build: update react refresh ignore

Co-authored-by: cuihz <cuihz@knowbox.cn>
Co-authored-by: crazywoola <427733928@qq.com>

.devcontainer/post_create_command.sh

@@ -1,11 +1,12 @@
 #!/bin/bash
 
-cd web && npm install
+npm add -g pnpm@9.12.2
+cd web && pnpm install
 pipx install poetry
 
 echo 'alias start-api="cd /workspaces/dify/api && poetry run python -m flask run --host 0.0.0.0 --port=5001 --debug"' >> ~/.bashrc
 echo 'alias start-worker="cd /workspaces/dify/api && poetry run python -m celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion"' >> ~/.bashrc
-echo 'alias start-web="cd /workspaces/dify/web && npm run dev"' >> ~/.bashrc
+echo 'alias start-web="cd /workspaces/dify/web && pnpm dev"' >> ~/.bashrc
 echo 'alias start-containers="cd /workspaces/dify/docker && docker-compose -f docker-compose.middleware.yaml -p dify up -d"' >> ~/.bashrc
 
-source /home/vscode/.bashrc
+source /home/vscode/.bashrc

.github/workflows/api-tests.yml

@@ -27,18 +27,17 @@ 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

@@ -5,7 +5,6 @@ on:
     branches:
       - "main"
       - "deploy/dev"
-      - "fix/external-knowledge-retrieval-issues"
   release:
     types: [published]
 
@@ -126,7 +125,7 @@ jobs:
         with:
           images: ${{ env[matrix.image_name_env] }}
           tags: |
-            type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/') && !contains(github.ref, '-beta') }}
+            type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/') && !contains(github.ref, '-') }}
             type=ref,event=branch
             type=sha,enable=true,priority=100,prefix=,suffix=,format=long
             type=raw,value=${{ github.ref_name }},enable=${{ startsWith(github.ref, 'refs/tags/') }}

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

@@ -23,18 +23,17 @@ 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

@@ -24,15 +24,16 @@ 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
@@ -75,16 +76,16 @@ jobs:
         if: steps.changed-files.outputs.any_changed == 'true'
         with:
           node-version: 20
-          cache: yarn
+          cache: pnpm
           cache-dependency-path: ./web/package.json
 
       - name: Web dependencies
         if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn install --frozen-lockfile
+        run: pnpm install --frozen-lockfile
 
       - name: Web style check
         if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn run lint
+        run: pnpm run lint
 
 
   superlinter:

.github/workflows/tool-test-sdks.yaml

@@ -32,10 +32,10 @@ jobs:
         with:
           node-version: ${{ matrix.node-version }}
           cache: ''
-          cache-dependency-path: 'yarn.lock'
+          cache-dependency-path: 'pnpm-lock.yaml'
 
       - name: Install Dependencies
-        run: yarn install
+        run: pnpm install
 
       - name: Test
-        run: yarn test
+        run: pnpm test

.github/workflows/translate-i18n-base-on-english.yml

@@ -38,11 +38,11 @@ jobs:
 
       - name: Install dependencies
         if: env.FILES_CHANGED == 'true'
-        run: yarn install --frozen-lockfile
+        run: pnpm install --frozen-lockfile
 
       - name: Run npm script
         if: env.FILES_CHANGED == 'true'
-        run: npm run auto-gen-i18n
+        run: pnpm run auto-gen-i18n
 
       - name: Create Pull Request
         if: env.FILES_CHANGED == 'true'

.github/workflows/web-tests.yml

@@ -34,13 +34,13 @@ jobs:
         if: steps.changed-files.outputs.any_changed == 'true'
         with:
           node-version: 20
-          cache: yarn
+          cache: pnpm
           cache-dependency-path: ./web/package.json
 
       - name: Install dependencies
         if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn install --frozen-lockfile
+        run: pnpm install --frozen-lockfile
 
       - name: Run tests
         if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn test
+        run: pnpm test

.gitignore

@@ -187,4 +187,7 @@ pyrightconfig.json
 api/.vscode
 
 .idea/
-.vscode
+.vscode
+
+# pnpm
+/.pnpm-store

api/.env.example

@@ -20,6 +20,9 @@ FILES_URL=http://127.0.0.1:5001
 # The time in seconds after the signature is rejected
 FILES_ACCESS_TIMEOUT=300
 
+# Access token expiration time in minutes
+ACCESS_TOKEN_EXPIRE_MINUTES=60
+
 # celery configuration
 CELERY_BROKER_URL=redis://:difyai123456@localhost:6379/1
 
@@ -39,7 +42,7 @@ DB_DATABASE=dify
 
 # Storage configuration
 # use for store upload files, private keys...
-# storage type: local, s3, azure-blob, google-storage, tencent-cos, huawei-obs, volcengine-tos, baidu-obs
+# 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
@@ -99,11 +102,16 @@ VOLCENGINE_TOS_ACCESS_KEY=your-access-key
 VOLCENGINE_TOS_SECRET_KEY=your-secret-key
 VOLCENGINE_TOS_REGION=your-region
 
+# Supabase Storage Configuration
+SUPABASE_BUCKET_NAME=your-bucket-name
+SUPABASE_API_KEY=your-access-key
+SUPABASE_URL=your-server-url
+
 # CORS configuration
 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
+# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, vikingdb
 VECTOR_STORE=weaviate
 
