpUrl, NegativeInt, NonNegativeInt, PositiveInt, computed_field
 from pydantic_settings import BaseSettings
 
 from configs.feature.hosted_service import HostedServiceConfig
@@ -27,24 +18,9 @@ class SecurityConfig(BaseSettings):
         default="",
     )
 
-    RESET_PASSWORD_TOKEN_EXPIRY_MINUTES: PositiveInt = Field(
-        description="Duration in minutes for which a password reset token remains valid",
-        default=5,
-    )
-
-    LOGIN_DISABLED: bool = Field(
-        description="Whether to disable login checks",
-        default=False,
-    )
-
-    ADMIN_API_KEY_ENABLE: bool = Field(
-        description="Whether to enable admin api key for authentication",
-        default=False,
-    )
-
-    ADMIN_API_KEY: Optional[str] = Field(
-        description="admin api key for authentication",
-        default=None,
+    RESET_PASSWORD_TOKEN_EXPIRY_HOURS: PositiveInt = Field(
+        description="Duration in hours for which a password reset token remains valid",
+        default=24,
     )
 
 
@@ -319,16 +295,6 @@ class LoggingConfig(BaseSettings):
         default=None,
     )
 
-    LOG_FILE_MAX_SIZE: PositiveInt = Field(
-        description="Maximum file size for file rotation retention, the unit is megabytes (MB)",
-        default=20,
-    )
-
-    LOG_FILE_BACKUP_COUNT: PositiveInt = Field(
-        description="Maximum file backup count file rotation retention",
-        default=5,
-    )
-
     LOG_FORMAT: str = Field(
         description="Format string for log messages",
         default="%(asctime)s.%(msecs)03d %(levelname)s [%(threadName)s] [%(filename)s:%(lineno)d] - %(message)s",
@@ -517,11 +483,6 @@ class MailConfig(BaseSettings):
         default=False,
     )
 
-    EMAIL_SEND_IP_LIMIT_PER_MINUTE: PositiveInt = Field(
-        description="Maximum number of emails allowed to be sent from the same IP address in a minute",
-        default=50,
-    )
-
 
 class RagEtlConfig(BaseSettings):
     """
@@ -556,26 +517,16 @@ class DataSetConfig(BaseSettings):
     Configuration for dataset management
     """
 
-    PLAN_SANDBOX_CLEAN_DAY_SETTING: PositiveInt = Field(
-        description="Interval in days for dataset cleanup operations - plan: sandbox",
+    CLEAN_DAY_SETTING: PositiveInt = Field(
+        description="Interval in days for dataset cleanup operations",
         default=30,
     )
 
-    PLAN_PRO_CLEAN_DAY_SETTING: PositiveInt = Field(
-        description="Interval in days for dataset cleanup operations - plan: pro and team",
-        default=7,
-    )
-
     DATASET_OPERATOR_ENABLED: bool = Field(
         description="Enable or disable dataset operator functionality",
         default=False,
     )
 
-    TIDB_SERVERLESS_NUMBER: PositiveInt = Field(
-        description="number of tidb serverless cluster",
-        default=500,
-    )
-
 
 class WorkspaceConfig(BaseSettings):
     """
@@ -669,33 +620,6 @@ class PositionConfig(BaseSettings):
         return {item.strip() for item in self.POSITION_TOOL_EXCLUDES.split(",") if item.strip() != ""}
 
 
-class LoginConfig(BaseSettings):
-    ENABLE_EMAIL_CODE_LOGIN: bool = Field(
-        description="whether to enable email code login",
-        default=False,
-    )
-    ENABLE_EMAIL_PASSWORD_LOGIN: bool = Field(
-        description="whether to enable email password login",
-        default=True,
-    )
-    ENABLE_SOCIAL_OAUTH_LOGIN: bool = Field(
-        description="whether to enable github/google oauth login",
-        default=False,
-    )
-    EMAIL_CODE_LOGIN_TOKEN_EXPIRY_MINUTES: PositiveInt = Field(
-        description="expiry time in minutes for email code login token",
-        default=5,
-    )
-    ALLOW_REGISTER: bool = Field(
-        description="whether to enable register",
-        default=False,
-    )
-    ALLOW_CREATE_WORKSPACE: bool = Field(
-        description="whether to enable create workspace",
-        default=False,
-    )
-
-
 class FeatureConfig(
     # place the configs in alphabet order
     AppExecutionConfig,
@@ -721,7 +645,6 @@ class FeatureConfig(
     UpdateConfig,
     WorkflowConfig,
     WorkspaceConfig,
-    LoginConfig,
     # hosted services config
     HostedServiceConfig,
     CeleryBeatConfig,

api/configs/middleware/__init__.py

@@ -27,9 +27,7 @@ from configs.middleware.vdb.pgvectors_config import PGVectoRSConfig
 from configs.middleware.vdb.qdrant_config import QdrantConfig
 from configs.middleware.vdb.relyt_config import RelytConfig
 from configs.middleware.vdb.tencent_vector_config import TencentVectorDBConfig
-from configs.middleware.vdb.tidb_on_qdrant_config import TidbOnQdrantConfig
 from configs.middleware.vdb.tidb_vector_config import TiDBVectorConfig
-from configs.middleware.vdb.upstash_config import UpstashConfig
 from configs.middleware.vdb.vikingdb_config import VikingDBConfig
 from configs.middleware.vdb.weaviate_config import WeaviateConfig
 
@@ -37,8 +35,7 @@ from configs.middleware.vdb.weaviate_config import WeaviateConfig
 class StorageConfig(BaseSettings):
     STORAGE_TYPE: str = Field(
         description="Type of storage to use."
-        " Options: 'local', 's3', 'aliyun-oss', 'azure-blob', 'baidu-obs', 'google-storage', 'huawei-obs', "
-        "'oci-storage', 'tencent-cos', 'volcengine-tos', 'supabase'. Default is 'local'.",
+        " Options: 'local', 's3', 'azure-blob', 'aliyun-oss', 'google-storage'. Default is 'local'.",
         default="local",
     )
 
@@ -55,11 +52,6 @@ class VectorStoreConfig(BaseSettings):
         default=None,
     )
 
-    VECTOR_STORE_WHITELIST_ENABLE: Optional[bool] = Field(
-        description="Enable whitelist for vector store.",
-        default=False,
-    )
-
 
 class KeywordStoreConfig(BaseSettings):
     KEYWORD_STORE: str = Field(
@@ -253,7 +245,5 @@ class MiddlewareConfig(
     ElasticsearchConfig,
     InternalTestConfig,
     VikingDBConfig,
-    UpstashConfig,
-    TidbOnQdrantConfig,
 ):
     pass

api/configs/middleware/vdb/oracle_config.py

@@ -14,7 +14,7 @@ class OracleConfig(BaseSettings):
         default=None,
     )
 
-    ORACLE_PORT: PositiveInt = Field(
+    ORACLE_PORT: Optional[PositiveInt] = Field(
         description="Port number on which the Oracle database server is listening (default is 1521)",
         default=1521,
     )

api/configs/middleware/vdb/pgvector_config.py

@@ -14,7 +14,7 @@ class PGVectorConfig(BaseSettings):
         default=None,
     )
 
-    PGVECTOR_PORT: PositiveInt = Field(
+    PGVECTOR_PORT: Optional[PositiveInt] = Field(
         description="Port number on which the PostgreSQL server is listening (default is 5433)",
         default=5433,
     )

api/configs/middleware/vdb/pgvectors_config.py

@@ -14,7 +14,7 @@ class PGVectoRSConfig(BaseSettings):
         default=None,
     )
 
-    PGVECTO_RS_PORT: PositiveInt = Field(
+    PGVECTO_RS_PORT: Optional[PositiveInt] = Field(
         description="Port number on which the PostgreSQL server with PGVecto.RS is listening (default is 5431)",
         default=5431,
     )

api/configs/middleware/vdb/tidb_on_qdrant_config.py

@@ -1,65 +0,0 @@
-from typing import Optional
-
-from pydantic import Field, NonNegativeInt, PositiveInt
-from pydantic_settings import BaseSettings
-
-
-class TidbOnQdrantConfig(BaseSettings):
-    """
-    Tidb on Qdrant configs
-    """
-
-    TIDB_ON_QDRANT_URL: Optional[str] = Field(
-        description="Tidb on Qdrant url",
-        default=None,
-    )
-
-    TIDB_ON_QDRANT_API_KEY: Optional[str] = Field(
-        description="Tidb on Qdrant api key",
-        default=None,
-    )
-
-    TIDB_ON_QDRANT_CLIENT_TIMEOUT: NonNegativeInt = Field(
-        description="Tidb on Qdrant client timeout in seconds",
-        default=20,
-    )
-
-    TIDB_ON_QDRANT_GRPC_ENABLED: bool = Field(
-        description="whether enable grpc support for Tidb on Qdrant connection",
-        default=False,
-    )
-
-    TIDB_ON_QDRANT_GRPC_PORT: PositiveInt = Field(
-        description="Tidb on Qdrant grpc port",
-        default=6334,
-    )
-
-    TIDB_PUBLIC_KEY: Optional[str] = Field(
-        description="Tidb account public key",
-        default=None,
-    )
-
-    TIDB_PRIVATE_KEY: Optional[str] = Field(
-        description="Tidb account private key",
-        default=None,
-    )
-
-    TIDB_API_URL: Optional[str] = Field(
-        description="Tidb API url",
-        default=None,
-    )
-
-    TIDB_IAM_API_URL: Optional[str] = Field(
-        description="Tidb IAM API url",
-        default=None,
-    )
-
-    TIDB_REGION: Optional[str] = Field(
-        description="Tidb serverless region",
-        default="regions/aws-us-east-1",
-    )
-
-    TIDB_PROJECT_ID: Optional[str] = Field(
-        description="Tidb project id",
-        default=None,
-    )

api/configs/middleware/vdb/upstash_config.py

@@ -1,20 +0,0 @@
-from typing import Optional
-
-from pydantic import Field
-from pydantic_settings import BaseSettings
-
-
-class UpstashConfig(BaseSettings):
-    """
-    Configuration settings for Upstash vector database
-    """
-
-    UPSTASH_VECTOR_URL: Optional[str] = Field(
-        description="URL of the upstash server (e.g., 'https://vector.upstash.io')",
-        default=None,
-    )
-
-    UPSTASH_VECTOR_TOKEN: Optional[str] = Field(
-        description="Token for authenticating with the upstash server",
-        default=None,
-    )

api/configs/middleware/vdb/vikingdb_config.py

@@ -11,39 +11,27 @@ class VikingDBConfig(BaseModel):
     """
 
     VIKINGDB_ACCESS_KEY: Optional[str] = Field(
-        description="The Access Key provided by Volcengine VikingDB for API authentication."
-        "Refer to the following documentation for details on obtaining credentials:"
-        "https://www.volcengine.com/docs/6291/65568",
-        default=None,
+        default=None, description="The Access Key provided by Volcengine VikingDB for API authentication."
     )
-
     VIKINGDB_SECRET_KEY: Optional[str] = Field(
-        description="The Secret Key provided by Volcengine VikingDB for API authentication.",
-        default=None,
+        default=None, description="The Secret Key provided by Volcengine VikingDB for API authentication."
     )
-
-    VIKINGDB_REGION: str = Field(
-        description="The region of the Volcengine VikingDB service.(e.g., 'cn-shanghai', 'cn-beijing').",
+    VIKINGDB_REGION: Optional[str] = Field(
         default="cn-shanghai",
+        description="The region of the Volcengine VikingDB service.(e.g., 'cn-shanghai', 'cn-beijing').",
     )
-
-    VIKINGDB_HOST: str = Field(
+    VIKINGDB_HOST: Optional[str] = Field(
+        default="api-vikingdb.mlp.cn-shanghai.volces.com",
         description="The host of the Volcengine VikingDB service.(e.g., 'api-vikingdb.volces.com', \
             'api-vikingdb.mlp.cn-shanghai.volces.com')",
-        default="api-vikingdb.mlp.cn-shanghai.volces.com",
     )
-
-    VIKINGDB_SCHEME: str = Field(
-        description="The scheme of the Volcengine VikingDB service.(e.g., 'http', 'https').",
+    VIKINGDB_SCHEME: Optional[str] = Field(
         default="http",
+        description="The scheme of the Volcengine VikingDB service.(e.g., 'http', 'https').",
     )
-
-    VIKINGDB_CONNECTION_TIMEOUT: int = Field(
-        description="The connection timeout of the Volcengine VikingDB service.",
-        default=30,
+    VIKINGDB_CONNECTION_TIMEOUT: Optional[int] = Field(
+        default=30, description="The connection timeout of the Volcengine VikingDB service."
     )
-
-    VIKINGDB_SOCKET_TIMEOUT: int = Field(
-        description="The socket timeout of the Volcengine VikingDB service.",
-        default=30,
+    VIKINGDB_SOCKET_TIMEOUT: Optional[int] = Field(
+        default=30, description="The socket timeout of the Volcengine VikingDB service."
     )

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="0.10.2",
+        default="0.10.0-beta3",
     )
 
     COMMIT_SHA: str = Field(

api/constants/__init__.py

@@ -12,13 +12,10 @@ VIDEO_EXTENSIONS.extend([ext.upper() for ext in VIDEO_EXTENSIONS])
 AUDIO_EXTENSIONS = ["mp3", "m4a", "wav", "webm", "amr"]
 AUDIO_EXTENSIONS.extend([ext.upper() for ext in AUDIO_EXTENSIONS])
 
+DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls", "docx", "csv"]
+DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])
 
 if dify_config.ETL_TYPE == "Unstructured":
     DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls"]
-    DOCUMENT_EXTENSIONS.extend(("docx", "csv", "eml", "msg", "pptx", "xml", "epub"))
-    if dify_config.UNSTRUCTURED_API_URL:
-        DOCUMENT_EXTENSIONS.append("ppt")
-    DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])
-else:
-    DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls", "docx", "csv"]
+    DOCUMENT_EXTENSIONS.extend(("docx", "csv", "eml", "msg", "pptx", "ppt", "xml", "epub"))
     DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])

api/controllers/console/admin.py

@@ -1,10 +1,10 @@
+import os
 from functools import wraps
 
 from flask import request
 from flask_restful import Resource, reqparse
 from werkzeug.exceptions import NotFound, Unauthorized
 
-from configs import dify_config
 from constants.languages import supported_language
 from controllers.console import api
 from controllers.console.wraps import only_edition_cloud
@@ -15,7 +15,7 @@ from models.model import App, InstalledApp, RecommendedApp
 def admin_required(view):
     @wraps(view)
     def decorated(*args, **kwargs):
-        if not dify_config.ADMIN_API_KEY:
+        if not os.getenv("ADMIN_API_KEY"):
             raise Unauthorized("API key is invalid.")
 
         auth_header = request.headers.get("Authorization")
@@ -31,7 +31,7 @@ def admin_required(view):
         if auth_scheme != "bearer":
             raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
 
-        if dify_config.ADMIN_API_KEY != auth_token:
+        if os.getenv("ADMIN_API_KEY") != auth_token:
             raise Unauthorized("API key is invalid.")
 
