update text spliter

Signed-off-by: yihong0618 <zouzou0208@gmail.com>

.devcontainer/Dockerfile

@@ -1,5 +1,5 @@
-FROM mcr.microsoft.com/devcontainers/python:3.10
+FROM mcr.microsoft.com/devcontainers/python:3.12
 
 # [Optional] Uncomment this section to install additional OS packages.
 # RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
-#     && apt-get -y install --no-install-recommends <your-package-list-here>
+#     && apt-get -y install --no-install-recommends <your-package-list-here>

.devcontainer/devcontainer.json

@@ -1,7 +1,7 @@
 // For format details, see https://aka.ms/devcontainer.json. For config options, see the
 // README at: https://github.com/devcontainers/templates/tree/main/src/anaconda
 {
-	"name": "Python 3.10",
+	"name": "Python 3.12",
 	"build": { 
 		"context": "..",
 		"dockerfile": "Dockerfile"

.github/actions/setup-poetry/action.yml

@@ -4,7 +4,7 @@ inputs:
   python-version:
     description: Python version to use and the Poetry installed with
     required: true
-    default: '3.10'
+    default: '3.11'
   poetry-version:
     description: Poetry version to set up
     required: true

.github/workflows/api-tests.yml

@@ -20,7 +20,6 @@ jobs:
     strategy:
       matrix:
         python-version:
-          - "3.10"
           - "3.11"
           - "3.12"
 

.github/workflows/vdb-tests.yml

@@ -8,6 +8,8 @@ on:
       - api/core/rag/datasource/**
       - docker/**
       - .github/workflows/vdb-tests.yml
+      - api/poetry.lock
+      - api/pyproject.toml
 
 concurrency:
   group: vdb-tests-${{ github.head_ref || github.run_id }}
@@ -20,7 +22,6 @@ jobs:
     strategy:
       matrix:
         python-version:
-          - "3.10"
           - "3.11"
           - "3.12"
 

CONTRIBUTING.md

@@ -1,6 +1,8 @@
+# CONTRIBUTING
+
 So you're looking to contribute to Dify - that's awesome, we can't wait to see what you do. As a startup with limited headcount and funding, we have grand ambitions to design the most intuitive workflow for building and managing LLM applications. Any help from the community counts, truly.
 
-We need to be nimble and ship fast given where we are, but we also want to make sure that contributors like you get as smooth an experience at contributing as possible. We've assembled this contribution guide for that purpose, aiming at getting you familiarized with the codebase & how we work with contributors, so you could quickly jump to the fun part. 
+We need to be nimble and ship fast given where we are, but we also want to make sure that contributors like you get as smooth an experience at contributing as possible. We've assembled this contribution guide for that purpose, aiming at getting you familiarized with the codebase & how we work with contributors, so you could quickly jump to the fun part.
 
 This guide, like Dify itself, is a constant work in progress. We highly appreciate your understanding if at times it lags behind the actual project, and welcome any feedback for us to improve.
 
@@ -10,14 +12,12 @@ In terms of licensing, please take a minute to read our short [License and Contr
 
 [Find](https://github.com/langgenius/dify/issues?q=is:issue+is:open) an existing issue, or [open](https://github.com/langgenius/dify/issues/new/choose) a new one. We categorize issues into 2 types:
 
-### Feature requests:
+### Feature requests
 
 * If you're opening a new feature request, we'd like you to explain what the proposed feature achieves, and include as much context as possible. [@perzeusss](https://github.com/perzeuss) has made a solid [Feature Request Copilot](https://udify.app/chat/MK2kVSnw1gakVwMX) that helps you draft out your needs. Feel free to give it a try.
 
 * If you want to pick one up from the existing issues, simply drop a comment below it saying so.
 
-  
-
   A team member working in the related direction will be looped in. If all looks good, they will give the go-ahead for you to start coding. We ask that you hold off working on the feature until then, so none of your work goes to waste should we propose changes.
 
