feat: 白名单中去除 maas 平台

Co-authored-by: 开坦克的贝塔 <k@aircode.io>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>

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

@@ -38,13 +38,14 @@ jobs:
       - name: Install dependencies
         run: poetry install -C api
 
-      - name: Set up Middleware
+      - name: Set up Middlewares
         uses: hoverkraft-tech/compose-action@v2.0.0
         with:
           compose-file: |
             docker/docker-compose.middleware.yaml
           services: |
             db
+            redis
 
       - name: Prepare configs
         run: |
@@ -54,4 +55,4 @@ jobs:
       - name: Run DB Migration
         run: |
           cd api
-          poetry run python -m flask db upgrade
+          poetry run python -m flask upgrade-db

.github/workflows/style.yml

@@ -39,7 +39,7 @@ jobs:
 
       - name: Ruff check
         if: steps.changed-files.outputs.any_changed == 'true'
-        run: poetry run -C api ruff check --preview ./api
+        run: poetry run -C api ruff check ./api
 
       - name: Dotenv check
         if: steps.changed-files.outputs.any_changed == 'true'

.gitignore

@@ -136,6 +136,7 @@ web/.vscode/settings.json
 # Intellij IDEA Files
 .idea/*
 !.idea/vcs.xml
+!.idea/icon.png
 .ideaDataSources/
 
 api/.env

api/.env.example

@@ -65,6 +65,13 @@ ALIYUN_OSS_REGION=your-region
 GOOGLE_STORAGE_BUCKET_NAME=yout-bucket-name
 GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON=your-google-service-account-json-base64-string
 
+# Tencent COS Storage configuration
+TENCENT_COS_BUCKET_NAME=your-bucket-name
+TENCENT_COS_SECRET_KEY=your-secret-key
+TENCENT_COS_SECRET_ID=your-secret-id
+TENCENT_COS_REGION=your-region
+TENCENT_COS_SCHEME=your-scheme
+
 # CORS configuration
 WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*

api/README.md

@@ -11,24 +11,34 @@
    docker-compose -f docker-compose.middleware.yaml -p dify up -d
    cd ../api
    ```
+
 2. Copy `.env.example` to `.env`
 3. Generate a `SECRET_KEY` in the `.env` file.
 
-   ```bash
+   ```bash for Linux
    sed -i "/^SECRET_KEY=/c\SECRET_KEY=$(openssl rand -base64 42)" .env
    ```
+
+   ```bash for Mac
+   secret_key=$(openssl rand -base64 42)
+   sed -i '' "/^SECRET_KEY=/c\\
+   SECRET_KEY=${secret_key}" .env
+   ```
+
 4. Create environment.
 
    Dify API service uses [Poetry](https://python-poetry.org/docs/) to manage dependencies. You can execute `poetry shell` to activate the environment.
 
-   > Using pip can be found [below](#usage-with-pip). 
-   
-6. Install dependencies
-   
+   > Using pip can be found [below](#usage-with-pip).
+
+5. Install dependencies
+
+=======
    ```bash
+   poetry env use 3.10
    poetry install
    ```
-   
+
    In case of contributors missing to update dependencies for `pyproject.toml`, you can perform the following shell instead.
 
    ```bash
@@ -37,23 +47,23 @@
    poetry add $(cat requirements-dev.txt) --group dev    # install dependencies of development and update pyproject.toml
    ```
 
-7. Run migrate
+6. Run migrate
 
    Before the first launch, migrate the database to the latest version.
-   
+
    ```bash
    poetry run python -m flask db upgrade
    ```
 
-8. Start backend
-    
+7. Start backend
+
    ```bash
    poetry run python -m flask run --host 0.0.0.0 --port=5001 --debug
    ```
 
-9. Start Dify [web](../web) service.
-10. Setup your application by visiting `http://localhost:3000`...
-11. If you need to debug local async processing, please start the worker service.
+8. Start Dify [web](../web) service.
+9. Setup your application by visiting `http://localhost:3000`...
+10. If you need to debug local async processing, please start the worker service.
 
    ```bash
    poetry run python -m celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail
@@ -61,23 +71,21 @@
 
    The started celery app handles the async tasks, e.g. dataset importing and documents indexing.
 
-
 ## Testing
 
 1. Install dependencies for both the backend and the test environment
-   
+
    ```bash
    poetry install --with dev
-   ``` 
-   
+   ```
+
 2. Run the tests locally with mocked system environment variables in `tool.pytest_env` section in `pyproject.toml`
-   
+
    ```bash
    cd ../
    poetry run -C api bash dev/pytest/pytest_all_tests.sh
    ```
 
-
 ## Usage with pip
 
 > [!NOTE]  
@@ -92,7 +100,7 @@
    docker-compose -f docker-compose.middleware.yaml -p dify up -d
    cd ../api
    ```
-   
+
 2. Copy `.env.example` to `.env`
 3. Generate a `SECRET_KEY` in the `.env` file.
 