         return view(*args, **kwargs)

api/controllers/console/app/generator.py

@@ -52,39 +52,4 @@ class RuleGenerateApi(Resource):
         return rules
 
 
-class RuleCodeGenerateApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument("instruction", type=str, required=True, nullable=False, location="json")
-        parser.add_argument("model_config", type=dict, required=True, nullable=False, location="json")
-        parser.add_argument("no_variable", type=bool, required=True, default=False, location="json")
-        parser.add_argument("code_language", type=str, required=False, default="javascript", location="json")
-        args = parser.parse_args()
-
-        account = current_user
-        CODE_GENERATION_MAX_TOKENS = int(os.getenv("CODE_GENERATION_MAX_TOKENS", "1024"))
-        try:
-            code_result = LLMGenerator.generate_code(
-                tenant_id=account.current_tenant_id,
-                instruction=args["instruction"],
-                model_config=args["model_config"],
-                code_language=args["code_language"],
-                max_tokens=CODE_GENERATION_MAX_TOKENS,
-            )
-        except ProviderTokenNotInitError as ex:
-            raise ProviderNotInitializeError(ex.description)
-        except QuotaExceededError:
-            raise ProviderQuotaExceededError()
-        except ModelCurrentlyNotSupportError:
-            raise ProviderModelCurrentlyNotSupportError()
-        except InvokeError as e:
-            raise CompletionRequestError(e.description)
-
-        return code_result
-
-
 api.add_resource(RuleGenerateApi, "/rule-generate")
-api.add_resource(RuleCodeGenerateApi, "/rule-code-generate")

api/controllers/console/app/message.py

@@ -105,8 +105,6 @@ class ChatMessageListApi(Resource):
             if rest_count > 0:
                 has_more = True
 
-        history_messages = list(reversed(history_messages))
-
         return InfiniteScrollPagination(data=history_messages, limit=args["limit"], has_more=has_more)
 
 

api/controllers/console/app/workflow_statistic.py

@@ -10,10 +10,10 @@ from controllers.console import api
 from controllers.console.app.wraps import get_app_model
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
+from enums import WorkflowRunTriggeredFrom
 from extensions.ext_database import db
 from libs.helper import DatetimeString
 from libs.login import login_required
-from models.enums import WorkflowRunTriggeredFrom
 from models.model import AppMode
 
 

api/controllers/console/auth/activate.py

@@ -1,15 +1,17 @@
+import base64
 import datetime
+import secrets
 
-from flask import request
 from flask_restful import Resource, reqparse
 
 from constants.languages import supported_language
 from controllers.console import api
 from controllers.console.error import AlreadyActivateError
 from extensions.ext_database import db
-from libs.helper import StrLen, email, extract_remote_ip, timezone
-from models.account import AccountStatus, Tenant
-from services.account_service import AccountService, RegisterService
+from libs.helper import StrLen, email, timezone
+from libs.password import hash_password, valid_password
+from models.account import AccountStatus
+from services.account_service import RegisterService
 
 
 class ActivateCheckApi(Resource):
@@ -25,18 +27,8 @@ class ActivateCheckApi(Resource):
         token = args["token"]
 
         invitation = RegisterService.get_invitation_if_token_valid(workspaceId, reg_email, token)
-        if invitation:
-            data = invitation.get("data", {})
-            tenant: Tenant = invitation.get("tenant", None)
-            workspace_name = tenant.name if tenant else None
-            workspace_id = tenant.id if tenant else None
-            invitee_email = data.get("email") if data else None
-            return {
-                "is_valid": invitation is not None,
-                "data": {"workspace_name": workspace_name, "workspace_id": workspace_id, "email": invitee_email},
-            }
-        else:
-            return {"is_valid": False}
+
+        return {"is_valid": invitation is not None, "workspace_name": invitation["tenant"].name if invitation else None}
 
 
 class ActivateApi(Resource):
@@ -46,6 +38,7 @@ class ActivateApi(Resource):
         parser.add_argument("email", type=email, required=False, nullable=True, location="json")
         parser.add_argument("token", type=str, required=True, nullable=False, location="json")
         parser.add_argument("name", type=StrLen(30), required=True, nullable=False, location="json")
+        parser.add_argument("password", type=valid_password, required=True, nullable=False, location="json")
         parser.add_argument(
             "interface_language", type=supported_language, required=True, nullable=False, location="json"
         )
@@ -61,6 +54,15 @@ class ActivateApi(Resource):
         account = invitation["account"]
         account.name = args["name"]
 
+        # generate password salt
+        salt = secrets.token_bytes(16)
+        base64_salt = base64.b64encode(salt).decode()
+
+        # encrypt password with salt
+        password_hashed = hash_password(args["password"], salt)
+        base64_password_hashed = base64.b64encode(password_hashed).decode()
+        account.password = base64_password_hashed
+        account.password_salt = base64_salt
         account.interface_language = args["interface_language"]
         account.timezone = args["timezone"]
         account.interface_theme = "light"
@@ -68,9 +70,7 @@ class ActivateApi(Resource):
         account.initialized_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
         db.session.commit()
 
-        token_pair = AccountService.login(account, ip_address=extract_remote_ip(request))
-
-        return {"result": "success", "data": token_pair.model_dump()}
+        return {"result": "success"}
 
 
 api.add_resource(ActivateCheckApi, "/activate/check")

api/controllers/console/auth/error.py

@@ -27,29 +27,5 @@ class InvalidTokenError(BaseHTTPException):
 
 class PasswordResetRateLimitExceededError(BaseHTTPException):
     error_code = "password_reset_rate_limit_exceeded"
-    description = "Too many password reset emails have been sent. Please try again in 1 minutes."
-    code = 429
-
-
-class EmailCodeError(BaseHTTPException):
-    error_code = "email_code_error"
-    description = "Email code is invalid or expired."
-    code = 400
-
-
-class EmailOrPasswordMismatchError(BaseHTTPException):
-    error_code = "email_or_password_mismatch"
-    description = "The email or password is mismatched."
-    code = 400
-
-
-class EmailPasswordLoginLimitError(BaseHTTPException):
-    error_code = "email_code_login_limit"
-    description = "Too many incorrect password attempts. Please try again later."
-    code = 429
-
-
-class EmailCodeLoginRateLimitExceededError(BaseHTTPException):
-    error_code = "email_code_login_rate_limit_exceeded"
-    description = "Too many login emails have been sent. Please try again in 5 minutes."
+    description = "Password reset rate limit exceeded. Try again later."
     code = 429

api/controllers/console/auth/forgot_password.py

@@ -1,82 +1,65 @@
 import base64
+import logging
 import secrets
 
-from flask import request
 from flask_restful import Resource, reqparse
 
-from constants.languages import languages
 from controllers.console import api
 from controllers.console.auth.error import (
-    EmailCodeError,
     InvalidEmailError,
     InvalidTokenError,
     PasswordMismatchError,
+    PasswordResetRateLimitExceededError,
 )
-from controllers.console.error import EmailSendIpLimitError, NotAllowedRegister
 from controllers.console.setup import setup_required
-from events.tenant_event import tenant_was_created
 from extensions.ext_database import db
-from libs.helper import email, extract_remote_ip
+from libs.helper import email as email_validate
 from libs.password import hash_password, valid_password
-from models.account import Account
-from services.account_service import AccountService, TenantService
-from services.errors.workspace import WorkSpaceNotAllowedCreateError
-from services.feature_service import FeatureService
+from models import Account
+from services.account_service import AccountService
+from services.errors.account import RateLimitExceededError
 
 
 class ForgotPasswordSendEmailApi(Resource):
     @setup_required
     def post(self):
         parser = reqparse.RequestParser()
-        parser.add_argument("email", type=email, required=True, location="json")
-        parser.add_argument("language", type=str, required=False, location="json")
+        parser.add_argument("email", type=str, required=True, location="json")
         args = parser.parse_args()
 
-        ip_address = extract_remote_ip(request)
-        if AccountService.is_email_send_ip_limit(ip_address):
-            raise EmailSendIpLimitError()
+        email = args["email"]
 
-        if args["language"] is not None and args["language"] == "zh-Hans":
-            language = "zh-Hans"
+        if not email_validate(email):
+            raise InvalidEmailError()
+
+        account = Account.query.filter_by(email=email).first()
+
+        if account:
+            try:
+                AccountService.send_reset_password_email(account=account)
+            except RateLimitExceededError:
+                logging.warning(f"Rate limit exceeded for email: {account.email}")
+                raise PasswordResetRateLimitExceededError()
         else:
-            language = "en-US"
+            # Return success to avoid revealing email registration status
+            logging.warning(f"Attempt to reset password for unregistered email: {email}")
 
-        account = Account.query.filter_by(email=args["email"]).first()
-        token = None
-        if account is None:
-            if FeatureService.get_system_features().is_allow_register:
-                token = AccountService.send_reset_password_email(email=args["email"], language=language)
-                return {"result": "fail", "data": token, "code": "account_not_found"}
-            else:
-                raise NotAllowedRegister()
-        else:
-            token = AccountService.send_reset_password_email(account=account, email=args["email"], language=language)
-
-        return {"result": "success", "data": token}
+        return {"result": "success"}
 
 
 class ForgotPasswordCheckApi(Resource):
     @setup_required
     def post(self):
         parser = reqparse.RequestParser()
-        parser.add_argument("email", type=str, required=True, location="json")
-        parser.add_argument("code", type=str, required=True, location="json")
         parser.add_argument("token", type=str, required=True, nullable=False, location="json")
         args = parser.parse_args()
+        token = args["token"]
 
-        user_email = args["email"]
+        reset_data = AccountService.get_reset_password_data(token)
 
-        token_data = AccountService.get_reset_password_data(args["token"])
-        if token_data is None:
-            raise InvalidTokenError()
-
-        if user_email != token_data.get("email"):
-            raise InvalidEmailError()
-
-        if args["code"] != token_data.get("code"):
-            raise EmailCodeError()
-
-        return {"is_valid": True, "email": token_data.get("email")}
+        if reset_data is None:
+            return {"is_valid": False, "email": None}
+        return {"is_valid": True, "email": reset_data.get("email")}
 
 
 class ForgotPasswordResetApi(Resource):
@@ -109,26 +92,9 @@ class ForgotPasswordResetApi(Resource):
         base64_password_hashed = base64.b64encode(password_hashed).decode()
 
         account = Account.query.filter_by(email=reset_data.get("email")).first()
-        if account:
-            account.password = base64_password_hashed
-            account.password_salt = base64_salt
-            db.session.commit()
-            tenant = TenantService.get_join_tenants(account)
-            if not tenant and not FeatureService.get_system_features().is_allow_create_workspace:
-                tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
-                TenantService.create_tenant_member(tenant, account, role="owner")
-                account.current_tenant = tenant
-                tenant_was_created.send(tenant)
-        else:
-            try:
-                account = AccountService.create_account_and_tenant(
-                    email=reset_data.get("email"),
-                    name=reset_data.get("email"),
-                    password=password_confirm,
-                    interface_language=languages[0],
-                )
-            except WorkSpaceNotAllowedCreateError:
-                pass
+        account.password = base64_password_hashed
+        account.password_salt = base64_salt
+        db.session.commit()
 
         return {"result": "success"}
 

api/controllers/console/auth/login.py

@@ -5,29 +5,12 @@ from flask import request
 from flask_restful import Resource, reqparse
 
 import services
-from constants.languages import languages
 from controllers.console import api
-from controllers.console.auth.error import (
-    EmailCodeError,
-    EmailOrPasswordMismatchError,
-    EmailPasswordLoginLimitError,
-    InvalidEmailError,
-    InvalidTokenError,
-)
-from controllers.console.error import (
-    AccountBannedError,
-    EmailSendIpLimitError,
-    NotAllowedCreateWorkspace,
-    NotAllowedRegister,
-)
 from controllers.console.setup import setup_required
-from events.tenant_event import tenant_was_created
 from libs.helper import email, extract_remote_ip
 from libs.password import valid_password
-from models.account import Account
-from services.account_service import AccountService, RegisterService, TenantService
-from services.errors.workspace import WorkSpaceNotAllowedCreateError
-from services.feature_service import FeatureService
+from models import Account
+from services.account_service import AccountService, TenantService
 
 
 class LoginApi(Resource):
@@ -40,43 +23,15 @@ class LoginApi(Resource):
         parser.add_argument("email", type=email, required=True, location="json")
         parser.add_argument("password", type=valid_password, required=True, location="json")
         parser.add_argument("remember_me", type=bool, required=False, default=False, location="json")
-        parser.add_argument("invite_token", type=str, required=False, default=None, location="json")
-        parser.add_argument("language", type=str, required=False, default="en-US", location="json")
         args = parser.parse_args()
 
-        is_login_error_rate_limit = AccountService.is_login_error_rate_limit(args["email"])
-        if is_login_error_rate_limit:
-            raise EmailPasswordLoginLimitError()
-
-        invitation = args["invite_token"]
-        if invitation:
-            invitation = RegisterService.get_invitation_if_token_valid(None, args["email"], invitation)
-
-        if args["language"] is not None and args["language"] == "zh-Hans":
-            language = "zh-Hans"
-        else:
-            language = "en-US"
+        # todo: Verify the recaptcha
 
         try:
-            if invitation:
-                data = invitation.get("data", {})
-                invitee_email = data.get("email") if data else None
-                if invitee_email != args["email"]:
-                    raise InvalidEmailError()
-                account = AccountService.authenticate(args["email"], args["password"], args["invite_token"])
-            else:
-                account = AccountService.authenticate(args["email"], args["password"])
-        except services.errors.account.AccountLoginError:
-            raise AccountBannedError()
-        except services.errors.account.AccountPasswordError:
-            AccountService.add_login_error_rate_limit(args["email"])
-            raise EmailOrPasswordMismatchError()
-        except services.errors.account.AccountNotFoundError:
-            if FeatureService.get_system_features().is_allow_register:
-                token = AccountService.send_reset_password_email(email=args["email"], language=language)
-                return {"result": "fail", "data": token, "code": "account_not_found"}
-            else:
-                raise NotAllowedRegister()
+            account = AccountService.authenticate(args["email"], args["password"])
+        except services.errors.account.AccountLoginError as e:
+            return {"code": "unauthorized", "message": str(e)}, 401
+
         # SELF_HOSTED only have one workspace
         tenants = TenantService.get_join_tenants(account)
         if len(tenants) == 0:
@@ -86,7 +41,7 @@ class LoginApi(Resource):
             }
 
         token_pair = AccountService.login(account=account, ip_address=extract_remote_ip(request))
-        AccountService.reset_login_error_rate_limit(args["email"])
+
         return {"result": "success", "data": token_pair.model_dump()}
 
 
@@ -94,111 +49,60 @@ class LogoutApi(Resource):
     @setup_required
     def get(self):
         account = cast(Account, flask_login.current_user)
-        if isinstance(account, flask_login.AnonymousUserMixin):
-            return {"result": "success"}
         AccountService.logout(account=account)
         flask_login.logout_user()
         return {"result": "success"}
 
 
-class ResetPasswordSendEmailApi(Resource):
+class ResetPasswordApi(Resource):
     @setup_required
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument("email", type=email, required=True, location="json")
-        parser.add_argument("language", type=str, required=False, location="json")
-        args = parser.parse_args()
+    def get(self):
+        # parser = reqparse.RequestParser()
+        # parser.add_argument('email', type=email, required=True, location='json')
+        # args = parser.parse_args()
 
-        if args["language"] is not None and args["language"] == "zh-Hans":
-            language = "zh-Hans"
-        else:
-            language = "en-US"
+        # import mailchimp_transactional as MailchimpTransactional
+        # from mailchimp_transactional.api_client import ApiClientError
 
-        account = AccountService.get_user_through_email(args["email"])
-        if account is None:
-            if FeatureService.get_system_features().is_allow_register:
-                token = AccountService.send_reset_password_email(email=args["email"], language=language)
-            else:
-                raise NotAllowedRegister()
-        else:
-            token = AccountService.send_reset_password_email(account=account, language=language)
+        # account = {'email': args['email']}
+        # account = AccountService.get_by_email(args['email'])
+        # if account is None:
+        #     raise ValueError('Email not found')
+        # new_password = AccountService.generate_password()
+        # AccountService.update_password(account, new_password)
 
-        return {"result": "success", "data": token}
+        # todo: Send email
+        # MAILCHIMP_API_KEY = dify_config.MAILCHIMP_TRANSACTIONAL_API_KEY
+        # mailchimp = MailchimpTransactional(MAILCHIMP_API_KEY)
 