 # Weaviate configuration
@@ -203,6 +211,24 @@ OPENSEARCH_USER=admin
 OPENSEARCH_PASSWORD=admin
 OPENSEARCH_SECURE=true
 
+# Baidu configuration
+BAIDU_VECTOR_DB_ENDPOINT=http://127.0.0.1:5287
+BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS=30000
+BAIDU_VECTOR_DB_ACCOUNT=root
+BAIDU_VECTOR_DB_API_KEY=dify
+BAIDU_VECTOR_DB_DATABASE=dify
+BAIDU_VECTOR_DB_SHARD=1
+BAIDU_VECTOR_DB_REPLICAS=3
+
+# ViKingDB configuration
+VIKINGDB_ACCESS_KEY=your-ak
+VIKINGDB_SECRET_KEY=your-sk
+VIKINGDB_REGION=cn-shanghai
+VIKINGDB_HOST=api-vikingdb.xxx.volces.com
+VIKINGDB_SCHEMA=http
+VIKINGDB_CONNECTION_TIMEOUT=30
+VIKINGDB_SOCKET_TIMEOUT=30
+
 # Upload configuration
 UPLOAD_FILE_SIZE_LIMIT=15
 UPLOAD_FILE_BATCH_LIMIT=5

api/README.md

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

api/app.py

@@ -10,44 +10,19 @@ 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 Flask, Response, request
-from flask_cors import CORS
-from werkzeug.exceptions import Unauthorized
+from flask import Response
 
-import contexts
-from commands import register_commands
-from configs import dify_config
+from app_factory import create_app
 
 # 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
 
@@ -60,188 +35,12 @@ 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.get("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:
-            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, token=auth_token)
-    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"]

api/app_factory.py

@@ -0,0 +1,213 @@
+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
+import logging
+import sys
+from logging.handlers import RotatingFileHandler
+
+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_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 = 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.get("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:
+            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)

api/commands.py

@@ -259,6 +259,25 @@ 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,
+    }
     page = 1
     while True:
         try:
@@ -284,11 +303,9 @@ def migrate_knowledge_vector_database():
                         skipped_count = skipped_count + 1
                         continue
                 collection_name = ""
-                if vector_type == VectorType.WEAVIATE:
-                    dataset_id = dataset.id
+                dataset_id = dataset.id
+                if vector_type in upper_colletion_vector_types:
                     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 = (
@@ -301,55 +318,15 @@ 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 == 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 in lower_colletion_vector_types:
+                    collection_name = Dataset.gen_collection_name_by_id(dataset_id).lower()
                 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

@@ -360,9 +360,9 @@ class WorkflowConfig(BaseSettings):
     )
 
 
-class OAuthConfig(BaseSettings):
+class AuthConfig(BaseSettings):
     """
-    Configuration for OAuth authentication
+    Configuration for authentication and OAuth
     """
 
     OAUTH_REDIRECT_PATH: str = Field(
@@ -371,7 +371,7 @@ class OAuthConfig(BaseSettings):
     )
 
     GITHUB_CLIENT_ID: Optional[str] = Field(
-        description="GitHub OAuth client secret",
+        description="GitHub OAuth client ID",
         default=None,
     )
 
@@ -390,6 +390,11 @@ class OAuthConfig(BaseSettings):
         default=None,
     )
 
+    ACCESS_TOKEN_EXPIRE_MINUTES: PositiveInt = Field(
+        description="Expiration time for access tokens in minutes",
+        default=60,
+    )
+
 
 class ModerationConfig(BaseSettings):
     """
@@ -501,11 +506,16 @@ class DataSetConfig(BaseSettings):
     Configuration for dataset management
     """
 
-    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 - plan: sandbox",
         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,
@@ -607,6 +617,7 @@ class PositionConfig(BaseSettings):
 class FeatureConfig(
     # place the configs in alphabet order
     AppExecutionConfig,
+    AuthConfig,  # Changed from OAuthConfig to AuthConfig
     BillingConfig,
     CodeExecutionSandboxConfig,
     DataSetConfig,
@@ -621,14 +632,13 @@ class FeatureConfig(
     MailConfig,
     ModelLoadBalanceConfig,
     ModerationConfig,
-    OAuthConfig,
+    PositionConfig,
     RagEtlConfig,
     SecurityConfig,
     ToolConfig,
     UpdateConfig,
     WorkflowConfig,
     WorkspaceConfig,
-    PositionConfig,
     # hosted services config
     HostedServiceConfig,
     CeleryBeatConfig,

api/configs/middleware/__init__.py

@@ -12,6 +12,7 @@ from configs.middleware.storage.baidu_obs_storage_config import BaiduOBSStorageC
 from configs.middleware.storage.google_cloud_storage_config import GoogleCloudStorageConfig
 from configs.middleware.storage.huawei_obs_storage_config import HuaweiCloudOBSStorageConfig
 from configs.middleware.storage.oci_storage_config import OCIStorageConfig
+from configs.middleware.storage.supabase_storage_config import SupabaseStorageConfig
 from configs.middleware.storage.tencent_cos_storage_config import TencentCloudCOSStorageConfig
 from configs.middleware.storage.volcengine_tos_storage_config import VolcengineTOSStorageConfig
 from configs.middleware.vdb.analyticdb_config import AnalyticdbConfig
@@ -27,6 +28,7 @@ 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_vector_config import TiDBVectorConfig
+from configs.middleware.vdb.vikingdb_config import VikingDBConfig
 from configs.middleware.vdb.weaviate_config import WeaviateConfig
 
 
@@ -222,6 +224,7 @@ class MiddlewareConfig(
     HuaweiCloudOBSStorageConfig,
     OCIStorageConfig,
     S3StorageConfig,
+    SupabaseStorageConfig,
     TencentCloudCOSStorageConfig,
     VolcengineTOSStorageConfig,
     # configs of vdb and vdb providers
@@ -241,5 +244,6 @@ class MiddlewareConfig(
     WeaviateConfig,
     ElasticsearchConfig,
     InternalTestConfig,
+    VikingDBConfig,
 ):
     pass

api/configs/middleware/storage/supabase_storage_config.py

@@ -0,0 +1,24 @@
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+class SupabaseStorageConfig(BaseModel):
+    """
+    Configuration settings for Supabase Object Storage Service
+    """
+
+    SUPABASE_BUCKET_NAME: Optional[str] = Field(
+        description="Name of the Supabase bucket to store and retrieve objects (e.g., 'dify-bucket')",
+        default=None,
+    )
+
+    SUPABASE_API_KEY: Optional[str] = Field(
+        description="API KEY for authenticating with Supabase",
+        default=None,
+    )
+
+    SUPABASE_URL: Optional[str] = Field(
+        description="URL of the Supabase",
+        default=None,
+    )