@@ -101,21 +109,21 @@
    ```
 
 4. Create environment.
-   
+
    If you use Anaconda, create a new environment and activate it
   
    ```bash
    conda create --name dify python=3.10
    conda activate dify
    ```
-      
-6. Install dependencies
-   
+
+5. Install dependencies
+
    ```bash
    pip install -r requirements.txt
    ```
 
-7. Run migrate
+6. Run migrate
 
    Before the first launch, migrate the database to the latest version.
 
@@ -123,27 +131,17 @@
    flask db upgrade
    ```
 
-8. Start backend:
+7. Start backend:
+
    ```bash
    flask run --host 0.0.0.0 --port=5001 --debug
    ```
-9. Setup your application by visiting http://localhost:5001/console/api/setup or other apis...
-10. If you need to debug local async processing, please start the worker service.
+
+8. Setup your application by visiting <http://localhost:5001/console/api/setup> or other apis...
+9. If you need to debug local async processing, please start the worker service.
+
    ```bash
    celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail
    ```
+
    The started celery app handles the async tasks, e.g. dataset importing and documents indexing.
-
-
-## Testing
-
-1. Install dependencies for both the backend and the test environment
-   ```bash
-   pip install -r requirements.txt -r requirements-dev.txt
-   ``` 
-   
-2. Run the tests locally with mocked system environment variables in `tool.pytest_env` section in `pyproject.toml`
-   ```bash
-   dev/pytest/pytest_all_tests.sh
-   ```
-

api/commands.py

@@ -1,5 +1,6 @@
 import base64
 import json
+import logging
 import secrets
 from typing import Optional
 
@@ -12,6 +13,7 @@ from core.rag.datasource.vdb.vector_factory import Vector
 from core.rag.datasource.vdb.vector_type import VectorType
 from core.rag.models.document import Document
 from extensions.ext_database import db
+from extensions.ext_redis import redis_client
 from libs.helper import email as email_validate
 from libs.password import hash_password, password_pattern, valid_password
 from libs.rsa import generate_key_pair
@@ -553,6 +555,28 @@ def create_tenant(email: str, language: Optional[str] = None):
                            'Account: {}\nPassword: {}'.format(email, new_password), fg='green'))
 
 
+@click.command('upgrade-db', help='upgrade the database')
+def upgrade_db():
+    click.echo('Preparing database migration...')
+    lock = redis_client.lock(name='db_upgrade_lock', timeout=60)
+    if lock.acquire(blocking=False):
+        try:
+            click.echo(click.style('Start database migration.', fg='green'))
+
+            # run db migration
+            import flask_migrate
+            flask_migrate.upgrade()
+
+            click.echo(click.style('Database migration successful!', fg='green'))
+
+        except Exception as e:
+            logging.exception(f'Database migration failed, error: {e}')
+        finally:
+            lock.release()
+    else:
+        click.echo('Database migration skipped')
+
+
 def register_commands(app):
     app.cli.add_command(reset_password)
     app.cli.add_command(reset_email)
@@ -561,4 +585,4 @@ def register_commands(app):
     app.cli.add_command(convert_to_agent_apps)
     app.cli.add_command(add_qdrant_doc_id_index)
     app.cli.add_command(create_tenant)
-
+    app.cli.add_command(upgrade_db)

api/config.py

@@ -253,6 +253,13 @@ class Config:
         self.GOOGLE_STORAGE_BUCKET_NAME = get_env('GOOGLE_STORAGE_BUCKET_NAME')
         self.GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64 = get_env('GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64')
 
+        # Tencent Cos Storage settings
+        self.TENCENT_COS_BUCKET_NAME = get_env('TENCENT_COS_BUCKET_NAME')
+        self.TENCENT_COS_REGION = get_env('TENCENT_COS_REGION')
+        self.TENCENT_COS_SECRET_ID = get_env('TENCENT_COS_SECRET_ID')
+        self.TENCENT_COS_SECRET_KEY = get_env('TENCENT_COS_SECRET_KEY')
+        self.TENCENT_COS_SCHEME = get_env('TENCENT_COS_SCHEME')
+
         # ------------------------
         # Vector Store Configurations.
         # Currently, only support: qdrant, milvus, zilliz, weaviate, relyt, pgvector

api/constants/languages.py

@@ -1,6 +1,6 @@
 
 
-languages = ['en-US', 'zh-Hans', 'zh-Hant', 'pt-BR', 'es-ES', 'fr-FR', 'de-DE', 'ja-JP', 'ko-KR', 'ru-RU', 'it-IT', 'uk-UA', 'vi-VN', 'pl-PL']
+languages = ['en-US', 'zh-Hans', 'zh-Hant', 'pt-BR', 'es-ES', 'fr-FR', 'de-DE', 'ja-JP', 'ko-KR', 'ru-RU', 'it-IT', 'uk-UA', 'vi-VN', 'pl-PL', 'hi-IN']
 
 language_timezone_mapping = {
     'en-US': 'America/New_York',
@@ -18,6 +18,7 @@ language_timezone_mapping = {
     'vi-VN': 'Asia/Ho_Chi_Minh',
     'ro-RO': 'Europe/Bucharest',
     'pl-PL': 'Europe/Warsaw',
+    'hi-IN': 'Asia/Kolkata'
 }
 
 

api/controllers/console/app/app.py

@@ -129,6 +129,10 @@ class AppApi(Resource):
     @marshal_with(app_detail_fields_with_site)
     def put(self, app_model):
         """Update app"""
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        
         parser = reqparse.RequestParser()
         parser.add_argument('name', type=str, required=True, nullable=False, location='json')
         parser.add_argument('description', type=str, location='json')
@@ -147,6 +151,7 @@ class AppApi(Resource):
     @get_app_model
     def delete(self, app_model):
         """Delete app"""
+        # The role of the current user in the ta table must be admin, owner, or editor
         if not current_user.is_editor:
             raise Forbidden()
 
@@ -203,6 +208,10 @@ class AppNameApi(Resource):
     @get_app_model
     @marshal_with(app_detail_fields)
     def post(self, app_model):
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        
         parser = reqparse.RequestParser()
         parser.add_argument('name', type=str, required=True, location='json')
         args = parser.parse_args()
@@ -220,6 +229,10 @@ class AppIconApi(Resource):
     @get_app_model
     @marshal_with(app_detail_fields)
     def post(self, app_model):
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        
         parser = reqparse.RequestParser()
         parser.add_argument('icon', type=str, location='json')
         parser.add_argument('icon_background', type=str, location='json')
@@ -241,6 +254,7 @@ class AppSiteStatus(Resource):
         # The role of the current user in the ta table must be admin, owner, or editor
         if not current_user.is_editor:
             raise Forbidden()
+        
         parser = reqparse.RequestParser()
         parser.add_argument('enable_site', type=bool, required=True, location='json')
         args = parser.parse_args()
@@ -261,6 +275,7 @@ class AppApiStatus(Resource):
         # The role of the current user in the ta table must be admin or owner
         if not current_user.is_admin_or_owner:
             raise Forbidden()
+        
         parser = reqparse.RequestParser()
         parser.add_argument('enable_api', type=bool, required=True, location='json')
         args = parser.parse_args()

api/controllers/console/app/workflow.py

@@ -3,7 +3,7 @@ import logging
 
 from flask import abort, request
 from flask_restful import Resource, marshal_with, reqparse
-from werkzeug.exceptions import InternalServerError, NotFound
+from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
 import services
 from controllers.console import api
@@ -36,6 +36,10 @@ class DraftWorkflowApi(Resource):
         """
         Get draft workflow
         """
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        
         # fetch draft workflow by app_model
         workflow_service = WorkflowService()
         workflow = workflow_service.get_draft_workflow(app_model=app_model)
@@ -54,6 +58,10 @@ class DraftWorkflowApi(Resource):
         """
         Sync draft workflow
         """
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        
         content_type = request.headers.get('Content-Type')
 
         if 'application/json' in content_type:
@@ -110,6 +118,10 @@ class AdvancedChatDraftWorkflowRunApi(Resource):
         """
         Run draft workflow
         """
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        
         parser = reqparse.RequestParser()
         parser.add_argument('inputs', type=dict, location='json')
         parser.add_argument('query', type=str, required=True, location='json', default='')
@@ -146,6 +158,10 @@ class AdvancedChatDraftRunIterationNodeApi(Resource):
         """
         Run draft workflow iteration node
         """
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        
         parser = reqparse.RequestParser()
         parser.add_argument('inputs', type=dict, location='json')
         args = parser.parse_args()
@@ -179,6 +195,10 @@ class WorkflowDraftRunIterationNodeApi(Resource):
         """
         Run draft workflow iteration node
         """
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        
         parser = reqparse.RequestParser()
         parser.add_argument('inputs', type=dict, location='json')
         args = parser.parse_args()
@@ -212,6 +232,10 @@ class DraftWorkflowRunApi(Resource):
         """
         Run draft workflow
         """
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        
         parser = reqparse.RequestParser()
         parser.add_argument('inputs', type=dict, required=True, nullable=False, location='json')
         parser.add_argument('files', type=list, required=False, location='json')
@@ -243,6 +267,10 @@ class WorkflowTaskStopApi(Resource):
         """
         Stop workflow task
         """
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        
         AppQueueManager.set_stop_flag(task_id, InvokeFrom.DEBUGGER, current_user.id)
 
         return {
@@ -260,6 +288,10 @@ class DraftWorkflowNodeRunApi(Resource):
         """
         Run draft workflow node
         """
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        
         parser = reqparse.RequestParser()
         parser.add_argument('inputs', type=dict, required=True, nullable=False, location='json')
         args = parser.parse_args()
@@ -286,6 +318,10 @@ class PublishedWorkflowApi(Resource):
         """
         Get published workflow
         """
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        
         # fetch published workflow by app_model
         workflow_service = WorkflowService()
         workflow = workflow_service.get_published_workflow(app_model=app_model)
@@ -301,6 +337,10 @@ class PublishedWorkflowApi(Resource):
         """
         Publish workflow
         """
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        
         workflow_service = WorkflowService()
         workflow = workflow_service.publish_workflow(app_model=app_model, account=current_user)
 
@@ -319,6 +359,10 @@ class DefaultBlockConfigsApi(Resource):
         """
         Get default block config
         """
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        
         # Get default block configs
         workflow_service = WorkflowService()
         return workflow_service.get_default_block_configs()
@@ -333,6 +377,10 @@ class DefaultBlockConfigApi(Resource):
         """
         Get default block config
         """
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        
         parser = reqparse.RequestParser()
         parser.add_argument('q', type=str, location='args')
         args = parser.parse_args()
@@ -363,6 +411,10 @@ class ConvertToWorkflowApi(Resource):
         Convert expert mode of chatbot app to workflow mode
         Convert Completion App to Workflow App
         """
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        
         if request.data:
             parser = reqparse.RequestParser()
             parser.add_argument('name', type=str, required=False, nullable=True, location='json')

api/controllers/console/auth/data_source_bearer_auth.py

@@ -16,15 +16,21 @@ class ApiKeyAuthDataSource(Resource):
     @login_required
     @account_initialization_required
     def get(self):
-        # The role of the current user in the table must be admin or owner
-        if not current_user.is_admin_or_owner:
-            raise Forbidden()
         data_source_api_key_bindings = ApiKeyAuthService.get_provider_auth_list(current_user.current_tenant_id)
         if data_source_api_key_bindings:
             return {
-                'settings': [data_source_api_key_binding.to_dict() for data_source_api_key_binding in
-                             data_source_api_key_bindings]}
-        return {'settings': []}
+                'sources': [{
+                                'id': data_source_api_key_binding.id,
+                                'category': data_source_api_key_binding.category,
+                                'provider': data_source_api_key_binding.provider,
+                                'disabled': data_source_api_key_binding.disabled,
+                                'created_at': int(data_source_api_key_binding.created_at.timestamp()),
+                                'updated_at': int(data_source_api_key_binding.updated_at.timestamp()),
+                            }
+                            for data_source_api_key_binding in
+                             data_source_api_key_bindings]
+            }
+        return {'sources': []}
 
 
 class ApiKeyAuthDataSourceBinding(Resource):

api/core/agent/cot_agent_runner.py

@@ -32,9 +32,9 @@ class CotAgentRunner(BaseAgentRunner, ABC):
     _prompt_messages_tools: list[PromptMessage] = None
 
     def run(self, message: Message,
-        query: str,
-        inputs: dict[str, str],
-    ) -> Union[Generator, LLMResult]:
+            query: str,
+            inputs: dict[str, str],
+            ) -> Union[Generator, LLMResult]:
         """
         Run Cot agent application
         """
@@ -52,7 +52,8 @@ class CotAgentRunner(BaseAgentRunner, ABC):
         # init instruction
         inputs = inputs or {}
         instruction = app_config.prompt_template.simple_prompt_template
-        self._instruction = self._fill_in_inputs_from_external_data_tools(instruction, inputs)
+        self._instruction = self._fill_in_inputs_from_external_data_tools(
+            instruction, inputs)
 
         iteration_step = 1
         max_iteration_steps = min(app_config.agent.max_iteration, 5) + 1
@@ -60,8 +61,6 @@ class CotAgentRunner(BaseAgentRunner, ABC):
         # convert tools into ModelRuntime Tool format
         tool_instances, self._prompt_messages_tools = self._init_prompt_tools()
 
-        prompt_messages = self._organize_prompt_messages()
-        
         function_call_state = True
         llm_usage = {
             'usage': None
@@ -120,9 +119,10 @@ class CotAgentRunner(BaseAgentRunner, ABC):
             # check llm result
             if not chunks:
                 raise ValueError("failed to invoke llm")
-            
+
             usage_dict = {}
-            react_chunks = CotAgentOutputParser.handle_react_stream_output(chunks, usage_dict)
+            react_chunks = CotAgentOutputParser.handle_react_stream_output(
+                chunks, usage_dict)
             scratchpad = AgentScratchpadUnit(
                 agent_response='',
                 thought='',
@@ -160,15 +160,16 @@ class CotAgentRunner(BaseAgentRunner, ABC):
                         )
                     )
 
-            scratchpad.thought = scratchpad.thought.strip() or 'I am thinking about how to help you'
+            scratchpad.thought = scratchpad.thought.strip(
+            ) or 'I am thinking about how to help you'
             self._agent_scratchpad.append(scratchpad)
-            
+
             # get llm usage
             if 'usage' in usage_dict:
                 increase_usage(llm_usage, usage_dict['usage'])
             else:
                 usage_dict['usage'] = LLMUsage.empty_usage()
-            
+
             self.save_agent_thought(
                 agent_thought=agent_thought,
                 tool_name=scratchpad.action.action_name if scratchpad.action else '',
@@ -182,7 +183,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):
                 messages_ids=[],
                 llm_usage=usage_dict['usage']
             )
-            
+
             if not scratchpad.is_final():
                 self.queue_manager.publish(QueueAgentThoughtEvent(
                     agent_thought_id=agent_thought.id
@@ -196,7 +197,8 @@ class CotAgentRunner(BaseAgentRunner, ABC):
                     # action is final answer, return final answer directly
                     try:
                         if isinstance(scratchpad.action.action_input, dict):
-                            final_answer = json.dumps(scratchpad.action.action_input)
+                            final_answer = json.dumps(
+                                scratchpad.action.action_input)
                         elif isinstance(scratchpad.action.action_input, str):
                             final_answer = scratchpad.action.action_input
                         else:
@@ -207,7 +209,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):
                     function_call_state = True
                     # action is tool call, invoke tool
                     tool_invoke_response, tool_invoke_meta = self._handle_invoke_action(
-                        action=scratchpad.action, 
+                        action=scratchpad.action,
                         tool_instances=tool_instances,
                         message_file_ids=message_file_ids
                     )
@@ -217,10 +219,13 @@ class CotAgentRunner(BaseAgentRunner, ABC):
                     self.save_agent_thought(
                         agent_thought=agent_thought,
                         tool_name=scratchpad.action.action_name,
-                        tool_input={scratchpad.action.action_name: scratchpad.action.action_input},
+                        tool_input={
+                            scratchpad.action.action_name: scratchpad.action.action_input},
                         thought=scratchpad.thought,
-                        observation={scratchpad.action.action_name: tool_invoke_response},
-                        tool_invoke_meta={scratchpad.action.action_name: tool_invoke_meta.to_dict()},
+                        observation={
+                            scratchpad.action.action_name: tool_invoke_response},
+                        tool_invoke_meta={
+                            scratchpad.action.action_name: tool_invoke_meta.to_dict()},
                         answer=scratchpad.agent_response,
                         messages_ids=message_file_ids,
                         llm_usage=usage_dict['usage']
@@ -232,7 +237,8 @@ class CotAgentRunner(BaseAgentRunner, ABC):
 
                 # update prompt tool message
                 for prompt_tool in self._prompt_messages_tools:
-                    self.update_prompt_message_tool(tool_instances[prompt_tool.name], prompt_tool)
+                    self.update_prompt_message_tool(
+                        tool_instances[prompt_tool.name], prompt_tool)
 
             iteration_step += 1
 
@@ -251,12 +257,12 @@ class CotAgentRunner(BaseAgentRunner, ABC):
 
         # save agent thought
         self.save_agent_thought(
-            agent_thought=agent_thought, 
+            agent_thought=agent_thought,
             tool_name='',
             tool_input={},
             tool_invoke_meta={},
             thought=final_answer,
-            observation={}, 
+            observation={},
             answer=final_answer,
             messages_ids=[]
         )
@@ -269,11 +275,12 @@ class CotAgentRunner(BaseAgentRunner, ABC):
             message=AssistantPromptMessage(
                 content=final_answer
             ),
-            usage=llm_usage['usage'] if llm_usage['usage'] else LLMUsage.empty_usage(),
+            usage=llm_usage['usage'] if llm_usage['usage'] else LLMUsage.empty_usage(
+            ),
             system_fingerprint=''
         )), PublishFrom.APPLICATION_MANAGER)
 
-    def _handle_invoke_action(self, action: AgentScratchpadUnit.Action, 
+    def _handle_invoke_action(self, action: AgentScratchpadUnit.Action,
                               tool_instances: dict[str, Tool],
                               message_file_ids: list[str]) -> tuple[str, ToolInvokeMeta]:
         """
@@ -290,7 +297,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):
         if not tool_instance:
             answer = f"there is not a tool named {tool_call_name}"
             return answer, ToolInvokeMeta.error_instance(answer)
-        
+
         if isinstance(tool_call_args, str):
             try:
                 tool_call_args = json.loads(tool_call_args)
@@ -311,7 +318,8 @@ class CotAgentRunner(BaseAgentRunner, ABC):
         # publish files
         for message_file, save_as in message_files:
             if save_as:
-                self.variables_pool.set_file(tool_name=tool_call_name, value=message_file.id, name=save_as)
+                self.variables_pool.set_file(
+                    tool_name=tool_call_name, value=message_file.id, name=save_as)
 
             # publish message file
             self.queue_manager.publish(QueueMessageFileEvent(
@@ -342,7 +350,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):
                 continue
 
         return instruction
-    
+
     def _init_react_state(self, query) -> None:
         """
         init agent scratchpad
@@ -350,7 +358,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):
         self._query = query
         self._agent_scratchpad = []
         self._historic_prompt_messages = self._organize_historic_prompt_messages()
-    
+
     @abstractmethod
     def _organize_prompt_messages(self) -> list[PromptMessage]:
         """
@@ -379,54 +387,54 @@ class CotAgentRunner(BaseAgentRunner, ABC):
             organize historic prompt messages
         """
         result: list[PromptMessage] = []
-        scratchpad: list[AgentScratchpadUnit] = []
+        scratchpads: list[AgentScratchpadUnit] = []
         current_scratchpad: AgentScratchpadUnit = None
 
-        self.history_prompt_messages = AgentHistoryPromptTransform(
-            model_config=self.model_config,
-            prompt_messages=current_session_messages or [],
-            history_messages=self.history_prompt_messages,
-            memory=self.memory
-        ).get_prompt()
-
         for message in self.history_prompt_messages:
             if isinstance(message, AssistantPromptMessage):
-                current_scratchpad = AgentScratchpadUnit(
-                    agent_response=message.content,
-                    thought=message.content or 'I am thinking about how to help you',
-                    action_str='',
-                    action=None,
-                    observation=None,
-                )
+                if not current_scratchpad:
+                    current_scratchpad = AgentScratchpadUnit(
+                        agent_response=message.content,
+                        thought=message.content or 'I am thinking about how to help you',
+                        action_str='',
+                        action=None,
+                        observation=None,
+                    )
+                    scratchpads.append(current_scratchpad)
                 if message.tool_calls:
                     try:
                         current_scratchpad.action = AgentScratchpadUnit.Action(
                             action_name=message.tool_calls[0].function.name,
-                            action_input=json.loads(message.tool_calls[0].function.arguments)
+                            action_input=json.loads(
+                                message.tool_calls[0].function.arguments)
                         )
                         current_scratchpad.action_str = json.dumps(
                             current_scratchpad.action.to_dict()
                         )
                     except:
                         pass
-                
-                scratchpad.append(current_scratchpad)
             elif isinstance(message, ToolPromptMessage):
                 if current_scratchpad:
                     current_scratchpad.observation = message.content
             elif isinstance(message, UserPromptMessage):
+                if scratchpads:
+                    result.append(AssistantPromptMessage(
+                        content=self._format_assistant_message(scratchpads)
+                    ))
+                    scratchpads = []
+                    current_scratchpad = None
+
                 result.append(message)
 
-                if scratchpad:
-                    result.append(AssistantPromptMessage(
-                        content=self._format_assistant_message(scratchpad)
-                    ))
-
-                scratchpad = []
-
-        if scratchpad:
+        if scratchpads:
             result.append(AssistantPromptMessage(
-                content=self._format_assistant_message(scratchpad)
+                content=self._format_assistant_message(scratchpads)
             ))
-        
-        return result
+
+        historic_prompts = AgentHistoryPromptTransform(
+            model_config=self.model_config,
+            prompt_messages=current_session_messages or [],
+            history_messages=result,
+            memory=self.memory
+        ).get_prompt()
+        return historic_prompts

api/core/agent/cot_chat_agent_runner.py

@@ -5,6 +5,7 @@ from core.model_runtime.entities.message_entities import (
     AssistantPromptMessage,
     PromptMessage,
     SystemPromptMessage,
+    TextPromptMessageContent,
     UserPromptMessage,
 )
 from core.model_runtime.utils.encoders import jsonable_encoder
@@ -25,6 +26,21 @@ class CotChatAgentRunner(CotAgentRunner):
 
         return SystemPromptMessage(content=system_prompt)
 
+    def _organize_user_query(self, query,  prompt_messages: list[PromptMessage] = None) -> list[PromptMessage]:
+        """
+        Organize user query
+        """
+        if self.files:
+            prompt_message_contents = [TextPromptMessageContent(data=query)]
+            for file_obj in self.files:
+                prompt_message_contents.append(file_obj.prompt_message_content)
+
+            prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
+        else:
+            prompt_messages.append(UserPromptMessage(content=query))
+
+        return prompt_messages
+
     def _organize_prompt_messages(self) -> list[PromptMessage]:
         """
         Organize 
@@ -51,27 +67,27 @@ class CotChatAgentRunner(CotAgentRunner):
             assistant_messages = [assistant_message]
 
         # query messages
-        query_messages = UserPromptMessage(content=self._query)
+        query_messages = self._organize_user_query(self._query, [])
 
         if assistant_messages:
             # organize historic prompt messages
             historic_messages = self._organize_historic_prompt_messages([
                 system_message,
-                query_messages,
+                *query_messages,
                 *assistant_messages,
                 UserPromptMessage(content='continue')
-            ])            
+            ])
             messages = [
                 system_message,
                 *historic_messages,