+        # message = {
+        #     'from_email': 'noreply@example.com',
+        #     'to': [{'email': account['email']}],
+        #     'subject': 'Reset your Dify password',
+        #     'html': """
+        #         <p>Dear User,</p>
+        #         <p>The Dify team has generated a new password for you, details as follows:</p>
+        #         <p><strong>{new_password}</strong></p>
+        #         <p>Please change your password to log in as soon as possible.</p>
+        #         <p>Regards,</p>
+        #         <p>The Dify Team</p>
+        #     """
+        # }
 
-class EmailCodeLoginSendEmailApi(Resource):
-    @setup_required
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument("email", type=email, required=True, location="json")
-        parser.add_argument("language", type=str, required=False, location="json")
-        args = parser.parse_args()
+        # response = mailchimp.messages.send({
+        #     'message': message,
+        #     # required for transactional email
+        #     ' settings': {
+        #         'sandbox_mode': dify_config.MAILCHIMP_SANDBOX_MODE,
+        #     },
+        # })
 
-        ip_address = extract_remote_ip(request)
-        if AccountService.is_email_send_ip_limit(ip_address):
-            raise EmailSendIpLimitError()
+        # Check if MSG was sent
+        # if response.status_code != 200:
+        #     # handle error
+        #     pass
 
-        if args["language"] is not None and args["language"] == "zh-Hans":
-            language = "zh-Hans"
-        else:
-            language = "en-US"
-
-        account = AccountService.get_user_through_email(args["email"])
-        if account is None:
-            if FeatureService.get_system_features().is_allow_register:
-                token = AccountService.send_email_code_login_email(email=args["email"], language=language)
-            else:
-                raise NotAllowedRegister()
-        else:
-            token = AccountService.send_email_code_login_email(account=account, language=language)
-
-        return {"result": "success", "data": token}
-
-
-class EmailCodeLoginApi(Resource):
-    @setup_required
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument("email", type=str, required=True, location="json")
-        parser.add_argument("code", type=str, required=True, location="json")
-        parser.add_argument("token", type=str, required=True, location="json")
-        args = parser.parse_args()
-
-        user_email = args["email"]
-
-        token_data = AccountService.get_email_code_login_data(args["token"])
-        if token_data is None:
-            raise InvalidTokenError()
-
-        if token_data["email"] != args["email"]:
-            raise InvalidEmailError()
-
-        if token_data["code"] != args["code"]:
-            raise EmailCodeError()
-
-        AccountService.revoke_email_code_login_token(args["token"])
-        account = AccountService.get_user_through_email(user_email)
-        if account:
-            tenant = TenantService.get_join_tenants(account)
-            if not tenant:
-                if not FeatureService.get_system_features().is_allow_create_workspace:
-                    raise NotAllowedCreateWorkspace()
-                else:
-                    tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
-                    TenantService.create_tenant_member(tenant, account, role="owner")
-                    account.current_tenant = tenant
-                    tenant_was_created.send(tenant)
-
-        if account is None:
-            try:
-                account = AccountService.create_account_and_tenant(
-                    email=user_email, name=user_email, interface_language=languages[0]
-                )
-            except WorkSpaceNotAllowedCreateError:
-                return NotAllowedCreateWorkspace()
-        token_pair = AccountService.login(account, ip_address=extract_remote_ip(request))
-        AccountService.reset_login_error_rate_limit(args["email"])
-        return {"result": "success", "data": token_pair.model_dump()}
+        return {"result": "success"}
 
 
 class RefreshTokenApi(Resource):
@@ -216,7 +120,4 @@ class RefreshTokenApi(Resource):
 
 api.add_resource(LoginApi, "/login")
 api.add_resource(LogoutApi, "/logout")
-api.add_resource(EmailCodeLoginSendEmailApi, "/email-code-login")
-api.add_resource(EmailCodeLoginApi, "/email-code-login/validity")
-api.add_resource(ResetPasswordSendEmailApi, "/reset-password")
 api.add_resource(RefreshTokenApi, "/refresh-token")

api/controllers/console/auth/oauth.py

@@ -5,20 +5,15 @@ from typing import Optional
 import requests
 from flask import current_app, redirect, request
 from flask_restful import Resource
-from werkzeug.exceptions import Unauthorized
 
 from configs import dify_config
 from constants.languages import languages
-from events.tenant_event import tenant_was_created
 from extensions.ext_database import db
 from libs.helper import extract_remote_ip
 from libs.oauth import GitHubOAuth, GoogleOAuth, OAuthUserInfo
 from models import Account
 from models.account import AccountStatus
 from services.account_service import AccountService, RegisterService, TenantService
-from services.errors.account import AccountNotFoundError
-from services.errors.workspace import WorkSpaceNotAllowedCreateError, WorkSpaceNotFoundError
-from services.feature_service import FeatureService
 
 from .. import api
 
@@ -48,7 +43,6 @@ def get_oauth_providers():
 
 class OAuthLogin(Resource):
     def get(self, provider: str):
-        invite_token = request.args.get("invite_token") or None
         OAUTH_PROVIDERS = get_oauth_providers()
         with current_app.app_context():
             oauth_provider = OAUTH_PROVIDERS.get(provider)
@@ -56,7 +50,7 @@ class OAuthLogin(Resource):
         if not oauth_provider:
             return {"error": "Invalid provider"}, 400
 
-        auth_url = oauth_provider.get_authorization_url(invite_token=invite_token)
+        auth_url = oauth_provider.get_authorization_url()
         return redirect(auth_url)
 
 
@@ -69,11 +63,6 @@ class OAuthCallback(Resource):
             return {"error": "Invalid provider"}, 400
 
         code = request.args.get("code")
-        state = request.args.get("state")
-        invite_token = None
-        if state:
-            invite_token = state
-
         try:
             token = oauth_provider.get_access_token(code)
             user_info = oauth_provider.get_user_info(token)
@@ -81,43 +70,17 @@ class OAuthCallback(Resource):
             logging.exception(f"An error occurred during the OAuth process with {provider}: {e.response.text}")
             return {"error": "OAuth process failed"}, 400
 
-        if invite_token and RegisterService.is_valid_invite_token(invite_token):
-            invitation = RegisterService._get_invitation_by_token(token=invite_token)
-            if invitation:
-                invitation_email = invitation.get("email", None)
-                if invitation_email != user_info.email:
-                    return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Invalid invitation token.")
-
-            return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin/invite-settings?invite_token={invite_token}")
-
-        try:
-            account = _generate_account(provider, user_info)
-        except AccountNotFoundError:
-            return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Account not found.")
-        except (WorkSpaceNotFoundError, WorkSpaceNotAllowedCreateError):
-            return redirect(
-                f"{dify_config.CONSOLE_WEB_URL}/signin"
-                "?message=Workspace not found, please contact system admin to invite you to join in a workspace."
-            )
-
+        account = _generate_account(provider, user_info)
         # Check account status
-        if account.status == AccountStatus.BANNED.value:
-            return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Account is banned.")
+        if account.status in {AccountStatus.BANNED.value, AccountStatus.CLOSED.value}:
+            return {"error": "Account is banned or closed."}, 403
 
         if account.status == AccountStatus.PENDING.value:
             account.status = AccountStatus.ACTIVE.value
             account.initialized_at = datetime.now(timezone.utc).replace(tzinfo=None)
             db.session.commit()
 
-        try:
-            TenantService.create_owner_tenant_if_not_exist(account)
-        except Unauthorized:
-            return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Workspace not found.")
-        except WorkSpaceNotAllowedCreateError:
-            return redirect(
-                f"{dify_config.CONSOLE_WEB_URL}/signin"
-                "?message=Workspace not found, please contact system admin to invite you to join in a workspace."
-            )
+        TenantService.create_owner_tenant_if_not_exist(account)
 
         token_pair = AccountService.login(
             account=account,
@@ -142,20 +105,8 @@ def _generate_account(provider: str, user_info: OAuthUserInfo):
     # Get account by openid or email.
     account = _get_account_by_openid_or_email(provider, user_info)
 
-    if account:
-        tenant = TenantService.get_join_tenants(account)
-        if not tenant:
-            if not FeatureService.get_system_features().is_allow_create_workspace:
-                raise WorkSpaceNotAllowedCreateError()
-            else:
-                tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
-                TenantService.create_tenant_member(tenant, account, role="owner")
-                account.current_tenant = tenant
-                tenant_was_created.send(tenant)
-
     if not account:
-        if not FeatureService.get_system_features().is_allow_register:
-            raise AccountNotFoundError()
+        # Create account
         account_name = user_info.name or "Dify"
         account = RegisterService.register(
             email=user_info.email, name=account_name, password=None, open_id=user_info.id, provider=provider

api/controllers/console/datasets/datasets.py

@@ -102,13 +102,6 @@ class DatasetListApi(Resource):
             help="type is required. Name must be between 1 to 40 characters.",
             type=_validate_name,
         )
-        parser.add_argument(
-            "description",
-            type=str,
-            nullable=True,
-            required=False,
-            default="",
-        )
         parser.add_argument(
             "indexing_technique",
             type=str,
@@ -147,7 +140,6 @@ class DatasetListApi(Resource):
             dataset = DatasetService.create_empty_dataset(
                 tenant_id=current_user.current_tenant_id,
                 name=args["name"],
-                description=args["description"],
                 indexing_technique=args["indexing_technique"],
                 account=current_user,
                 permission=DatasetPermissionEnum.ONLY_ME,
@@ -627,7 +619,6 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.PGVECTO_RS
                 | VectorType.BAIDU
                 | VectorType.VIKINGDB
-                | VectorType.UPSTASH
             ):
                 return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
             case (
@@ -639,7 +630,6 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.ORACLE
                 | VectorType.ELASTICSEARCH
                 | VectorType.PGVECTOR
-                | VectorType.TIDB_ON_QDRANT
             ):
                 return {
                     "retrieval_method": [
@@ -667,7 +657,6 @@ class DatasetRetrievalSettingMockApi(Resource):
                 | VectorType.PGVECTO_RS
                 | VectorType.BAIDU
                 | VectorType.VIKINGDB
-                | VectorType.UPSTASH
             ):
                 return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
             case (

api/controllers/console/datasets/file.py

@@ -2,7 +2,7 @@ import urllib.parse
 
 from flask import request
 from flask_login import current_user
-from flask_restful import Resource, marshal_with, reqparse
+from flask_restful import Resource, marshal_with
 
 import services
 from configs import dify_config
@@ -30,12 +30,13 @@ class FileApi(Resource):
     @account_initialization_required
     @marshal_with(upload_config_fields)
     def get(self):
+        file_size_limit = dify_config.UPLOAD_FILE_SIZE_LIMIT
+        batch_count_limit = dify_config.UPLOAD_FILE_BATCH_LIMIT
+        image_file_size_limit = dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT
         return {
-            "file_size_limit": dify_config.UPLOAD_FILE_SIZE_LIMIT,
-            "batch_count_limit": dify_config.UPLOAD_FILE_BATCH_LIMIT,
-            "image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT,
-            "video_file_size_limit": dify_config.UPLOAD_VIDEO_FILE_SIZE_LIMIT,
-            "audio_file_size_limit": dify_config.UPLOAD_AUDIO_FILE_SIZE_LIMIT,
+            "file_size_limit": file_size_limit,
+            "batch_count_limit": batch_count_limit,
+            "image_file_size_limit": image_file_size_limit,
         }, 200
 
     @setup_required
@@ -47,10 +48,6 @@ class FileApi(Resource):
         # get file from request
         file = request.files["file"]
 
-        parser = reqparse.RequestParser()
-        parser.add_argument("source", type=str, required=False, location="args")
-        source = parser.parse_args().get("source")
-
         # check file
         if "file" not in request.files:
             raise NoFileUploadedError()
@@ -58,7 +55,7 @@ class FileApi(Resource):
         if len(request.files) > 1:
             raise TooManyFilesError()
         try:
-            upload_file = FileService.upload_file(file=file, user=current_user, source=source)
+            upload_file = FileService.upload_file(file=file, user=current_user)
         except services.errors.file.FileTooLargeError as file_too_large_error:
             raise FileTooLargeError(file_too_large_error.description)
         except services.errors.file.UnsupportedFileTypeError:

api/controllers/console/datasets/hit_testing.py

@@ -1,24 +1,88 @@
-from flask_restful import Resource
+import logging
 
+from flask_login import current_user
+from flask_restful import Resource, marshal, reqparse
+from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
+
+import services
 from controllers.console import api
-from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase
+from controllers.console.app.error import (
+    CompletionRequestError,
+    ProviderModelCurrentlyNotSupportError,
+    ProviderNotInitializeError,
+    ProviderQuotaExceededError,
+)
+from controllers.console.datasets.error import DatasetNotInitializedError
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
+from core.errors.error import (
+    LLMBadRequestError,
+    ModelCurrentlyNotSupportError,
+    ProviderTokenNotInitError,
+    QuotaExceededError,
+)
+from core.model_runtime.errors.invoke import InvokeError
+from fields.hit_testing_fields import hit_testing_record_fields
 from libs.login import login_required
+from services.dataset_service import DatasetService
+from services.hit_testing_service import HitTestingService
 
 
-class HitTestingApi(Resource, DatasetsHitTestingBase):
+class HitTestingApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
     def post(self, dataset_id):
         dataset_id_str = str(dataset_id)
 
-        dataset = self.get_and_validate_dataset(dataset_id_str)
-        args = self.parse_args()
-        self.hit_testing_args_check(args)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
 
-        return self.perform_hit_testing(dataset, args)
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("query", type=str, location="json")
+        parser.add_argument("retrieval_model", type=dict, required=False, location="json")
+        parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
+        args = parser.parse_args()
+
+        HitTestingService.hit_testing_args_check(args)
+
+        try:
+            response = HitTestingService.retrieve(
+                dataset=dataset,
+                query=args["query"],
+                account=current_user,
+                retrieval_model=args["retrieval_model"],
+                external_retrieval_model=args["external_retrieval_model"],
+                limit=10,
+            )
+
+            return {"query": response["query"], "records": marshal(response["records"], hit_testing_record_fields)}
+        except services.errors.index.IndexNotInitializedError:
+            raise DatasetNotInitializedError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except LLMBadRequestError:
+            raise ProviderNotInitializeError(
+                "No Embedding Model or Reranking Model available. Please configure a valid provider "
+                "in the Settings -> Model Provider."
+            )
+        except InvokeError as e:
+            raise CompletionRequestError(e.description)
+        except ValueError as e:
+            raise ValueError(str(e))
+        except Exception as e:
+            logging.exception("Hit testing failed.")
+            raise InternalServerError(str(e))
 
 
 api.add_resource(HitTestingApi, "/datasets/<uuid:dataset_id>/hit-testing")