api/configs/middleware/vdb/baidu_vector_config.py

@@ -0,0 +1,45 @@
+from typing import Optional
+
+from pydantic import Field, NonNegativeInt, PositiveInt
+from pydantic_settings import BaseSettings
+
+
+class BaiduVectorDBConfig(BaseSettings):
+    """
+    Configuration settings for Baidu Vector Database
+    """
+
+    BAIDU_VECTOR_DB_ENDPOINT: Optional[str] = Field(
+        description="URL of the Baidu Vector Database service (e.g., 'http://vdb.bj.baidubce.com')",
+        default=None,
+    )
+
+    BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS: PositiveInt = Field(
+        description="Timeout in milliseconds for Baidu Vector Database operations (default is 30000 milliseconds)",
+        default=30000,
+    )
+
+    BAIDU_VECTOR_DB_ACCOUNT: Optional[str] = Field(
+        description="Account for authenticating with the Baidu Vector Database",
+        default=None,
+    )
+
+    BAIDU_VECTOR_DB_API_KEY: Optional[str] = Field(
+        description="API key for authenticating with the Baidu Vector Database service",
+        default=None,
+    )
+
+    BAIDU_VECTOR_DB_DATABASE: Optional[str] = Field(
+        description="Name of the specific Baidu Vector Database to connect to",
+        default=None,
+    )
+
+    BAIDU_VECTOR_DB_SHARD: PositiveInt = Field(
+        description="Number of shards for the Baidu Vector Database (default is 1)",
+        default=1,
+    )
+
+    BAIDU_VECTOR_DB_REPLICAS: NonNegativeInt = Field(
+        description="Number of replicas for the Baidu Vector Database (default is 3)",
+        default=3,
+    )

api/configs/middleware/vdb/oracle_config.py

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

api/configs/middleware/vdb/vikingdb_config.py

@@ -0,0 +1,49 @@
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+class VikingDBConfig(BaseModel):
+    """
+    Configuration for connecting to Volcengine VikingDB.
+    Refer to the following documentation for details on obtaining credentials:
+    https://www.volcengine.com/docs/6291/65568
+    """
+
+    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,
+    )
+
+    VIKINGDB_SECRET_KEY: Optional[str] = Field(
+        description="The Secret Key provided by Volcengine VikingDB for API authentication.",
+        default=None,
+    )
+
+    VIKINGDB_REGION: str = Field(
+        description="The region of the Volcengine VikingDB service.(e.g., 'cn-shanghai', 'cn-beijing').",
+        default="cn-shanghai",
+    )
+
+    VIKINGDB_HOST: str = Field(
+        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').",
+        default="http",
+    )
+
+    VIKINGDB_CONNECTION_TIMEOUT: int = Field(
+        description="The connection timeout of the Volcengine VikingDB service.",
+        default=30,
+    )
+
+    VIKINGDB_SOCKET_TIMEOUT: int = Field(
+        description="The socket timeout of the Volcengine VikingDB service.",
+        default=30,
+    )

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="0.9.1-fix1",
+        default="0.9.2",
     )
 
     COMMIT_SHA: str = Field(

api/controllers/console/auth/login.py

@@ -7,7 +7,7 @@ from flask_restful import Resource, reqparse
 import services
 from controllers.console import api
 from controllers.console.setup import setup_required
-from libs.helper import email, get_remote_ip
+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, TenantService
@@ -40,17 +40,16 @@ class LoginApi(Resource):
                 "data": "workspace not found, please contact system admin to invite you to join in a workspace",
             }
 
-        token = AccountService.login(account, ip_address=get_remote_ip(request))
+        token_pair = AccountService.login(account=account, ip_address=extract_remote_ip(request))
 
-        return {"result": "success", "data": token}
+        return {"result": "success", "data": token_pair.model_dump()}
 
 
 class LogoutApi(Resource):
     @setup_required
     def get(self):
         account = cast(Account, flask_login.current_user)
-        token = request.headers.get("Authorization", "").split(" ")[1]
-        AccountService.logout(account=account, token=token)
+        AccountService.logout(account=account)
         flask_login.logout_user()
         return {"result": "success"}
 
@@ -106,5 +105,19 @@ class ResetPasswordApi(Resource):
         return {"result": "success"}
 
 
+class RefreshTokenApi(Resource):
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("refresh_token", type=str, required=True, location="json")
+        args = parser.parse_args()
+
+        try:
+            new_token_pair = AccountService.refresh_token(args["refresh_token"])
+            return {"result": "success", "data": new_token_pair.model_dump()}
+        except Exception as e:
+            return {"result": "fail", "data": str(e)}, 401
+
+
 api.add_resource(LoginApi, "/login")
 api.add_resource(LogoutApi, "/logout")
+api.add_resource(RefreshTokenApi, "/refresh-token")

api/controllers/console/auth/oauth.py

@@ -9,7 +9,7 @@ from flask_restful import Resource
 from configs import dify_config
 from constants.languages import languages
 from extensions.ext_database import db
-from libs.helper import get_remote_ip
+from libs.helper import extract_remote_ip
 from libs.oauth import GitHubOAuth, GoogleOAuth, OAuthUserInfo
 from models.account import Account, AccountStatus
 from services.account_service import AccountService, RegisterService, TenantService
@@ -81,9 +81,14 @@ class OAuthCallback(Resource):
 
         TenantService.create_owner_tenant_if_not_exist(account)
 
-        token = AccountService.login(account, ip_address=get_remote_ip(request))
+        token_pair = AccountService.login(
+            account=account,
+            ip_address=extract_remote_ip(request),
+        )
 