-                query_messages,
+                *query_messages,
                 *assistant_messages,
                 UserPromptMessage(content='continue')
             ]
         else:
             # organize historic prompt messages
-            historic_messages = self._organize_historic_prompt_messages([system_message, query_messages])
-            messages = [system_message, *historic_messages, query_messages]
+            historic_messages = self._organize_historic_prompt_messages([system_message, *query_messages])
+            messages = [system_message, *historic_messages, *query_messages]
 
         # join all messages
-        return messages
+        return messages

api/core/agent/output_parser/cot_output_parser.py

@@ -17,6 +17,10 @@ class CotAgentOutputParser:
                 action_name = None
                 action_input = None
 
+                # cohere always returns a list
+                if isinstance(action, list) and len(action) == 1:
+                    action = action[0]
+
                 for key, value in action.items():
                     if 'input' in key.lower():
                         action_input = value

api/core/app/entities/queue_entities.py

@@ -77,8 +77,8 @@ class QueueIterationNextEvent(AppQueueEvent):
     node_run_index: int
     output: Optional[Any] = None # output for the current iteration
 
-    @classmethod
     @field_validator('output', mode='before')
+    @classmethod
     def set_output(cls, v):
         """
         Set output

api/core/app/entities/task_entities.py

@@ -367,7 +367,7 @@ class IterationNodeNextStreamResponse(StreamResponse):
 
 class IterationNodeCompletedStreamResponse(StreamResponse):
     """
-    NodeStartStreamResponse entity
+    NodeCompletedStreamResponse entity
     """
     class Data(BaseModel):
         """
@@ -385,6 +385,7 @@ class IterationNodeCompletedStreamResponse(StreamResponse):
         error: Optional[str] = None
         elapsed_time: float
         total_tokens: int
+        execution_metadata: Optional[dict] = None
         finished_at: int
         steps: int
 
@@ -545,4 +546,4 @@ class WorkflowIterationState(BaseModel):
         total_tokens: int = 0
         node_data: BaseNodeData
 
-    current_iterations: dict[str, Data] = None
+    current_iterations: dict[str, Data] = None

api/core/app/task_pipeline/workflow_iteration_cycle_manage.py

@@ -17,6 +17,7 @@ from core.app.entities.task_entities import (
 )
 from core.app.task_pipeline.workflow_cycle_state_manager import WorkflowCycleStateManager
 from core.workflow.entities.node_entities import NodeType
+from core.workflow.workflow_engine_manager import WorkflowEngineManager
 from extensions.ext_database import db
 from models.workflow import (
     WorkflowNodeExecution,
@@ -94,6 +95,9 @@ class WorkflowIterationCycleManage(WorkflowCycleStateManager):
                     error=None,
                     elapsed_time=time.perf_counter() - current_iteration.started_at,
                     total_tokens=current_iteration.total_tokens,
+                    execution_metadata={
+                        'total_tokens': current_iteration.total_tokens,
+                    },
                     finished_at=int(time.time()),
                     steps=current_iteration.current_index
                 )
@@ -205,7 +209,7 @@ class WorkflowIterationCycleManage(WorkflowCycleStateManager):
 
         db.session.close()
 
-    def _handle_iteration_completed(self, event: QueueIterationCompletedEvent) -> WorkflowNodeExecution:
+    def _handle_iteration_completed(self, event: QueueIterationCompletedEvent):
         if event.node_id not in self._iteration_state.current_iterations:
             return
         
@@ -215,9 +219,9 @@ class WorkflowIterationCycleManage(WorkflowCycleStateManager):
         ).first()
 
         workflow_node_execution.status = WorkflowNodeExecutionStatus.SUCCEEDED.value
-        workflow_node_execution.outputs = json.dumps(event.outputs) if event.outputs else None
+        workflow_node_execution.outputs = json.dumps(WorkflowEngineManager.handle_special_values(event.outputs)) if event.outputs else None
         workflow_node_execution.elapsed_time = time.perf_counter() - current_iteration.started_at
-        
+
         original_node_execution_metadata = workflow_node_execution.execution_metadata_dict
         if original_node_execution_metadata:
             original_node_execution_metadata['steps_boundary'] = current_iteration.iteration_steps_boundary
@@ -275,7 +279,10 @@ class WorkflowIterationCycleManage(WorkflowCycleStateManager):
                     error=error,
                     elapsed_time=time.perf_counter() - current_iteration.started_at,
                     total_tokens=current_iteration.total_tokens,
+                    execution_metadata={
+                        'total_tokens': current_iteration.total_tokens,
+                    },
                     finished_at=int(time.time()),
                     steps=current_iteration.current_index
                 )
-            )
+            )

api/core/model_runtime/entities/message_entities.py

@@ -124,6 +124,7 @@ class AssistantPromptMessage(PromptMessage):
         function: ToolCallFunction
 
         @field_validator('id', mode='before')
+        @classmethod
         def transform_id_to_str(cls, value) -> str:
             if not isinstance(value, str):
                 return str(value)

api/core/model_runtime/model_providers/azure_openai/_assets/icon_s_en.svg

@@ -1,5 +1,5 @@
 <svg width="21" height="22" viewBox="0 0 21 22" fill="none" xmlns="http://www.w3.org/2000/svg">
-<g id="Microsfot">
+<g id="Microsoft">
 <rect id="Rectangle 1010" y="0.5" width="10" height="10" fill="#EF4F21"/>
 <rect id="Rectangle 1012" y="11.5" width="10" height="10" fill="#03A4EE"/>
 <rect id="Rectangle 1011" x="11" y="0.5" width="10" height="10" fill="#7EB903"/>

api/core/model_runtime/model_providers/bedrock/bedrock.yaml

@@ -23,7 +23,7 @@ provider_credential_schema:
     - variable: aws_access_key_id
       required: false
       label:
-        en_US: Access Key (If not provided, credentials are obtained from your running environment. e.g. IAM role)
+        en_US: Access Key (If not provided, credentials are obtained from the running environment.)
         zh_Hans: Access Key
       type: secret-input
       placeholder:

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

@@ -8,6 +8,8 @@
 - anthropic.claude-3-haiku-v1:0
 - cohere.command-light-text-v14
 - cohere.command-text-v14
+- cohere.command-r-plus-v1.0
+- cohere.command-r-v1.0
 - meta.llama3-8b-instruct-v1:0
 - meta.llama3-70b-instruct-v1:0
 - meta.llama2-13b-chat-v1

api/core/model_runtime/model_providers/bedrock/llm/cohere.command-r-plus-v1.0.yaml

@@ -0,0 +1,45 @@
+model: cohere.command-r-plus-v1:0
+label:
+  en_US: Command R+
+model_type: llm
+features:
+  #- multi-tool-call
+  - agent-thought
+  #- stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    max: 5.0
+  - name: p
+    use_template: top_p
+    default: 0.75
+    min: 0.01
+    max: 0.99
+  - name: 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
+    default: 0
+    min: 0
+    max: 500
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+  - name: max_tokens
+    use_template: max_tokens
+    default: 1024
+    max: 4096
+pricing:
+  input: '3'
+  output: '15'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/bedrock/llm/cohere.command-r-v1.0.yaml

@@ -0,0 +1,45 @@
+model: cohere.command-r-v1:0
+label:
+  en_US: Command R
+model_type: llm
+features:
+  #- multi-tool-call
+  - agent-thought
+  #- stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    max: 5.0
+  - name: p
+    use_template: top_p
+    default: 0.75
+    min: 0.01
+    max: 0.99
+  - name: 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
+    default: 0
+    min: 0
+    max: 500
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+  - name: max_tokens
+    use_template: max_tokens
+    default: 1024
+    max: 4096
+pricing:
+  input: '0.5'
+  output: '1.5'
+  unit: '0.000001'
+  currency: USD

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

@@ -25,6 +25,7 @@ from botocore.exceptions import (
     ServiceNotInRegionError,
     UnknownServiceError,
 )
+from cohere import ChatMessage
 
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from core.model_runtime.entities.message_entities import (
@@ -48,6 +49,7 @@ from core.model_runtime.errors.invoke import (
 )
 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.cohere.llm.llm import CohereLargeLanguageModel
 
 logger = logging.getLogger(__name__)
 
@@ -75,8 +77,86 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
         # invoke anthropic models via anthropic official SDK
         if "anthropic" in model:
             return self._generate_anthropic(model, credentials, prompt_messages, model_parameters, stop, stream, user)
+        # invoke Cohere models via boto3 client
+        if "cohere.command-r" in model:
+            return self._generate_cohere_chat(model, credentials, prompt_messages, model_parameters, stop, stream, user, tools)
         # invoke other models via boto3 client
         return self._generate(model, credentials, prompt_messages, model_parameters, stop, stream, user)
+    
+    def _generate_cohere_chat(
+            self, model: str, credentials: dict, prompt_messages: list[PromptMessage], model_parameters: dict,
+            stop: Optional[list[str]] = None, stream: bool = True, user: Optional[str] = None,
+            tools: Optional[list[PromptMessageTool]] = None,) -> Union[LLMResult, Generator]:
+        cohere_llm = CohereLargeLanguageModel()
+        client_config = Config(
+            region_name=credentials["aws_region"]
+        )
+
+        runtime_client = boto3.client(
+            service_name='bedrock-runtime',
+            config=client_config,
+            aws_access_key_id=credentials["aws_access_key_id"],
+            aws_secret_access_key=credentials["aws_secret_access_key"]
+        )
+
+        extra_model_kwargs = {}
+        if stop:
+            extra_model_kwargs['stop_sequences'] = stop
+
+        if tools:
+            tools = cohere_llm._convert_tools(tools)
+            model_parameters['tools'] = tools
+
+        message, chat_histories, tool_results \
+            = cohere_llm._convert_prompt_messages_to_message_and_chat_histories(prompt_messages)
+
+        if tool_results:
+            model_parameters['tool_results'] = tool_results
+
+        payload = {
+            **model_parameters,
+            "message": message,
+            "chat_history": chat_histories,
+        }
+
+        # need workaround for ai21 models which doesn't support streaming
+        if stream:
+            invoke = runtime_client.invoke_model_with_response_stream
+        else:
+            invoke = runtime_client.invoke_model
+
+        def serialize(obj):
+            if isinstance(obj, ChatMessage):
+                return obj.__dict__
+            raise TypeError(f"Type {type(obj)} not serializable")
+
+        try:
+            body_jsonstr=json.dumps(payload, default=serialize)
+            response = invoke(
+                modelId=model,
+                contentType="application/json",
+                accept="*/*",
+                body=body_jsonstr
+            )
+        except ClientError as ex:
+            error_code = ex.response['Error']['Code']
+            full_error_msg = f"{error_code}: {ex.response['Error']['Message']}"
+            raise self._map_client_to_invoke_error(error_code, full_error_msg)
+
+        except (EndpointConnectionError, NoRegionError, ServiceNotInRegionError) as ex:
+            raise InvokeConnectionError(str(ex))
+
+        except UnknownServiceError as ex:
+            raise InvokeServerUnavailableError(str(ex))
+
+        except Exception as ex:
+            raise InvokeError(str(ex))
+
+        if stream:
+            return self._handle_generate_stream_response(model, credentials, response, prompt_messages)
+
+        return self._handle_generate_response(model, credentials, response, prompt_messages)
+
 
     def _generate_anthropic(self, model: str, credentials: dict, prompt_messages: list[PromptMessage], model_parameters: dict,
                 stop: Optional[list[str]] = None, stream: bool = True, user: Optional[str] = None) -> Union[LLMResult, Generator]:

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

@@ -49,8 +49,8 @@ class BedrockTextEmbeddingModel(TextEmbeddingModel):
         bedrock_runtime = boto3.client(
             service_name='bedrock-runtime',
             config=client_config,
-            aws_access_key_id=credentials["aws_access_key_id"],
-            aws_secret_access_key=credentials["aws_secret_access_key"]
+            aws_access_key_id=credentials.get("aws_access_key_id", None),
+            aws_secret_access_key=credentials.get("aws_secret_access_key", None)
         )
 
         embeddings = []

api/core/model_runtime/model_providers/deepseek/llm/deepseek-chat.yaml

@@ -23,7 +23,7 @@ parameter_rules:
     type: int
     default: 4096
     min: 1
-    max: 32000
+    max: 4096
     help:
       zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.

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

@@ -7,7 +7,7 @@ features:
   - agent-thought
 model_properties:
   mode: chat
-  context_size: 16000
+  context_size: 32000
 parameter_rules:
   - name: temperature
     use_template: temperature
@@ -22,5 +22,5 @@ parameter_rules:
   - name: max_tokens
     use_template: max_tokens
     min: 1
-    max: 32000
+    max: 4096
     default: 1024

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

@@ -73,7 +73,7 @@ class LocalAILanguageModel(LargeLanguageModel):
 
         def tokens(text: str):
             """
-                We cloud not determine which tokenizer to use, cause the model is customized.
+                We could not determine which tokenizer to use, cause the model is customized.
                 So we use gpt2 tokenizer to calculate the num tokens for convenience.
             """
             return self._get_num_tokens_by_gpt2(text)

api/core/model_runtime/model_providers/model_provider_factory.py

@@ -201,10 +201,15 @@ class ModelProviderFactory:
         model_providers_path = os.path.dirname(current_path)
 
         # get all folders path under model_providers_path that do not start with __
+        whitelist = [
+            "baichuan", "chatglm", "deepseek", "hunyuan", "minimax", "moonshot",
+            "tongyi",
+            "wenxin", "yi", "zhipuai"
+        ]
         model_provider_dir_paths = [
             os.path.join(model_providers_path, model_provider_dir)
             for model_provider_dir in os.listdir(model_providers_path)
-            if not model_provider_dir.startswith('__')
+            if model_provider_dir in whitelist
                and os.path.isdir(os.path.join(model_providers_path, model_provider_dir))
         ]
 

api/core/model_runtime/model_providers/vertex_ai/llm/gemini-1.0-pro-vision.yaml

@@ -3,9 +3,8 @@ label:
   en_US: Gemini 1.0 Pro Vision
 model_type: llm
 features:
+  - agent-thought
   - vision
-  - tool-call
-  - stream-tool-call
 model_properties:
   mode: chat
   context_size: 16384

api/core/model_runtime/model_providers/vertex_ai/llm/gemini-1.0-pro.yaml

@@ -4,8 +4,6 @@ label:
 model_type: llm
 features:
   - agent-thought
-  - tool-call
-  - stream-tool-call
 model_properties:
   mode: chat
   context_size: 32760

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

@@ -1,11 +1,10 @@
-model: gemini-1.5-flash-preview-0514
+model: gemini-1.5-flash-001
 label:
   en_US: Gemini 1.5 Flash
 model_type: llm
 features:
+  - agent-thought
   - vision
-  - tool-call
-  - stream-tool-call
 model_properties:
   mode: chat
   context_size: 1048576

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

@@ -1,12 +1,10 @@
-model: gemini-1.5-pro-preview-0514
+model: gemini-1.5-pro-001
 label:
   en_US: Gemini 1.5 Pro
 model_type: llm
 features:
   - agent-thought
   - vision
-  - tool-call
-  - stream-tool-call
 model_properties:
   mode: chat
   context_size: 1048576

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

@@ -99,7 +99,7 @@ class VertexAiLargeLanguageModel(LargeLanguageModel):
             credentials.refresh(request)
             token = credentials.token
 
-        # Vertex AI Anthropic Claude3 Opus model avaiable in us-east5 region, Sonnet and Haiku avaiable in us-central1 region
+        # Vertex AI Anthropic Claude3 Opus model available in us-east5 region, Sonnet and Haiku available in us-central1 region
         if 'opus' in model:
             location = 'us-east5'
         else:

api/core/rag/datasource/vdb/weaviate/weaviate_vector.py

@@ -174,10 +174,15 @@ class WeaviateVector(BaseVector):
         schema = self._default_schema(self._collection_name)
         if self._client.schema.contains(schema):
             for uuid in ids:
-                self._client.data_object.delete(
-                    class_name=self._collection_name,
-                    uuid=uuid,
-                )
+                try:
+                    self._client.data_object.delete(
+                        class_name=self._collection_name,
+                        uuid=uuid,
+                    )
+                except weaviate.UnexpectedStatusCodeException as e:
+                    # tolerate not found error
+                    if e.status_code != 404:
+                        raise e
 
     def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]:
         """Look up similar documents by embedding vector in Weaviate."""

api/core/tools/entities/tool_entities.py

@@ -116,10 +116,10 @@ class ToolParameterOption(BaseModel):
     value: str = Field(..., description="The value of the option")
     label: I18nObject = Field(..., description="The label of the option")
 
-    @classmethod
     @field_validator('value', mode='before')
+    @classmethod
     def transform_id_to_str(cls, value) -> str:
-        if isinstance(value, bool):
+        if not isinstance(value, str):
             return str(value)
         else:
             return value

api/core/tools/provider/builtin/_positions.py

@@ -17,4 +17,7 @@ class BuiltinToolProviderSort:
 
         sorted_providers = sort_by_position_map(cls._position, providers, name_func)
 
-        return sorted_providers
+        blacklist = ['duckduckgo', 'brave', 'dalle', 'github', 'google', 'jina', 'slack', 'stablediffusion', 'youtube']
+        filtered_providers = [provider for provider in sorted_providers if provider.name not in blacklist]
+        return filtered_providers
+

api/core/tools/provider/builtin/azuredalle/tools/dalle3.py

@@ -1,3 +1,4 @@
+import random
 from base64 import b64decode
 from typing import Any, Union
 

api/core/tools/provider/builtin/duckduckgo/tools/ddgo_search.yaml

@@ -54,7 +54,6 @@ parameters:
     form: form
   - name: require_summary
     type: boolean
-    required: true
     default: false
     label:
       en_US: Require Summary

api/core/tools/provider/builtin/novitaai/novitaai.py

@@ -0,0 +1,30 @@
+from typing import Any
+
+from core.tools.errors import ToolProviderCredentialValidationError
+from core.tools.provider.builtin.novitaai.tools.novitaai_txt2img import NovitaAiTxt2ImgTool
+from core.tools.provider.builtin_tool_provider import BuiltinToolProviderController
+
+
+class NovitaAIProvider(BuiltinToolProviderController):
+    def _validate_credentials(self, credentials: dict[str, Any]) -> None:
+        try:
+            result = NovitaAiTxt2ImgTool().fork_tool_runtime(
+                runtime={
+                    "credentials": credentials,
+                }
+            ).invoke(
+                user_id='',
+                tool_parameters={
+                    'model_name': 'cinenautXLATRUE_cinenautV10_392434.safetensors',
+                    'prompt': 'a futuristic city with flying cars',
+                    'negative_prompt': '',
+                    'width': 128,
+                    'height': 128,
+                    'image_num': 1,
+                    'guidance_scale': 7.5,
+                    'seed': -1,
+                    'steps': 1,
+                },
+            )
+        except Exception as e:
+            raise ToolProviderCredentialValidationError(str(e))

api/core/tools/provider/builtin/novitaai/novitaai.yaml

@@ -0,0 +1,32 @@
+identity:
+  author: Xiao Ley
+  name: novitaai
+  label:
+    en_US: Novita AI
+    zh_Hans: Novita AI
+    pt_BR: Novita AI
+  description:
+    en_US: Innovative AI for Image Generation
+    zh_Hans: 用于图像生成的创新人工智能。
+    pt_BR: Innovative AI for Image Generation
+  icon: icon.ico
+  tags:
+    - image
+    - productivity
+credentials_for_provider:
+  api_key:
+    type: secret-input
+    required: true
+    label:
+      en_US: API Key
+      zh_Hans: API 密钥
+      pt_BR: Chave API
+    placeholder:
+      en_US: Please enter your Novita AI API key
+      zh_Hans: 请输入你的 Novita AI API 密钥
+      pt_BR: Por favor, insira sua chave de API do Novita AI
+    help:
+      en_US: Get your Novita AI API key from Novita AI
+      zh_Hans: 从 Novita AI 获取您的 Novita AI API 密钥
+      pt_BR: Obtenha sua chave de API do Novita AI na Novita AI
+    url: https://novita.ai

api/core/tools/provider/builtin/novitaai/tools/novitaai_createtile.py

@@ -0,0 +1,51 @@
+from base64 import b64decode
+from copy import deepcopy
+from typing import Any, Union
+
+from novita_client import (
+    NovitaClient,
+)
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.errors import ToolProviderCredentialValidationError
+from core.tools.tool.builtin_tool import BuiltinTool
+
+
+class NovitaAiCreateTileTool(BuiltinTool):
+    def _invoke(self,
+                user_id: str,
+                tool_parameters: dict[str, Any],
+                ) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
+        """
+            invoke tools
+        """
+        if 'api_key' not in self.runtime.credentials or not self.runtime.credentials.get('api_key'):
+            raise ToolProviderCredentialValidationError("Novita AI API Key is required.")
+
+        api_key = self.runtime.credentials.get('api_key')
+
+        client = NovitaClient(api_key=api_key)
+        param = self._process_parameters(tool_parameters)
+        client_result = client.create_tile(**param)
+
+        results = []
+        results.append(
+            self.create_blob_message(blob=b64decode(client_result.image_file),
+                                     meta={'mime_type': f'image/{client_result.image_type}'},
+                                     save_as=self.VARIABLE_KEY.IMAGE.value)
+        )
+
+        return results
+
+    def _process_parameters(self, parameters: dict[str, Any]) -> dict[str, Any]:
+        """
+            process parameters
+        """
+        res_parameters = deepcopy(parameters)
+
+        # delete none and empty
+        keys_to_delete = [k for k, v in res_parameters.items() if v is None or v == '']
+        for k in keys_to_delete:
+            del res_parameters[k]
+
+        return res_parameters

api/core/tools/provider/builtin/novitaai/tools/novitaai_createtile.yaml

@@ -0,0 +1,80 @@
+identity:
+  name: novitaai_createtile
+  author: Xiao Ley
+  label:
+    en_US: Novita AI Create Tile
+    zh_Hans: Novita AI 创建平铺图案
+description:
+  human:
+    en_US: This feature produces images designed for seamless tiling, ideal for creating continuous patterns in fabrics, wallpapers, and various textures.
+    zh_Hans: 该功能生成设计用于无缝平铺的图像，非常适合用于制作连续图案的织物、壁纸和各种纹理。
+  llm: A tool for create images designed for seamless tiling, ideal for creating continuous patterns in fabrics, wallpapers, and various textures.
+parameters:
+  - name: prompt
+    type: string
+    required: true
+    label:
+      en_US: prompt
+      zh_Hans: 提示
+    human_description:
+      en_US: Positive prompt word of the created tile, divided by `,`, Range [1, 512]. Only English input is allowed.
+      zh_Hans: 生成平铺图案的正向提示，用 `,` 分隔，范围 [1, 512]。仅允许输入英文。
+    llm_description: Image prompt of Novita AI, you should describe the image you want to generate as a list of words as possible as detailed, divided by `,`, Range [1, 512]. Only English input is allowed.
+    form: llm
+  - name: negative_prompt
+    type: string
+    required: false
+    label:
+      en_US: negative prompt
+      zh_Hans: 负向提示
+    human_description:
+      en_US: Negtive prompt word of the created tile, divided by `,`, Range [1, 512]. Only English input is allowed.
+      zh_Hans: 生成平铺图案的负向提示，用 `,` 分隔，范围 [1, 512]。仅允许输入英文。
+    llm_description: Image negative prompt of Novita AI, divided by `,`, Range [1, 512]. Only English input is allowed.
+    form: llm
+  - name: width
+    type: number
+    default: 256
+    min: 128
+    max: 1024
+    required: true
+    label:
+      en_US: width
+      zh_Hans: 宽
+    human_description:
+      en_US: Image width, Range [128, 1024].
+      zh_Hans: 图像宽度，范围 [128, 1024]
+    form: form
+  - name: height
+    type: number
+    default: 256
+    min: 128
+    max: 1024
+    required: true
+    label:
+      en_US: height
+      zh_Hans: 高
+    human_description:
+      en_US: Image height, Range [128, 1024].
+      zh_Hans: 图像高度，范围 [128, 1024]
+    form: form
+  - name: response_image_type
+    type: select
+    default: jpeg
+    required: false
+    label:
+      en_US: response image type
+      zh_Hans: 响应图像类型
+    human_description:
+      en_US: Response image type, png or jpeg
+      zh_Hans: 响应图像类型，png 或 jpeg
+    form: form
+    options:
+      - value: jpeg
+        label:
+          en_US: jpeg
+          zh_Hans: jpeg
+      - value: png
+        label:
+          en_US: png
+          zh_Hans: png

api/core/tools/provider/builtin/novitaai/tools/novitaai_modelquery.py

@@ -0,0 +1,137 @@
+import json
+from copy import deepcopy
+from typing import Any, Union
+
+from pandas import DataFrame
+from yarl import URL
+
+from core.helper import ssrf_proxy
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.errors import ToolProviderCredentialValidationError
+from core.tools.tool.builtin_tool import BuiltinTool
+
+
+class NovitaAiModelQueryTool(BuiltinTool):
+    _model_query_endpoint = 'https://api.novita.ai/v3/model'
+
+    def _invoke(self,
+                user_id: str,
+                tool_parameters: dict[str, Any],
+                ) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
+        """
+            invoke tools
+        """
+        if 'api_key' not in self.runtime.credentials or not self.runtime.credentials.get('api_key'):
+            raise ToolProviderCredentialValidationError("Novita AI API Key is required.")
+
+        api_key = self.runtime.credentials.get('api_key')
+        headers = {
+            'Content-Type': 'application/json',
+            'Authorization': "Bearer " + api_key
+        }
+        params = self._process_parameters(tool_parameters)
+        result_type = params.get('result_type')
+        del params['result_type']
+
+        models_data = self._query_models(
+            models_data=[],
+            headers=headers,
+            params=params,
+            recursive=False if result_type == 'first sd_name' or result_type == 'first name sd_name pair' else True
+        )
+