api/controllers/console/datasets/hit_testing_base.py

@@ -1,85 +0,0 @@
-import logging
-
-from flask_login import current_user
-from flask_restful import marshal, reqparse
-from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
-
-import services.dataset_service
-from controllers.console.app.error import (
-    CompletionRequestError,
-    ProviderModelCurrentlyNotSupportError,
-    ProviderNotInitializeError,
-    ProviderQuotaExceededError,
-)
-from controllers.console.datasets.error import DatasetNotInitializedError
-from core.errors.error import (
-    LLMBadRequestError,
-    ModelCurrentlyNotSupportError,
-    ProviderTokenNotInitError,
-    QuotaExceededError,
-)
-from core.model_runtime.errors.invoke import InvokeError
-from fields.hit_testing_fields import hit_testing_record_fields
-from services.dataset_service import DatasetService
-from services.hit_testing_service import HitTestingService
-
-
-class DatasetsHitTestingBase:
-    @staticmethod
-    def get_and_validate_dataset(dataset_id: str):
-        dataset = DatasetService.get_dataset(dataset_id)
-        if dataset is None:
-            raise NotFound("Dataset not found.")
-
-        try:
-            DatasetService.check_dataset_permission(dataset, current_user)
-        except services.errors.account.NoPermissionError as e:
-            raise Forbidden(str(e))
-
-        return dataset
-
-    @staticmethod
-    def hit_testing_args_check(args):
-        HitTestingService.hit_testing_args_check(args)
-
-    @staticmethod
-    def parse_args():
-        parser = reqparse.RequestParser()
-
-        parser.add_argument("query", type=str, location="json")
-        parser.add_argument("retrieval_model", type=dict, required=False, location="json")
-        parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
-        return parser.parse_args()
-
-    @staticmethod
-    def perform_hit_testing(dataset, args):
-        try:
-            response = HitTestingService.retrieve(
-                dataset=dataset,
-                query=args["query"],
-                account=current_user,
-                retrieval_model=args["retrieval_model"],
-                external_retrieval_model=args["external_retrieval_model"],
-                limit=10,
-            )
-            return {"query": response["query"], "records": marshal(response["records"], hit_testing_record_fields)}
-        except services.errors.index.IndexNotInitializedError:
-            raise DatasetNotInitializedError()
-        except ProviderTokenNotInitError as ex:
-            raise ProviderNotInitializeError(ex.description)
-        except QuotaExceededError:
-            raise ProviderQuotaExceededError()
-        except ModelCurrentlyNotSupportError:
-            raise ProviderModelCurrentlyNotSupportError()
-        except LLMBadRequestError:
-            raise ProviderNotInitializeError(
-                "No Embedding Model or Reranking Model available. Please configure a valid provider "
-                "in the Settings -> Model Provider."
-            )
-        except InvokeError as e:
-            raise CompletionRequestError(e.description)
-        except ValueError as e:
-            raise ValueError(str(e))
-        except Exception as e:
-            logging.exception("Hit testing failed.")
-            raise InternalServerError(str(e))

api/controllers/console/error.py

@@ -38,27 +38,3 @@ class AlreadyActivateError(BaseHTTPException):
     error_code = "already_activate"
     description = "Auth Token is invalid or account already activated, please check again."
     code = 403
-
-
-class NotAllowedCreateWorkspace(BaseHTTPException):
-    error_code = "not_allowed_create_workspace"
-    description = "Workspace not found, please contact system admin to invite you to join in a workspace."
-    code = 400
-
-
-class AccountBannedError(BaseHTTPException):
-    error_code = "account_banned"
-    description = "Account is banned."
-    code = 400
-
-
-class NotAllowedRegister(BaseHTTPException):
-    error_code = "unauthorized"
-    description = "Account not found."
-    code = 400
-
-
-class EmailSendIpLimitError(BaseHTTPException):
-    error_code = "email_send_ip_limit"
-    description = "Too many emails have been sent from this IP address recently. Please try again later."
-    code = 429

api/controllers/console/explore/parameter.py

@@ -21,12 +21,7 @@ class AppParameterApi(InstalledAppResource):
         "options": fields.List(fields.String),
     }
 
-    system_parameters_fields = {
-        "image_file_size_limit": fields.Integer,
-        "video_file_size_limit": fields.Integer,
-        "audio_file_size_limit": fields.Integer,
-        "file_size_limit": fields.Integer,
-    }
+    system_parameters_fields = {"image_file_size_limit": fields.String}
 
     parameters_fields = {
         "opening_statement": fields.String,
@@ -87,12 +82,7 @@ class AppParameterApi(InstalledAppResource):
                     }
                 },
             ),
-            "system_parameters": {
-                "image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT,
-                "video_file_size_limit": dify_config.UPLOAD_VIDEO_FILE_SIZE_LIMIT,
-                "audio_file_size_limit": dify_config.UPLOAD_AUDIO_FILE_SIZE_LIMIT,
-                "file_size_limit": dify_config.UPLOAD_FILE_SIZE_LIMIT,
-            },
+            "system_parameters": {"image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT},
         }
 
 

api/controllers/files/image_preview.py

@@ -1,5 +1,5 @@
 from flask import Response, request
-from flask_restful import Resource, reqparse
+from flask_restful import Resource
 from werkzeug.exceptions import NotFound
 
 import services
@@ -10,10 +10,6 @@ from services.file_service import FileService
 
 
 class ImagePreviewApi(Resource):
-    """
-    Deprecated
-    """
-
     def get(self, file_id):
         file_id = str(file_id)
 
@@ -41,39 +37,24 @@ class FilePreviewApi(Resource):
     def get(self, file_id):
         file_id = str(file_id)
 
-        parser = reqparse.RequestParser()
-        parser.add_argument("timestamp", type=str, required=True, location="args")
-        parser.add_argument("nonce", type=str, required=True, location="args")
-        parser.add_argument("sign", type=str, required=True, location="args")
-        parser.add_argument("as_attachment", type=bool, required=False, default=False, location="args")
+        timestamp = request.args.get("timestamp")
+        nonce = request.args.get("nonce")
+        sign = request.args.get("sign")
 
-        args = parser.parse_args()
-
-        if not args["timestamp"] or not args["nonce"] or not args["sign"]:
+        if not timestamp or not nonce or not sign:
             return {"content": "Invalid request."}, 400
 
         try:
-            generator, upload_file = FileService.get_file_generator_by_file_id(
+            generator, mimetype = FileService.get_signed_file_preview(
                 file_id=file_id,
-                timestamp=args["timestamp"],
-                nonce=args["nonce"],
-                sign=args["sign"],
+                timestamp=timestamp,
+                nonce=nonce,
+                sign=sign,
             )
         except services.errors.file.UnsupportedFileTypeError:
             raise UnsupportedFileTypeError()
 
-        response = Response(
-            generator,
-            mimetype=upload_file.mime_type,
-            direct_passthrough=True,
-            headers={},
-        )
-        if upload_file.size > 0:
-            response.headers["Content-Length"] = str(upload_file.size)
-        if args["as_attachment"]:
-            response.headers["Content-Disposition"] = f"attachment; filename={upload_file.name}"
-
-        return response
+        return Response(generator, mimetype=mimetype)
 
 
 class WorkspaceWebappLogoApi(Resource):

api/controllers/files/tool_files.py

@@ -16,7 +16,6 @@ class ToolFilePreviewApi(Resource):
         parser.add_argument("timestamp", type=str, required=True, location="args")
         parser.add_argument("nonce", type=str, required=True, location="args")
         parser.add_argument("sign", type=str, required=True, location="args")
-        parser.add_argument("as_attachment", type=bool, required=False, default=False, location="args")
 
         args = parser.parse_args()
 
@@ -29,27 +28,18 @@ class ToolFilePreviewApi(Resource):
             raise Forbidden("Invalid request.")
 
         try:
-            stream, tool_file = ToolFileManager.get_file_generator_by_tool_file_id(
+            result = ToolFileManager.get_file_generator_by_tool_file_id(
                 file_id,
             )
 
-            if not stream or not tool_file:
+            if not result:
                 raise NotFound("file is not found")
+
+            generator, mimetype = result
         except Exception:
             raise UnsupportedFileTypeError()
 
-        response = Response(
-            stream,
-            mimetype=tool_file.mimetype,
-            direct_passthrough=True,
-            headers={},
-        )
-        if tool_file.size > 0:
-            response.headers["Content-Length"] = str(tool_file.size)
-        if args["as_attachment"]:
-            response.headers["Content-Disposition"] = f"attachment; filename={tool_file.name}"
-
-        return response
+        return Response(generator, mimetype=mimetype)
 
 
 api.add_resource(ToolFilePreviewApi, "/files/tools/<uuid:file_id>.<string:extension>")

api/controllers/inner_api/workspace/workspace.py

@@ -21,7 +21,7 @@ class EnterpriseWorkspace(Resource):
         if account is None:
             return {"message": "owner account not found."}, 404
 
-        tenant = TenantService.create_tenant(args["name"], is_from_dashboard=True)
+        tenant = TenantService.create_tenant(args["name"])
         TenantService.create_tenant_member(tenant, account, role="owner")
 
         tenant_was_created.send(tenant)

api/controllers/service_api/__init__.py

@@ -5,6 +5,7 @@ from libs.external_api import ExternalApi
 bp = Blueprint("service_api", __name__, url_prefix="/v1")
 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, segment

api/controllers/service_api/app/app.py

@@ -21,12 +21,7 @@ class AppParameterApi(Resource):
         "options": fields.List(fields.String),
     }
 
-    system_parameters_fields = {
-        "image_file_size_limit": fields.Integer,
-        "video_file_size_limit": fields.Integer,
-        "audio_file_size_limit": fields.Integer,
-        "file_size_limit": fields.Integer,
-    }
+    system_parameters_fields = {"image_file_size_limit": fields.String}
 
     parameters_fields = {
         "opening_statement": fields.String,
@@ -86,12 +81,7 @@ class AppParameterApi(Resource):
                     }
                 },
             ),
-            "system_parameters": {
-                "image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT,
-                "video_file_size_limit": dify_config.UPLOAD_VIDEO_FILE_SIZE_LIMIT,
-                "audio_file_size_limit": dify_config.UPLOAD_AUDIO_FILE_SIZE_LIMIT,
-                "file_size_limit": dify_config.UPLOAD_FILE_SIZE_LIMIT,
-            },
+            "system_parameters": {"image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT},
         }
 
 

api/controllers/service_api/app/completion.py

@@ -4,6 +4,7 @@ from flask_restful import Resource, reqparse
 from werkzeug.exceptions import InternalServerError, NotFound
 
 import services
+from constants import UUID_NIL
 from controllers.service_api import api
 from controllers.service_api.app.error import (
     AppUnavailableError,
@@ -107,6 +108,7 @@ class ChatApi(Resource):
         parser.add_argument("conversation_id", type=uuid_value, location="json")
         parser.add_argument("retriever_from", type=str, required=False, default="dev", location="json")
         parser.add_argument("auto_generate_name", type=bool, required=False, default=True, location="json")
+        parser.add_argument("parent_message_id", type=uuid_value, required=False, default=UUID_NIL, location="json")
 
         args = parser.parse_args()
 

api/controllers/service_api/app/message.py

@@ -48,7 +48,7 @@ class MessageListApi(Resource):
         "tool_input": fields.String,
         "created_at": TimestampField,
         "observation": fields.String,
-        "message_files": fields.List(fields.Nested(message_file_fields)),
+        "message_files": fields.List(fields.String),
     }
 
     message_fields = {

api/controllers/service_api/dataset/dataset.py

@@ -66,13 +66,6 @@ class DatasetListApi(DatasetApiResource):
             help="type is required. Name must be between 1 to 40 characters.",
             type=_validate_name,
         )
-        parser.add_argument(
-            "description",
-            type=str,
-            nullable=True,
-            required=False,
-            default="",
-        )
         parser.add_argument(
             "indexing_technique",
             type=str,
@@ -115,7 +108,6 @@ class DatasetListApi(DatasetApiResource):
             dataset = DatasetService.create_empty_dataset(
                 tenant_id=tenant_id,
                 name=args["name"],
-                description=args["description"],
                 indexing_technique=args["indexing_technique"],
                 account=current_user,
                 permission=args["permission"],

api/controllers/service_api/dataset/hit_testing.py

@@ -1,17 +0,0 @@
-from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase
-from controllers.service_api import api
-from controllers.service_api.wraps import DatasetApiResource
-
-
-class HitTestingApi(DatasetApiResource, DatasetsHitTestingBase):
-    def post(self, tenant_id, dataset_id):
-        dataset_id_str = str(dataset_id)
-
-        dataset = self.get_and_validate_dataset(dataset_id_str)
-        args = self.parse_args()
-        self.hit_testing_args_check(args)
-
-        return self.perform_hit_testing(dataset, args)
-
-
-api.add_resource(HitTestingApi, "/datasets/<uuid:dataset_id>/hit-testing")

api/controllers/web/app.py

@@ -21,12 +21,7 @@ class AppParameterApi(WebApiResource):
         "options": fields.List(fields.String),
     }
 
-    system_parameters_fields = {
-        "image_file_size_limit": fields.Integer,
-        "video_file_size_limit": fields.Integer,
-        "audio_file_size_limit": fields.Integer,
-        "file_size_limit": fields.Integer,
-    }
+    system_parameters_fields = {"image_file_size_limit": fields.String}
 
     parameters_fields = {
         "opening_statement": fields.String,
@@ -85,12 +80,7 @@ class AppParameterApi(WebApiResource):
                     }
                 },
             ),
-            "system_parameters": {
-                "image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT,
-                "video_file_size_limit": dify_config.UPLOAD_VIDEO_FILE_SIZE_LIMIT,
-                "audio_file_size_limit": dify_config.UPLOAD_AUDIO_FILE_SIZE_LIMIT,
-                "file_size_limit": dify_config.UPLOAD_FILE_SIZE_LIMIT,
-            },
+            "system_parameters": {"image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT},
         }
 
 

api/controllers/web/file.py

@@ -1,7 +1,7 @@
 import urllib.parse
 
 from flask import request
-from flask_restful import marshal_with, reqparse
+from flask_restful import marshal_with
 
 import services
 from controllers.web import api
@@ -18,10 +18,6 @@ class FileApi(WebApiResource):
         # get file from request
         file = request.files["file"]
 
-        parser = reqparse.RequestParser()
-        parser.add_argument("source", type=str, required=False, location="args")
-        source = parser.parse_args().get("source")
-
         # check file
         if "file" not in request.files:
             raise NoFileUploadedError()
@@ -29,7 +25,7 @@ class FileApi(WebApiResource):
         if len(request.files) > 1:
             raise TooManyFilesError()
         try:
-            upload_file = FileService.upload_file(file=file, user=end_user, source=source)
+            upload_file = FileService.upload_file(file, end_user)
         except services.errors.file.FileTooLargeError as file_too_large_error:
             raise FileTooLargeError(file_too_large_error.description)
         except services.errors.file.UnsupportedFileTypeError:
@@ -46,7 +42,7 @@ class RemoteFileInfoApi(WebApiResource):
             response = ssrf_proxy.head(decoded_url)
             return {
                 "file_type": response.headers.get("Content-Type", "application/octet-stream"),
-                "file_length": int(response.headers.get("Content-Length", -1)),
+                "file_length": int(response.headers.get("Content-Length", 0)),
             }
         except Exception as e:
             return {"error": str(e)}, 400

api/core/agent/base_agent_runner.py

@@ -165,12 +165,6 @@ class BaseAgentRunner(AppRunner):
                 continue
 
             parameter_type = parameter.type.as_normal_type()
-            if parameter.type in {
-                ToolParameter.ToolParameterType.SYSTEM_FILES,
-                ToolParameter.ToolParameterType.FILE,
-                ToolParameter.ToolParameterType.FILES,
-            }:
-                continue
             enum = []
             if parameter.type == ToolParameter.ToolParameterType.SELECT:
                 enum = [option.value for option in parameter.options]
@@ -256,12 +250,6 @@ class BaseAgentRunner(AppRunner):
                 continue
 
             parameter_type = parameter.type.as_normal_type()
-            if parameter.type in {
-                ToolParameter.ToolParameterType.SYSTEM_FILES,
-                ToolParameter.ToolParameterType.FILE,
-                ToolParameter.ToolParameterType.FILES,
-            }:
-                continue
             enum = []
             if parameter.type == ToolParameter.ToolParameterType.SELECT:
                 enum = [option.value for option in parameter.options]

api/core/agent/output_parser/cot_output_parser.py

@@ -62,8 +62,6 @@ class CotAgentOutputParser:
         thought_str = "thought:"
         thought_idx = 0
 