-        return redirect(f"{dify_config.CONSOLE_WEB_URL}?console_token={token}")
+        return redirect(
+            f"{dify_config.CONSOLE_WEB_URL}?access_token={token_pair.access_token}&refresh_token={token_pair.refresh_token}"
+        )
 
 
 def _get_account_by_openid_or_email(provider: str, user_info: OAuthUserInfo) -> Optional[Account]:

api/controllers/console/datasets/datasets.py

@@ -617,6 +617,8 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.CHROMA
                 | VectorType.TENCENT
                 | VectorType.PGVECTO_RS
+                | VectorType.BAIDU
+                | VectorType.VIKINGDB
             ):
                 return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
             case (
@@ -653,6 +655,8 @@ class DatasetRetrievalSettingMockApi(Resource):
                 | VectorType.CHROMA
                 | VectorType.TENCENT
                 | VectorType.PGVECTO_RS
+                | VectorType.BAIDU
+                | VectorType.VIKINGDB
             ):
                 return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
             case (

api/controllers/console/datasets/hit_testing.py

@@ -1,88 +1,24 @@
-import logging
+from flask_restful import Resource
 
-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.app.error import (
-    CompletionRequestError,
-    ProviderModelCurrentlyNotSupportError,
-    ProviderNotInitializeError,
-    ProviderQuotaExceededError,
-)
-from controllers.console.datasets.error import DatasetNotInitializedError
+from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase
 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):
+class HitTestingApi(Resource, DatasetsHitTestingBase):
     @setup_required
     @login_required
     @account_initialization_required
     def post(self, dataset_id):
         dataset_id_str = str(dataset_id)
 
-        dataset = DatasetService.get_dataset(dataset_id_str)
-        if dataset is None:
-            raise NotFound("Dataset not found.")
+        dataset = self.get_and_validate_dataset(dataset_id_str)
+        args = self.parse_args()
+        self.hit_testing_args_check(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))
+        return self.perform_hit_testing(dataset, args)
 
 
 api.add_resource(HitTestingApi, "/datasets/<uuid:dataset_id>/hit-testing")

api/controllers/console/datasets/hit_testing_base.py

@@ -0,0 +1,85 @@
+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/setup.py

@@ -4,7 +4,7 @@ from flask import request
 from flask_restful import Resource, reqparse
 
 from configs import dify_config
-from libs.helper import StrLen, email, get_remote_ip
+from libs.helper import StrLen, email, extract_remote_ip
 from libs.password import valid_password
 from models.model import DifySetup
 from services.account_service import RegisterService, TenantService
@@ -46,7 +46,7 @@ class SetupApi(Resource):
 
         # setup
         RegisterService.setup(
-            email=args["email"], name=args["name"], password=args["password"], ip_address=get_remote_ip(request)
+            email=args["email"], name=args["name"], password=args["password"], ip_address=extract_remote_ip(request)
         )
 
         return {"result": "success"}, 201

api/controllers/service_api/__init__.py

@@ -5,7 +5,6 @@ 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, segment
+from .dataset import dataset, document, hit_testing, segment

api/controllers/service_api/app/completion.py

@@ -4,7 +4,6 @@ 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,
@@ -108,7 +107,6 @@ 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/dataset/hit_testing.py

@@ -0,0 +1,17 @@
+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/core/agent/output_parser/cot_output_parser.py

@@ -62,6 +62,8 @@ 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
@@ -74,35 +76,38 @@ class CotAgentOutputParser:
             while index < len(response):
                 steps = 1
                 delta = response[index : index + steps]
-                last_character = response[index - 1] if index > 0 else ""
+                yield_delta = False
 
                 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):
@@ -112,24 +117,25 @@ 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):
@@ -139,12 +145,20 @@ 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 = ""
 
@@ -156,8 +170,10 @@ 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
@@ -168,16 +184,19 @@ 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/apps/advanced_chat/app_generator.py

@@ -10,6 +10,7 @@ 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
@@ -122,7 +123,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             inputs=conversation.inputs if conversation else self._get_cleaned_inputs(inputs, app_config),
             query=query,
             files=file_objs,
-            parent_message_id=args.get("parent_message_id"),
+            parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
             user_id=user.id,
             stream=stream,
             invoke_from=invoke_from,

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

@@ -56,6 +56,7 @@ from models.account import Account
 from models.model import Conversation, EndUser, Message
 from models.workflow import (
     Workflow,
+    WorkflowNodeExecution,
     WorkflowRunStatus,
 )
 
@@ -72,6 +73,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
     _workflow: Workflow
     _user: Union[Account, EndUser]
     _workflow_system_variables: dict[SystemVariableKey, Any]
+    _wip_workflow_node_executions: dict[str, WorkflowNodeExecution]
 
     def __init__(
         self,
@@ -115,6 +117,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
         }
 
         self._task_state = WorkflowTaskState()
+        self._wip_workflow_node_executions = {}
 
         self._conversation_name_generate_thread = None
 

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

@@ -8,6 +8,7 @@ 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
@@ -127,7 +128,7 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
             inputs=conversation.inputs if conversation else self._get_cleaned_inputs(inputs, app_config),
             query=query,
             files=file_objs,
-            parent_message_id=args.get("parent_message_id"),
+            parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
             user_id=user.id,
             stream=stream,
             invoke_from=invoke_from,

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

@@ -8,6 +8,7 @@ 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
@@ -128,7 +129,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             inputs=conversation.inputs if conversation else self._get_cleaned_inputs(inputs, app_config),
             query=query,
             files=file_objs,
-            parent_message_id=args.get("parent_message_id"),
+            parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
             user_id=user.id,
             stream=stream,
             invoke_from=invoke_from,