+        result_str = ''
+        if result_type == 'first sd_name':
+            result_str = models_data[0]['sd_name_in_api']
+        elif result_type == 'first name sd_name pair':
+            result_str = json.dumps({'name': models_data[0]['name'], 'sd_name': models_data[0]['sd_name_in_api']})
+        elif result_type == 'sd_name array':
+            sd_name_array = [model['sd_name_in_api'] for model in models_data]
+            result_str = json.dumps(sd_name_array)
+        elif result_type == 'name array':
+            name_array = [model['name'] for model in models_data]
+            result_str = json.dumps(name_array)
+        elif result_type == 'name sd_name pair array':
+            name_sd_name_pair_array = [{'name': model['name'], 'sd_name': model['sd_name_in_api']} for model in models_data]
+            result_str = json.dumps(name_sd_name_pair_array)
+        elif result_type == 'whole info array':
+            result_str = json.dumps(models_data)
+        else:
+            raise NotImplementedError
+
+        return self.create_text_message(result_str)
+
+    def _query_models(self, models_data: list, headers: dict[str, Any],
+                      params: dict[str, Any], pagination_cursor: str = '', recursive: bool = True) -> list:
+        """
+            query models
+        """
+        inside_params = deepcopy(params)
+
+        if pagination_cursor != '':
+            inside_params['pagination.cursor'] = pagination_cursor
+
+        response = ssrf_proxy.get(
+            url=str(URL(self._model_query_endpoint)),
+            headers=headers,
+            params=params,
+            timeout=(10, 60)
+        )
+
+        res_data = response.json()
+
+        models_data.extend(res_data['models'])
+
+        res_data_len = len(res_data['models'])
+        if res_data_len == 0 or res_data_len < int(params['pagination.limit']) or recursive is False:
+            # deduplicate
+            df = DataFrame.from_dict(models_data)
+            df_unique = df.drop_duplicates(subset=['id'])
+            models_data = df_unique.to_dict('records')
+            return models_data
+
+        return self._query_models(
+            models_data=models_data,
+            headers=headers,
+            params=inside_params,
+            pagination_cursor=res_data['pagination']['next_cursor']
+        )
+
+    def _process_parameters(self, parameters: dict[str, Any]) -> dict[str, Any]:
+        """
+            process parameters
+        """
+        process_parameters = deepcopy(parameters)
+        res_parameters = {}
+
+        # delete none or empty
+        keys_to_delete = [k for k, v in process_parameters.items() if v is None or v == '']
+        for k in keys_to_delete:
+            del process_parameters[k]
+
+        if 'query' in process_parameters and process_parameters.get('query') != 'unspecified':
+            res_parameters['filter.query'] = process_parameters['query']
+
+        if 'visibility' in process_parameters and process_parameters.get('visibility') != 'unspecified':
+            res_parameters['filter.visibility'] = process_parameters['visibility']
+
+        if 'source' in process_parameters and process_parameters.get('source') != 'unspecified':
+            res_parameters['filter.source'] = process_parameters['source']
+
+        if 'type' in process_parameters and process_parameters.get('type') != 'unspecified':
+            res_parameters['filter.types'] = process_parameters['type']
+
+        if 'is_sdxl' in process_parameters:
+            if process_parameters['is_sdxl'] == 'true':
+                res_parameters['filter.is_sdxl'] = True
+            elif process_parameters['is_sdxl'] == 'false':
+                res_parameters['filter.is_sdxl'] = False
+
+        res_parameters['result_type'] = process_parameters.get('result_type', 'first sd_name')
+
+        res_parameters['pagination.limit'] = 1 \
+            if res_parameters.get('result_type') == 'first sd_name' \
+            or res_parameters.get('result_type') == 'first name sd_name pair'\
+            else 100
+
+        return res_parameters

api/core/tools/provider/builtin/novitaai/tools/novitaai_modelquery.yaml

@@ -0,0 +1,174 @@
+identity:
+  name: novitaai_modelquery
+  author: Xiao Ley
+  label:
+    en_US: Novita AI Model Query
+    zh_Hans: Novita AI 模型查询
+description:
+  human:
+    en_US: Retrieve information on both public and private models. It allows users to access details such as model specifications, status, and usage guidelines, ensuring comprehensive insight into the available modeling resources.
+    zh_Hans: 检索公开和私有模型信息。它允许用户访问模型规范、状态和使用指南等详细信息，确保了解可用的建模资源。
+  llm: A tool for retrieve information on both public and private Novita AI models.
+parameters:
+  - name: query
+    type: string
+    required: false
+    label:
+      en_US: query
+      zh_Hans: 查询
+    human_description:
+      en_US: Seaching the content of sd_name, name, tags.
+      zh_Hans: 搜索 sd_name、name、tags 中的内容
+    form: form
+  - name: result_type
+    type: select
+    default: "first sd_name"
+    required: true
+    label:
+      en_US: result format
+      zh_Hans: 结果格式
+    human_description:
+      en_US: The format of result
+      zh_Hans: 请求结果的格式
+    form: form
+    options:
+      - value: "first sd_name"
+        label:
+          en_US: "first sd_name"
+          zh_Hans: "第一个 sd_name"
+      - value: "first name sd_name pair"
+        label:
+          en_US: "first name and sd_name pair: {name, sd_name}"
+          zh_Hans: "第一个 name sd_name 组合：{name, sd_name}"
+      - value: "sd_name array"
+        label:
+          en_US: "sd_name array: [sd_name]"
+          zh_Hans: "sd_name 数组：[sd_name]"
+      - value: "name array"
+        label:
+          en_US: "name array: [name]"
+          zh_Hans: "name 数组：[name]"
+      - value: "name sd_name pair array"
+        label:
+          en_US: "name and sd_name pair array: [{name, sd_name}]"
+          zh_Hans: "name sd_name 组合数组：[{name, sd_name}]"
+      - value: "whole info array"
+        label:
+          en_US: whole info array
+          zh_Hans: 完整信息数组
+  - name: visibility
+    type: select
+    default: unspecified
+    required: false
+    label:
+      en_US: visibility
+      zh_Hans: 可见性
+    human_description:
+      en_US: Whether the model is public or private
+      zh_Hans: 模型是否公开或私有
+    form: form
+    options:
+      - value: unspecified
+        label:
+          en_US: Unspecified
+          zh_Hans: 未指定
+      - value: public
+        label:
+          en_US: Public
+          zh_Hans: 公开
+      - value: private
+        label:
+          en_US: Private
+          zh_Hans: 私有
+  - name: source
+    type: select
+    default: unspecified
+    required: false
+    label:
+      en_US: source
+      zh_Hans: 来源
+    human_description:
+      en_US: Source of the model
+      zh_Hans: 模型来源
+    form: form
+    options:
+      - value: unspecified
+        label:
+          en_US: Unspecified
+          zh_Hans: 未指定
+      - value: civitai
+        label:
+          en_US: Civitai
+          zh_Hans: Civitai
+      - value: training
+        label:
+          en_US: Training
+          zh_Hans: 训练
+      - value: uploading
+        label:
+          en_US: Uploading
+          zh_Hans: 上传
+  - name: type
+    type: select
+    default: unspecified
+    required: false
+    label:
+      en_US: type
+      zh_Hans: 类型
+    human_description:
+      en_US: Specifies the type of models to include in the query.
+      zh_Hans: 指定要查询的模型类型
+    form: form
+    options:
+      - value: unspecified
+        label:
+          en_US: Unspecified
+          zh_Hans: 未指定
+      - value: checkpoint
+        label:
+          en_US: Checkpoint
+          zh_Hans: Checkpoint
+      - value: lora
+        label:
+          en_US: LoRA
+          zh_Hans: LoRA
+      - value: vae
+        label:
+          en_US: VAE
+          zh_Hans: VAE
+      - value: controlnet
+        label:
+          en_US: ControlNet
+          zh_Hans: ControlNet
+      - value: upscaler
+        label:
+          en_US: Upscaler
+          zh_Hans: Upscaler
+      - value: textualinversion
+        label:
+          en_US: Textual inversion
+          zh_Hans: Textual Inversion
+  - name: is_sdxl
+    type: select
+    default: unspecified
+    required: false
+    label:
+      en_US: is sdxl
+      zh_Hans: 是否是 SDXL
+    human_description:
+      en_US: Whether sdxl model or not. Setting this parameter to `true` includes only sdxl models in the query results, which are typically large-scale, high-performance models designed for extensive data processing tasks. Conversely, setting it to `false` excludes these models from the results. If left unspecified, the filter will not discriminate based on the sdxl classification, including all model types in the search results.
+      zh_Hans: 是否是 SDXL 模型。设置此参数为 `是`，只查询 SDXL 模型，并包含大规模，高性能的模型。相反，设置为 `否`，将排除这些模型。如果未指定，将不会根据 SDXL 分类进行区分，包括查询结果中的所有模型类型。
+    form: form
+    options:
+      - value: unspecified
+        label:
+          en_US: Unspecified
+          zh_Hans: 未指定
+      - value: "true"
+        label:
+          en_US: "True"
+          zh_Hans: 是
+      - value: "false"
+        label:
+          en_US: "False"
+          zh_Hans: 否

api/core/tools/provider/builtin/novitaai/tools/novitaai_txt2img.py

@@ -0,0 +1,137 @@
+from base64 import b64decode
+from copy import deepcopy
+from typing import Any, Union
+
+from novita_client import (
+    NovitaClient,
+    Txt2ImgV3Embedding,
+    Txt2ImgV3HiresFix,
+    Txt2ImgV3LoRA,
+    Txt2ImgV3Refiner,
+    V3TaskImage,
+)
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.errors import ToolProviderCredentialValidationError
+from core.tools.tool.builtin_tool import BuiltinTool
+
+
+class NovitaAiTxt2ImgTool(BuiltinTool):
+    def _invoke(self,
+                user_id: str,
+                tool_parameters: dict[str, Any],
+                ) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
+        """
+            invoke tools
+        """
+        if 'api_key' not in self.runtime.credentials or not self.runtime.credentials.get('api_key'):
+            raise ToolProviderCredentialValidationError("Novita AI API Key is required.")
+
+        api_key = self.runtime.credentials.get('api_key')
+
+        client = NovitaClient(api_key=api_key)
+        param = self._process_parameters(tool_parameters)
+        client_result = client.txt2img_v3(**param)
+
+        results = []
+        for image_encoded, image in zip(client_result.images_encoded, client_result.images):
+            if self._is_hit_nsfw_detection(image, 0.8):
+                results = self.create_text_message(text='NSFW detected!')
+                break
+
+            results.append(
+                self.create_blob_message(blob=b64decode(image_encoded),
+                                         meta={'mime_type': f'image/{image.image_type}'},
+                                         save_as=self.VARIABLE_KEY.IMAGE.value)
+            )
+
+        return results
+
+    def _process_parameters(self, parameters: dict[str, Any]) -> dict[str, Any]:
+        """
+            process parameters
+        """
+        res_parameters = deepcopy(parameters)
+
+        # delete none and empty
+        keys_to_delete = [k for k, v in res_parameters.items() if v is None or v == '']
+        for k in keys_to_delete:
+            del res_parameters[k]
+
+        if 'clip_skip' in res_parameters and res_parameters.get('clip_skip') == 0:
+            del res_parameters['clip_skip']
+
+        if 'refiner_switch_at' in res_parameters and res_parameters.get('refiner_switch_at') == 0:
+            del res_parameters['refiner_switch_at']
+
+        if 'enabled_enterprise_plan' in res_parameters:
+            res_parameters['enterprise_plan'] = {'enabled': res_parameters['enabled_enterprise_plan']}
+            del res_parameters['enabled_enterprise_plan']
+
+        if 'nsfw_detection_level' in res_parameters:
+            res_parameters['nsfw_detection_level'] = int(res_parameters['nsfw_detection_level'])
+
+        # process loras
+        if 'loras' in res_parameters:
+            loras_ori_list = res_parameters.get('loras').strip().split(';')
+            locals_list = []
+            for lora_str in loras_ori_list:
+                lora_info = lora_str.strip().split(',')
+                lora = Txt2ImgV3LoRA(
+                    model_name=lora_info[0].strip(),
+                    strength=float(lora_info[1]),
+                )
+                locals_list.append(lora)
+
+            res_parameters['loras'] = locals_list
+
+        # process embeddings
+        if 'embeddings' in res_parameters:
+            embeddings_ori_list = res_parameters.get('embeddings').strip().split(';')
+            locals_list = []
+            for embedding_str in embeddings_ori_list:
+                embedding = Txt2ImgV3Embedding(
+                    model_name=embedding_str.strip()
+                )
+                locals_list.append(embedding)
+
+            res_parameters['embeddings'] = locals_list
+
+        # process hires_fix
+        if 'hires_fix' in res_parameters:
+            hires_fix_ori = res_parameters.get('hires_fix')
+            hires_fix_info = hires_fix_ori.strip().split(',')
+            if 'upscaler' in hires_fix_info:
+                hires_fix = Txt2ImgV3HiresFix(
+                    target_width=int(hires_fix_info[0]),
+                    target_height=int(hires_fix_info[1]),
+                    strength=float(hires_fix_info[2]),
+                    upscaler=hires_fix_info[3].strip()
+                )
+            else:
+                hires_fix = Txt2ImgV3HiresFix(
+                    target_width=int(hires_fix_info[0]),
+                    target_height=int(hires_fix_info[1]),
+                    strength=float(hires_fix_info[2])
+                )
+
+            res_parameters['hires_fix'] = hires_fix
+
+            if 'refiner_switch_at' in res_parameters:
+                refiner = Txt2ImgV3Refiner(
+                    switch_at=float(res_parameters.get('refiner_switch_at'))
+                )
+                del res_parameters['refiner_switch_at']
+                res_parameters['refiner'] = refiner
+
+        return res_parameters
+
+    def _is_hit_nsfw_detection(self, image: V3TaskImage, confidence_threshold: float) -> bool:
+        """
+            is hit nsfw
+        """
+        if image.nsfw_detection_result is None:
+            return False
+        if image.nsfw_detection_result.valid and image.nsfw_detection_result.confidence >= confidence_threshold:
+            return True
+        return False

api/core/tools/provider/builtin/novitaai/tools/novitaai_txt2img.yaml

@@ -0,0 +1,341 @@
+identity:
+  name: novitaai_txt2img
+  author: Xiao Ley
+  label:
+    en_US: Novita AI Text to Image
+    zh_Hans: Novita AI 文字转图像
+description:
+  human:
+    en_US: Generate images from text prompts using Stable Diffusion models
+    zh_Hans: 通过 Stable Diffusion 模型根据文字提示生成图像
+  llm: A tool for generate images from English text prompts.
+parameters:
+  - name: model_name
+    type: string
+    required: true
+    label:
+      en_US: model name
+      zh_Hans: 模块名字
+    human_description:
+      en_US: Specify the name of the model checkpoint. You can use the "Novita AI Model Query" tool to query the corresponding "sd_name" value (type select "Checkpoint").
+      zh_Hans: 指定 Model Checkpoint 名称。可通过“Novita AI 模型请求”工具查询对应的“sd_name”值（类型选择“Checkpoint”）。
+    form: form
+  - name: prompt
+    type: string
+    required: true
+    label:
+      en_US: prompt
+      zh_Hans: 提示
+    human_description:
+      en_US: Text input required to guide the image generation, divided by `,`, Range [1, 1024]. Only English input is allowed.
+      zh_Hans: 生成图像的正向提示，用 `,` 分隔，范围 [1, 1024]。仅允许输入英文。
+    llm_description: Image prompt of Novita AI, you should describe the image you want to generate as a list of words as possible as detailed, divided by `,`, Range [1, 1024]. Only English input is allowed.
+    form: llm
+  - name: negative_prompt
+    type: string
+    required: false
+    label:
+      en_US: negative prompt
+      zh_Hans: 负向提示
+    human_description:
+      en_US: Text input that will not guide the image generation, divided by `,`, Range [1, 1024]. Only English input is allowed.
+      zh_Hans: 生成图像的负向提示，用 `,` 分隔，范围 [1, 1024]。仅允许输入英文。
+    llm_description: Image negative prompt of Novita AI, divided by `,`, Range [1, 1024]. Only English input is allowed.
+    form: llm
+  - name: width
+    type: number
+    default: 512
+    min: 128
+    max: 2048
+    required: true
+    label:
+      en_US: width
+      zh_Hans: 宽
+    human_description:
+      en_US: Image width, Range [128, 2048].
+      zh_Hans: 图像宽度，范围 [128, 2048]
+    form: form
+  - name: height
+    type: number
+    default: 512
+    min: 128
+    max: 2048
+    required: true
+    label:
+      en_US: height
+      zh_Hans: 高
+    human_description:
+      en_US: Image height, Range [128, 2048].
+      zh_Hans: 图像高度，范围 [128, 2048]
+    form: form
+  - name: image_num
+    type: number
+    default: 1
+    min: 1
+    max: 8
+    required: true
+    label:
+      en_US: image num
+      zh_Hans: 图片数
+    human_description:
+      en_US: Image num, Range [1, 8].
+      zh_Hans: 图片数，范围 [1, 8]
+    form: form
+  - name: steps
+    type: number
+    default: 20
+    min: 1
+    max: 100
+    required: true
+    label:
+      en_US: steps
+      zh_Hans: 步数
+    human_description:
+      en_US: The number of denoising steps. More steps usually can produce higher quality images, but take more time to generate, Range [1, 100].
+      zh_Hans: 生成步数。更多步数可能会产生更好的图像，但生成时间更长，范围 [1, 100]
+    form: form
+  - name: seed
+    type: number
+    default: -1
+    required: true
+    label:
+      en_US: seed
+      zh_Hans: 种子
+    human_description:
+      en_US: A seed is a number from which Stable Diffusion generates noise, which, makes generation deterministic. Using the same seed and set of parameters will produce identical image each time, minimum -1.
+      zh_Hans: 种子是 Stable Diffusion 生成噪声的数字，它使生成具有确定性。使用相同的种子和参数设置将生成每次生成相同的图像，最小值 -1。
+    form: form
+  - name: clip_skip
+    type: number
+    min: 1
+    max: 12
+    required: false
+    label:
+      en_US: clip skip
+      zh_Hans: 层跳过数
+    human_description:
+      en_US: This parameter indicates the number of layers to stop from the bottom during optimization, so clip_skip on 2 would mean, that in SD1.x model where the CLIP has 12 layers, you would stop at 10th layer, Range [1, 12], get reference at https://novita.ai/get-started/Misc.html#what-s-clip-skip.
+      zh_Hans: 此参数表示优化过程中从底部停止的层数，因此 clip_skip 的值为 2，表示在 SD1.x 模型中，CLIP 有 12 层，你将停止在 10 层，范围 [1, 12]，参考 https://novita.ai/get-started/Misc.html#what-s-clip-skip。
+    form: form
+  - name: guidance_scale
+    type: number
+    default: "7.5"
+    min: 1.0
+    max: 30.0
+    required: true
+    label:
+      en_US: guidance scale
+      zh_Hans: 提示词遵守程度
+    human_description:
+      en_US: This setting says how close the Stable Diffusion will listen to your prompt, higer guidance forces the model to better follow the prompt, but result in lower quality output.Range [1, 30].
+      zh_Hans: 此设置表明 Stable Diffusion 如何听从您的提示，较高的 guidance_scale 会强制模型更好跟随提示，但结果会更低质量输出。范围 [1.0, 30.0]。
+    form: form
+  - name: sampler_name
+    type: select
+    required: true
+    label:
+      en_US: sampler name
+      zh_Hans: 采样器名称
+    human_description:
+      en_US: This parameter determines the denoising algorithm employed during the sampling phase of Stable Diffusion. Get reference at https://novita.ai/get-started/Misc.htmll#what-is-samplers.
+      zh_Hans: 此参数决定了在稳定扩散采样阶段使用的去噪算法。参考 https://novita.ai/get-started/Misc.htmll#what-is-samplers。
+    form: form
+    options:
+      - value: "Euler a"
+        label:
+          en_US: Euler a
+          zh_Hans: Euler a
+      - value: "Euler"
+        label:
+          en_US: Euler
+          zh_Hans: Euler
+      - value: "LMS"
+        label:
+          en_US: LMS
+          zh_Hans: LMS
+      - value: "Heun"
+        label:
+          en_US: Heun
+          zh_Hans: Heun
+      - value: "DPM2"
+        label:
+          en_US: DPM2
+          zh_Hans: DPM2
+      - value: "DPM2 a"
+        label:
+          en_US: DPM2 a
+          zh_Hans: DPM2 a
+      - value: "DPM++ 2S a"
+        label:
+          en_US: DPM++ 2S a
+          zh_Hans: DPM++ 2S a
+      - value: "DPM++ 2M"
+        label:
+          en_US: DPM++ 2M
+          zh_Hans: DPM++ 2M
+      - value: "DPM++ SDE"
+        label:
+          en_US: DPM++ SDE
+          zh_Hans: DPM++ SDE
+      - value: "DPM fast"
+        label:
+          en_US: DPM fast
+          zh_Hans: DPM fast
+      - value: "DPM adaptive"
+        label:
+          en_US: DPM adaptive
+          zh_Hans: DPM adaptive
+      - value: "LMS Karras"
+        label:
+          en_US: LMS Karras
+          zh_Hans: LMS Karras
+      - value: "DPM2 Karras"
+        label:
+          en_US: DPM2 Karras
+          zh_Hans: DPM2 Karras
+      - value: "DPM2 a Karras"
+        label:
+          en_US: DPM2 a Karras
+          zh_Hans: DPM2 a Karras
+      - value: "DPM++ 2S a Karras"
+        label:
+          en_US: DPM++ 2S a Karras
+          zh_Hans: DPM++ 2S a Karras
+      - value: "DPM++ 2M Karras"
+        label:
+          en_US: DPM++ 2M Karras
+          zh_Hans: DPM++ 2M Karras
+      - value: "DPM++ SDE Karras"
+        label:
+          en_US: DPM++ SDE Karras
+          zh_Hans: DPM++ SDE Karras
+      - value: "DDIM"
+        label:
+          en_US: DDIM
+          zh_Hans: DDIM
+      - value: "PLMS"
+        label:
+          en_US: PLMS
+          zh_Hans: PLMS
+      - value: "UniPC"
+        label:
+          en_US: UniPC
+          zh_Hans: UniPC
+  - name: sd_vae
+    type: string
+    required: false
+    label:
+      en_US: sd vae
+      zh_Hans: sd vae
+    human_description:
+      en_US: VAE(Variational Autoencoder), get reference at https://novita.ai/get-started/Misc.html#what-s-variational-autoencoders-vae. You can use the "Novita AI Model Query" tool to query the corresponding "sd_name" value (type select "VAE").
+      zh_Hans: VAE（变分自编码器），参考 https://novita.ai/get-started/Misc.html#what-s-variational-autoencoders-vae。可通过“Novita AI 模型请求”工具查询对应的“sd_name”值（类型选择“VAE”）。
+    form: form
+  - name: loras
+    type: string
+    required: false
+    label:
+      en_US: loRAs
+      zh_Hans: loRAs
+    human_description:
+      en_US: LoRA models. Currenlty supports up to 5 LoRAs. You can use the "Novita AI Model Query" tool to query the corresponding "sd_name" value (type select "LoRA"). Input template is "<sd_name>,<strength [0-1.0]>;<sd_name>,<strength [0-1.0]>;...". Such as"Film Grain style_331903,0.5;DoggystylePOV_9600,0.5"
+      zh_Hans: LoRA 模型。目前仅支持 5 个 LoRA。可通过“Novita AI 模型请求”工具查询对应的“sd_name”值（类型选择“LoRA”）。输入模板：“<sd_name>,<strength [0-1.0]>;<sd_name>,<strength [0-1.0]>;...”，例如：“Film Grain style_331903,0.5;DoggystylePOV_9600,0.5”
+    form: form
+  - name: embeddings
+    type: string
+    required: false
+    label:
+      en_US: text embeddings
+      zh_Hans: 文本嵌入
+    human_description:
+      en_US: Textual Inversion is a training method for personalizing models by learning new text embeddings from a few example images, currenlty supports up to 5 embeddings. You can use the "Novita AI Model Query" tool to query the corresponding "sd_name" value (type select "Text Inversion"). Input template is "<sd_name>;<sd_name>;...". Such as "EasyNegativeV2_75525;AS-YoungerV2"
+      zh_Hans: 文本反转是一种通过从一些示例图像中学习新的文本嵌入来个性化模型的训练方法，目前仅支持 5 个嵌入。可通过“Novita AI 模型请求”工具查询对应的“sd_name”值（类型选择“Text Inversion”）。输入模板：“<sd_name>;<sd_name>;...”，例如：“EasyNegativeV2_75525;AS-YoungerV2”
+    form: form
+  - name: hires_fix
+    type: string
+    required: false
+    label:
+      en_US: hires fix
+      zh_Hans: 高分辨率修复
+    human_description:
+      en_US: Use high resolution image fix. Input template is "<target_width [128, 4096]>,<target_height [128, 4096]>,<strength [0, 1.0]>,<upscaler (optional, selec type, `RealESRGAN_x4plus_anime_6B`, `RealESRNet_x4plus` or `Latent`)>". Such as "1024,1024,0.8", "1024,1024,0.8,RealESRGAN_x4plus_anime_6B"
+      zh_Hans: 使用高分辨率修复。输入模板 “<target_width [128, 4096]>,<target_height [128, 4096]>,<strength [0, 1.0]>,<upscaler (可选, 选项类型, `RealESRGAN_x4plus_anime_6B`, `RealESRNet_x4plus` 或 `Latent`)>”。例如 “1024,1024,0.8”、“1024,1024,0.8,RealESRGAN_x4plus_anime_6B”
+    form: form
+  - name: refiner_switch_at
+    type: number
+    min: 0.0
+    max: 1.0
+    required: false
+    label:
+      en_US: refiner switch at
+      zh_Hans: 重采样参与时刻
+    human_description:
+      en_US: This parameter in the context of a refiner allows you to set the extent to which the refiner alters the output of a model. When set to 0, the refiner has no effect; at 1, it's fully active. Intermediate values like 0.5 provide a balanced effect, where the refiner is moderately engaged, enhancing or adjusting the output without dominating the original model's characteristics. This setting is particularly useful for fine-tuning the output to achieve a desired balance between refinement and the original generative features, Range [0, 1.0]. Is not all models support refiners!
+      zh_Hans: 此参数允许您设置重采样更改模型输出的程度。当设置为0时，重采样不起作用；1时，它处于完全活动状态。像0.5这样的中间值提供了一种平衡效果，其中重采样适度参与，增强或调整输出，而不会主导原始模型的特性。此设置对于微调输出特别有用，范围 [0, 1.0]。不是所有模型都支持重采样！
+    form: form
+  - name: response_image_type
+    type: select
+    default: jpeg
+    required: false
+    label:
+      en_US: response image type
+      zh_Hans: 响应图像类型
+    human_description:
+      en_US: Response image type, png or jpeg
+      zh_Hans: 响应图像类型，png 或 jpeg
+    form: form
+    options:
+      - value: jpeg
+        label:
+          en_US: jpeg
+          zh_Hans: jpeg
+      - value: png
+        label:
+          en_US: png
+          zh_Hans: png
+  - name: enabled_enterprise_plan
+    type: boolean
+    default: false
+    required: false
+    label:
+      en_US: enterprise plan enabled
+      zh_Hans: 企业版计划启用
+    human_description:
+      en_US: Enable enterprise plan
+      zh_Hans: 启用企业版计划
+    form: form
+  - name: enable_nsfw_detection
+    type: boolean
+    default: false
+    required: false
+    label:
+      en_US: enable nsfw detection
+      zh_Hans: 启用 NSFW 检测
+    human_description:
+      en_US: Enable nsfw detection
+      zh_Hans: 启用 NSFW 检测
+    form: form
+  - name: nsfw_detection_level
+    type: select
+    default: "2"
+    required: false
+    label:
+      en_US: nsfw detection level
+      zh_Hans: NSFW 检测级别
+    human_description:
+      en_US: Nsfw detection level, from low to high
+      zh_Hans: NSFW 检测级别，越高越严格
+    form: form
+    options:
+      - value: "0"
+        label:
+          en_US: low
+          zh_Hans: 低
+      - value: "1"
+        label:
+          en_US: middle
+          zh_Hans: 中
+      - value: "2"
+        label:
+          en_US: high
+          zh_Hans: 高

api/core/tools/provider/builtin/twilio/tools/send_message.py

@@ -32,8 +32,8 @@ class TwilioAPIWrapper(BaseModel):
         must be empty.
     """
 
-    @classmethod
     @field_validator('client', mode='before')