-        last_character = ""
-
         for response in llm_response:
             if response.delta.usage:
                 usage_dict["usage"] = response.delta.usage
@@ -76,38 +74,35 @@ class CotAgentOutputParser:
             while index < len(response):
                 steps = 1
                 delta = response[index : index + steps]
-                yield_delta = False
+                last_character = response[index - 1] if index > 0 else ""
 
                 if delta == "`":
-                    last_character = delta
                     code_block_cache += delta
                     code_block_delimiter_count += 1
                 else:
                     if not in_code_block:
                         if code_block_delimiter_count > 0:
-                            last_character = delta
                             yield code_block_cache
                         code_block_cache = ""
                     else:
-                        last_character = delta
                         code_block_cache += delta
                     code_block_delimiter_count = 0
 
                 if not in_code_block and not in_json:
                     if delta.lower() == action_str[action_idx] and action_idx == 0:
                         if last_character not in {"\n", " ", ""}:
-                            yield_delta = True
-                        else:
-                            last_character = delta
-                            action_cache += delta
-                            action_idx += 1
-                            if action_idx == len(action_str):
-                                action_cache = ""
-                                action_idx = 0
                             index += steps
+                            yield delta
                             continue
+
+                        action_cache += delta
+                        action_idx += 1
+                        if action_idx == len(action_str):
+                            action_cache = ""
+                            action_idx = 0
+                        index += steps
+                        continue
                     elif delta.lower() == action_str[action_idx] and action_idx > 0:
-                        last_character = delta
                         action_cache += delta
                         action_idx += 1
                         if action_idx == len(action_str):
@@ -117,25 +112,24 @@ class CotAgentOutputParser:
                         continue
                     else:
                         if action_cache:
-                            last_character = delta
                             yield action_cache
                             action_cache = ""
                             action_idx = 0
 
                     if delta.lower() == thought_str[thought_idx] and thought_idx == 0:
                         if last_character not in {"\n", " ", ""}:
-                            yield_delta = True
-                        else:
-                            last_character = delta
-                            thought_cache += delta
-                            thought_idx += 1
-                            if thought_idx == len(thought_str):
-                                thought_cache = ""
-                                thought_idx = 0
                             index += steps
+                            yield delta
                             continue
+
+                        thought_cache += delta
+                        thought_idx += 1
+                        if thought_idx == len(thought_str):
+                            thought_cache = ""
+                            thought_idx = 0
+                        index += steps
+                        continue
                     elif delta.lower() == thought_str[thought_idx] and thought_idx > 0:
-                        last_character = delta
                         thought_cache += delta
                         thought_idx += 1
                         if thought_idx == len(thought_str):
@@ -145,20 +139,12 @@ class CotAgentOutputParser:
                         continue
                     else:
                         if thought_cache:
-                            last_character = delta
                             yield thought_cache
                             thought_cache = ""
                             thought_idx = 0
 
-                    if yield_delta:
-                        index += steps
-                        last_character = delta
-                        yield delta
-                        continue
-
                 if code_block_delimiter_count == 3:
                     if in_code_block:
-                        last_character = delta
                         yield from extra_json_from_code_block(code_block_cache)
                         code_block_cache = ""
 
@@ -170,10 +156,8 @@ class CotAgentOutputParser:
                     if delta == "{":
                         json_quote_count += 1
                         in_json = True
-                        last_character = delta
                         json_cache += delta
                     elif delta == "}":
-                        last_character = delta
                         json_cache += delta
                         if json_quote_count > 0:
                             json_quote_count -= 1
@@ -184,19 +168,16 @@ class CotAgentOutputParser:
                                 continue
                     else:
                         if in_json:
-                            last_character = delta
                             json_cache += delta
 
                     if got_json:
                         got_json = False
-                        last_character = delta
                         yield parse_action(json_cache)
                         json_cache = ""
                         json_quote_count = 0
                         in_json = False
 
                 if not in_code_block and not in_json:
-                    last_character = delta
                     yield delta.replace("`", "")
 
                 index += steps

api/core/app/app_config/easy_ui_based_app/variables/manager.py

@@ -53,11 +53,11 @@ class BasicVariablesConfigManager:
                     VariableEntity(
                         type=variable_type,
                         variable=variable.get("variable"),
-                        description=variable.get("description") or "",
+                        description=variable.get("description", ""),
                         label=variable.get("label"),
                         required=variable.get("required", False),
                         max_length=variable.get("max_length"),
-                        options=variable.get("options") or [],
+                        options=variable.get("options", []),
                     )
                 )
 

api/core/app/app_config/entities.py

@@ -2,7 +2,7 @@ from collections.abc import Sequence
 from enum import Enum
 from typing import Any, Optional
 
-from pydantic import BaseModel, Field, field_validator
+from pydantic import BaseModel, Field
 
 from core.file import FileExtraConfig, FileTransferMethod, FileType
 from core.model_runtime.entities.message_entities import PromptMessageRole
@@ -114,16 +114,6 @@ class VariableEntity(BaseModel):
     allowed_file_extensions: Sequence[str] = Field(default_factory=list)
     allowed_file_upload_methods: Sequence[FileTransferMethod] = Field(default_factory=list)
 
-    @field_validator("description", mode="before")
-    @classmethod
-    def convert_none_description(cls, v: Any) -> str:
-        return v or ""
-
-    @field_validator("options", mode="before")
-    @classmethod
-    def convert_none_options(cls, v: Any) -> Sequence[str]:
-        return v or []
-
 
 class ExternalDataVariableEntity(BaseModel):
     """

api/core/app/app_config/features/file_upload/manager.py

@@ -17,13 +17,10 @@ class FileUploadConfigManager:
         file_upload_dict = config.get("file_upload")
         if file_upload_dict:
             if file_upload_dict.get("enabled"):
-                transform_methods = file_upload_dict.get("allowed_file_upload_methods") or file_upload_dict.get(
-                    "allowed_upload_methods", []
-                )
                 data = {
                     "image_config": {
                         "number_limits": file_upload_dict["number_limits"],
-                        "transfer_methods": transform_methods,
+                        "transfer_methods": file_upload_dict["allowed_file_upload_methods"],
                     }
                 }
 

api/core/app/apps/advanced_chat/app_generator.py

@@ -10,7 +10,6 @@ from flask import Flask, current_app
 from pydantic import ValidationError
 
 import contexts
-from constants import UUID_NIL
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.app.apps.advanced_chat.app_config_manager import AdvancedChatAppConfigManager
 from core.app.apps.advanced_chat.app_runner import AdvancedChatAppRunner
@@ -23,10 +22,10 @@ from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity,
 from core.app.entities.task_entities import ChatbotAppBlockingResponse, ChatbotAppStreamResponse
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.ops.ops_trace_manager import TraceQueueManager
+from enums import CreatedByRole
 from extensions.ext_database import db
 from factories import file_factory
 from models.account import Account
-from models.enums import CreatedByRole
 from models.model import App, Conversation, EndUser, Message
 from models.workflow import Workflow
 
@@ -133,7 +132,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
             query=query,
             files=file_objs,
-            parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
+            parent_message_id=args.get("parent_message_id"),
             user_id=user.id,
             stream=stream,
             invoke_from=invoke_from,

api/core/app/apps/advanced_chat/app_runner.py

@@ -20,8 +20,8 @@ from core.workflow.callbacks import WorkflowCallback, WorkflowLoggingCallback
 from core.workflow.entities.variable_pool import VariablePool
 from core.workflow.enums import SystemVariableKey
 from core.workflow.workflow_entry import WorkflowEntry
+from enums import UserFrom
 from extensions.ext_database import db
-from models.enums import UserFrom
 from models.model import App, Conversation, EndUser, Message
 from models.workflow import ConversationVariable, WorkflowType
 

api/core/app/apps/advanced_chat/generate_task_pipeline.py

@@ -51,12 +51,12 @@ from core.model_runtime.utils.encoders import jsonable_encoder
 from core.ops.ops_trace_manager import TraceQueueManager
 from core.workflow.enums import SystemVariableKey
 from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState
-from core.workflow.nodes import NodeType
+from enums import CreatedByRole
+from enums.workflow_nodes import NodeType
 from events.message_event import message_was_created
 from extensions.ext_database import db
 from models import Conversation, EndUser, Message, MessageFile
 from models.account import Account
-from models.enums import CreatedByRole
 from models.workflow import (
     Workflow,
     WorkflowNodeExecution,

api/core/app/apps/agent_chat/app_generator.py

@@ -8,7 +8,6 @@ from typing import Any, Literal, Union, overload
 from flask import Flask, current_app
 from pydantic import ValidationError
 
-from constants import UUID_NIL
 from core.app.app_config.easy_ui_based_app.model_config.converter import ModelConfigConverter
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.app.apps.agent_chat.app_config_manager import AgentChatAppConfigManager
@@ -20,10 +19,10 @@ from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueMa
 from core.app.entities.app_invoke_entities import AgentChatAppGenerateEntity, InvokeFrom
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.ops.ops_trace_manager import TraceQueueManager
+from enums import CreatedByRole
 from extensions.ext_database import db
 from factories import file_factory
 from models import Account, App, EndUser
-from models.enums import CreatedByRole
 
 logger = logging.getLogger(__name__)
 
@@ -141,7 +140,7 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
             else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
             query=query,
             files=file_objs,
-            parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
+            parent_message_id=args.get("parent_message_id"),
             user_id=user.id,
             stream=stream,
             invoke_from=invoke_from,

api/core/app/apps/base_app_generator.py

@@ -7,7 +7,7 @@ from factories import file_factory
 
 if TYPE_CHECKING:
     from core.app.app_config.entities import AppConfig, VariableEntity
-    from models.enums import CreatedByRole
+    from enums import CreatedByRole
 
 
 class BaseAppGenerator:

api/core/app/apps/chat/app_generator.py

@@ -8,7 +8,6 @@ from typing import Any, Literal, Union, overload
 from flask import Flask, current_app
 from pydantic import ValidationError
 
-from constants import UUID_NIL
 from core.app.app_config.easy_ui_based_app.model_config.converter import ModelConfigConverter
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.app.apps.base_app_queue_manager import AppQueueManager, GenerateTaskStoppedError, PublishFrom
@@ -20,10 +19,10 @@ from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueMa
 from core.app.entities.app_invoke_entities import ChatAppGenerateEntity, InvokeFrom
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.ops.ops_trace_manager import TraceQueueManager
+from enums import CreatedByRole
 from extensions.ext_database import db
 from factories import file_factory
 from models.account import Account
-from models.enums import CreatedByRole
 from models.model import App, EndUser
 
 logger = logging.getLogger(__name__)
@@ -139,7 +138,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
             query=query,
             files=file_objs,
-            parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
+            parent_message_id=args.get("parent_message_id"),
             user_id=user.id,
             invoke_from=invoke_from,
             extras=extras,

api/core/app/apps/completion/app_generator.py

@@ -19,10 +19,10 @@ from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueMa
 from core.app.entities.app_invoke_entities import CompletionAppGenerateEntity, InvokeFrom
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.ops.ops_trace_manager import TraceQueueManager
+from enums import CreatedByRole
 from extensions.ext_database import db
 from factories import file_factory
 from models import Account, App, EndUser, Message
-from models.enums import CreatedByRole
 from services.errors.app import MoreLikeThisDisabledError
 from services.errors.message import MessageNotExistsError
 

api/core/app/apps/message_based_app_generator.py

@@ -27,7 +27,6 @@ from core.app.task_pipeline.easy_ui_based_generate_task_pipeline import EasyUIBa
 from core.prompt.utils.prompt_template_parser import PromptTemplateParser
 from extensions.ext_database import db
 from models import Account
-from models.enums import CreatedByRole
 from models.model import App, AppMode, AppModelConfig, Conversation, EndUser, Message, MessageFile
 from services.errors.app_model_config import AppModelConfigBrokenError
 from services.errors.conversation import ConversationCompletedError, ConversationNotExistsError
@@ -241,7 +240,7 @@ class MessageBasedAppGenerator(BaseAppGenerator):
                 belongs_to="user",
                 url=file.remote_url,
                 upload_file_id=file.related_id,
-                created_by_role=(CreatedByRole.ACCOUNT if account_id else CreatedByRole.END_USER),
+                created_by_role=("account" if account_id else "end_user"),
                 created_by=account_id or end_user_id or "",
             )
             db.session.add(message_file)

api/core/app/apps/workflow/app_generator.py

@@ -22,10 +22,10 @@ from core.app.entities.app_invoke_entities import InvokeFrom, WorkflowAppGenerat
 from core.app.entities.task_entities import WorkflowAppBlockingResponse, WorkflowAppStreamResponse
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.ops.ops_trace_manager import TraceQueueManager
+from enums import CreatedByRole
 from extensions.ext_database import db
 from factories import file_factory
 from models import Account, App, EndUser, Workflow
-from models.enums import CreatedByRole
 
 logger = logging.getLogger(__name__)
 

api/core/app/apps/workflow/app_runner.py

@@ -13,8 +13,8 @@ from core.workflow.callbacks import WorkflowCallback, WorkflowLoggingCallback
 from core.workflow.entities.variable_pool import VariablePool
 from core.workflow.enums import SystemVariableKey
 from core.workflow.workflow_entry import WorkflowEntry
+from enums import UserFrom
 from extensions.ext_database import db
-from models.enums import UserFrom
 from models.model import App, EndUser
 from models.workflow import WorkflowType
 

api/core/app/apps/workflow_app_runner.py

@@ -40,10 +40,11 @@ from core.workflow.graph_engine.entities.event import (
     ParallelBranchRunSucceededEvent,
 )
 from core.workflow.graph_engine.entities.graph import Graph
-from core.workflow.nodes import NodeType
-from core.workflow.nodes.iteration import IterationNodeData
-from core.workflow.nodes.node_mapping import node_type_classes_mapping
+from core.workflow.nodes.base_node import BaseNode
+from core.workflow.nodes.iteration.entities import IterationNodeData
+from core.workflow.nodes.node_mapping import node_classes
 from core.workflow.workflow_entry import WorkflowEntry
+from enums import NodeType
 from extensions.ext_database import db
 from models.model import App
 from models.workflow import Workflow
@@ -136,8 +137,9 @@ class WorkflowBasedAppRunner(AppRunner):
             raise ValueError("iteration node id not found in workflow graph")
 
         # Get node class
-        node_type = NodeType(iteration_node_config.get("data", {}).get("type"))
-        node_cls = node_type_classes_mapping[node_type]
+        node_type = NodeType.value_of(iteration_node_config.get("data", {}).get("type"))
+        node_cls = node_classes.get(node_type)
+        node_cls = cast(type[BaseNode], node_cls)
 
         # init variable pool
         variable_pool = VariablePool(

api/core/app/entities/app_invoke_entities.py

@@ -2,9 +2,8 @@ from collections.abc import Mapping, Sequence
 from enum import Enum
 from typing import Any, Optional
 
-from pydantic import BaseModel, ConfigDict, Field, ValidationInfo, field_validator
+from pydantic import BaseModel, ConfigDict
 
-from constants import UUID_NIL
 from core.app.app_config.entities import AppConfig, EasyUIBasedAppConfig, WorkflowUIBasedAppConfig
 from core.entities.provider_configuration import ProviderModelBundle
 from core.file.models import File
@@ -117,36 +116,13 @@ class EasyUIBasedAppGenerateEntity(AppGenerateEntity):
     model_config = ConfigDict(protected_namespaces=())
 
 
-class ConversationAppGenerateEntity(AppGenerateEntity):
-    """
-    Base entity for conversation-based app generation.
-    """
-
-    conversation_id: Optional[str] = None
-    parent_message_id: Optional[str] = Field(
-        default=None,
-        description=(
-            "Starting from v0.9.0, parent_message_id is used to support message regeneration for internal chat API."
-            "For service API, we need to ensure its forward compatibility, "
-            "so passing in the parent_message_id as request arg is not supported for now. "
-            "It needs to be set to UUID_NIL so that the subsequent processing will treat it as legacy messages."
-        ),
-    )
-
-    @field_validator("parent_message_id")
-    @classmethod
-    def validate_parent_message_id(cls, v, info: ValidationInfo):
-        if info.data.get("invoke_from") == InvokeFrom.SERVICE_API and v != UUID_NIL:
-            raise ValueError("parent_message_id should be UUID_NIL for service API")
-        return v
-
-
-class ChatAppGenerateEntity(ConversationAppGenerateEntity, EasyUIBasedAppGenerateEntity):
+class ChatAppGenerateEntity(EasyUIBasedAppGenerateEntity):
     """
     Chat Application Generate Entity.
     """
 