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

@@ -52,6 +52,7 @@ from models.workflow import (
     Workflow,
     WorkflowAppLog,
     WorkflowAppLogCreatedFrom,
+    WorkflowNodeExecution,
     WorkflowRun,
     WorkflowRunStatus,
 )
@@ -69,6 +70,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
     _task_state: WorkflowTaskState
     _application_generate_entity: WorkflowAppGenerateEntity
     _workflow_system_variables: dict[SystemVariableKey, Any]
+    _wip_workflow_node_executions: dict[str, WorkflowNodeExecution]
 
     def __init__(
         self,
@@ -103,6 +105,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
         }
 
         self._task_state = WorkflowTaskState()
+        self._wip_workflow_node_executions = {}
 
     def process(self) -> Union[WorkflowAppBlockingResponse, Generator[WorkflowAppStreamResponse, None, None]]:
         """

api/core/app/entities/app_invoke_entities.py

@@ -2,8 +2,9 @@ from collections.abc import Mapping
 from enum import Enum
 from typing import Any, Optional
 
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, Field, ValidationInfo, field_validator
 
+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.file_obj import FileVar
@@ -116,13 +117,36 @@ class EasyUIBasedAppGenerateEntity(AppGenerateEntity):
     model_config = ConfigDict(protected_namespaces=())
 
 
-class ChatAppGenerateEntity(EasyUIBasedAppGenerateEntity):
+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):
     """
     Chat Application Generate Entity.
     """
 
-    conversation_id: Optional[str] = None
-    parent_message_id: Optional[str] = None
+    pass
 
 
 class CompletionAppGenerateEntity(EasyUIBasedAppGenerateEntity):
@@ -133,16 +157,15 @@ class CompletionAppGenerateEntity(EasyUIBasedAppGenerateEntity):
     pass
 
 
-class AgentChatAppGenerateEntity(EasyUIBasedAppGenerateEntity):
+class AgentChatAppGenerateEntity(ConversationAppGenerateEntity, EasyUIBasedAppGenerateEntity):
     """
     Agent Chat Application Generate Entity.
     """
 
-    conversation_id: Optional[str] = None
-    parent_message_id: Optional[str] = None
+    pass
 
 
-class AdvancedChatAppGenerateEntity(AppGenerateEntity):
+class AdvancedChatAppGenerateEntity(ConversationAppGenerateEntity):
     """
     Advanced Chat Application Generate Entity.
     """
@@ -150,8 +173,6 @@ class AdvancedChatAppGenerateEntity(AppGenerateEntity):
     # 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/task_pipeline/message_cycle_manage.py

@@ -1,8 +1,10 @@
+import logging
 from threading import Thread
 from typing import Optional, Union
 
 from flask import Flask, current_app
 
+from configs import dify_config
 from core.app.entities.app_invoke_entities import (
     AdvancedChatAppGenerateEntity,
     AgentChatAppGenerateEntity,
@@ -83,7 +85,9 @@ class MessageCycleManage:
                     name = LLMGenerator.generate_conversation_name(app_model.tenant_id, query)
                     conversation.name = name
                 except Exception as e:
-                    logging.exception(f"generate conversation name failed: {e}")
+                    if dify_config.DEBUG:
+                        logging.exception(f"generate conversation name failed: {e}")
+                    pass
 
                 db.session.merge(conversation)
                 db.session.commit()

api/core/app/task_pipeline/workflow_cycle_manage.py

@@ -57,6 +57,7 @@ class WorkflowCycleManage:
     _user: Union[Account, EndUser]
     _task_state: WorkflowTaskState
     _workflow_system_variables: dict[SystemVariableKey, Any]
+    _wip_workflow_node_executions: dict[str, WorkflowNodeExecution]
 
     def _handle_workflow_run_start(self) -> WorkflowRun:
         max_sequence = (
@@ -251,6 +252,8 @@ class WorkflowCycleManage:
         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:
@@ -263,20 +266,36 @@ class WorkflowCycleManage:
 
         inputs = WorkflowEntry.handle_special_values(event.inputs)
         outputs = WorkflowEntry.handle_special_values(event.outputs)
+        execution_metadata = (
+            json.dumps(jsonable_encoder(event.execution_metadata)) if event.execution_metadata else None
+        )
+        finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        elapsed_time = (finished_at - event.start_at).total_seconds()
+
+        db.session.query(WorkflowNodeExecution).filter(WorkflowNodeExecution.id == workflow_node_execution.id).update(
+            {
+                WorkflowNodeExecution.status: WorkflowNodeExecutionStatus.SUCCEEDED.value,
+                WorkflowNodeExecution.inputs: json.dumps(inputs) if inputs else None,
+                WorkflowNodeExecution.process_data: json.dumps(event.process_data) if event.process_data else None,
+                WorkflowNodeExecution.outputs: json.dumps(outputs) if outputs else None,
+                WorkflowNodeExecution.execution_metadata: execution_metadata,
+                WorkflowNodeExecution.finished_at: finished_at,
+                WorkflowNodeExecution.elapsed_time: elapsed_time,
+            }
+        )
+
+        db.session.commit()
+        db.session.close()
 
         workflow_node_execution.status = WorkflowNodeExecutionStatus.SUCCEEDED.value
         workflow_node_execution.inputs = json.dumps(inputs) if inputs else None
         workflow_node_execution.process_data = json.dumps(event.process_data) if event.process_data else None
         workflow_node_execution.outputs = json.dumps(outputs) if outputs else None
-        workflow_node_execution.execution_metadata = (
-            json.dumps(jsonable_encoder(event.execution_metadata)) if event.execution_metadata else None
-        )
-        workflow_node_execution.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
-        workflow_node_execution.elapsed_time = (workflow_node_execution.finished_at - event.start_at).total_seconds()
+        workflow_node_execution.execution_metadata = execution_metadata
+        workflow_node_execution.finished_at = finished_at
+        workflow_node_execution.elapsed_time = elapsed_time
 