+    @classmethod
     def set_validator(cls, values: dict) -> dict:
         """Validate that api key and python package exists in environment."""
         try:

api/core/tools/provider/builtin/websearch/_assets/icon.svg

@@ -0,0 +1,23 @@
+<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
+	 width="100%" viewBox="0 0 176 323" enable-background="new 0 0 176 323" xml:space="preserve">
+<path fill="#F03F30" opacity="1.000000" stroke="none"
+	d="
+M41.044968,257.626282
+	C27.696184,236.155075 31.957315,212.441483 52.045750,197.344925
+	C79.002586,177.086716 106.149689,157.081665 133.645813,136.647858
+	C139.760117,144.272156 142.374191,152.876511 142.340073,162.386032
+	C142.284485,177.881165 135.226303,189.665787 122.998329,198.722351
+	C97.096687,217.906250 71.232124,237.140259 45.308189,256.293945
+	C44.162773,257.140198 42.580475,257.395203 41.044968,257.626282
+z"/>
+<path fill="#F03F30" opacity="1.000000" stroke="none"
+	d="
+M99.096405,138.076599
+	C79.500099,152.629852 60.200359,166.985321 40.905945,181.336838
+	C27.259842,163.327515 29.469128,137.268982 46.741867,123.517693
+	C67.654190,106.868828 89.408379,91.276695 110.817230,75.252617
+	C117.976021,69.894424 125.193146,64.614182 132.376923,59.303246
+	C147.358932,78.560143 142.926590,105.166771 122.208939,120.964401
+	C114.681282,126.704391 107.002701,132.246460 99.096405,138.076599
+z"/>
+</svg>

api/core/tools/provider/builtin/websearch/tools/get_markdown.py

@@ -0,0 +1,51 @@
+from typing import Any, Union
+
+import requests
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.tool.builtin_tool import BuiltinTool
+
+BASE_URL = "https://api.serply.io/v1/request"
+
+
+class SerplyApi:
+    """
+    SerplyAPI tool provider.
+    """
+
+    def __init__(self, api_key: str) -> None:
+        """Initialize SerplyAPI tool provider."""
+        self.serply_api_key = api_key
+
+    def run(self, url: str, **kwargs: Any) -> str:
+        """Run query through SerplyAPI and parse result."""
+
+        location = kwargs.get("location", "US")
+
+        headers = {
+            "X-API-KEY": self.serply_api_key,
+            "X-User-Agent": kwargs.get("device", "desktop"),
+            "X-Proxy-Location": location,
+            "User-Agent": "Dify",
+        }
+        data = {"url": url, "method": "GET", "response_type": "markdown"}
+        res = requests.post(url, headers=headers, json=data)
+        return res.text
+
+
+class GetMarkdownTool(BuiltinTool):
+    def _invoke(
+        self,
+        user_id: str,
+        tool_parameters: dict[str, Any],
+    ) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
+        """
+        Invoke the SerplyApi tool.
+        """
+        url = tool_parameters["url"]
+        location = tool_parameters.get("location", None)
+
+        api_key = self.runtime.credentials["serply_api_key"]
+        result = SerplyApi(api_key).run(url, location=location)
+
+        return self.create_text_message(text=result)

api/core/tools/provider/builtin/websearch/tools/get_markdown.yaml

@@ -0,0 +1,96 @@
+identity:
+  name: get_markdown
+  author: Dify
+  label:
+    en_US: Get Markdown API
+    zh_Hans: Get Markdown API
+description:
+  human:
+    en_US: A tool to perform convert a webpage to markdown to make it easier for LLMs to understand.
+    zh_Hans: 一个将网页转换为 Markdown 的工具，以便模型更容易理解
+  llm: A tool to perform convert a webpage to markdown to make it easier for LLMs to understand.
+parameters:
+  - name: url
+    type: string
+    required: true
+    label:
+      en_US: URL
+      zh_Hans: URL
+    human_description:
+      en_US: URL that you want to grab the content from
+      zh_Hans: 您要从中获取内容的 URL
+    llm_description: Defines the link want to grab content from.
+    form: llm
+  - name: location
+    type: string
+    required: false
+    default: US
+    label:
+      en_US: Location
+      zh_Hans: 询问
+    human_description:
+      en_US: Defines from where you want the search to originate. (For example - New York)
+      zh_Hans: 定义您想要搜索的起始位置。 （例如 - 纽约）
+    llm_description: Defines from where you want the search to originate. (For example - New York)
+    form: form
+    options:
+      - value: AU
+        label:
+          en_US: Australia
+          zh_Hans: 澳大利亚
+          pt_BR: Australia
+      - value: BR
+        label:
+          en_US: Brazil
+          zh_Hans: 巴西
+          pt_BR: Brazil
+      - value: CA
+        label:
+          en_US: Canada
+          zh_Hans: 加拿大
+          pt_BR: Canada
+      - value: DE
+        label:
+          en_US: Germany
+          zh_Hans: 德国
+          pt_BR: Germany
+      - value: FR
+        label:
+          en_US: France
+          zh_Hans: 法国
+          pt_BR: France
+      - value: GB
+        label:
+          en_US: United Kingdom
+          zh_Hans: 英国
+          pt_BR: United Kingdom
+      - value: US
+        label:
+          en_US: United States
+          zh_Hans: 美国
+          pt_BR: United States
+      - value: JP
+        label:
+          en_US: Japan
+          zh_Hans: 日本
+          pt_BR: Japan
+      - value: IN
+        label:
+          en_US: India
+          zh_Hans: 印度
+          pt_BR: India
+      - value: KR
+        label:
+          en_US: Korea
+          zh_Hans: 韩国
+          pt_BR: Korea
+      - value: SG
+        label:
+          en_US: Singapore
+          zh_Hans: 新加坡
+          pt_BR: Singapore
+      - value: SE
+        label:
+          en_US: Sweden
+          zh_Hans: 瑞典
+          pt_BR: Sweden

api/core/tools/provider/builtin/websearch/tools/job_search.py

@@ -0,0 +1,86 @@
+from typing import Any, Union
+from urllib.parse import urlencode
+
+import requests
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.tool.builtin_tool import BuiltinTool
+
+BASE_URL = "https://api.serply.io/v1/news/"
+
+
+class SerplyApi:
+    """
+    SerplyAPI tool provider.
+    """
+
+    def __init__(self, api_key: str) -> None:
+        """Initialize SerplyAPI tool provider."""
+        self.serply_api_key = api_key
+
+    def run(self, query: str, **kwargs: Any) -> str:
+        """Run query through SerplyAPI and parse result."""
+        params = {"q": query, "hl": kwargs.get("hl", "en"), "gl": kwargs.get("gl", "US"), "num": kwargs.get("num", 10)}
+        location = kwargs.get("location", "US")
+
+        headers = {
+            "X-API-KEY": self.serply_api_key,
+            "X-User-Agent": kwargs.get("device", "desktop"),
+            "X-Proxy-Location": location,
+            "User-Agent": "Dify",
+        }
+
+        url = f"{BASE_URL}{urlencode(params)}"
+        res = requests.get(
+            url,
+            headers=headers,
+        )
+        res = res.json()
+
+        return self.parse_results(res)
+
+    @staticmethod
+    def parse_results(res: dict) -> str:
+        """Process response from Serply Job Search."""
+        jobs = res.get("jobs", [])
+        if not jobs:
+            raise ValueError(f"Got error from Serply: {res}")
+
+        string = []
+        for job in jobs[:10]:
+            try:
+                string.append(
+                    "\n".join([
+                        f"Position: {job['position']}",
+                        f"Employer: {job['employer']}",
+                        f"Location: {job['location']}",
+                        f"Link: {job['link']}",
+                        f"""Highest: {", ".join([h for h in job["highlights"]])}""",
+                        "---",
+                    ])
+                )
+            except KeyError:
+                continue
+
+        content = "\n".join(string)
+        return f"\nJobs results:\n {content}\n"
+
+
+class JobSearchTool(BuiltinTool):
+    def _invoke(
+        self,
+        user_id: str,
+        tool_parameters: dict[str, Any],
+    ) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
+        """
+        Invoke the SerplyApi tool.
+        """
+        query = tool_parameters["query"]
+        gl = tool_parameters.get("gl", "us")
+        hl = tool_parameters.get("hl", "en")
+        location = tool_parameters.get("location", None)
+
+        api_key = self.runtime.credentials["serply_api_key"]
+        result = SerplyApi(api_key).run(query, gl=gl, hl=hl, location=location)
+
+        return self.create_text_message(text=result)

api/core/tools/provider/builtin/websearch/tools/job_search.yaml

@@ -0,0 +1,41 @@
+identity:
+  name: job_search
+  author: Dify
+  label:
+    en_US: Job Search API
+    zh_Hans: Job Search API
+description:
+  human:
+    en_US: A tool to retrieve job titles, company names and description from Google Jobs engine.
+    zh_Hans: 一个从 Google 招聘引擎检索职位名称、公司名称和描述的工具。
+  llm: A tool to retrieve job titles, company names and description from Google Jobs engine.
+parameters:
+  - name: query
+    type: string
+    required: true
+    label:
+      en_US: Query
+      zh_Hans: 询问
+    human_description:
+      en_US: Defines the query you want to search.
+      zh_Hans: 定义您要搜索的查询。
+    llm_description: Defines the search query you want to search.
+    form: llm
+  - name: location
+    type: string
+    required: false
+    default: US
+    label:
+      en_US: Location
+      zh_Hans: 询问
+    human_description:
+      en_US: Defines from where you want the search to originate. (For example - New York)
+      zh_Hans: 定义您想要搜索的起始位置。 （例如 - 纽约）
+    llm_description: Defines from where you want the search to originate. (For example - New York)
+    form: form
+    options:
+      - value: US
+        label:
+          en_US: United States
+          zh_Hans: 美国
+          pt_BR: United States

api/core/tools/provider/builtin/websearch/tools/news_search.py

@@ -0,0 +1,88 @@
+from typing import Any, Union
+from urllib.parse import urlencode
+
+import requests
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.tool.builtin_tool import BuiltinTool
+
+BASE_URL = "https://api.serply.io/v1/news/"
+
+
+class SerplyApi:
+    """
+    SerplyApi tool provider.
+    """
+
+    def __init__(self, api_key: str) -> None:
+        """Initialize SerplyApi tool provider."""
+        self.serply_api_key = api_key
+
+    def run(self, query: str, **kwargs: Any) -> str:
+        """Run query through SerplyApi and parse result."""
+        params = {"q": query, "hl": kwargs.get("hl", "en"), "gl": kwargs.get("gl", "US"), "num": kwargs.get("num", 10)}
+        location = kwargs.get("location", "US")
+
+        headers = {
+            "X-API-KEY": self.serply_api_key,
+            "X-User-Agent": kwargs.get("device", "desktop"),
+            "X-Proxy-Location": location,
+            "User-Agent": "Dify",
+        }
+
+        url = f"{BASE_URL}{urlencode(params)}"
+        res = requests.get(
+            url,
+            headers=headers,
+        )
+        res = res.json()
+
+        return self.parse_results(res)
+
+    @staticmethod
+    def parse_results(res: dict) -> str:
+        """Process response from Serply News Search."""
+        news = res.get("entries", [])
+        if not news:
+            raise ValueError(f"Got error from Serply: {res}")
+
+        string = []
+        for entry in news:
+            try:
+                # follow url
+                r = requests.get(entry["link"])
+                final_link = r.history[-1].headers["Location"]
+                string.append(
+                    "\n".join([
+                        f"Title: {entry['title']}",
+                        f"Link: {final_link}",
+                        f"Source: {entry['source']['title']}",
+                        f"Published: {entry['published']}",
+                        "---",
+                    ])
+                )
+            except KeyError:
+                continue
+
+        content = "\n".join(string)
+        return f"\nNews:\n {content}\n"
+
+
+class NewsSearchTool(BuiltinTool):
+    def _invoke(
+        self,
+        user_id: str,
+        tool_parameters: dict[str, Any],
+    ) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
+        """
+        Invoke the SerplyApi tool.
+        """
+        query = tool_parameters["query"]
+        gl = tool_parameters.get("gl", "us")
+        hl = tool_parameters.get("hl", "en")
+        location = tool_parameters.get("location", None)
+
+        api_key = self.runtime.credentials["serply_api_key"]
+        result = SerplyApi(api_key).run(query, gl=gl, hl=hl, location=location)
+
+        return self.create_text_message(text=result)

api/core/tools/provider/builtin/websearch/tools/news_search.yaml

@@ -0,0 +1,501 @@
+identity:
+  name: news_search
+  author: Dify
+  label:
+    en_US: News Search API
+    zh_Hans: News Search API
+description:
+  human:
+    en_US: A tool to retrieve organic search results snippets and links from Google News engine.
+    zh_Hans: 一种从 Google 新闻引擎检索有机搜索结果片段和链接的工具。
+  llm: A tool to retrieve organic search results snippets and links from Google News engine.
+parameters:
+  - name: query
+    type: string
+    required: true
+    label:
+      en_US: Query
+      zh_Hans: 询问
+    human_description:
+      en_US: Defines the query you want to search.
+      zh_Hans: 定义您要搜索的查询。
+    llm_description: Defines the search query you want to search.
+    form: llm
+  - name: location
+    type: string
+    required: false
+    default: US
+    label:
+      en_US: Location
+      zh_Hans: 询问
+    human_description:
+      en_US: Defines from where you want the search to originate. (For example - New York)
+      zh_Hans: 定义您想要搜索的起始位置。 （例如 - 纽约）
+    llm_description: Defines from where you want the search to originate. (For example - New York)
+    form: form
+    options:
+      - value: AU
+        label:
+          en_US: Australia
+          zh_Hans: 澳大利亚
+          pt_BR: Australia
+      - value: BR
+        label:
+          en_US: Brazil
+          zh_Hans: 巴西
+          pt_BR: Brazil
+      - value: CA
+        label:
+          en_US: Canada
+          zh_Hans: 加拿大
+          pt_BR: Canada
+      - value: DE
+        label:
+          en_US: Germany
+          zh_Hans: 德国
+          pt_BR: Germany
+      - value: FR
+        label:
+          en_US: France
+          zh_Hans: 法国
+          pt_BR: France
+      - value: GB
+        label:
+          en_US: United Kingdom
+          zh_Hans: 英国
+          pt_BR: United Kingdom
+      - value: US
+        label:
+          en_US: United States
+          zh_Hans: 美国
+          pt_BR: United States
+      - value: JP
+        label:
+          en_US: Japan
+          zh_Hans: 日本
+          pt_BR: Japan
+      - value: IN
+        label:
+          en_US: India
+          zh_Hans: 印度
+          pt_BR: India
+      - value: KR
+        label:
+          en_US: Korea
+          zh_Hans: 韩国
+          pt_BR: Korea
+      - value: SG
+        label:
+          en_US: Singapore
+          zh_Hans: 新加坡
+          pt_BR: Singapore
+      - value: SE
+        label:
+          en_US: Sweden
+          zh_Hans: 瑞典
+          pt_BR: Sweden
+  - name: gl
+    type: select
+    label:
+      en_US: Country
+      zh_Hans: 国家/地区
+    required: false
+    human_description:
+      en_US: Defines the country of the search. Default is "US".
+      zh_Hans: 定义搜索的国家/地区。默认为“美国”。
+    llm_description: Defines the gl parameter of the Google search.
+    form: form
+    default: US
+    options:
+      - value: AR
+        label:
+          en_US: Argentina
+          zh_Hans: 阿根廷
+          pt_BR: Argentina
+      - value: AU
+        label:
+          en_US: Australia
+          zh_Hans: 澳大利亚
+          pt_BR: Australia
+      - value: AT
+        label:
+          en_US: Austria
+          zh_Hans: 奥地利
+          pt_BR: Austria
+      - value: BE
+        label:
+          en_US: Belgium
+          zh_Hans: 比利时
+          pt_BR: Belgium
+      - value: BR
+        label:
+          en_US: Brazil
+          zh_Hans: 巴西
+          pt_BR: Brazil
+      - value: CA
+        label:
+          en_US: Canada
+          zh_Hans: 加拿大
+          pt_BR: Canada
+      - value: CL
+        label:
+          en_US: Chile
+          zh_Hans: 智利
+          pt_BR: Chile
+      - value: CO
+        label:
+          en_US: Colombia
+          zh_Hans: 哥伦比亚
+          pt_BR: Colombia
+      - value: CN
+        label:
+          en_US: China
+          zh_Hans: 中国
+          pt_BR: China
+      - value: CZ
+        label:
+          en_US: Czech Republic
+          zh_Hans: 捷克共和国
+          pt_BR: Czech Republic
+      - value: DK
+        label:
+          en_US: Denmark
+          zh_Hans: 丹麦
+          pt_BR: Denmark
+      - value: FI
+        label:
+          en_US: Finland
+          zh_Hans: 芬兰
+          pt_BR: Finland
+      - value: FR
+        label:
+          en_US: France
+          zh_Hans: 法国
+          pt_BR: France
+      - value: DE
+        label:
+          en_US: Germany
+          zh_Hans: 德国
+          pt_BR: Germany
+      - value: HK
+        label:
+          en_US: Hong Kong
+          zh_Hans: 香港
+          pt_BR: Hong Kong
+      - value: IN
+        label:
+          en_US: India
+          zh_Hans: 印度
+          pt_BR: India
+      - value: ID
+        label:
+          en_US: Indonesia
+          zh_Hans: 印度尼西亚
+          pt_BR: Indonesia
+      - value: IT
+        label:
+          en_US: Italy
+          zh_Hans: 意大利
+          pt_BR: Italy
+      - value: JP
+        label:
+          en_US: Japan
+          zh_Hans: 日本
+          pt_BR: Japan
+      - value: KR
+        label:
+          en_US: Korea
+          zh_Hans: 韩国
+          pt_BR: Korea
+      - value: MY
+        label:
+          en_US: Malaysia
+          zh_Hans: 马来西亚
+          pt_BR: Malaysia
+      - value: MX
+        label:
+          en_US: Mexico
+          zh_Hans: 墨西哥
+          pt_BR: Mexico
+      - value: NL
+        label:
+          en_US: Netherlands
+          zh_Hans: 荷兰
+          pt_BR: Netherlands
+      - value: NZ
+        label:
+          en_US: New Zealand
+          zh_Hans: 新西兰
+          pt_BR: New Zealand
+      - value: NO
+        label:
+          en_US: Norway
+          zh_Hans: 挪威
+          pt_BR: Norway
+      - value: PH
+        label:
+          en_US: Philippines
+          zh_Hans: 菲律宾
+          pt_BR: Philippines
+      - value: PL
+        label:
+          en_US: Poland
+          zh_Hans: 波兰
+          pt_BR: Poland
+      - value: PT
+        label:
+          en_US: Portugal
+          zh_Hans: 葡萄牙
+          pt_BR: Portugal
+      - value: RU
+        label:
+          en_US: Russia
+          zh_Hans: 俄罗斯
+          pt_BR: Russia
+      - value: SA
+        label:
+          en_US: Saudi Arabia
+          zh_Hans: 沙特阿拉伯
+          pt_BR: Saudi Arabia
+      - value: SG
+        label:
+          en_US: Singapore
+          zh_Hans: 新加坡
+          pt_BR: Singapore
+      - value: ZA
+        label:
+          en_US: South Africa
+          zh_Hans: 南非
+          pt_BR: South Africa
+      - value: ES
+        label:
+          en_US: Spain
+          zh_Hans: 西班牙
+          pt_BR: Spain
+      - value: SE
+        label:
+          en_US: Sweden
+          zh_Hans: 瑞典
+          pt_BR: Sweden
+      - value: CH
+        label:
+          en_US: Switzerland
+          zh_Hans: 瑞士
+          pt_BR: Switzerland
+      - value: TW
+        label:
+          en_US: Taiwan
+          zh_Hans: 台湾
+          pt_BR: Taiwan
+      - value: TH
+        label:
+          en_US: Thailand
+          zh_Hans: 泰国
+          pt_BR: Thailand
+      - value: TR
+        label:
+          en_US: Turkey
+          zh_Hans: 土耳其
+          pt_BR: Turkey
+      - value: GB
+        label:
+          en_US: United Kingdom
+          zh_Hans: 英国
+          pt_BR: United Kingdom
+      - value: US
+        label:
+          en_US: United States
+          zh_Hans: 美国
+          pt_BR: United States
+  - name: hl
+    type: select
+    label:
+      en_US: Language
+      zh_Hans: 语言
+    human_description:
+      en_US: Defines the interface language of the search. Default is "en".
+      zh_Hans: 定义搜索的界面语言。默认为“en”。
+    required: false
+    default: en
+    form: form
+    options:
+      - value: ar
+        label:
+          en_US: Arabic
+          zh_Hans: 阿拉伯语
+      - value: bg
+        label:
+          en_US: Bulgarian
+          zh_Hans: 保加利亚语
+      - value: ca
+        label:
+          en_US: Catalan
+          zh_Hans: 加泰罗尼亚语
+      - value: zh-cn
+        label:
+          en_US: Chinese (Simplified)
+          zh_Hans: 中文（简体）
+      - value: zh-tw
+        label:
+          en_US: Chinese (Traditional)
+          zh_Hans: 中文（繁体）
+      - value: cs
+        label:
+          en_US: Czech
+          zh_Hans: 捷克语
+      - value: da
+        label:
+          en_US: Danish
+          zh_Hans: 丹麦语
+      - value: nl
+        label:
+          en_US: Dutch
+          zh_Hans: 荷兰语
+      - value: en
+        label:
+          en_US: English
+          zh_Hans: 英语
+      - value: et
+        label:
+          en_US: Estonian
+          zh_Hans: 爱沙尼亚语
+      - value: fi
+        label:
+          en_US: Finnish
+          zh_Hans: 芬兰语
+      - value: fr
+        label:
+          en_US: French
+          zh_Hans: 法语
+      - value: de
+        label:
+          en_US: German
+          zh_Hans: 德语
+      - value: el
+        label:
+          en_US: Greek
+          zh_Hans: 希腊语
+      - value: iw
+        label:
+          en_US: Hebrew
+          zh_Hans: 希伯来语
+      - value: hi
+        label:
+          en_US: Hindi
+          zh_Hans: 印地语
+      - value: hu
+        label:
+          en_US: Hungarian
+          zh_Hans: 匈牙利语
+      - value: id
+        label:
+          en_US: Indonesian
+          zh_Hans: 印尼语
+      - value: it
+        label:
+          en_US: Italian
+          zh_Hans: 意大利语
+      - value: ja
+        label:
+          en_US: Japanese
+          zh_Hans: 日语
+      - value: kn
+        label:
+          en_US: Kannada
+          zh_Hans: 卡纳达语
+      - value: ko
+        label:
+          en_US: Korean
+          zh_Hans: 韩语
+      - value: lv
+        label:
+          en_US: Latvian
+          zh_Hans: 拉脱维亚语
+      - value: lt
+        label:
+          en_US: Lithuanian
+          zh_Hans: 立陶宛语
+      - value: my
+        label:
+          en_US: Malay
+          zh_Hans: 马来语
+      - value: ml
+        label:
+          en_US: Malayalam
+          zh_Hans: 马拉雅拉姆语
+      - value: mr
+        label:
+          en_US: Marathi
+          zh_Hans: 马拉地语
+      - value: "no"
+        label:
+          en_US: Norwegian
+          zh_Hans: 挪威语
+      - value: pl
+        label:
+          en_US: Polish
+          zh_Hans: 波兰语
+      - value: pt-br
+        label:
+          en_US: Portuguese (Brazil)
+          zh_Hans: 葡萄牙语（巴西）
+      - value: pt-pt
+        label:
+          en_US: Portuguese (Portugal)
+          zh_Hans: 葡萄牙语（葡萄牙）
+      - value: pa
+        label:
+          en_US: Punjabi
+          zh_Hans: 旁遮普语
+      - value: ro
+        label:
+          en_US: Romanian
+          zh_Hans: 罗马尼亚语
+      - value: ru
+        label:
+          en_US: Russian
+          zh_Hans: 俄语
+      - value: sr
+        label:
+          en_US: Serbian
+          zh_Hans: 塞尔维亚语
+      - value: sk
+        label:
+          en_US: Slovak
+          zh_Hans: 斯洛伐克语
+      - value: sl
+        label:
+          en_US: Slovenian
+          zh_Hans: 斯洛文尼亚语
+      - value: es
+        label:
+          en_US: Spanish
+          zh_Hans: 西班牙语
+      - value: sv
+        label:
+          en_US: Swedish
+          zh_Hans: 瑞典语
+      - value: ta
+        label:
+          en_US: Tamil
+          zh_Hans: 泰米尔语
+      - value: te
+        label:
+          en_US: Telugu
+          zh_Hans: 泰卢固语
+      - value: th
+        label:
+          en_US: Thai
+          zh_Hans: 泰语
+      - value: tr
+        label:
+          en_US: Turkish
+          zh_Hans: 土耳其语
+      - value: uk
+        label:
+          en_US: Ukrainian
+          zh_Hans: 乌克兰语
+      - value: vi
+        label:
+          en_US: Vietnamese
+          zh_Hans: 越南语

api/core/tools/provider/builtin/websearch/tools/scholar_search.py

@@ -0,0 +1,91 @@
+from typing import Any, Union
+from urllib.parse import urlencode
+
+import requests
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.tool.builtin_tool import BuiltinTool
+
+BASE_URL = "https://api.serply.io/v1/scholar/"
+
+
+class SerplyApi:
+    """
+    SerplyApi tool provider.
+    """
+
+    def __init__(self, api_key: str) -> None:
+        """Initialize SerplyApi tool provider."""
+        self.serply_api_key = api_key
+
+    def run(self, query: str, **kwargs: Any) -> str:
+        """Run query through SerplyApi and parse result."""
+        params = {"q": query, "hl": kwargs.get("hl", "en"), "gl": kwargs.get("gl", "US"), "num": kwargs.get("num", 10)}
+        location = kwargs.get("location", "US")
+
+        headers = {
+            "X-API-KEY": self.serply_api_key,
+            "X-User-Agent": kwargs.get("device", "desktop"),
+            "X-Proxy-Location": location,
+            "User-Agent": "Dify",
+        }
+
+        url = f"{BASE_URL}{urlencode(params)}"
+        res = requests.get(
+            url,
+            headers=headers,
+        )
+        res = res.json()
+
+        return self.parse_results(res)
+
+    @staticmethod
+    def parse_results(res: dict) -> str:
+        """Process response from Serply News Search."""
+        articles = res.get("articles", [])
+        if not articles:
+            raise ValueError(f"Got error from Serply: {res}")
+
+        string = []
+        for article in articles:
+            try:
+                if "doc" in article:
+                    link = article["doc"]["link"]
+                else:
+                    link = article["link"]
+                authors = [author["name"] for author in article["author"]["authors"]]
+                string.append(
+                    "\n".join([
+                        f"Title: {article['title']}",
+                        f"Link: {link}",
+                        f"Description: {article['description']}",
+                        f"Cite: {article['cite']}",
+                        f"Authors: {', '.join(authors)}",
+                        "---",
+                    ])
+                )
+            except KeyError:
+                continue
+
+        content = "\n".join(string)
+        return f"\nScholar results:\n {content}\n"
+
+
+class ScholarSearchTool(BuiltinTool):
+    def _invoke(
+        self,
+        user_id: str,
+        tool_parameters: dict[str, Any],
+    ) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
+        """
+        Invoke the SerplyApi tool.
+        """
+        query = tool_parameters["query"]
+        gl = tool_parameters.get("gl", "us")
+        hl = tool_parameters.get("hl", "en")
+        location = tool_parameters.get("location", None)
+
+        api_key = self.runtime.credentials["serply_api_key"]
+        result = SerplyApi(api_key).run(query, gl=gl, hl=hl, location=location)
+
+        return self.create_text_message(text=result)

api/core/tools/provider/builtin/websearch/tools/scholar_search.yaml

@@ -0,0 +1,501 @@
+identity:
+  name: scholar_search
+  author: Dify
+  label:
+    en_US: Scholar API
+    zh_Hans: Scholar API
+description:
+  human:
+    en_US: A tool to retrieve scholarly literature.
+    zh_Hans: 学术文献检索工具
+  llm: A tool to retrieve scholarly literature.
+parameters:
+  - name: query
+    type: string
+    required: true
+    label:
+      en_US: Query
+      zh_Hans: 询问
+    human_description:
+      en_US: Defines the query you want to search.
+      zh_Hans: 定义您要搜索的查询。
+    llm_description: Defines the search query you want to search.
+    form: llm
+  - name: location
+    type: string
+    required: false
+    default: US
+    label:
+      en_US: Location
+      zh_Hans: 询问
+    human_description:
+      en_US: Defines from where you want the search to originate. (For example - New York)
+      zh_Hans: 定义您想要搜索的起始位置。 （例如 - 纽约）
+    llm_description: Defines from where you want the search to originate. (For example - New York)
+    form: form
+    options:
+      - value: AU
+        label:
+          en_US: Australia
+          zh_Hans: 澳大利亚
+          pt_BR: Australia
+      - value: BR
+        label:
+          en_US: Brazil
+          zh_Hans: 巴西
+          pt_BR: Brazil
+      - value: CA
+        label:
+          en_US: Canada
+          zh_Hans: 加拿大
+          pt_BR: Canada
+      - value: DE
+        label:
+          en_US: Germany
+          zh_Hans: 德国
+          pt_BR: Germany
+      - value: FR
+        label:
+          en_US: France
+          zh_Hans: 法国
+          pt_BR: France
+      - value: GB
+        label:
+          en_US: United Kingdom
+          zh_Hans: 英国
+          pt_BR: United Kingdom
+      - value: US
+        label:
+          en_US: United States
+          zh_Hans: 美国
+          pt_BR: United States
+      - value: JP
+        label:
+          en_US: Japan
+          zh_Hans: 日本
+          pt_BR: Japan
+      - value: IN
+        label:
+          en_US: India
+          zh_Hans: 印度
+          pt_BR: India
+      - value: KR
+        label:
+          en_US: Korea
+          zh_Hans: 韩国
+          pt_BR: Korea
+      - value: SG
+        label:
+          en_US: Singapore
+          zh_Hans: 新加坡
+          pt_BR: Singapore
+      - value: SE
+        label:
+          en_US: Sweden
+          zh_Hans: 瑞典
+          pt_BR: Sweden
+  - name: gl
+    type: select
+    label:
+      en_US: Country
+      zh_Hans: 国家/地区
+    required: false
+    human_description:
+      en_US: Defines the country of the search. Default is "US".
+      zh_Hans: 定义搜索的国家/地区。默认为“美国”。
+    llm_description: Defines the gl parameter of the Google search.
+    form: form
+    default: US
+    options:
+      - value: AR
+        label:
+          en_US: Argentina
+          zh_Hans: 阿根廷
+          pt_BR: Argentina
+      - value: AU
+        label:
+          en_US: Australia
+          zh_Hans: 澳大利亚
+          pt_BR: Australia
+      - value: AT
+        label:
+          en_US: Austria
+          zh_Hans: 奥地利
+          pt_BR: Austria
+      - value: BE
+        label:
+          en_US: Belgium
+          zh_Hans: 比利时
+          pt_BR: Belgium
+      - value: BR
+        label:
+          en_US: Brazil
+          zh_Hans: 巴西
+          pt_BR: Brazil
+      - value: CA
+        label:
+          en_US: Canada
+          zh_Hans: 加拿大
+          pt_BR: Canada
+      - value: CL
+        label:
+          en_US: Chile
+          zh_Hans: 智利
+          pt_BR: Chile
+      - value: CO
+        label:
+          en_US: Colombia
+          zh_Hans: 哥伦比亚
+          pt_BR: Colombia
+      - value: CN
+        label:
+          en_US: China
+          zh_Hans: 中国
+          pt_BR: China
+      - value: CZ
+        label:
+          en_US: Czech Republic
+          zh_Hans: 捷克共和国
+          pt_BR: Czech Republic
+      - value: DK
+        label:
+          en_US: Denmark
+          zh_Hans: 丹麦
+          pt_BR: Denmark
+      - value: FI
+        label:
+          en_US: Finland
+          zh_Hans: 芬兰
+          pt_BR: Finland
+      - value: FR
+        label:
+          en_US: France
+          zh_Hans: 法国
+          pt_BR: France
+      - value: DE
+        label:
+          en_US: Germany
+          zh_Hans: 德国
+          pt_BR: Germany
+      - value: HK
+        label:
+          en_US: Hong Kong
+          zh_Hans: 香港
+          pt_BR: Hong Kong
+      - value: IN
+        label:
+          en_US: India
+          zh_Hans: 印度
+          pt_BR: India
+      - value: ID
+        label:
+          en_US: Indonesia
+          zh_Hans: 印度尼西亚
+          pt_BR: Indonesia
+      - value: IT
+        label:
+          en_US: Italy
+          zh_Hans: 意大利
+          pt_BR: Italy
+      - value: JP
+        label:
+          en_US: Japan
+          zh_Hans: 日本
+          pt_BR: Japan
+      - value: KR
+        label:
+          en_US: Korea
+          zh_Hans: 韩国
+          pt_BR: Korea
+      - value: MY
+        label:
+          en_US: Malaysia
+          zh_Hans: 马来西亚
+          pt_BR: Malaysia
+      - value: MX
+        label:
+          en_US: Mexico
+          zh_Hans: 墨西哥
+          pt_BR: Mexico
+      - value: NL
+        label:
+          en_US: Netherlands
+          zh_Hans: 荷兰
+          pt_BR: Netherlands
+      - value: NZ
+        label:
+          en_US: New Zealand
+          zh_Hans: 新西兰
+          pt_BR: New Zealand
+      - value: "NO"
+        label:
+          en_US: Norway
+          zh_Hans: 挪威
+          pt_BR: Norway
+      - value: PH
+        label:
+          en_US: Philippines
+          zh_Hans: 菲律宾
+          pt_BR: Philippines
+      - value: PL
+        label:
+          en_US: Poland
+          zh_Hans: 波兰
+          pt_BR: Poland
+      - value: PT
+        label:
+          en_US: Portugal
+          zh_Hans: 葡萄牙
+          pt_BR: Portugal
+      - value: RU
+        label:
+          en_US: Russia
+          zh_Hans: 俄罗斯
+          pt_BR: Russia
+      - value: SA
+        label:
+          en_US: Saudi Arabia
+          zh_Hans: 沙特阿拉伯
+          pt_BR: Saudi Arabia
+      - value: SG
+        label:
+          en_US: Singapore
+          zh_Hans: 新加坡
+          pt_BR: Singapore
+      - value: ZA
+        label:
+          en_US: South Africa
+          zh_Hans: 南非
+          pt_BR: South Africa
+      - value: ES
+        label:
+          en_US: Spain
+          zh_Hans: 西班牙
+          pt_BR: Spain
+      - value: SE
+        label:
+          en_US: Sweden
+          zh_Hans: 瑞典
+          pt_BR: Sweden
+      - value: CH
+        label:
+          en_US: Switzerland
+          zh_Hans: 瑞士
+          pt_BR: Switzerland
+      - value: TW
+        label:
+          en_US: Taiwan
+          zh_Hans: 台湾
+          pt_BR: Taiwan
+      - value: TH
+        label:
+          en_US: Thailand
+          zh_Hans: 泰国
+          pt_BR: Thailand
+      - value: TR
+        label:
+          en_US: Turkey
+          zh_Hans: 土耳其
+          pt_BR: Turkey
+      - value: GB
+        label:
+          en_US: United Kingdom
+          zh_Hans: 英国
+          pt_BR: United Kingdom
+      - value: US
+        label:
+          en_US: United States
+          zh_Hans: 美国
+          pt_BR: United States
+  - name: hl
+    type: select
+    label:
+      en_US: Language
+      zh_Hans: 语言
+    human_description:
+      en_US: Defines the interface language of the search. Default is "en".
+      zh_Hans: 定义搜索的界面语言。默认为“en”。
+    required: false
+    default: en
+    form: form
+    options:
+      - value: ar
+        label:
+          en_US: Arabic
+          zh_Hans: 阿拉伯语
+      - value: bg
+        label:
+          en_US: Bulgarian
+          zh_Hans: 保加利亚语
+      - value: ca
+        label:
+          en_US: Catalan
+          zh_Hans: 加泰罗尼亚语
+      - value: zh-cn
+        label:
+          en_US: Chinese (Simplified)
+          zh_Hans: 中文（简体）
+      - value: zh-tw
+        label:
+          en_US: Chinese (Traditional)
+          zh_Hans: 中文（繁体）
+      - value: cs
+        label:
+          en_US: Czech
+          zh_Hans: 捷克语
+      - value: da
+        label:
+          en_US: Danish
+          zh_Hans: 丹麦语
+      - value: nl
+        label:
+          en_US: Dutch
+          zh_Hans: 荷兰语
+      - value: en
+        label:
+          en_US: English
+          zh_Hans: 英语
+      - value: et
+        label:
+          en_US: Estonian
+          zh_Hans: 爱沙尼亚语
+      - value: fi
+        label:
+          en_US: Finnish
+          zh_Hans: 芬兰语
+      - value: fr
+        label:
+          en_US: French
+          zh_Hans: 法语
+      - value: de
+        label:
+          en_US: German
+          zh_Hans: 德语
+      - value: el
+        label:
+          en_US: Greek
+          zh_Hans: 希腊语
+      - value: iw
+        label:
+          en_US: Hebrew
+          zh_Hans: 希伯来语
+      - value: hi
+        label:
+          en_US: Hindi
+          zh_Hans: 印地语
+      - value: hu
+        label:
+          en_US: Hungarian
+          zh_Hans: 匈牙利语
+      - value: id
+        label:
+          en_US: Indonesian
+          zh_Hans: 印尼语
+      - value: it
+        label:
+          en_US: Italian
+          zh_Hans: 意大利语
+      - value: ja
+        label:
+          en_US: Japanese
+          zh_Hans: 日语
+      - value: kn
+        label:
+          en_US: Kannada
+          zh_Hans: 卡纳达语
+      - value: ko
+        label:
+          en_US: Korean
+          zh_Hans: 韩语
+      - value: lv
+        label:
+          en_US: Latvian
+          zh_Hans: 拉脱维亚语
+      - value: lt
+        label:
+          en_US: Lithuanian
+          zh_Hans: 立陶宛语
+      - value: my
+        label:
+          en_US: Malay
+          zh_Hans: 马来语
+      - value: ml
+        label:
+          en_US: Malayalam
+          zh_Hans: 马拉雅拉姆语
+      - value: mr
+        label:
+          en_US: Marathi
+          zh_Hans: 马拉地语
+      - value: "no"
+        label:
+          en_US: Norwegian
+          zh_Hans: 挪威语
+      - value: pl
+        label:
+          en_US: Polish
+          zh_Hans: 波兰语
+      - value: pt-br
+        label:
+          en_US: Portuguese (Brazil)
+          zh_Hans: 葡萄牙语（巴西）
+      - value: pt-pt
+        label:
+          en_US: Portuguese (Portugal)
+          zh_Hans: 葡萄牙语（葡萄牙）
+      - value: pa
+        label:
+          en_US: Punjabi
+          zh_Hans: 旁遮普语
+      - value: ro
+        label:
+          en_US: Romanian
+          zh_Hans: 罗马尼亚语
+      - value: ru
+        label:
+          en_US: Russian
+          zh_Hans: 俄语
+      - value: sr
+        label:
+          en_US: Serbian
+          zh_Hans: 塞尔维亚语
+      - value: sk
+        label:
+          en_US: Slovak
+          zh_Hans: 斯洛伐克语
+      - value: sl
+        label:
+          en_US: Slovenian
+          zh_Hans: 斯洛文尼亚语
+      - value: es
+        label:
+          en_US: Spanish
+          zh_Hans: 西班牙语
+      - value: sv
+        label:
+          en_US: Swedish
+          zh_Hans: 瑞典语
+      - value: ta
+        label:
+          en_US: Tamil
+          zh_Hans: 泰米尔语
+      - value: te
+        label:
+          en_US: Telugu
+          zh_Hans: 泰卢固语
+      - value: th
+        label:
+          en_US: Thai
+          zh_Hans: 泰语
+      - value: tr
+        label:
+          en_US: Turkish
+          zh_Hans: 土耳其语
+      - value: uk
+        label:
+          en_US: Ukrainian
+          zh_Hans: 乌克兰语
+      - value: vi
+        label:
+          en_US: Vietnamese
+          zh_Hans: 越南语

api/core/tools/provider/builtin/websearch/tools/web_search.py

@@ -0,0 +1,88 @@
+import typing
+from urllib.parse import urlencode
+
+import requests
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.tool.builtin_tool import BuiltinTool
+
+
+class SerplyApi:
+    """
+    SerplyApi tool provider.
+    """
+
+    def __init__(self, api_key: str) -> None:
+        """Initialize Serply Web Search Tool provider."""
+        self.serply_api_key = api_key
+        self.base_url = "https://api.serply.io/v1/search/"
+
+    def run(self, query: str, **kwargs: typing.Any) -> str:
+        """Run query through Serply and parse result."""
+        params = {"q": query, "hl": kwargs.get("hl", "en"), "gl": kwargs.get("gl", "US"), "num": kwargs.get("num", 10)}
+        location = kwargs.get("location", "US")
+
+        headers = {
+            "X-API-KEY": self.serply_api_key,
+            "X-User-Agent": kwargs.get("device", "desktop"),
+            "X-Proxy-Location": location,
+            "User-Agent": "Dify",
+        }
+
+        url = f"{self.base_url}{urlencode(params)}"
+        res = requests.get(
+            url,
+            headers=headers,
+        )
+        res = res.json()
+
+        return self.parse_results(res)
+
+    @staticmethod
+    def parse_results(res: dict) -> str:
+        """Process response from Serply Web Search."""
+        results = res.get("results", [])
+        if not results:
+            raise ValueError(f"Got error from Serply: {res}")
+
+        string = []
+        for result in results:
+            try:
+                string.append(
+                    "\n".join([
+                        f"Title: {result['title']}",
+                        f"Link: {result['link']}",
+                        f"Description: {result['description'].strip()}",
+                        "---",
+                    ])
+                )
+            except KeyError:
+                continue
+
+        if related_questions := res.get("related_questions", []):
+            string.append("---")
+            string.append("Related Questions: ")
+            string.append("\n".join(related_questions))
+
+        content = "\n".join(string)
+        return f"\nSearch results:\n {content}\n"
+
+
+class WebSearchTool(BuiltinTool):
+    def _invoke(
+        self,
+        user_id: str,
+        tool_parameters: dict[str, typing.Any],
+    ) -> typing.Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
+        """
+        Invoke the SerplyApi tool.
+        """
+        query = tool_parameters["query"]
+        num = tool_parameters.get("num", 10)
+        gl = tool_parameters.get("gl", "us")
+        hl = tool_parameters.get("hl", "en")
+        location = tool_parameters.get("location", "None")
+
+        api_key = self.runtime.credentials["serply_api_key"]
+        result = SerplyApi(api_key).run(query=query, num=num, gl=gl, hl=hl, location=location)
+        return self.create_text_message(text=result)

api/core/tools/provider/builtin/websearch/tools/web_search.yaml

@@ -0,0 +1,376 @@
+identity:
+  name: web_search
+  author: Dify
+  label:
+    en_US: Web Search API
+    zh_Hans: Web Search API
+description:
+  human:
+    en_US: A tool to retrieve answer boxes, knowledge graphs, snippets, and webpages from Google Search engine.
+    zh_Hans: 一种从 Google 搜索引擎检索答案框、知识图、片段和网页的工具。
+  llm: A tool to retrieve answer boxes, knowledge graphs, snippets, and webpages from Google Search engine.
+parameters:
+  - name: query
+    type: string
+    required: true
+    label:
+      en_US: Query
+      zh_Hans: 询问
+    human_description:
+      en_US: Defines the query you want to search.
+      zh_Hans: 定义您要搜索的查询。
+    llm_description: Defines the search query you want to search.
+    form: llm
+  - name: location
+    type: string
+    required: false
+    default: US
+    label:
+      en_US: Location
+      zh_Hans: 询问
+    human_description:
+      en_US: Defines from where you want the search to originate. (For example - New York)
+      zh_Hans: 定义您想要搜索的起始位置。 （例如 - 纽约）
+    llm_description: Defines from where you want the search to originate. (For example - New York)
+    form: form
+    options:
+      - value: AU
+        label:
+          en_US: Australia
+          zh_Hans: 澳大利亚
+          pt_BR: Australia
+      - value: BR
+        label:
+          en_US: Brazil
+          zh_Hans: 巴西
+          pt_BR: Brazil
+      - value: CA
+        label:
+          en_US: Canada
+          zh_Hans: 加拿大
+          pt_BR: Canada
+      - value: DE
+        label:
+          en_US: Germany
+          zh_Hans: 德国
+          pt_BR: Germany
+      - value: FR
+        label:
+          en_US: France
+          zh_Hans: 法国
+          pt_BR: France
+      - value: GB
+        label:
+          en_US: United Kingdom
+          zh_Hans: 英国
+          pt_BR: United Kingdom
+      - value: US
+        label:
+          en_US: United States
+          zh_Hans: 美国
+          pt_BR: United States
+      - value: JP
+        label:
+          en_US: Japan
+          zh_Hans: 日本
+          pt_BR: Japan
+      - value: IN
+        label:
+          en_US: India
+          zh_Hans: 印度
+          pt_BR: India
+      - value: KR
+        label:
+          en_US: Korea
+          zh_Hans: 韩国
+          pt_BR: Korea
+      - value: SG
+        label:
+          en_US: Singapore
+          zh_Hans: 新加坡
+          pt_BR: Singapore
+      - value: SE
+        label:
+          en_US: Sweden
+          zh_Hans: 瑞典
+          pt_BR: Sweden
+  - name: device
+    type: select
+    label:
+      en_US: Device Type
+      zh_Hans: 汉斯先生
+    human_description:
+      en_US: Defines the device to make interface search. Default is "desktop".
+      zh_Hans: 定义进行接口搜索的设备。默认为“桌面”
+    required: false
+    default: desktop
+    form: form
+    options:
+      - value: desktop
+        label:
+          en_US: Desktop
+          zh_Hans: 桌面
+      - value: mobile
+        label:
+          en_US: Mobile
+          zh_Hans: 移动的
+  - name: gl
+    type: select
+    label:
+      en_US: Country
+      zh_Hans: 国家/地区
+    required: false
+    human_description:
+      en_US: Defines the country of the search. Default is "US".
+      zh_Hans: 定义搜索的国家/地区。默认为“美国”。
+    llm_description: Defines the gl parameter of the Google search.
+    form: form
+    default: US
+    options:
+      - value: AU
+        label:
+          en_US: Australia
+          zh_Hans: 澳大利亚
+          pt_BR: Australia
+      - value: BR
+        label:
+          en_US: Brazil
+          zh_Hans: 巴西
+          pt_BR: Brazil
+      - value: CA
+        label:
+          en_US: Canada
+          zh_Hans: 加拿大
+          pt_BR: Canada
+      - value: DE
+        label:
+          en_US: Germany
+          zh_Hans: 德国
+          pt_BR: Germany
+      - value: FR
+        label:
+          en_US: France
+          zh_Hans: 法国
+          pt_BR: France
+      - value: GB
+        label:
+          en_US: United Kingdom
+          zh_Hans: 英国
+          pt_BR: United Kingdom
+      - value: IN
+        label:
+          en_US: India
+          zh_Hans: 印度
+          pt_BR: India
+      - value: KR
+        label:
+          en_US: Korea
+          zh_Hans: 韩国
+          pt_BR: Korea
+      - value: SE
+        label:
+          en_US: Sweden
+          zh_Hans: 瑞典
+          pt_BR: Sweden
+      - value: SG
+        label:
+          en_US: Singapore
+          zh_Hans: 新加坡
+          pt_BR: Singapore
+      - value: US
+        label:
+          en_US: United States
+          zh_Hans: 美国
+          pt_BR: United States
+  - name: hl
+    type: select
+    label:
+      en_US: Language
+      zh_Hans: 语言
+    human_description:
+      en_US: Defines the interface language of the search. Default is "en".
+      zh_Hans: 定义搜索的界面语言。默认为“en”。
+    required: false
+    default: en
+    form: form
+    options:
+      - value: ar
+        label:
+          en_US: Arabic
+          zh_Hans: 阿拉伯语
+      - value: bg
+        label:
+          en_US: Bulgarian
+          zh_Hans: 保加利亚语
+      - value: ca
+        label:
+          en_US: Catalan
+          zh_Hans: 加泰罗尼亚语
+      - value: zh-cn
+        label:
+          en_US: Chinese (Simplified)
+          zh_Hans: 中文（简体）
+      - value: zh-tw
+        label:
+          en_US: Chinese (Traditional)
+          zh_Hans: 中文（繁体）
+      - value: cs
+        label:
+          en_US: Czech
+          zh_Hans: 捷克语
+      - value: da
+        label:
+          en_US: Danish
+          zh_Hans: 丹麦语
+      - value: nl
+        label:
+          en_US: Dutch
+          zh_Hans: 荷兰语
+      - value: en
+        label:
+          en_US: English
+          zh_Hans: 英语
+      - value: et
+        label:
+          en_US: Estonian
+          zh_Hans: 爱沙尼亚语
+      - value: fi
+        label:
+          en_US: Finnish
+          zh_Hans: 芬兰语
+      - value: fr
+        label:
+          en_US: French
+          zh_Hans: 法语
+      - value: de
+        label:
+          en_US: German
+          zh_Hans: 德语
+      - value: el
+        label:
+          en_US: Greek
+          zh_Hans: 希腊语
+      - value: iw
+        label:
+          en_US: Hebrew
+          zh_Hans: 希伯来语
+      - value: hi
+        label:
+          en_US: Hindi
+          zh_Hans: 印地语
+      - value: hu
+        label:
+          en_US: Hungarian
+          zh_Hans: 匈牙利语
+      - value: id
+        label:
+          en_US: Indonesian
+          zh_Hans: 印尼语
+      - value: it
+        label:
+          en_US: Italian
+          zh_Hans: 意大利语
+      - value: ja
+        label:
+          en_US: Japanese
+          zh_Hans: 日语
+      - value: kn
+        label:
+          en_US: Kannada
+          zh_Hans: 卡纳达语
+      - value: ko
+        label:
+          en_US: Korean
+          zh_Hans: 韩语
+      - value: lv
+        label:
+          en_US: Latvian
+          zh_Hans: 拉脱维亚语
+      - value: lt
+        label:
+          en_US: Lithuanian
+          zh_Hans: 立陶宛语
+      - value: my
+        label:
+          en_US: Malay
+          zh_Hans: 马来语
+      - value: ml
+        label:
+          en_US: Malayalam
+          zh_Hans: 马拉雅拉姆语
+      - value: mr
+        label:
+          en_US: Marathi
+          zh_Hans: 马拉地语
+      - value: "no"
+        label:
+          en_US: Norwegian
+          zh_Hans: 挪威语
+      - value: pl
+        label:
+          en_US: Polish
+          zh_Hans: 波兰语
+      - value: pt-br
+        label:
+          en_US: Portuguese (Brazil)
+          zh_Hans: 葡萄牙语（巴西）
+      - value: pt-pt
+        label:
+          en_US: Portuguese (Portugal)
+          zh_Hans: 葡萄牙语（葡萄牙）
+      - value: pa
+        label:
+          en_US: Punjabi
+          zh_Hans: 旁遮普语
+      - value: ro
+        label:
+          en_US: Romanian
+          zh_Hans: 罗马尼亚语
+      - value: ru
+        label:
+          en_US: Russian
+          zh_Hans: 俄语
+      - value: sr
+        label:
+          en_US: Serbian
+          zh_Hans: 塞尔维亚语
+      - value: sk
+        label:
+          en_US: Slovak
+          zh_Hans: 斯洛伐克语
+      - value: sl
+        label:
+          en_US: Slovenian
+          zh_Hans: 斯洛文尼亚语
+      - value: es
+        label:
+          en_US: Spanish
+          zh_Hans: 西班牙语
+      - value: sv
+        label:
+          en_US: Swedish
+          zh_Hans: 瑞典语
+      - value: ta
+        label:
+          en_US: Tamil
+          zh_Hans: 泰米尔语
+      - value: te
+        label:
+          en_US: Telugu
+          zh_Hans: 泰卢固语
+      - value: th
+        label:
+          en_US: Thai
+          zh_Hans: 泰语
+      - value: tr
+        label:
+          en_US: Turkish
+          zh_Hans: 土耳其语
+      - value: uk
+        label:
+          en_US: Ukrainian
+          zh_Hans: 乌克兰语
+      - value: vi
+        label:
+          en_US: Vietnamese
+          zh_Hans: 越南语

api/core/tools/provider/builtin/websearch/websearch.py

@@ -0,0 +1,21 @@
+from typing import Any
+
+from core.tools.errors import ToolProviderCredentialValidationError
+from core.tools.provider.builtin.websearch.tools.web_search import WebSearchTool
+from core.tools.provider.builtin_tool_provider import BuiltinToolProviderController
+
+
+class WebSearchAPIProvider(BuiltinToolProviderController):
+    # validate when saving the api_key
+    def _validate_credentials(self, credentials: dict[str, Any]) -> None:
+        try:
+            WebSearchTool().fork_tool_runtime(
+                runtime={
+                    "credentials": credentials,
+                }
+            ).invoke(
+                user_id="",
+                tool_parameters={"query": "what is llm"},
+            )
+        except Exception as e:
+            raise ToolProviderCredentialValidationError(str(e))

api/core/tools/provider/builtin/websearch/websearch.yaml

@@ -0,0 +1,34 @@
+identity:
+  name: websearch
+  author: Serply.io
+  label:
+    en_US: Serply.io
+    zh_Hans: Serply.io
+    pt_BR: Serply.io
+  description:
+    en_US: Serply.io is a robust real-time SERP API delivering structured data from a collection of search engines including Web Search, Jobs, News, and many more.
+    zh_Hans: Serply.io 是一个强大的实时 SERP API，可提供来自 搜索 招聘 新闻等搜索引擎集合的结构化数据。
+    pt_BR: Serply.io is a robust real-time SERP API delivering structured data from a collection of search engines including Web Search, Jobs, News, and many more.
+  icon: icon.svg
+  tags:
+    - search
+    - business
+    - news
+    - productivity
+credentials_for_provider:
+  serply_api_key:
+    type: secret-input
+    required: true
+    label:
+      en_US: Serply.io API key
+      zh_Hans: Serply.io API key
+      pt_BR: Serply.io API key
+    placeholder:
+      en_US: Please input your Serply.io API key
+      zh_Hans: 请输入你的 Serply.io API key
+      pt_BR: Please input your Serply.io API key
+    help:
+      en_US: Get your Serply.io API key from https://Serply.io/
+      zh_Hans: 从 Serply.io 获取您的 Serply.io API key
+      pt_BR: Get your Serply.io API key from Serply.io
+    url: https://Serply.io/

api/core/tools/tool/builtin_tool.py

@@ -66,7 +66,7 @@ class BuiltinTool(Tool):
             tenant_id=self.runtime.tenant_id,
             prompt_messages=prompt_messages
         )
-    
+
     def summary(self, user_id: str, content: str) -> str:
         max_tokens = self.get_max_tokens()
 

api/core/tools/tool/tool.py

@@ -32,8 +32,8 @@ class Tool(BaseModel, ABC):
     # pydantic configs
     model_config = ConfigDict(protected_namespaces=())
 
-    @classmethod
     @field_validator('parameters', mode='before')
+    @classmethod
     def set_parameters(cls, v, validation_info: ValidationInfo) -> list[ToolParameter]:
         return v or []
 

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

@@ -1,7 +1,7 @@
 import os
 from typing import Literal, Optional, Union
 
-from pydantic import BaseModel, field_validator
+from pydantic import BaseModel, ValidationInfo, field_validator
 
 from core.workflow.entities.base_node_data_entities import BaseNodeData
 
@@ -24,13 +24,13 @@ class HttpRequestNodeData(BaseNodeData):
         type: Literal['no-auth', 'api-key']
         config: Optional[Config]
 
-        @classmethod
         @field_validator('config', mode='before')
-        def check_config(cls, v, values):
+        @classmethod
+        def check_config(cls, v: Config, values: ValidationInfo):
             """
             Check config, if type is no-auth, config should be None, otherwise it should be a dict.
             """
-            if values['type'] == 'no-auth':
+            if values.data['type'] == 'no-auth':
                 return None
             else:
                 if not v or not isinstance(v, dict):

api/core/workflow/nodes/llm/llm_node.py

@@ -12,7 +12,11 @@ from core.file.file_obj import FileVar
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance, ModelManager
 from core.model_runtime.entities.llm_entities import LLMUsage
-from core.model_runtime.entities.message_entities import PromptMessage, PromptMessageContentType
+from core.model_runtime.entities.message_entities import (