-    pass
+    conversation_id: Optional[str] = None
+    parent_message_id: Optional[str] = None
 
 
 class CompletionAppGenerateEntity(EasyUIBasedAppGenerateEntity):
@@ -157,15 +133,16 @@ class CompletionAppGenerateEntity(EasyUIBasedAppGenerateEntity):
     pass
 
 
-class AgentChatAppGenerateEntity(ConversationAppGenerateEntity, EasyUIBasedAppGenerateEntity):
+class AgentChatAppGenerateEntity(EasyUIBasedAppGenerateEntity):
     """
     Agent Chat Application Generate Entity.
     """
 
-    pass
+    conversation_id: Optional[str] = None
+    parent_message_id: Optional[str] = None
 
 
-class AdvancedChatAppGenerateEntity(ConversationAppGenerateEntity):
+class AdvancedChatAppGenerateEntity(AppGenerateEntity):
     """
     Advanced Chat Application Generate Entity.
     """
@@ -173,6 +150,8 @@ class AdvancedChatAppGenerateEntity(ConversationAppGenerateEntity):
     # app config
     app_config: WorkflowUIBasedAppConfig
 
+    conversation_id: Optional[str] = None
+    parent_message_id: Optional[str] = None
     workflow_run_id: Optional[str] = None
     query: str
 

api/core/app/entities/queue_entities.py

@@ -5,10 +5,10 @@ from typing import Any, Optional
 from pydantic import BaseModel, field_validator
 
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk
+from core.workflow.entities.base_node_data_entities import BaseNodeData
 from core.workflow.entities.node_entities import NodeRunMetadataKey
 from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState
-from core.workflow.nodes import NodeType
-from core.workflow.nodes.base import BaseNodeData
+from enums import NodeType
 
 
 class QueueEvent(str, Enum):

api/core/app/task_pipeline/based_generate_task_pipeline.py

@@ -53,7 +53,7 @@ class BasedGenerateTaskPipeline:
         self._output_moderation_handler = self._init_output_moderation()
         self._stream = stream
 
-    def _handle_error(self, event: QueueErrorEvent, message: Optional[Message] = None):
+    def _handle_error(self, event: QueueErrorEvent, message: Optional[Message] = None) -> Exception:
         """
         Handle error event.
         :param event: event
@@ -100,7 +100,7 @@ class BasedGenerateTaskPipeline:
 
         return message
 
-    def _error_to_stream_response(self, e: Exception):
+    def _error_to_stream_response(self, e: Exception) -> ErrorStreamResponse:
         """
         Error to stream response.
         :param e: exception

api/core/app/task_pipeline/workflow_cycle_manage.py

@@ -4,8 +4,6 @@ from collections.abc import Mapping, Sequence
 from datetime import datetime, timezone
 from typing import Any, Optional, Union, cast
 
-from sqlalchemy.orm import Session
-
 from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, InvokeFrom, WorkflowAppGenerateEntity
 from core.app.entities.queue_entities import (
     QueueIterationCompletedEvent,
@@ -36,12 +34,11 @@ from core.ops.entities.trace_entity import TraceTaskName
 from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
 from core.tools.tool_manager import ToolManager
 from core.workflow.enums import SystemVariableKey
-from core.workflow.nodes import NodeType
 from core.workflow.nodes.tool.entities import ToolNodeData
 from core.workflow.workflow_entry import WorkflowEntry
+from enums import CreatedByRole, NodeType, WorkflowRunTriggeredFrom
 from extensions.ext_database import db
 from models.account import Account
-from models.enums import CreatedByRole, WorkflowRunTriggeredFrom
 from models.model import EndUser
 from models.workflow import (
     Workflow,
@@ -138,7 +135,7 @@ class WorkflowCycleManage:
         outputs = WorkflowEntry.handle_special_values(outputs)
 
         workflow_run.status = WorkflowRunStatus.SUCCEEDED.value
-        workflow_run.outputs = json.dumps(outputs or {})
+        workflow_run.outputs = json.dumps(outputs) if outputs else None
         workflow_run.elapsed_time = time.perf_counter() - start_at
         workflow_run.total_tokens = total_tokens
         workflow_run.total_steps = total_steps
@@ -234,30 +231,30 @@ class WorkflowCycleManage:
         self, workflow_run: WorkflowRun, event: QueueNodeStartedEvent
     ) -> WorkflowNodeExecution:
         # init workflow node execution
+        workflow_node_execution = WorkflowNodeExecution()
+        workflow_node_execution.tenant_id = workflow_run.tenant_id
+        workflow_node_execution.app_id = workflow_run.app_id
+        workflow_node_execution.workflow_id = workflow_run.workflow_id
+        workflow_node_execution.triggered_from = WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN.value
+        workflow_node_execution.workflow_run_id = workflow_run.id
+        workflow_node_execution.predecessor_node_id = event.predecessor_node_id
+        workflow_node_execution.index = event.node_run_index
+        workflow_node_execution.node_execution_id = event.node_execution_id
+        workflow_node_execution.node_id = event.node_id
+        workflow_node_execution.node_type = event.node_type.value
+        workflow_node_execution.title = event.node_data.title
+        workflow_node_execution.status = WorkflowNodeExecutionStatus.RUNNING.value
+        workflow_node_execution.created_by_role = workflow_run.created_by_role
+        workflow_node_execution.created_by = workflow_run.created_by
+        workflow_node_execution.created_at = datetime.now(timezone.utc).replace(tzinfo=None)
 
-        with Session(db.engine, expire_on_commit=False) as session:
-            workflow_node_execution = WorkflowNodeExecution()
-            workflow_node_execution.tenant_id = workflow_run.tenant_id
-            workflow_node_execution.app_id = workflow_run.app_id
-            workflow_node_execution.workflow_id = workflow_run.workflow_id
-            workflow_node_execution.triggered_from = WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN.value
-            workflow_node_execution.workflow_run_id = workflow_run.id
-            workflow_node_execution.predecessor_node_id = event.predecessor_node_id
-            workflow_node_execution.index = event.node_run_index
-            workflow_node_execution.node_execution_id = event.node_execution_id
-            workflow_node_execution.node_id = event.node_id
-            workflow_node_execution.node_type = event.node_type.value
-            workflow_node_execution.title = event.node_data.title
-            workflow_node_execution.status = WorkflowNodeExecutionStatus.RUNNING.value
-            workflow_node_execution.created_by_role = workflow_run.created_by_role
-            workflow_node_execution.created_by = workflow_run.created_by
-            workflow_node_execution.created_at = datetime.now(timezone.utc).replace(tzinfo=None)
-
-            session.add(workflow_node_execution)
-            session.commit()
-            session.refresh(workflow_node_execution)
+        db.session.add(workflow_node_execution)
+        db.session.commit()
+        db.session.refresh(workflow_node_execution)
+        db.session.close()
 
         self._wip_workflow_node_executions[workflow_node_execution.node_execution_id] = workflow_node_execution
+
         return workflow_node_execution
 
     def _handle_workflow_node_execution_success(self, event: QueueNodeSucceededEvent) -> WorkflowNodeExecution:

api/core/embedding/cached_embedding.py

@@ -6,11 +6,11 @@ import numpy as np
 from sqlalchemy.exc import IntegrityError
 
 from configs import dify_config
-from core.entities.embedding_type import EmbeddingInputType
+from core.embedding.embedding_constant import EmbeddingInputType
 from core.model_manager import ModelInstance
 from core.model_runtime.entities.model_entities import ModelPropertyKey
 from core.model_runtime.model_providers.__base.text_embedding_model import TextEmbeddingModel
-from core.rag.embedding.embedding_base import Embeddings
+from core.rag.datasource.entity.embedding import Embeddings
 from extensions.ext_database import db
 from extensions.ext_redis import redis_client
 from libs import helper

api/core/file/file_manager.py

@@ -1,11 +1,10 @@
 import base64
 
 from configs import dify_config
-from core.file import file_repository
-from core.helper import ssrf_proxy
-from core.model_runtime.entities import AudioPromptMessageContent, ImagePromptMessageContent
+from core.model_runtime.entities.message_entities import ImagePromptMessageContent
 from extensions.ext_database import db
 from extensions.ext_storage import storage
+from models import UploadFile
 
 from . import helpers
 from .enums import FileAttribute
@@ -13,7 +12,7 @@ from .models import File, FileTransferMethod, FileType
 from .tool_file_parser import ToolFileParser
 
 
-def get_attr(*, file: File, attr: FileAttribute):
+def get_attr(*, file: "File", attr: "FileAttribute"):
     match attr:
         case FileAttribute.TYPE:
             return file.type.value
@@ -33,7 +32,7 @@ def get_attr(*, file: File, attr: FileAttribute):
             raise ValueError(f"Invalid file attribute: {attr}")
 
 
-def to_prompt_message_content(f: File, /):
+def to_prompt_message_content(file: "File", /):
     """
     Convert a File object to an ImagePromptMessageContent object.
 
@@ -53,42 +52,34 @@ def to_prompt_message_content(f: File, /):
         The detail level of the image prompt is determined by the file's extra_config.
         If not specified, it defaults to ImagePromptMessageContent.DETAIL.LOW.
     """
-    match f.type:
-        case FileType.IMAGE:
-            if dify_config.MULTIMODAL_SEND_IMAGE_FORMAT == "url":
-                data = _to_url(f)
-            else:
-                data = _to_base64_data_string(f)
+    if file.type != FileType.IMAGE:
+        raise ValueError("Only image file can convert to prompt message content")
 
-            if f._extra_config and f._extra_config.image_config and f._extra_config.image_config.detail:
-                detail = f._extra_config.image_config.detail
-            else:
-                detail = ImagePromptMessageContent.DETAIL.LOW
+    url_or_b64_data = _get_url_or_b64_data(file=file)
+    if url_or_b64_data is None:
+        raise ValueError("Missing file data")
 
-            return ImagePromptMessageContent(data=data, detail=detail)
-        case FileType.AUDIO:
-            encoded_string = _file_to_encoded_string(f)
-            if f.extension is None:
-                raise ValueError("Missing file extension")
-            return AudioPromptMessageContent(data=encoded_string, format=f.extension.lstrip("."))
-        case _:
-            raise ValueError(f"file type {f.type} is not supported")
+    # decide the detail of image prompt message content
+    if file._extra_config and file._extra_config.image_config and file._extra_config.image_config.detail:
+        detail = file._extra_config.image_config.detail
+    else:
+        detail = ImagePromptMessageContent.DETAIL.LOW
+
+    return ImagePromptMessageContent(data=url_or_b64_data, detail=detail)
 
 
-def download(f: File, /):
-    if f.transfer_method == FileTransferMethod.TOOL_FILE:
-        tool_file = file_repository.get_tool_file(session=db.session(), file=f)
-        return _download_file_content(tool_file.file_key)
-    elif f.transfer_method == FileTransferMethod.LOCAL_FILE:
-        upload_file = file_repository.get_upload_file(session=db.session(), file=f)
-        return _download_file_content(upload_file.key)
-    # remote file
-    response = ssrf_proxy.get(f.remote_url, follow_redirects=True)
-    response.raise_for_status()
-    return response.content
+def download(*, upload_file_id: str, tenant_id: str):
+    upload_file = (
+        db.session.query(UploadFile).filter(UploadFile.id == upload_file_id, UploadFile.tenant_id == tenant_id).first()
+    )
+
+    if not upload_file:
+        raise ValueError("upload file not found")
+
+    return _download(upload_file.key)
 
 
-def _download_file_content(path: str, /):
+def _download(path: str, /):
     """
     Download and return the contents of a file as bytes.
 
@@ -109,56 +100,37 @@ def _download_file_content(path: str, /):
     return data
 
 
-def _get_encoded_string(f: File, /):
-    match f.transfer_method:
-        case FileTransferMethod.REMOTE_URL:
-            response = ssrf_proxy.get(f.remote_url)
-            response.raise_for_status()
-            content = response.content
-            encoded_string = base64.b64encode(content).decode("utf-8")
-            return encoded_string
-        case FileTransferMethod.LOCAL_FILE:
-            upload_file = file_repository.get_upload_file(session=db.session(), file=f)
-            data = _download_file_content(upload_file.key)
-            encoded_string = base64.b64encode(data).decode("utf-8")
-            return encoded_string
-        case FileTransferMethod.TOOL_FILE:
-            tool_file = file_repository.get_tool_file(session=db.session(), file=f)
-            data = _download_file_content(tool_file.file_key)
-            encoded_string = base64.b64encode(data).decode("utf-8")
-            return encoded_string
-        case _:
-            raise ValueError(f"Unsupported transfer method: {f.transfer_method}")
+def _get_base64(*, upload_file_id: str, tenant_id: str) -> str | None:
+    upload_file = (
+        db.session.query(UploadFile).filter(UploadFile.id == upload_file_id, UploadFile.tenant_id == tenant_id).first()
+    )
+
+    if not upload_file:
+        return None
+
+    data = _download(upload_file.key)
+    if data is None:
+        return None
+
+    encoded_string = base64.b64encode(data).decode("utf-8")
+    return f"data:{upload_file.mime_type};base64,{encoded_string}"
 
 
-def _to_base64_data_string(f: File, /):
-    encoded_string = _get_encoded_string(f)
-    return f"data:{f.mime_type};base64,{encoded_string}"
+def _get_url_or_b64_data(file: "File"):
+    if file.type == FileType.IMAGE:
+        if file.transfer_method == FileTransferMethod.REMOTE_URL:
+            return file.remote_url
+        elif file.transfer_method == FileTransferMethod.LOCAL_FILE:
+            if file.related_id is None:
+                raise ValueError("Missing file related_id")
 
-
-def _file_to_encoded_string(f: File, /):
-    match f.type:
-        case FileType.IMAGE:
-            return _to_base64_data_string(f)
-        case FileType.AUDIO:
-            return _get_encoded_string(f)
-        case _:
-            raise ValueError(f"file type {f.type} is not supported")
-
-
-def _to_url(f: File, /):
-    if f.transfer_method == FileTransferMethod.REMOTE_URL:
-        if f.remote_url is None:
-            raise ValueError("Missing file remote_url")
-        return f.remote_url
-    elif f.transfer_method == FileTransferMethod.LOCAL_FILE:
-        if f.related_id is None:
-            raise ValueError("Missing file related_id")
-        return helpers.get_signed_file_url(upload_file_id=f.related_id)
-    elif f.transfer_method == FileTransferMethod.TOOL_FILE:
-        # add sign url
-        if f.related_id is None or f.extension is None:
-            raise ValueError("Missing file related_id or extension")
-        return ToolFileParser.get_tool_file_manager().sign_file(tool_file_id=f.related_id, extension=f.extension)
-    else:
-        raise ValueError(f"Unsupported transfer method: {f.transfer_method}")
+            if dify_config.MULTIMODAL_SEND_IMAGE_FORMAT == "url":
+                return helpers.get_signed_image_url(upload_file_id=file.related_id)
+            return _get_base64(upload_file_id=file.related_id, tenant_id=file.tenant_id)
+        elif file.transfer_method == FileTransferMethod.TOOL_FILE:
+            # add sign url
+            if file.related_id is None or file.extension is None:
+                raise ValueError("Missing file related_id or extension")
+            return ToolFileParser.get_tool_file_manager().sign_file(
+                tool_file_id=file.related_id, extension=file.extension
+            )

api/core/file/file_repository.py

@@ -1,32 +0,0 @@
-from sqlalchemy import select
-from sqlalchemy.orm import Session
-
-from models import ToolFile, UploadFile
-
-from .models import File
-
-
-def get_upload_file(*, session: Session, file: File):
-    if file.related_id is None:
-        raise ValueError("Missing file related_id")
-    stmt = select(UploadFile).filter(
-        UploadFile.id == file.related_id,
-        UploadFile.tenant_id == file.tenant_id,
-    )
-    record = session.scalar(stmt)
-    if not record:
-        raise ValueError(f"upload file {file.related_id} not found")
-    return record
-
-
-def get_tool_file(*, session: Session, file: File):
-    if file.related_id is None:
-        raise ValueError("Missing file related_id")
-    stmt = select(ToolFile).filter(
-        ToolFile.id == file.related_id,
-        ToolFile.tenant_id == file.tenant_id,
-    )
-    record = session.scalar(stmt)
-    if not record:
-        raise ValueError(f"tool file {file.related_id} not found")
-    return record

api/core/file/helpers.py

@@ -7,6 +7,19 @@ import time
 from configs import dify_config
 
 
+def get_signed_image_url(upload_file_id: str) -> str:
+    url = f"{dify_config.FILES_URL}/files/{upload_file_id}/image-preview"
+
+    timestamp = str(int(time.time()))
+    nonce = os.urandom(16).hex()
+    key = dify_config.SECRET_KEY.encode()
+    msg = f"image-preview|{upload_file_id}|{timestamp}|{nonce}"
+    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}"
+
+
 def get_signed_file_url(upload_file_id: str) -> str:
     url = f"{dify_config.FILES_URL}/files/{upload_file_id}/file-preview"
 

api/core/file/models.py

@@ -72,7 +72,7 @@ class File(BaseModel):
             elif self.transfer_method == FileTransferMethod.LOCAL_FILE:
                 if self.related_id is None:
                     raise ValueError("Missing file related_id")
-                return helpers.get_signed_file_url(upload_file_id=self.related_id)
+                return helpers.get_signed_image_url(upload_file_id=self.related_id)
             elif self.transfer_method == FileTransferMethod.TOOL_FILE:
                 assert self.related_id is not None
                 assert self.extension is not None

api/core/hosting_configuration.py

@@ -1,9 +1,8 @@
 from typing import Optional
 
-from flask import Flask
+from flask import Config, Flask
 from pydantic import BaseModel
 