-        db.session.commit()
-        db.session.refresh(workflow_node_execution)
-        db.session.close()
+        self._wip_workflow_node_executions.pop(workflow_node_execution.node_execution_id)
 
         return workflow_node_execution
 
@@ -290,18 +309,33 @@ class WorkflowCycleManage:
 
         inputs = WorkflowEntry.handle_special_values(event.inputs)
         outputs = WorkflowEntry.handle_special_values(event.outputs)
+        finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        elapsed_time = (finished_at - event.start_at).total_seconds()
+
+        db.session.query(WorkflowNodeExecution).filter(WorkflowNodeExecution.id == workflow_node_execution.id).update(
+            {
+                WorkflowNodeExecution.status: WorkflowNodeExecutionStatus.FAILED.value,
+                WorkflowNodeExecution.error: event.error,
+                WorkflowNodeExecution.inputs: json.dumps(inputs) if inputs else None,
+                WorkflowNodeExecution.process_data: json.dumps(event.process_data) if event.process_data else None,
+                WorkflowNodeExecution.outputs: json.dumps(outputs) if outputs else None,
+                WorkflowNodeExecution.finished_at: finished_at,
+                WorkflowNodeExecution.elapsed_time: elapsed_time,
+            }
+        )
+
+        db.session.commit()
+        db.session.close()
 
         workflow_node_execution.status = WorkflowNodeExecutionStatus.FAILED.value
         workflow_node_execution.error = event.error
-        workflow_node_execution.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
         workflow_node_execution.inputs = json.dumps(inputs) if inputs else None
         workflow_node_execution.process_data = json.dumps(event.process_data) if event.process_data else None
         workflow_node_execution.outputs = json.dumps(outputs) if outputs else None
-        workflow_node_execution.elapsed_time = (workflow_node_execution.finished_at - event.start_at).total_seconds()
+        workflow_node_execution.finished_at = finished_at
+        workflow_node_execution.elapsed_time = elapsed_time
 
-        db.session.commit()
-        db.session.refresh(workflow_node_execution)
-        db.session.close()
+        self._wip_workflow_node_executions.pop(workflow_node_execution.node_execution_id)
 
         return workflow_node_execution
 
@@ -678,17 +712,7 @@ class WorkflowCycleManage:
         :param node_execution_id: workflow node execution id
         :return:
         """
-        workflow_node_execution = (
-            db.session.query(WorkflowNodeExecution)
-            .filter(
-                WorkflowNodeExecution.tenant_id == self._application_generate_entity.app_config.tenant_id,
-                WorkflowNodeExecution.app_id == self._application_generate_entity.app_config.app_id,
-                WorkflowNodeExecution.workflow_id == self._workflow.id,
-                WorkflowNodeExecution.triggered_from == WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN.value,
-                WorkflowNodeExecution.node_execution_id == node_execution_id,
-            )
-            .first()
-        )
+        workflow_node_execution = self._wip_workflow_node_executions.get(node_execution_id)
 
         if not workflow_node_execution:
             raise Exception(f"Workflow node execution not found: {node_execution_id}")

api/core/memory/token_buffer_memory.py

@@ -60,8 +60,8 @@ class TokenBufferMemory:
         thread_messages = extract_thread_messages(messages)
 
         # for newly created message, its answer is temporarily empty, we don't need to add it to memory
-        if thread_messages and not thread_messages[-1].answer:
-            thread_messages.pop()
+        if thread_messages and not thread_messages[0].answer:
+            thread_messages.pop(0)
 
         messages = list(reversed(thread_messages))
 

api/core/model_manager.py

@@ -3,7 +3,7 @@ import os
 from collections.abc import Callable, Generator, Sequence
 from typing import IO, Optional, Union, cast
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type 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/model_providers/__base/text_embedding_model.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 from pydantic import ConfigDict
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type 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/azure_openai/_constant.py

@@ -1098,6 +1098,14 @@ 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"),
@@ -1135,6 +1143,14 @@ 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/llm/llm.py

@@ -119,7 +119,15 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
         try:
             client = AzureOpenAI(**self._to_credential_kwargs(credentials))
 
-            if ai_model_entity.entity.model_properties.get(ModelPropertyKey.MODE) == LLMMode.CHAT.value:
+            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:
                 # chat model
                 client.chat.completions.create(
                     messages=[{"role": "user", "content": "ping"}],

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.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type 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.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type 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/eu.anthropic.claude-3-haiku-v1.yaml

@@ -52,6 +52,8 @@ 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

@@ -51,6 +51,8 @@ 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'

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

@@ -51,6 +51,8 @@ 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'

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

@@ -52,6 +52,8 @@ 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/us.anthropic.claude-3-opus-v1.yaml

@@ -52,6 +52,8 @@ 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: '0.015'
   output: '0.075'

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

@@ -51,6 +51,8 @@ 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'

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

@@ -51,6 +51,8 @@ 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'

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

@@ -13,7 +13,7 @@ from botocore.exceptions import (
     UnknownServiceError,
 )
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type 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/cohere/text_embedding/text_embedding.py

@@ -5,7 +5,7 @@ import cohere
 import numpy as np
 from cohere.core import RequestOptions
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type 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/fireworks/fireworks.yaml