+    ImagePromptMessageContent,
+    PromptMessage,
+    PromptMessageContentType,
+)
 from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
 from core.model_runtime.utils.encoders import jsonable_encoder
@@ -548,6 +552,7 @@ class LLMNode(BaseNode):
         stop = model_config.stop
 
         vision_enabled = node_data.vision.enabled
+        vision_detail = node_data.vision.configs.detail if node_data.vision.configs else None
         filtered_prompt_messages = []
         for prompt_message in prompt_messages:
             if prompt_message.is_empty():
@@ -556,7 +561,10 @@ class LLMNode(BaseNode):
             if not isinstance(prompt_message.content, str):
                 prompt_message_content = []
                 for content_item in prompt_message.content:
-                    if vision_enabled and content_item.type == PromptMessageContentType.IMAGE:
+                    if vision_enabled and content_item.type == PromptMessageContentType.IMAGE and isinstance(content_item, ImagePromptMessageContent):
+                        # Override vision config if LLM node has vision config
+                        if vision_detail:
+                            content_item.detail = ImagePromptMessageContent.DETAIL(vision_detail)
                         prompt_message_content.append(content_item)
                     elif content_item.type == PromptMessageContentType.TEXT:
                         prompt_message_content.append(content_item)

api/core/workflow/nodes/parameter_extractor/entities.py

@@ -25,8 +25,8 @@ class ParameterConfig(BaseModel):
     description: str
     required: bool
 
-    @classmethod
     @field_validator('name', mode='before')
+    @classmethod
     def validate_name(cls, value) -> str:
         if not value:
             raise ValueError('Parameter name is required')
@@ -45,8 +45,8 @@ class ParameterExtractorNodeData(BaseNodeData):
     memory: Optional[MemoryConfig] = None
     reasoning_mode: Literal['function_call', 'prompt']
 
-    @classmethod
     @field_validator('reasoning_mode', mode='before')
+    @classmethod
     def set_reasoning_mode(cls, v) -> str:
         return v or 'function_call'
 

api/core/workflow/nodes/parameter_extractor/parameter_extractor_node.py

@@ -95,7 +95,7 @@ class ParameterExtractorNode(LLMNode):
         # fetch memory
         memory = self._fetch_memory(node_data.memory, variable_pool, model_instance)
         
-        if set(model_schema.features or []) & set([ModelFeature.MULTI_TOOL_CALL, ModelFeature.MULTI_TOOL_CALL]) \
+        if set(model_schema.features or []) & set([ModelFeature.TOOL_CALL, ModelFeature.MULTI_TOOL_CALL]) \
             and node_data.reasoning_mode == 'function_call':
             # use function call 
             prompt_messages, prompt_message_tools = self._generate_function_call_prompt(

api/core/workflow/nodes/tool/entities.py

@@ -14,9 +14,9 @@ class ToolEntity(BaseModel):
     tool_label: str # redundancy
     tool_configurations: dict[str, Any]
 
-    @classmethod
     @field_validator('tool_configurations', mode='before')
-    def validate_tool_configurations(cls, value, values: ValidationInfo) -> dict[str, Any]:
+    @classmethod
+    def validate_tool_configurations(cls, value, values: ValidationInfo):
         if not isinstance(value, dict):
             raise ValueError('tool_configurations must be a dictionary')
         
@@ -32,8 +32,8 @@ class ToolNodeData(BaseNodeData, ToolEntity):
         value: Union[Any, list[str]]
         type: Literal['mixed', 'variable', 'constant']
 
-        @classmethod
         @field_validator('type', mode='before')
+        @classmethod
         def check_type(cls, value, validation_info: ValidationInfo):
             typ = value
             value = validation_info.data.get('value')

api/core/workflow/utils/variable_template_parser.py

@@ -7,11 +7,35 @@ REGEX = re.compile(r"\{\{(#[a-zA-Z0-9_]{1,50}(\.[a-zA-Z_][a-zA-Z0-9_]{0,29}){1,1
 
 class VariableTemplateParser:
     """
+    A class for parsing and manipulating template variables in a string.
+
     Rules:
 
     1. Template variables must be enclosed in `{{}}`.
     2. The template variable Key can only be: #node_id.var1.var2#.
     3. The template variable Key cannot contain new lines or spaces, and must comply with rule 2.
+
+    Example usage:
+
+    template = "Hello, {{#node_id.query.name#}}! Your age is {{#node_id.query.age#}}."
+    parser = VariableTemplateParser(template)
+
+    # Extract template variable keys
+    variable_keys = parser.extract()
+    print(variable_keys)
+    # Output: ['#node_id.query.name#', '#node_id.query.age#']
+
+    # Extract variable selectors
+    variable_selectors = parser.extract_variable_selectors()
+    print(variable_selectors)
+    # Output: [VariableSelector(variable='#node_id.query.name#', value_selector=['node_id', 'query', 'name']),
+    #          VariableSelector(variable='#node_id.query.age#', value_selector=['node_id', 'query', 'age'])]
+
+    # Format the template string
+    inputs = {'#node_id.query.name#': 'John', '#node_id.query.age#': 25}}
+    formatted_string = parser.format(inputs)
+    print(formatted_string)
+    # Output: "Hello, John! Your age is 25."
     """
 
     def __init__(self, template: str):
@@ -19,6 +43,12 @@ class VariableTemplateParser:
         self.variable_keys = self.extract()
 
     def extract(self) -> list:
+        """
+        Extracts all the template variable keys from the template string.
+
+        Returns:
+            A list of template variable keys.
+        """
         # Regular expression to match the template rules
         matches = re.findall(REGEX, self.template)
 
@@ -27,6 +57,12 @@ class VariableTemplateParser:
         return list(set(first_group_matches))
 
     def extract_variable_selectors(self) -> list[VariableSelector]:
+        """
+        Extracts the variable selectors from the template variable keys.
+
+        Returns:
+            A list of VariableSelector objects representing the variable selectors.
+        """
         variable_selectors = []
         for variable_key in self.variable_keys:
             remove_hash = variable_key.replace('#', '')
@@ -42,6 +78,16 @@ class VariableTemplateParser:
         return variable_selectors
 
     def format(self, inputs: dict, remove_template_variables: bool = True) -> str:
+        """
+        Formats the template string by replacing the template variables with their corresponding values.
+
+        Args:
+            inputs: A dictionary containing the values for the template variables.
+            remove_template_variables: A boolean indicating whether to remove the template variables from the output.
+
+        Returns:
+            The formatted string with template variables replaced by their values.
+        """
         def replacer(match):
             key = match.group(1)
             value = inputs.get(key, match.group(0))  # return original matched string if key not found
@@ -59,4 +105,13 @@ class VariableTemplateParser:
 
     @classmethod
     def remove_template_variables(cls, text: str):
+        """
+        Removes the template variables from the given text.
+
+        Args:
+            text: The text from which to remove the template variables.
+
+        Returns:
+            The text with template variables removed.
+        """
         return re.sub(REGEX, r'{\1}', text)

api/docker/entrypoint.sh

@@ -4,7 +4,7 @@ set -e
 
 if [[ "${MIGRATION_ENABLED}" == "true" ]]; then
   echo "Running migrations"
-  flask db upgrade
+  flask upgrade-db
 fi
 
 if [[ "${MODE}" == "worker" ]]; then

api/events/event_handlers/__init__.py

@@ -5,6 +5,7 @@ from .create_installed_app_when_app_created import handle
 from .create_site_record_when_app_created import handle
 from .deduct_quota_when_messaeg_created import handle
 from .delete_installed_app_when_app_deleted import handle
+from .delete_site_record_when_app_deleted import handle
 from .delete_tool_parameters_cache_when_sync_draft_workflow import handle
 from .delete_workflow_as_tool_when_app_deleted import handle
 from .update_app_dataset_join_when_app_model_config_updated import handle

api/events/event_handlers/delete_site_record_when_app_deleted.py

@@ -0,0 +1,11 @@
+from events.app_event import app_was_deleted
+from extensions.ext_database import db
+from models.model import Site
+
+
+@app_was_deleted.connect
+def handle(sender, **kwargs):
+    app = sender
+    site = db.session.query(Site).filter(Site.app_id == app.id).first()
+    db.session.delete(site)
+    db.session.commit()

api/extensions/ext_storage.py

@@ -8,6 +8,7 @@ from extensions.storage.azure_storage import AzureStorage
 from extensions.storage.google_storage import GoogleStorage
 from extensions.storage.local_storage import LocalStorage
 from extensions.storage.s3_storage import S3Storage
+from extensions.storage.tencent_storage import TencentStorage
 
 
 class Storage:
@@ -32,6 +33,10 @@ class Storage:
             self.storage_runner = GoogleStorage(
                 app=app
             )
+        elif storage_type == 'tencent-cos':
+            self.storage_runner = TencentStorage(
+                app=app
+            )
         else:
             self.storage_runner = LocalStorage(app=app)
 

api/extensions/storage/tencent_storage.py

@@ -0,0 +1,48 @@
+from collections.abc import Generator
+
+from flask import Flask
+from qcloud_cos import CosConfig, CosS3Client
+
+from extensions.storage.base_storage import BaseStorage
+
+
+class TencentStorage(BaseStorage):
+    """Implementation for tencent cos storage.
+    """
+
+    def __init__(self, app: Flask):
+        super().__init__(app)
+        app_config = self.app.config
+        self.bucket_name = app_config.get('TENCENT_COS_BUCKET_NAME')
+        config = CosConfig(
+            Region=app_config.get('TENCENT_COS_REGION'),
+            SecretId=app_config.get('TENCENT_COS_SECRET_ID'),
+            SecretKey=app_config.get('TENCENT_COS_SECRET_KEY'),
+            Scheme=app_config.get('TENCENT_COS_SCHEME'),
+        )
+        self.client = CosS3Client(config)
+
+    def save(self, filename, data):
+        self.client.put_object(Bucket=self.bucket_name, Body=data, Key=filename)
+
+    def load_once(self, filename: str) -> bytes:
+        data = self.client.get_object(Bucket=self.bucket_name, Key=filename)['Body'].get_raw_stream().read()
+        return data
+
+    def load_stream(self, filename: str) -> Generator:
+        def generate(filename: str = filename) -> Generator:
+            response = self.client.get_object(Bucket=self.bucket_name, Key=filename)
+            while chunk := response['Body'].get_stream(chunk_size=4096):
+                yield chunk
+
+        return generate()
+
+    def download(self, filename, target_filepath):
+        response = self.client.get_object(Bucket=self.bucket_name, Key=filename)
+        response['Body'].get_stream_to_file(target_filepath)
+
+    def exists(self, filename):
+        return self.client.object_exists(Bucket=self.bucket_name, Key=filename)
+
+    def delete(self, filename):
+        self.client.delete_object(Bucket=self.bucket_name, Key=filename)

api/libs/helper.py

@@ -25,7 +25,7 @@ class TimestampField(fields.Raw):
 
 def email(email):
     # Define a regex pattern for email addresses
-    pattern = r"^[\w\.-]+@([\w-]+\.)+[\w-]{2,}$"
+    pattern = r"^[\w\.!#$%&'*+\-/=?^_`{|}~]+@([\w-]+\.)+[\w-]{2,}$"
     # Check if the email matches the pattern
     if re.match(pattern, email) is not None:
         return email

api/migrations/README

@@ -1,2 +1 @@
 Single-database configuration for Flask.
-

api/poetry.lock

@@ -1088,13 +1088,13 @@ numpy = "*"
 
 [[package]]
 name = "chromadb"
-version = "0.5.0"
+version = "0.5.1"
 description = "Chroma."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "chromadb-0.5.0-py3-none-any.whl", hash = "sha256:8193dc65c143b61d8faf87f02c44ecfa778d471febd70de517f51c5d88a06009"},
-    {file = "chromadb-0.5.0.tar.gz", hash = "sha256:7954af614a9ff7b2902ddbd0a162f33f7ec0669e2429903905c4f7876d1f766f"},
+    {file = "chromadb-0.5.1-py3-none-any.whl", hash = "sha256:61f1f75a672b6edce7f1c8875c67e2aaaaf130dc1c1684431fbc42ad7240d01d"},
+    {file = "chromadb-0.5.1.tar.gz", hash = "sha256:e2b2b6a34c2a949bedcaa42fa7775f40c7f6667848fc8094dcbf97fc0d30bee7"},
 ]
 
 [package.dependencies]
@@ -1103,10 +1103,11 @@ build = ">=1.0.3"
 chroma-hnswlib = "0.7.3"
 fastapi = ">=0.95.2"
 grpcio = ">=1.58.0"
+httpx = ">=0.27.0"
 importlib-resources = "*"
 kubernetes = ">=28.1.0"
 mmh3 = ">=4.0.1"
-numpy = ">=1.22.5"
+numpy = ">=1.22.5,<2.0.0"
 onnxruntime = ">=1.14.1"
 opentelemetry-api = ">=1.2.0"
 opentelemetry-exporter-otlp-proto-grpc = ">=1.2.0"
@@ -1441,12 +1442,12 @@ test-no-images = ["pytest", "pytest-cov", "pytest-xdist", "wurlitzer"]
 
 [[package]]
 name = "cos-python-sdk-v5"
-version = "1.9.29"
+version = "1.9.30"
 description = "cos-python-sdk-v5"
 optional = false
 python-versions = "*"
 files = [
-    {file = "cos-python-sdk-v5-1.9.29.tar.gz", hash = "sha256:1bb07022368d178e7a50a3cc42e0d6cbf4b0bef2af12a3bb8436904339cdec8e"},
+    {file = "cos-python-sdk-v5-1.9.30.tar.gz", hash = "sha256:a23fd090211bf90883066d90cd74317860aa67c6d3aa80fe5e44b18c7e9b2a81"},
 ]
 
 [package.dependencies]
@@ -1636,6 +1637,22 @@ tiktoken = {version = "*", optional = true, markers = "extra == \"tokenizer\""}
 [package.extras]
 tokenizer = ["tiktoken"]
 
+[[package]]
+name = "dataclass-wizard"
+version = "0.22.3"
+description = "Marshal dataclasses to/from JSON. Use field properties with initial values. Construct a dataclass schema with JSON input."
+optional = false
+python-versions = "*"
+files = [
+    {file = "dataclass-wizard-0.22.3.tar.gz", hash = "sha256:4c46591782265058f1148cfd1f54a3a91221e63986fdd04c9d59f4ced61f4424"},
+    {file = "dataclass_wizard-0.22.3-py2.py3-none-any.whl", hash = "sha256:63751203e54b9b9349212cc185331da73c1adc99c51312575eb73bb5c00c1962"},
+]
+
+[package.extras]
+dev = ["Sphinx (==5.3.0)", "bump2version (==1.0.1)", "coverage (>=6.2)", "dataclass-factory (==2.12)", "dataclasses-json (==0.5.6)", "flake8 (>=3)", "jsons (==1.6.1)", "pip (>=21.3.1)", "pytest (==7.0.1)", "pytest-cov (==3.0.0)", "pytest-mock (>=3.6.1)", "pytimeparse (==1.1.8)", "sphinx-issues (==3.0.1)", "sphinx-issues (==4.0.0)", "tox (==3.24.5)", "twine (==3.8.0)", "watchdog[watchmedo] (==2.1.6)", "wheel (==0.37.1)", "wheel (==0.42.0)"]
+timedelta = ["pytimeparse (>=1.1.7)"]
+yaml = ["PyYAML (>=5.3)"]
+
 [[package]]
 name = "dataclasses"
 version = "0.6"
@@ -3381,24 +3398,24 @@ lxml = ["lxml"]
 
 [[package]]
 name = "httpcore"
-version = "0.17.3"
+version = "1.0.5"
 description = "A minimal low-level HTTP client."
 optional = false
-python-versions = ">=3.7"
+python-versions = ">=3.8"
 files = [
-    {file = "httpcore-0.17.3-py3-none-any.whl", hash = "sha256:c2789b767ddddfa2a5782e3199b2b7f6894540b17b16ec26b2c4d8e103510b87"},
-    {file = "httpcore-0.17.3.tar.gz", hash = "sha256:a6f30213335e34c1ade7be6ec7c47f19f50c56db36abef1a9dfa3815b1cb3888"},
+    {file = "httpcore-1.0.5-py3-none-any.whl", hash = "sha256:421f18bac248b25d310f3cacd198d55b8e6125c107797b609ff9b7a6ba7991b5"},
+    {file = "httpcore-1.0.5.tar.gz", hash = "sha256:34a38e2f9291467ee3b44e89dd52615370e152954ba21721378a87b2960f7a61"},
 ]
 
 [package.dependencies]
-anyio = ">=3.0,<5.0"
 certifi = "*"
 h11 = ">=0.13,<0.15"
-sniffio = "==1.*"
 
 [package.extras]
+asyncio = ["anyio (>=4.0,<5.0)"]
 http2 = ["h2 (>=3,<5)"]
 socks = ["socksio (==1.*)"]
+trio = ["trio (>=0.22.0,<0.26.0)"]
 
 [[package]]
 name = "httplib2"
@@ -3464,19 +3481,20 @@ test = ["Cython (>=0.29.24,<0.30.0)"]
 
 [[package]]
 name = "httpx"
-version = "0.24.1"
+version = "0.27.0"
 description = "The next generation HTTP client."
 optional = false
-python-versions = ">=3.7"
+python-versions = ">=3.8"
 files = [
-    {file = "httpx-0.24.1-py3-none-any.whl", hash = "sha256:06781eb9ac53cde990577af654bd990a4949de37a28bdb4a230d434f3a30b9bd"},
-    {file = "httpx-0.24.1.tar.gz", hash = "sha256:5853a43053df830c20f8110c5e69fe44d035d850b2dfe795e196f00fdb774bdd"},
+    {file = "httpx-0.27.0-py3-none-any.whl", hash = "sha256:71d5465162c13681bff01ad59b2cc68dd838ea1f10e51574bac27103f00c91a5"},
+    {file = "httpx-0.27.0.tar.gz", hash = "sha256:a0cb88a46f32dc874e04ee956e4c2764aba2aa228f650b06788ba6bda2962ab5"},
 ]
 
 [package.dependencies]
+anyio = "*"
 certifi = "*"
 h2 = {version = ">=3,<5", optional = true, markers = "extra == \"http2\""}
-httpcore = ">=0.15.0,<0.18.0"
+httpcore = "==1.*"
 idna = "*"
 sniffio = "*"
 socksio = {version = "==1.*", optional = true, markers = "extra == \"socks\""}
@@ -4615,6 +4633,22 @@ plot = ["matplotlib"]
 tgrep = ["pyparsing"]
 twitter = ["twython"]
 
+[[package]]
+name = "novita-client"
+version = "0.5.6"
+description = "novita SDK for Python"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "novita_client-0.5.6-py3-none-any.whl", hash = "sha256:9fa6cfd12f13a75c7da42b27f811a560b0320da24cf256480f517bde479bc57c"},
+    {file = "novita_client-0.5.6.tar.gz", hash = "sha256:2e4d956903d5da39d43127a41dcb020ae40322d2a6196413071b94b3d6988b98"},
+]
+
+[package.dependencies]
+dataclass-wizard = ">=0.22.2"
+pillow = ">=10.2.0"
+requests = ">=2.27.1"
+
 [[package]]
 name = "numba"
 version = "0.59.1"
@@ -6380,7 +6414,6 @@ files = [
     {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"},
     {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"},
     {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"},
-    {file = "PyYAML-6.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:326c013efe8048858a6d312ddd31d56e468118ad4cdeda36c719bf5bb6192290"},
     {file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"},
     {file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"},
     {file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"},
@@ -6388,16 +6421,8 @@ files = [
     {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"},
     {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"},
     {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"},
-    {file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"},
     {file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"},
     {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
-    {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
-    {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
-    {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a08c6f0fe150303c1c6b71ebcd7213c2858041a7e01975da3a99aed1e7a378ef"},
-    {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
-    {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
-    {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
-    {file = "PyYAML-6.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:0d3304d8c0adc42be59c5f8a4d9e3d7379e6955ad754aa9d6ab7a398b59dd1df"},
     {file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"},
     {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"},
     {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"},
@@ -6414,7 +6439,6 @@ files = [
     {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"},
     {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"},
     {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"},
-    {file = "PyYAML-6.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49a183be227561de579b4a36efbb21b3eab9651dd81b1858589f796549873dd6"},
     {file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"},
     {file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"},
     {file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"},
@@ -6422,7 +6446,6 @@ files = [
     {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"},
     {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"},
     {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"},
-    {file = "PyYAML-6.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:04ac92ad1925b2cff1db0cfebffb6ffc43457495c9b3c39d3fcae417d7125dc5"},
     {file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"},
     {file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"},
     {file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"},
@@ -8921,4 +8944,4 @@ testing = ["coverage (>=5.0.3)", "zope.event", "zope.testing"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "e967aa4b61dc7c40f2f50eb325038da1dc0ff633d8f778e7a7560bdabce744dc"
+content-hash = "21360e271c46e0368b8e3bd26287caca73145a73ee73287669f91e7eac6f05b9"

api/pyproject.toml

@@ -1,12 +1,17 @@
 [project]
 requires-python = ">=3.10"
 
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
 [tool.ruff]
 exclude = [
 ]
 line-length = 120
 
 [tool.ruff.lint]
+preview = true
 select = [
     "B", # flake8-bugbear rules
     "F", # pyflakes rules
@@ -77,17 +82,10 @@ MOCK_SWITCH = "true"
 CODE_MAX_STRING_LENGTH = "80000"
 CODE_EXECUTION_ENDPOINT="http://127.0.0.1:8194"
 CODE_EXECUTION_API_KEY="dify-sandbox"
-
 FIRECRAWL_API_KEY = "fc-"
 
-
-
 [tool.poetry]
 name = "dify-api"
-version = "0.6.11"
-description = ""
-authors = ["Dify <hello@dify.ai>"]
-readme = "README.md"
 package-mode = false
 
 [tool.poetry.dependencies]
@@ -155,7 +153,7 @@ numpy = "~1.26.4"
 unstructured = {version = "~0.10.27", extras = ["docx", "epub", "md", "msg", "ppt", "pptx"]}
 bs4 = "~0.0.1"
 markdown = "~3.5.1"
-httpx = {version = "~0.24.1", extras = ["socks"]}
+httpx = {version = "~0.27.0", extras = ["socks"]}
 matplotlib = "~3.8.2"
 yfinance = "~0.2.40"
 pydub = "~0.25.1"
@@ -183,7 +181,10 @@ vanna = {version = "0.5.5", extras = ["postgres", "mysql", "clickhouse", "duckdb
 kaleido = "0.2.1"
 tencentcloud-sdk-python-hunyuan = "~3.0.1158"
 tcvectordb = "1.3.2"
-chromadb = "~0.5.0"
+chromadb = "~0.5.1"
+tenacity = "~8.3.0"
+cos-python-sdk-v5 = "1.9.30"
+novita-client = "^0.5.6"
 
 [tool.poetry.group.dev]
 optional = true

api/requirements.txt

@@ -61,7 +61,7 @@ numpy~=1.26.4
 unstructured[docx,pptx,msg,md,ppt,epub]~=0.10.27
 bs4~=0.0.1
 markdown~=3.5.1
-httpx[socks]~=0.24.1
+httpx[socks]~=0.27.0
 matplotlib~=3.8.2
 yfinance~=0.2.40
 pydub~=0.25.1
@@ -87,4 +87,7 @@ tidb-vector==0.0.9
 google-cloud-aiplatform==1.49.0
 vanna[postgres,mysql,clickhouse,duckdb]==0.5.5
 tencentcloud-sdk-python-hunyuan~=3.0.1158
-chromadb~=0.5.0
+chromadb~=0.5.1
+novita_client~=0.5.6
+tenacity~=8.3.0
+cos-python-sdk-v5==1.9.30

api/services/file_service.py

@@ -31,7 +31,10 @@ class FileService:
 
     @staticmethod
     def upload_file(file: FileStorage, user: Union[Account, EndUser], only_image: bool = False) -> UploadFile:
+        filename = file.filename
         extension = file.filename.split('.')[-1]
+        if len(filename) > 200:
+            filename = filename.split('.')[0][:200] + '.' + extension
         etl_type = current_app.config['ETL_TYPE']
         allowed_extensions = UNSTRUSTURED_ALLOWED_EXTENSIONS + IMAGE_EXTENSIONS if etl_type == 'Unstructured' \
             else ALLOWED_EXTENSIONS + IMAGE_EXTENSIONS
@@ -75,7 +78,7 @@ class FileService:
             tenant_id=current_tenant_id,
             storage_type=config['STORAGE_TYPE'],
             key=file_key,
-            name=file.filename,
+            name=filename,
             size=file_size,
             extension=extension,
             mime_type=file.mimetype,
@@ -93,6 +96,8 @@ class FileService:
 
     @staticmethod
     def upload_text(text: str, text_name: str) -> UploadFile:
+        if len(text_name) > 200:
+            text_name = text_name[:200]
         # user uuid as file name
         file_uuid = str(uuid.uuid4())
         file_key = 'upload_files/' + current_user.current_tenant_id + '/' + file_uuid + '.txt'

api/tests/unit_tests/libs/test_email.py

@@ -0,0 +1,25 @@
+from libs.helper import email
+
+
+def test_email_with_valid_email():
+    assert email("test@example.com") == "test@example.com"
+    assert email("TEST12345@example.com") == "TEST12345@example.com"
+    assert email("test+test@example.com") == "test+test@example.com"
+    assert email("!#$%&'*+-/=?^_{|}~`@example.com") == "!#$%&'*+-/=?^_{|}~`@example.com"
+
+
+def test_email_with_invalid_email():
+    try:
+        email("invalid_email")
+    except ValueError as e:
+        assert str(e) == "invalid_email is not a valid email."
+
+    try:
+        email("@example.com")
+    except ValueError as e:
+        assert str(e) == "@example.com is not a valid email."
+
+    try:
+        email("()@example.com")
+    except ValueError as e:
+        assert str(e) == "()@example.com is not a valid email."

dev/reformat

@@ -9,7 +9,7 @@ if ! command -v ruff &> /dev/null; then
 fi
 
 # run ruff linter
-ruff check --fix --preview ./api
+ruff check --fix ./api
 
 # env files linting relies on `dotenv-linter` in path
 if ! command -v dotenv-linter &> /dev/null; then

docker/docker-compose.chroma.yaml

@@ -2,7 +2,7 @@ version: '3'
 services:
   # Chroma vector store.
   chroma:
-    image: ghcr.io/chroma-core/chroma:0.5.0
+    image: ghcr.io/chroma-core/chroma:0.5.1
     restart: always
     volumes:
       - ./volumes/chroma:/chroma/chroma

docker/docker-compose.yaml

@@ -96,6 +96,12 @@ services:
       GOOGLE_STORAGE_BUCKET_NAME: 'yout-bucket-name'
       # if you want to use Application Default Credentials, you can leave GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64 empty.
       GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64: 'your-google-service-account-json-base64-string'
+      # The Tencent COS storage configurations, only available when STORAGE_TYPE is `tencent-cos`.
+      TENCENT_COS_BUCKET_NAME: 'your-bucket-name'
+      TENCENT_COS_SECRET_KEY: 'your-secret-key'
+      TENCENT_COS_SECRET_ID: 'your-secret-id'
+      TENCENT_COS_REGION: 'your-region'
+      TENCENT_COS_SCHEME: 'your-scheme'
       # The type of vector store to use. Supported values are `weaviate`, `qdrant`, `milvus`, `relyt`.
       VECTOR_STORE: weaviate
       # The Weaviate endpoint URL. Only available when VECTOR_STORE is `weaviate`.
@@ -252,6 +258,12 @@ services:
       GOOGLE_STORAGE_BUCKET_NAME: 'yout-bucket-name'
       # if you want to use Application Default Credentials, you can leave GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64 empty.
       GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64: 'your-google-service-account-json-base64-string'
+      # The Tencent COS storage configurations, only available when STORAGE_TYPE is `tencent-cos`.
+      TENCENT_COS_BUCKET_NAME: 'your-bucket-name'
+      TENCENT_COS_SECRET_KEY: 'your-secret-key'
+      TENCENT_COS_SECRET_ID: 'your-secret-id'
+      TENCENT_COS_REGION: 'your-region'
+      TENCENT_COS_SCHEME: 'your-scheme'
       # The type of vector store to use. Supported values are `weaviate`, `qdrant`, `milvus`, `relyt`, `pgvector`.
       VECTOR_STORE: weaviate
       # The Weaviate endpoint URL. Only available when VECTOR_STORE is `weaviate`.

web/README.md

@@ -1,8 +1,11 @@
 # Dify Frontend
+
 This is a [Next.js](https://nextjs.org/) project bootstrapped with [`create-next-app`](https://github.com/vercel/next.js/tree/canary/packages/create-next-app).
 
 ## Getting Started
+
 ### Run by source code
+
 To start the web frontend service, you will need [Node.js v18.x (LTS)](https://nodejs.org/en) and [NPM version 8.x.x](https://www.npmjs.com/) or [Yarn](https://yarnpkg.com/).
 
 First, install the dependencies:
@@ -14,6 +17,7 @@ yarn install --frozen-lockfile
 ```
 