-from configs import dify_config
 from core.entities.provider_entities import QuotaUnit, RestrictModel
 from core.model_runtime.entities.model_entities import ModelType
 from models.provider import ProviderQuotaType
@@ -45,30 +44,32 @@ class HostingConfiguration:
     moderation_config: HostedModerationConfig = None
 
     def init_app(self, app: Flask) -> None:
-        if dify_config.EDITION != "CLOUD":
+        config = app.config
+
+        if config.get("EDITION") != "CLOUD":
             return
 
-        self.provider_map["azure_openai"] = self.init_azure_openai()
-        self.provider_map["openai"] = self.init_openai()
-        self.provider_map["anthropic"] = self.init_anthropic()
-        self.provider_map["minimax"] = self.init_minimax()
-        self.provider_map["spark"] = self.init_spark()
-        self.provider_map["zhipuai"] = self.init_zhipuai()
+        self.provider_map["azure_openai"] = self.init_azure_openai(config)
+        self.provider_map["openai"] = self.init_openai(config)
+        self.provider_map["anthropic"] = self.init_anthropic(config)
+        self.provider_map["minimax"] = self.init_minimax(config)
+        self.provider_map["spark"] = self.init_spark(config)
+        self.provider_map["zhipuai"] = self.init_zhipuai(config)
 
-        self.moderation_config = self.init_moderation_config()
+        self.moderation_config = self.init_moderation_config(config)
 
     @staticmethod
-    def init_azure_openai() -> HostingProvider:
+    def init_azure_openai(app_config: Config) -> HostingProvider:
         quota_unit = QuotaUnit.TIMES
-        if dify_config.HOSTED_AZURE_OPENAI_ENABLED:
+        if app_config.get("HOSTED_AZURE_OPENAI_ENABLED"):
             credentials = {
-                "openai_api_key": dify_config.HOSTED_AZURE_OPENAI_API_KEY,
-                "openai_api_base": dify_config.HOSTED_AZURE_OPENAI_API_BASE,
+                "openai_api_key": app_config.get("HOSTED_AZURE_OPENAI_API_KEY"),
+                "openai_api_base": app_config.get("HOSTED_AZURE_OPENAI_API_BASE"),
                 "base_model_name": "gpt-35-turbo",
             }
 
             quotas = []
-            hosted_quota_limit = dify_config.HOSTED_AZURE_OPENAI_QUOTA_LIMIT
+            hosted_quota_limit = int(app_config.get("HOSTED_AZURE_OPENAI_QUOTA_LIMIT", "1000"))
             trial_quota = TrialHostingQuota(
                 quota_limit=hosted_quota_limit,
                 restrict_models=[
@@ -121,31 +122,31 @@ class HostingConfiguration:
             quota_unit=quota_unit,
         )
 
-    def init_openai(self) -> HostingProvider:
+    def init_openai(self, app_config: Config) -> HostingProvider:
         quota_unit = QuotaUnit.CREDITS
         quotas = []
 
-        if dify_config.HOSTED_OPENAI_TRIAL_ENABLED:
-            hosted_quota_limit = dify_config.HOSTED_OPENAI_QUOTA_LIMIT
-            trial_models = self.parse_restrict_models_from_env("HOSTED_OPENAI_TRIAL_MODELS")
+        if app_config.get("HOSTED_OPENAI_TRIAL_ENABLED"):
+            hosted_quota_limit = int(app_config.get("HOSTED_OPENAI_QUOTA_LIMIT", "200"))
+            trial_models = self.parse_restrict_models_from_env(app_config, "HOSTED_OPENAI_TRIAL_MODELS")
             trial_quota = TrialHostingQuota(quota_limit=hosted_quota_limit, restrict_models=trial_models)
             quotas.append(trial_quota)
 
-        if dify_config.HOSTED_OPENAI_PAID_ENABLED:
-            paid_models = self.parse_restrict_models_from_env("HOSTED_OPENAI_PAID_MODELS")
+        if app_config.get("HOSTED_OPENAI_PAID_ENABLED"):
+            paid_models = self.parse_restrict_models_from_env(app_config, "HOSTED_OPENAI_PAID_MODELS")
             paid_quota = PaidHostingQuota(restrict_models=paid_models)
             quotas.append(paid_quota)
 
         if len(quotas) > 0:
             credentials = {
-                "openai_api_key": dify_config.HOSTED_OPENAI_API_KEY,
+                "openai_api_key": app_config.get("HOSTED_OPENAI_API_KEY"),
             }
 
-            if dify_config.HOSTED_OPENAI_API_BASE:
-                credentials["openai_api_base"] = dify_config.HOSTED_OPENAI_API_BASE
+            if app_config.get("HOSTED_OPENAI_API_BASE"):
+                credentials["openai_api_base"] = app_config.get("HOSTED_OPENAI_API_BASE")
 
-            if dify_config.HOSTED_OPENAI_API_ORGANIZATION:
-                credentials["openai_organization"] = dify_config.HOSTED_OPENAI_API_ORGANIZATION
+            if app_config.get("HOSTED_OPENAI_API_ORGANIZATION"):
+                credentials["openai_organization"] = app_config.get("HOSTED_OPENAI_API_ORGANIZATION")
 
             return HostingProvider(enabled=True, credentials=credentials, quota_unit=quota_unit, quotas=quotas)
 
@@ -155,26 +156,26 @@ class HostingConfiguration:
         )
 
     @staticmethod
-    def init_anthropic() -> HostingProvider:
+    def init_anthropic(app_config: Config) -> HostingProvider:
         quota_unit = QuotaUnit.TOKENS
         quotas = []
 
-        if dify_config.HOSTED_ANTHROPIC_TRIAL_ENABLED:
-            hosted_quota_limit = dify_config.HOSTED_ANTHROPIC_QUOTA_LIMIT
+        if app_config.get("HOSTED_ANTHROPIC_TRIAL_ENABLED"):
+            hosted_quota_limit = int(app_config.get("HOSTED_ANTHROPIC_QUOTA_LIMIT", "0"))
             trial_quota = TrialHostingQuota(quota_limit=hosted_quota_limit)
             quotas.append(trial_quota)
 
-        if dify_config.HOSTED_ANTHROPIC_PAID_ENABLED:
+        if app_config.get("HOSTED_ANTHROPIC_PAID_ENABLED"):
             paid_quota = PaidHostingQuota()
             quotas.append(paid_quota)
 
         if len(quotas) > 0:
             credentials = {
-                "anthropic_api_key": dify_config.HOSTED_ANTHROPIC_API_KEY,
+                "anthropic_api_key": app_config.get("HOSTED_ANTHROPIC_API_KEY"),
             }
 
-            if dify_config.HOSTED_ANTHROPIC_API_BASE:
-                credentials["anthropic_api_url"] = dify_config.HOSTED_ANTHROPIC_API_BASE
+            if app_config.get("HOSTED_ANTHROPIC_API_BASE"):
+                credentials["anthropic_api_url"] = app_config.get("HOSTED_ANTHROPIC_API_BASE")
 
             return HostingProvider(enabled=True, credentials=credentials, quota_unit=quota_unit, quotas=quotas)
 
@@ -184,9 +185,9 @@ class HostingConfiguration:
         )
 
     @staticmethod
-    def init_minimax() -> HostingProvider:
+    def init_minimax(app_config: Config) -> HostingProvider:
         quota_unit = QuotaUnit.TOKENS
-        if dify_config.HOSTED_MINIMAX_ENABLED:
+        if app_config.get("HOSTED_MINIMAX_ENABLED"):
             quotas = [FreeHostingQuota()]
 
             return HostingProvider(
@@ -202,9 +203,9 @@ class HostingConfiguration:
         )
 
     @staticmethod
-    def init_spark() -> HostingProvider:
+    def init_spark(app_config: Config) -> HostingProvider:
         quota_unit = QuotaUnit.TOKENS
-        if dify_config.HOSTED_SPARK_ENABLED:
+        if app_config.get("HOSTED_SPARK_ENABLED"):
             quotas = [FreeHostingQuota()]
 
             return HostingProvider(
@@ -220,9 +221,9 @@ class HostingConfiguration:
         )
 
     @staticmethod
-    def init_zhipuai() -> HostingProvider:
+    def init_zhipuai(app_config: Config) -> HostingProvider:
         quota_unit = QuotaUnit.TOKENS
-        if dify_config.HOSTED_ZHIPUAI_ENABLED:
+        if app_config.get("HOSTED_ZHIPUAI_ENABLED"):
             quotas = [FreeHostingQuota()]
 
             return HostingProvider(
@@ -238,15 +239,17 @@ class HostingConfiguration:
         )
 
     @staticmethod
-    def init_moderation_config() -> HostedModerationConfig:
-        if dify_config.HOSTED_MODERATION_ENABLED and dify_config.HOSTED_MODERATION_PROVIDERS:
-            return HostedModerationConfig(enabled=True, providers=dify_config.HOSTED_MODERATION_PROVIDERS.split(","))
+    def init_moderation_config(app_config: Config) -> HostedModerationConfig:
+        if app_config.get("HOSTED_MODERATION_ENABLED") and app_config.get("HOSTED_MODERATION_PROVIDERS"):
+            return HostedModerationConfig(
+                enabled=True, providers=app_config.get("HOSTED_MODERATION_PROVIDERS").split(",")
+            )
 
         return HostedModerationConfig(enabled=False)
 
     @staticmethod
-    def parse_restrict_models_from_env(env_var: str) -> list[RestrictModel]:
-        models_str = dify_config.model_dump().get(env_var)
+    def parse_restrict_models_from_env(app_config: Config, env_var: str) -> list[RestrictModel]:
+        models_str = app_config.get(env_var)
         models_list = models_str.split(",") if models_str else []
         return [
             RestrictModel(model=model_name.strip(), model_type=ModelType.LLM)

api/core/llm_generator/llm_generator.py

@@ -8,8 +8,6 @@ from core.llm_generator.output_parser.suggested_questions_after_answer import Su
 from core.llm_generator.prompts import (
     CONVERSATION_TITLE_PROMPT,
     GENERATOR_QA_PROMPT,
-    JAVASCRIPT_CODE_GENERATOR_PROMPT_TEMPLATE,
-    PYTHON_CODE_GENERATOR_PROMPT_TEMPLATE,
     WORKFLOW_RULE_CONFIG_PROMPT_GENERATE_TEMPLATE,
 )
 from core.model_manager import ModelManager
@@ -241,54 +239,6 @@ class LLMGenerator:
 
         return rule_config
 
-    @classmethod
-    def generate_code(
-        cls,
-        tenant_id: str,
-        instruction: str,
-        model_config: dict,
-        code_language: str = "javascript",
-        max_tokens: int = 1000,
-    ) -> dict:
-        if code_language == "python":
-            prompt_template = PromptTemplateParser(PYTHON_CODE_GENERATOR_PROMPT_TEMPLATE)
-        else:
-            prompt_template = PromptTemplateParser(JAVASCRIPT_CODE_GENERATOR_PROMPT_TEMPLATE)
-
-        prompt = prompt_template.format(
-            inputs={
-                "INSTRUCTION": instruction,
-                "CODE_LANGUAGE": code_language,
-            },
-            remove_template_variables=False,
-        )
-
-        model_manager = ModelManager()
-        model_instance = model_manager.get_model_instance(
-            tenant_id=tenant_id,
-            model_type=ModelType.LLM,
-            provider=model_config.get("provider") if model_config else None,
-            model=model_config.get("name") if model_config else None,
-        )
-
-        prompt_messages = [UserPromptMessage(content=prompt)]
-        model_parameters = {"max_tokens": max_tokens, "temperature": 0.01}
-
-        try:
-            response = model_instance.invoke_llm(
-                prompt_messages=prompt_messages, model_parameters=model_parameters, stream=False
-            )
-
-            generated_code = response.message.content
-            return {"code": generated_code, "language": code_language, "error": ""}
-
-        except InvokeError as e:
-            error = str(e)
-            return {"code": "", "language": code_language, "error": f"Failed to generate code. Error: {error}"}
-        except Exception as e:
-            logging.exception(e)
-            return {"code": "", "language": code_language, "error": f"An unexpected error occurred: {str(e)}"}
-
     @classmethod
     def generate_qa_document(cls, tenant_id: str, query, document_language: str):
         prompt = GENERATOR_QA_PROMPT.format(language=document_language)

api/core/llm_generator/prompts.py

@@ -61,73 +61,6 @@ User Input: yo, 你今天咋样？
 User Input: 
 """  # noqa: E501
 
-PYTHON_CODE_GENERATOR_PROMPT_TEMPLATE = (
-    "You are an expert programmer. Generate code based on the following instructions:\n\n"
-    "Instructions: {{INSTRUCTION}}\n\n"
-    "Write the code in {{CODE_LANGUAGE}}.\n\n"
-    "Please ensure that you meet the following requirements:\n"
-    "1. Define a function named 'main'.\n"
-    "2. The 'main' function must return a dictionary (dict).\n"
-    "3. You may modify the arguments of the 'main' function, but include appropriate type hints.\n"
-    "4. The returned dictionary should contain at least one key-value pair.\n\n"
-    "5. You may ONLY use the following libraries in your code: \n"
-    "- json\n"
-    "- datetime\n"
-    "- math\n"
-    "- random\n"
-    "- re\n"
-    "- string\n"
-    "- sys\n"
-    "- time\n"
-    "- traceback\n"
-    "- uuid\n"
-    "- os\n"
-    "- base64\n"
-    "- hashlib\n"
-    "- hmac\n"
-    "- binascii\n"
-    "- collections\n"
-    "- functools\n"
-    "- operator\n"
-    "- itertools\n\n"
-    "Example:\n"
-    "def main(arg1: str, arg2: int) -> dict:\n"
-    "    return {\n"
-    '        "result": arg1 * arg2,\n'
-    "    }\n\n"
-    "IMPORTANT:\n"
-    "- Provide ONLY the code without any additional explanations, comments, or markdown formatting.\n"
-    "- DO NOT use markdown code blocks (``` or ``` python). Return the raw code directly.\n"
-    "- The code should start immediately after this instruction, without any preceding newlines or spaces.\n"
-    "- The code should be complete, functional, and follow best practices for {{CODE_LANGUAGE}}.\n\n"
-    "- Always use the format return {'result': ...} for the output.\n\n"
-    "Generated Code:\n"
-)
-JAVASCRIPT_CODE_GENERATOR_PROMPT_TEMPLATE = (
-    "You are an expert programmer. Generate code based on the following instructions:\n\n"
-    "Instructions: {{INSTRUCTION}}\n\n"
-    "Write the code in {{CODE_LANGUAGE}}.\n\n"
-    "Please ensure that you meet the following requirements:\n"
-    "1. Define a function named 'main'.\n"
-    "2. The 'main' function must return an object.\n"
-    "3. You may modify the arguments of the 'main' function, but include appropriate JSDoc annotations.\n"
-    "4. The returned object should contain at least one key-value pair.\n\n"
-    "5. The returned object should always be in the format: {result: ...}\n\n"
-    "Example:\n"
-    "function main(arg1, arg2) {\n"
-    "    return {\n"
-    "        result: arg1 * arg2\n"
-    "    };\n"
-    "}\n\n"
-    "IMPORTANT:\n"
-    "- Provide ONLY the code without any additional explanations, comments, or markdown formatting.\n"
-    "- DO NOT use markdown code blocks (``` or ``` javascript). Return the raw code directly.\n"
-    "- The code should start immediately after this instruction, without any preceding newlines or spaces.\n"
-    "- The code should be complete, functional, and follow best practices for {{CODE_LANGUAGE}}.\n\n"
-    "Generated Code:\n"
-)
-
-
 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"