@@ -18,6 +18,7 @@ supported_model_types:
   - text-embedding
 configurate_methods:
   - predefined-model
+  - customizable-model
 provider_credential_schema:
   credential_form_schemas:
     - variable: fireworks_api_key
@@ -28,3 +29,75 @@ provider_credential_schema:
       placeholder:
         zh_Hans: 在此输入您的 API Key
         en_US: Enter your API Key
+model_credential_schema:
+  model:
+    label:
+      en_US: Model URL
+      zh_Hans: 模型URL
+    placeholder:
+      en_US: Enter your Model URL
+      zh_Hans: 输入模型URL
+  credential_form_schemas:
+    - variable: model_label_zh_Hanns
+      label:
+        zh_Hans: 模型中文名称
+        en_US: The zh_Hans of Model
+      required: true
+      type: text-input
+      placeholder:
+        zh_Hans: 在此输入您的模型中文名称
+        en_US: Enter your zh_Hans of Model
+    - variable: model_label_en_US
+      label:
+        zh_Hans: 模型英文名称
+        en_US: The en_US of Model
+      required: true
+      type: text-input
+      placeholder:
+        zh_Hans: 在此输入您的模型英文名称
+        en_US: Enter your en_US of Model
+    - variable: fireworks_api_key
+      label:
+        en_US: API Key
+      type: secret-input
+      required: true
+      placeholder:
+        zh_Hans: 在此输入您的 API Key
+        en_US: Enter your API Key
+    - variable: context_size
+      label:
+        zh_Hans: 模型上下文长度
+        en_US: Model context size
+      required: true
+      type: text-input
+      default: '4096'
+      placeholder:
+        zh_Hans: 在此输入您的模型上下文长度
+        en_US: Enter your Model context size
+    - variable: max_tokens
+      label:
+        zh_Hans: 最大 token 上限
+        en_US: Upper bound for max tokens
+      default: '4096'
+      type: text-input
+      show_on:
+        - variable: __model_type
+          value: llm
+    - variable: function_calling_type
+      label:
+        en_US: Function calling
+      type: select
+      required: false
+      default: no_call
+      options:
+        - value: no_call
+          label:
+            en_US: Not Support
+            zh_Hans: 不支持
+        - value: function_call
+          label:
+            en_US: Support
+            zh_Hans: 支持
+      show_on:
+        - variable: __model_type
+          value: llm

api/core/model_runtime/model_providers/fireworks/llm/gemma2-9b-it.yaml

@@ -43,3 +43,4 @@ pricing:
   output: '0.2'
   unit: '0.000001'
   currency: USD
+deprecated: true

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

@@ -8,7 +8,8 @@ from openai.types.chat.chat_completion_chunk import ChoiceDeltaFunctionCall, Cho
 from openai.types.chat.chat_completion_message import FunctionCall
 
 from core.model_runtime.callbacks.base_callback import Callback
-from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta
+from core.model_runtime.entities.common_entities import I18nObject
+from core.model_runtime.entities.llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta
 from core.model_runtime.entities.message_entities import (
     AssistantPromptMessage,
     ImagePromptMessageContent,
@@ -20,6 +21,15 @@ from core.model_runtime.entities.message_entities import (
     ToolPromptMessage,
     UserPromptMessage,
 )
+from core.model_runtime.entities.model_entities import (
+    AIModelEntity,
+    FetchFrom,
+    ModelFeature,
+    ModelPropertyKey,
+    ModelType,
+    ParameterRule,
+    ParameterType,
+)
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
 from core.model_runtime.model_providers.fireworks._common import _CommonFireworks
@@ -608,3 +618,50 @@ class FireworksLargeLanguageModel(_CommonFireworks, LargeLanguageModel):
                     num_tokens += self._get_num_tokens_by_gpt2(required_field)
 
         return num_tokens
+
+    def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity:
+        return AIModelEntity(
+            model=model,
+            label=I18nObject(
+                en_US=credentials.get("model_label_en_US", model),
+                zh_Hans=credentials.get("model_label_zh_Hanns", model),
+            ),
+            model_type=ModelType.LLM,
+            features=[ModelFeature.TOOL_CALL, ModelFeature.MULTI_TOOL_CALL, ModelFeature.STREAM_TOOL_CALL]
+            if credentials.get("function_calling_type") == "function_call"
+            else [],
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_properties={
+                ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size", 4096)),
+                ModelPropertyKey.MODE: LLMMode.CHAT.value,
+            },
+            parameter_rules=[
+                ParameterRule(
+                    name="temperature",
+                    use_template="temperature",
+                    label=I18nObject(en_US="Temperature", zh_Hans="温度"),
+                    type=ParameterType.FLOAT,
+                ),
+                ParameterRule(
+                    name="max_tokens",
+                    use_template="max_tokens",
+                    default=512,
+                    min=1,
+                    max=int(credentials.get("max_tokens", 4096)),
+                    label=I18nObject(en_US="Max Tokens", zh_Hans="最大标记"),
+                    type=ParameterType.INT,
+                ),
+                ParameterRule(
+                    name="top_p",
+                    use_template="top_p",
+                    label=I18nObject(en_US="Top P", zh_Hans="Top P"),
+                    type=ParameterType.FLOAT,
+                ),
+                ParameterRule(
+                    name="top_k",
+                    use_template="top_k",
+                    label=I18nObject(en_US="Top K", zh_Hans="Top K"),
+                    type=ParameterType.FLOAT,
+                ),
+            ],
+        )

api/core/model_runtime/model_providers/fireworks/llm/qwen2p5-72b-instruct.yaml

@@ -0,0 +1,46 @@
+model: accounts/fireworks/models/qwen2p5-72b-instruct
+label:
+  zh_Hans: Qwen2.5 72B Instruct
+  en_US: Qwen2.5 72B Instruct
+model_type: llm
+features:
+  - agent-thought
+  - tool-call
+model_properties:
+  mode: chat
+  context_size: 32768
+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.
+  - name: max_tokens
+    use_template: max_tokens
+  - name: context_length_exceeded_behavior
+    default: None
+    label:
+      zh_Hans: 上下文长度超出行为
+      en_US: Context Length Exceeded Behavior
+    help:
+      zh_Hans: 上下文长度超出行为
+      en_US: Context Length Exceeded Behavior
+    type: string
+    options:
+      - None
+      - truncate
+      - error
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.9'
+  output: '0.9'
+  unit: '0.000001'
+  currency: USD

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

@@ -5,7 +5,7 @@ from typing import Optional, Union
 import numpy as np
 from openai import OpenAI
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type 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.validate import CredentialsValidateFailedError

api/core/model_runtime/model_providers/google/llm/gemini-1.5-flash-001.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-flash-002.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-flash-8b-exp-0827.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-flash-8b-exp-0924.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-flash-exp-0827.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-flash-latest.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-flash.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-pro-001.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-pro-002.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-pro-exp-0801.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-pro-exp-0827.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-pro-latest.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-pro.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-pro-vision.yaml