 Then, configure the environment variables. Create a file named `.env.local` in the current directory and copy the contents from `.env.example`. Modify the values of these environment variables according to your requirements:
+
 ```
 # For production release, change this to PRODUCTION
 NEXT_PUBLIC_DEPLOY_ENV=DEVELOPMENT
@@ -45,27 +49,35 @@ Open [http://localhost:3000](http://localhost:3000) with your browser to see the
 You can start editing the file under folder `app`. The page auto-updates as you edit the file.
 
 ## Deploy
+
 ### Deploy on server
+
 First, build the app for production:
+
 ```bash
 npm run build
 ```
 
 Then, start the server:
+
 ```bash
 npm run start
 ```
 
 If you want to customize the host and port:
+
 ```bash
 npm run start --port=3001 --host=0.0.0.0
 ```
 
 ## Lint Code
+
 If your IDE is VSCode, rename `web/.vscode/settings.example.json` to `web/.vscode/settings.json` for lint code setting.
 
 ## Documentation
-Visit https://docs.dify.ai/getting-started/readme to view the full documentation.
+
+Visit <https://docs.dify.ai/getting-started/readme> to view the full documentation.
 
 ## Community
+
 The Dify community can be found on [Discord community](https://discord.gg/5AEfbxcd9k), where you can ask questions, voice ideas, and share your projects.

web/app/(commonLayout)/apps/AppCard.tsx

@@ -279,27 +279,27 @@ const AppCard = ({ app, onRefresh }: AppCardProps) => {
           'items-center shrink-0 mt-1 pt-1 pl-[14px] pr-[6px] pb-[6px] h-[42px]',
           tags.length ? 'flex' : '!hidden group-hover:!flex',
         )}>
-          <div className={cn('grow flex items-center gap-1 w-0')} onClick={(e) => {
-            e.stopPropagation()
-            e.preventDefault()
-          }}>
-            <div className={cn(
-              'group-hover:!block group-hover:!mr-0 mr-[41px] grow w-full',
-              tags.length ? '!block' : '!hidden',
-            )}>
-              <TagSelector
-                position='bl'
-                type='app'
-                targetID={app.id}
-                value={tags.map(tag => tag.id)}
-                selectedTags={tags}
-                onCacheUpdate={setTags}
-                onChange={onRefresh}
-              />
-            </div>
-          </div>
           {isCurrentWorkspaceEditor && (
             <>
+              <div className={cn('grow flex items-center gap-1 w-0')} onClick={(e) => {
+                e.stopPropagation()
+                e.preventDefault()
+              }}>
+                <div className={cn(
+                  'group-hover:!block group-hover:!mr-0 mr-[41px] grow w-full',
+                  tags.length ? '!block' : '!hidden',
+                )}>
+                  <TagSelector
+                    position='bl'
+                    type='app'
+                    targetID={app.id}
+                    value={tags.map(tag => tag.id)}
+                    selectedTags={tags}
+                    onCacheUpdate={setTags}
+                    onChange={onRefresh}
+                  />
+                </div>
+              </div>
               <div className='!hidden group-hover:!flex shrink-0 mx-1 w-[1px] h-[14px] bg-gray-200'/>
               <div className='!hidden group-hover:!flex shrink-0'>
                 <CustomPopover

web/app/activate/activateForm.tsx

@@ -86,7 +86,7 @@ const ActivateForm = () => {
           timezone,
         },
       })
-      setLocaleOnClient(language.startsWith('en') ? 'en-US' : 'zh-Hans', false)
+      setLocaleOnClient(language, false)
       setShowSuccess(true)
     }
     catch {

web/app/components/app-sidebar/app-info.tsx

@@ -16,7 +16,7 @@ import Divider from '@/app/components/base/divider'
 import Confirm from '@/app/components/base/confirm'
 import { useStore as useAppStore } from '@/app/components/app/store'
 import { ToastContext } from '@/app/components/base/toast'
-import AppsContext from '@/context/app-context'
+import AppsContext, { useAppContext } from '@/context/app-context'
 import { useProviderContext } from '@/context/provider-context'
 import { copyApp, deleteApp, exportAppConfig, updateAppInfo } from '@/service/apps'
 import DuplicateAppModal from '@/app/components/app/duplicate-modal'
@@ -142,6 +142,8 @@ const AppInfo = ({ expand }: IAppInfoProps) => {
     setShowConfirmDelete(false)
   }, [appDetail, mutateApps, notify, onPlanInfoChanged, replace, t])
 
+  const { isCurrentWorkspaceEditor } = useAppContext()
+
   if (!appDetail)
     return null
 
@@ -154,10 +156,13 @@ const AppInfo = ({ expand }: IAppInfoProps) => {
     >
       <div className='relative'>
         <PortalToFollowElemTrigger
-          onClick={() => setOpen(v => !v)}
+          onClick={() => {
+            if (isCurrentWorkspaceEditor)
+              setOpen(v => !v)
+          }}
           className='block'
         >
-          <div className={cn('flex cursor-pointer p-1 rounded-lg hover:bg-gray-100', open && 'bg-gray-100')}>
+          <div className={cn('flex p-1 rounded-lg', open && 'bg-gray-100', isCurrentWorkspaceEditor && 'hover:bg-gray-100 cursor-pointer')}>
             <div className='relative shrink-0 mr-2'>
               <AppIcon size={expand ? 'large' : 'small'} icon={appDetail.icon} background={appDetail.icon_background} />
               <span className={cn(
@@ -185,7 +190,7 @@ const AppInfo = ({ expand }: IAppInfoProps) => {
               <div className="grow w-0">
                 <div className='flex justify-between items-center text-sm leading-5 font-medium text-gray-900'>
                   <div className='truncate' title={appDetail.name}>{appDetail.name}</div>
-                  <ChevronDown className='shrink-0 ml-[2px] w-3 h-3 text-gray-500' />
+                  {isCurrentWorkspaceEditor && <ChevronDown className='shrink-0 ml-[2px] w-3 h-3 text-gray-500' />}
                 </div>
                 <div className='flex items-center text-[10px] leading-[18px] font-medium text-gray-500 gap-1'>
                   {appDetail.mode === 'advanced-chat' && (

web/app/components/app/annotation/batch-add-annotation-modal/index.tsx

@@ -87,7 +87,7 @@ const BatchModal: FC<IBatchModalProps> = ({
   }
 
   return (
-    <Modal isShow={isShow} onClose={() => { }} wrapperClassName='!z-[20]' className='px-8 py-6 !max-w-[520px] !rounded-xl'>
+    <Modal isShow={isShow} onClose={() => { }} className='px-8 py-6 !max-w-[520px] !rounded-xl'>
       <div className='relative pb-1 text-xl font-medium leading-[30px] text-gray-900'>{t('appAnnotation.batchModal.title')}</div>
       <div className='absolute right-4 top-4 p-2 cursor-pointer' onClick={onCancel}>
         <XClose className='w-4 h-4 text-gray-500' />

web/app/components/app/configuration/config-prompt/conversation-histroy/edit-modal.tsx

@@ -27,7 +27,6 @@ const EditModal: FC<Props> = ({
       title={t('appDebug.feature.conversationHistory.editModal.title')}
       isShow={isShow}
       onClose={onClose}
-      wrapperClassName='!z-[101]'
     >
       <div className={'mt-6 font-medium text-sm leading-[21px] text-gray-900'}>{t('appDebug.feature.conversationHistory.editModal.userPrefix')}</div>
       <input className={'mt-2 w-full rounded-lg h-10 box-border px-3 text-sm leading-10 bg-gray-100'}

web/app/components/app/configuration/config-var/config-modal/index.tsx

@@ -132,7 +132,6 @@ const ConfigModal: FC<IConfigModalProps> = ({
       title={t(`appDebug.variableConig.${isCreate ? 'addModalTitle' : 'editModalTitle'}`)}
       isShow={isShow}
       onClose={onClose}
-      wrapperClassName='!z-[100]'
     >
       <div className='mb-8'>
         <div className='space-y-2'>

web/app/components/app/configuration/dataset-config/select-dataset/index.tsx

@@ -94,7 +94,6 @@ const SelectDataSet: FC<ISelectDataSetProps> = ({
       isShow={isShow}
       onClose={onClose}
       className='w-[400px]'
-      wrapperClassName='!z-[101]'
       title={t('appDebug.feature.dataSet.selectTitle')}
     >
       {!loaded && (

web/app/components/app/configuration/tools/external-data-tool-modal.tsx

@@ -186,7 +186,6 @@ const ExternalDataToolModal: FC<ExternalDataToolModalProps> = ({
     <Modal
       isShow
       onClose={() => { }}
-      wrapperClassName='z-[101]'
       className='!p-8 !pb-6 !max-w-none !w-[640px]'
     >
       <div className='mb-2 text-xl font-semibold text-gray-900'>
@@ -287,7 +286,6 @@ const ExternalDataToolModal: FC<ExternalDataToolModalProps> = ({
       {
         showEmojiPicker && (
           <EmojiPicker
-            className='!z-[200]'
             onSelect={(icon, icon_background) => {
               handleValueChange({ icon, icon_background })
               setShowEmojiPicker(false)

web/app/components/app/create-app-modal/index.tsx

@@ -83,7 +83,6 @@ const CreateAppModal = ({ show, onSuccess, onClose }: CreateAppDialogProps) => {
   return (
     <Modal
       overflowVisible
-      wrapperClassName='z-20'
       className='!p-0 !max-w-[720px] !w-[720px] rounded-xl'
       isShow={show}
       onClose={() => {}}

web/app/components/app/create-from-dsl-modal/index.tsx

@@ -78,7 +78,6 @@ const CreateFromDSLModal = ({ show, onSuccess, onClose }: CreateFromDSLModalProp
 
   return (
     <Modal
-      wrapperClassName='z-20'
       className='px-8 py-6 max-w-[520px] w-[520px] rounded-xl'
       isShow={show}
       onClose={() => {}}

web/app/components/app/switch-app-modal/index.tsx

@@ -87,7 +87,6 @@ const SwitchAppModal = ({ show, appDetail, inAppDetail = false, onSuccess, onClo
   return (
     <>
       <Modal
-        wrapperClassName='z-20'
         className={cn('p-8 max-w-[600px] w-[600px]', s.bg)}
         isShow={show}
         onClose={() => {}}

web/app/components/base/emoji-picker/index.tsx

@@ -86,7 +86,7 @@ const EmojiPicker: FC<IEmojiPickerProps> = ({
     onClose={() => { }}
     isShow
     closable={false}
-    wrapperClassName={`!z-50 ${className}`}
+    wrapperClassName={className}
     className={cn(s.container, '!w-[362px] !p-0')}
   >
     <div className='flex flex-col items-center w-full p-3'>

web/app/components/base/icons/assets/public/llm/microsoft.svg

@@ -1,5 +1,5 @@
 <svg width="21" height="22" viewBox="0 0 21 22" fill="none" xmlns="http://www.w3.org/2000/svg">
-<g id="Microsfot">
+<g id="Microsoft">
 <rect id="Rectangle 1010" y="0.5" width="10" height="10" fill="#EF4F21"/>
 <rect id="Rectangle 1012" y="11.5" width="10" height="10" fill="#03A4EE"/>
 <rect id="Rectangle 1011" x="11" y="0.5" width="10" height="10" fill="#7EB903"/>