api/core/memory/token_buffer_memory.py

@@ -1,8 +1,7 @@
 from typing import Optional
 
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
-from core.file import file_manager
-from core.file.models import FileType
+from core.file import FileType, file_manager
 from core.model_manager import ModelInstance
 from core.model_runtime.entities import (
     AssistantPromptMessage,
@@ -99,9 +98,10 @@ class TokenBufferMemory:
                     prompt_message_contents: list[PromptMessageContent] = []
                     prompt_message_contents.append(TextPromptMessageContent(data=message.query))
                     for file_obj in file_objs:
-                        if file_obj.type in {FileType.IMAGE, FileType.AUDIO}:
-                            prompt_message = file_manager.to_prompt_message_content(file_obj)
-                            prompt_message_contents.append(prompt_message)
+                        if file_obj.type != FileType.IMAGE:
+                            continue
+                        prompt_message = file_manager.to_prompt_message_content(file_obj)
+                        prompt_message_contents.append(prompt_message)
 
                     prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
             else:

api/core/model_manager.py

@@ -3,7 +3,7 @@ import os
 from collections.abc import Callable, Generator, Iterable, Sequence
 from typing import IO, Any, Optional, Union, cast
 
-from core.entities.embedding_type import EmbeddingInputType
+from core.embedding.embedding_constant import EmbeddingInputType
 from core.entities.provider_configuration import ProviderConfiguration, ProviderModelBundle
 from core.entities.provider_entities import ModelLoadBalancingConfiguration
 from core.errors.error import ProviderTokenNotInitError

api/core/model_runtime/docs/en_US/customizable_model_scale_out.md

@@ -218,7 +218,7 @@ For instance, Xinference supports `max_tokens`, `temperature`, and `top_p` param
 However, some vendors may support different parameters for different models. For example, the `OpenLLM` vendor supports `top_k`, but not all models provided by this vendor support `top_k`. Let's say model A supports `top_k` but model B does not. In such cases, we need to dynamically generate the model parameter schema, as illustrated below:
 
 ```python
-    def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
+    def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity | None:
         """
             used to define customizable model schema
         """

api/core/model_runtime/docs/zh_Hans/customizable_model_scale_out.md

@@ -205,7 +205,7 @@ provider_credential_schema:
   但是有的供应商根据不同的模型支持不同的参数，如供应商`OpenLLM`支持`top_k`，但是并不是这个供应商提供的所有模型都支持`top_k`，我们这里举例A模型支持`top_k`，B模型不支持`top_k`，那么我们需要在这里动态生成模型参数的Schema，如下所示：
   
     ```python
-    def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
+    def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity | None:
         """
             used to define customizable model schema
         """

api/core/model_runtime/entities/__init__.py

@@ -1,7 +1,6 @@
 from .llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from .message_entities import (
     AssistantPromptMessage,
-    AudioPromptMessageContent,
     ImagePromptMessageContent,
     PromptMessage,
     PromptMessageContent,
@@ -34,5 +33,4 @@ __all__ = [
     "LLMResult",
     "LLMResultChunk",
     "LLMResultChunkDelta",
-    "AudioPromptMessageContent",
 ]

api/core/model_runtime/entities/llm_entities.py

@@ -105,7 +105,6 @@ class LLMResult(BaseModel):
     Model class for llm result.
     """
 
-    id: Optional[str] = None
     model: str
     prompt_messages: list[PromptMessage]
     message: AssistantPromptMessage

api/core/model_runtime/entities/message_entities.py

@@ -2,7 +2,7 @@ from abc import ABC
 from enum import Enum
 from typing import Optional
 
-from pydantic import BaseModel, Field, field_validator
+from pydantic import BaseModel, field_validator
 
 
 class PromptMessageRole(Enum):
@@ -55,7 +55,6 @@ class PromptMessageContentType(Enum):
 
     TEXT = "text"
     IMAGE = "image"
-    AUDIO = "audio"
 
 
 class PromptMessageContent(BaseModel):
@@ -75,12 +74,6 @@ class TextPromptMessageContent(PromptMessageContent):
     type: PromptMessageContentType = PromptMessageContentType.TEXT
 
 
-class AudioPromptMessageContent(PromptMessageContent):
-    type: PromptMessageContentType = PromptMessageContentType.AUDIO
-    data: str = Field(..., description="Base64 encoded audio data")
-    format: str = Field(..., description="Audio format")
-
-
 class ImagePromptMessageContent(PromptMessageContent):
     """
     Model class for image prompt message content.

api/core/model_runtime/model_providers/__base/large_language_model.py

@@ -107,16 +107,7 @@ class LargeLanguageModel(AIModel):
                     callbacks=callbacks,
                 )
             else:
-                result = self._invoke(
-                    model=model,
-                    credentials=credentials,
-                    prompt_messages=prompt_messages,
-                    model_parameters=model_parameters,
-                    tools=tools,
-                    stop=stop,
-                    stream=stream,
-                    user=user,
-                )
+                result = self._invoke(model, credentials, prompt_messages, model_parameters, tools, stop, stream, user)
         except Exception as e:
             self._trigger_invoke_error_callbacks(
                 model=model,

api/core/model_runtime/model_providers/__base/text_embedding_model.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 from pydantic import ConfigDict
 
-from core.entities.embedding_type import EmbeddingInputType
+from core.embedding.embedding_constant import EmbeddingInputType
 from core.model_runtime.entities.model_entities import ModelPropertyKey, ModelType
 from core.model_runtime.entities.text_embedding_entities import TextEmbeddingResult
 from core.model_runtime.model_providers.__base.ai_model import AIModel

api/core/model_runtime/model_providers/anthropic/llm/_position.yaml

@@ -1,4 +1,3 @@
-- claude-3-5-sonnet-20241022
 - claude-3-5-sonnet-20240620
 - claude-3-haiku-20240307
 - claude-3-opus-20240229

api/core/model_runtime/model_providers/anthropic/llm/claude-3-5-sonnet-20241022.yaml

@@ -1,39 +0,0 @@
-model: claude-3-5-sonnet-20241022
-label:
-  en_US: claude-3-5-sonnet-20241022
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - tool-call
-  - stream-tool-call
-model_properties:
-  mode: chat
-  context_size: 200000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_tokens
-    use_template: max_tokens
-    required: true
-    default: 8192
-    min: 1
-    max: 8192
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '3.00'
-  output: '15.00'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/azure_ai_studio/llm/llm.py

@@ -294,7 +294,7 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
             ],
         }
 
-    def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
+    def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity | None:
         """
         Used to define customizable model schema
         """

api/core/model_runtime/model_providers/azure_ai_studio/rerank/rerank.py

@@ -148,7 +148,7 @@ class AzureRerankModel(RerankModel):
             InvokeBadRequestError: [InvokeBadRequestError, KeyError, ValueError, json.JSONDecodeError],
         }
 
-    def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
+    def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity | None:
         """
         used to define customizable model schema
         """

api/core/model_runtime/model_providers/azure_openai/_constant.py

@@ -1098,14 +1098,6 @@ LLM_BASE_MODELS = [
                 ModelPropertyKey.CONTEXT_SIZE: 128000,
             },
             parameter_rules=[
-                ParameterRule(
-                    name="temperature",
-                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TEMPERATURE],
-                ),
-                ParameterRule(
-                    name="top_p",
-                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TOP_P],
-                ),
                 ParameterRule(
                     name="response_format",
                     label=I18nObject(zh_Hans="回复格式", en_US="response_format"),
@@ -1143,14 +1135,6 @@ LLM_BASE_MODELS = [
                 ModelPropertyKey.CONTEXT_SIZE: 128000,
             },
             parameter_rules=[
-                ParameterRule(
-                    name="temperature",
-                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TEMPERATURE],
-                ),
-                ParameterRule(
-                    name="top_p",
-                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TOP_P],
-                ),
                 ParameterRule(
                     name="response_format",
                     label=I18nObject(zh_Hans="回复格式", en_US="response_format"),

api/core/model_runtime/model_providers/azure_openai/azure_openai.yaml

@@ -53,9 +53,6 @@ model_credential_schema:
       type: select
       required: true
       options:
-        - label:
-            en_US: 2024-10-01-preview
-          value: 2024-10-01-preview
         - label:
             en_US: 2024-09-01-preview
           value: 2024-09-01-preview

api/core/model_runtime/model_providers/azure_openai/llm/llm.py

@@ -45,7 +45,9 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
         stream: bool = True,
         user: Optional[str] = None,
     ) -> Union[LLMResult, Generator]:
-        base_model_name = self._get_base_model_name(credentials)
+        base_model_name = credentials.get("base_model_name")
+        if not base_model_name:
+            raise ValueError("Base Model Name is required")
         ai_model_entity = self._get_ai_model_entity(base_model_name=base_model_name, model=model)
 
         if ai_model_entity and ai_model_entity.entity.model_properties.get(ModelPropertyKey.MODE) == LLMMode.CHAT.value:
@@ -79,7 +81,9 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
         prompt_messages: list[PromptMessage],
         tools: Optional[list[PromptMessageTool]] = None,
     ) -> int:
-        base_model_name = self._get_base_model_name(credentials)
+        base_model_name = credentials.get("base_model_name")
+        if not base_model_name:
+            raise ValueError("Base Model Name is required")
         model_entity = self._get_ai_model_entity(base_model_name=base_model_name, model=model)
         if not model_entity:
             raise ValueError(f"Base Model Name {base_model_name} is invalid")
@@ -104,7 +108,9 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
         if "base_model_name" not in credentials:
             raise CredentialsValidateFailedError("Base Model Name is required")
 
-        base_model_name = self._get_base_model_name(credentials)
+        base_model_name = credentials.get("base_model_name")
+        if not base_model_name:
+            raise CredentialsValidateFailedError("Base Model Name is required")
         ai_model_entity = self._get_ai_model_entity(base_model_name=base_model_name, model=model)
 
         if not ai_model_entity:
@@ -113,15 +119,7 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
         try:
             client = AzureOpenAI(**self._to_credential_kwargs(credentials))
 
-            if model.startswith("o1"):
-                client.chat.completions.create(
-                    messages=[{"role": "user", "content": "ping"}],
-                    model=model,
-                    temperature=1,
-                    max_completion_tokens=20,
-                    stream=False,
-                )
-            elif ai_model_entity.entity.model_properties.get(ModelPropertyKey.MODE) == LLMMode.CHAT.value:
+            if ai_model_entity.entity.model_properties.get(ModelPropertyKey.MODE) == LLMMode.CHAT.value:
                 # chat model
                 client.chat.completions.create(
                     messages=[{"role": "user", "content": "ping"}],
@@ -143,7 +141,9 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
             raise CredentialsValidateFailedError(str(ex))
 
     def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
-        base_model_name = self._get_base_model_name(credentials)
+        base_model_name = credentials.get("base_model_name")
+        if not base_model_name:
+            raise ValueError("Base Model Name is required")
         ai_model_entity = self._get_ai_model_entity(base_model_name=base_model_name, model=model)
         return ai_model_entity.entity if ai_model_entity else None
 
@@ -300,6 +300,11 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
 
         if tools:
             extra_model_kwargs["tools"] = [helper.dump_model(PromptMessageFunction(function=tool)) for tool in tools]
+            # extra_model_kwargs['functions'] = [{
+            #     "name": tool.name,
+            #     "description": tool.description,
+            #     "parameters": tool.parameters
+            # } for tool in tools]
 
         if stop:
             extra_model_kwargs["stop"] = stop
@@ -756,9 +761,3 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
                 ai_model_entity_copy.entity.label.en_US = model
                 ai_model_entity_copy.entity.label.zh_Hans = model
                 return ai_model_entity_copy
-
-    def _get_base_model_name(self, credentials: dict) -> str:
-        base_model_name = credentials.get("base_model_name")
-        if not base_model_name:
-            raise ValueError("Base Model Name is required")
-        return base_model_name

api/core/model_runtime/model_providers/azure_openai/text_embedding/text_embedding.py

@@ -7,7 +7,7 @@ import numpy as np
 import tiktoken
 from openai import AzureOpenAI
 
-from core.entities.embedding_type import EmbeddingInputType
+from core.embedding.embedding_constant import EmbeddingInputType
 from core.model_runtime.entities.model_entities import AIModelEntity, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.validate import CredentialsValidateFailedError

api/core/model_runtime/model_providers/baichuan/text_embedding/text_embedding.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 from requests import post
 
-from core.entities.embedding_type import EmbeddingInputType
+from core.embedding.embedding_constant import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.invoke import (

api/core/model_runtime/model_providers/bedrock/llm/anthropic.claude-3-sonnet-v2.yaml

@@ -1,60 +0,0 @@
-model: anthropic.claude-3-5-sonnet-20241022-v2:0
-label:
-  en_US: Claude 3.5 Sonnet V2
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - tool-call
-  - stream-tool-call
-model_properties:
-  mode: chat
-  context_size: 200000
-# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
-parameter_rules:
-  - name: max_tokens
-    use_template: max_tokens
-    required: true
-    type: int
-    default: 4096
-    min: 1
-    max: 4096
-    help:
-      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
-      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
-  - name: temperature
-    use_template: temperature
-    required: false
-    type: float
-    default: 1
-    min: 0.0
-    max: 1.0
-    help:
-      zh_Hans: 生成内容的随机性。
-      en_US: The amount of randomness injected into the response.
-  - name: top_p
-    required: false
-    type: float
-    default: 0.999
-    min: 0.000
-    max: 1.000
-    help:
-      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
-      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
-  - name: top_k
-    required: false
-    type: int
-    default: 0
-    min: 0
-    # tip docs from aws has error, max value is 500
-    max: 500
-    help:
-      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
-      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '0.003'
-  output: '0.015'
-  unit: '0.001'
-  currency: USD

api/core/model_runtime/model_providers/bedrock/llm/eu.anthropic.claude-3-haiku-v1.yaml

@@ -52,8 +52,6 @@ parameter_rules:
     help:
       zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
       en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
-  - name: response_format
-    use_template: response_format
 pricing:
   input: '0.00025'
   output: '0.00125'

api/core/model_runtime/model_providers/bedrock/llm/eu.anthropic.claude-3-sonnet-v1.5.yaml

@@ -51,8 +51,6 @@ parameter_rules:
     help:
       zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
       en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
-  - name: response_format
-    use_template: response_format
 pricing:
   input: '0.003'
   output: '0.015'