@@ -27,15 +27,6 @@ parameter_rules:
     default: 4096
     min: 1
     max: 4096
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-pro.yaml

@@ -31,15 +31,6 @@ parameter_rules:
     max: 2048
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

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

@@ -6,7 +6,7 @@ import numpy as np
 import requests
 from huggingface_hub import HfApi, InferenceClient
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelType, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult

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

@@ -1,7 +1,7 @@
 import time
 from typing import Optional
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult

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

@@ -9,7 +9,7 @@ from tencentcloud.common.profile.client_profile import ClientProfile
 from tencentcloud.common.profile.http_profile import HttpProfile
 from tencentcloud.hunyuan.v20230901 import hunyuan_client, models
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type 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/jina/text_embedding/text_embedding.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 from requests import post
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult

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

@@ -5,7 +5,7 @@ from typing import Optional
 from requests import post
 from yarl import URL
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult

api/core/model_runtime/model_providers/minimax/llm/abab6.5t-chat.yaml

@@ -0,0 +1,44 @@
+model: abab6.5t-chat
+label:
+  en_US: Abab6.5t-Chat
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0.01
+    max: 1
+    default: 0.9
+  - name: top_p
+    use_template: top_p
+    min: 0.01
+    max: 1
+    default: 0.95
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 3072
+    min: 1
+    max: 8192
+  - name: mask_sensitive_info
+    type: boolean
+    default: true
+    label:
+      zh_Hans: 隐私保护
+      en_US: Moderate
+    help:
+      zh_Hans: 对输出中易涉及隐私问题的文本信息进行打码，目前包括但不限于邮箱、域名、链接、证件号、家庭住址等，默认true，即开启打码
+      en_US: Mask the sensitive info of the generated content, such as email/domain/link/address/phone/id..
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '0.005'
+  output: '0.005'
+  unit: '0.001'
+  currency: RMB

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

@@ -4,7 +4,7 @@ from typing import Optional
 
 from requests import post
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type 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 (
@@ -61,7 +61,8 @@ class MinimaxTextEmbeddingModel(TextEmbeddingModel):
         url = f"{self.api_base}?GroupId={group_id}"
         headers = {"Authorization": "Bearer " + api_key, "Content-Type": "application/json"}
 
-        data = {"model": "embo-01", "texts": texts, "type": "db"}
+        embedding_type = "db" if input_type == EmbeddingInputType.DOCUMENT else "query"
+        data = {"model": "embo-01", "texts": texts, "type": embedding_type}
 
         try:
             response = post(url, headers=headers, data=dumps(data))

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

@@ -4,7 +4,7 @@ from typing import Optional
 
 import requests
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult

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

@@ -5,7 +5,7 @@ from typing import Optional
 from nomic import embed
 from nomic import login as nomic_login
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import (
     EmbeddingUsage,

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

@@ -4,7 +4,7 @@ from typing import Optional
 
 from requests import post
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type 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/oci/text_embedding/text_embedding.py

@@ -6,7 +6,7 @@ from typing import Optional
 import numpy as np
 import oci
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type 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/ollama/text_embedding/text_embedding.py

@@ -8,7 +8,7 @@ from urllib.parse import urljoin
 import numpy as np
 import requests
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import (
     AIModelEntity,

api/core/model_runtime/model_providers/openai/openai.py

@@ -19,9 +19,9 @@ class OpenAIProvider(ModelProvider):
         try:
             model_instance = self.get_model_instance(ModelType.LLM)
 
-            # Use `gpt-3.5-turbo` model for validate,
+            # Use `gpt-4o-mini` model for validate,
             # no matter what model you pass in, text completion model or chat model
-            model_instance.validate_credentials(model="gpt-3.5-turbo", credentials=credentials)
+            model_instance.validate_credentials(model="gpt-4o-mini", credentials=credentials)
         except CredentialsValidateFailedError as ex:
             raise ex
         except Exception as ex:

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

@@ -6,7 +6,7 @@ import numpy as np
 import tiktoken
 from openai import OpenAI
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type 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.validate import CredentialsValidateFailedError

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

@@ -7,7 +7,7 @@ from urllib.parse import urljoin
 import numpy as np
 import requests
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import (
     AIModelEntity,

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

@@ -5,7 +5,7 @@ from typing import Optional
 from requests import post
 from requests.exceptions import ConnectionError, InvalidSchema, MissingSchema
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type 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/openrouter/llm/deepseek-chat.yaml

@@ -35,6 +35,15 @@ parameter_rules:
     help:
       zh_Hans: 控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。
       en_US: Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.
+  - 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: frequency_penalty
     use_template: frequency_penalty
     default: 0

api/core/model_runtime/model_providers/openrouter/llm/deepseek-coder.yaml

@@ -18,6 +18,15 @@ parameter_rules:
     min: 0
     max: 1
     default: 1
+  - 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
     min: 1

api/core/model_runtime/model_providers/openrouter/llm/gpt-3.5-turbo.yaml

@@ -14,6 +14,15 @@ parameter_rules:
     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: presence_penalty
     use_template: presence_penalty
   - name: frequency_penalty

api/core/model_runtime/model_providers/openrouter/llm/gpt-4-32k.yaml

@@ -14,6 +14,15 @@ parameter_rules:
     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: presence_penalty
     use_template: presence_penalty
   - name: frequency_penalty

api/core/model_runtime/model_providers/openrouter/llm/gpt-4.yaml

@@ -14,6 +14,15 @@ parameter_rules:
     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: presence_penalty
     use_template: presence_penalty
   - name: frequency_penalty

api/core/model_runtime/model_providers/openrouter/llm/gpt-4o-2024-08-06.yaml

@@ -16,6 +16,15 @@ parameter_rules:
     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: presence_penalty
     use_template: presence_penalty
   - name: frequency_penalty