   Depending on whichever area the proposed feature falls under, you might talk to different team members. Here's rundown of the areas each our team members are working on at the moment:
@@ -40,7 +40,7 @@ In terms of licensing, please take a minute to read our short [License and Contr
   | Non-core features and minor enhancements                     | Low Priority    |
   | Valuable but not immediate                                   | Future-Feature  |
 
-### Anything else (e.g. bug report, performance optimization, typo correction):
+### Anything else (e.g. bug report, performance optimization, typo correction)
 
 * Start coding right away.
 
@@ -52,7 +52,6 @@ In terms of licensing, please take a minute to read our short [License and Contr
   | Non-critical bugs, performance boosts                        | Medium Priority |
   | Minor fixes (typos, confusing but working UI)                | Low Priority    |
 
-
 ## Installing
 
 Here are the steps to set up Dify for development:
@@ -63,7 +62,7 @@ Here are the steps to set up Dify for development:
 
  Clone the forked repository from your terminal:
 
-```
+```shell
 git clone git@github.com:<github_username>/dify.git
 ```
 
@@ -71,11 +70,11 @@ git clone git@github.com:<github_username>/dify.git
 
 Dify requires the following dependencies to build, make sure they're installed on your system:
 
-- [Docker](https://www.docker.com/)
+* [Docker](https://www.docker.com/)
-- [Docker Compose](https://docs.docker.com/compose/install/)
+* [Docker Compose](https://docs.docker.com/compose/install/)
-- [Node.js v18.x (LTS)](http://nodejs.org)
+* [Node.js v18.x (LTS)](http://nodejs.org)
-- [npm](https://www.npmjs.com/) version 8.x.x or [Yarn](https://yarnpkg.com/)
+* [npm](https://www.npmjs.com/) version 8.x.x or [Yarn](https://yarnpkg.com/)
-- [Python](https://www.python.org/) version 3.10.x
+* [Python](https://www.python.org/) version 3.11.x or 3.12.x
 
 ### 4. Installations
 
@@ -85,7 +84,7 @@ Check the [installation FAQ](https://docs.dify.ai/learn-more/faq/install-faq) fo
 
 ### 5. Visit dify in your browser
 
-To validate your set up, head over to [http://localhost:3000](http://localhost:3000) (the default, or your self-configured URL and port) in your browser. You should now see Dify up and running. 
+To validate your set up, head over to [http://localhost:3000](http://localhost:3000) (the default, or your self-configured URL and port) in your browser. You should now see Dify up and running.
 
 ## Developing
 
@@ -97,9 +96,9 @@ To help you quickly navigate where your contribution fits, a brief, annotated ou
 
 ### Backend
 
-Dify’s backend is written in Python using [Flask](https://flask.palletsprojects.com/en/3.0.x/). It uses [SQLAlchemy](https://www.sqlalchemy.org/) for ORM and [Celery](https://docs.celeryq.dev/en/stable/getting-started/introduction.html) for task queueing. Authorization logic goes via Flask-login. 
+Dify’s backend is written in Python using [Flask](https://flask.palletsprojects.com/en/3.0.x/). It uses [SQLAlchemy](https://www.sqlalchemy.org/) for ORM and [Celery](https://docs.celeryq.dev/en/stable/getting-started/introduction.html) for task queueing. Authorization logic goes via Flask-login.
 
-```
+```text
 [api/]
 ├── constants             // Constant settings used throughout code base.
 ├── controllers           // API route definitions and request handling logic.           
@@ -121,7 +120,7 @@ Dify’s backend is written in Python using [Flask](https://flask.palletsproject
 
 The website is bootstrapped on [Next.js](https://nextjs.org/) boilerplate in Typescript and uses [Tailwind CSS](https://tailwindcss.com/) for styling. [React-i18next](https://react.i18next.com/) is used for internationalization.
 
-```
+```text
 [web/]
 ├── app                   // layouts, pages, and components
 │   ├── (commonLayout)    // common layout used throughout the app
@@ -149,10 +148,10 @@ The website is bootstrapped on [Next.js](https://nextjs.org/) boilerplate in Typ
 
 ## Submitting your PR
 
-At last, time to open a pull request (PR) to our repo. For major features, we first merge them into the `deploy/dev` branch for testing, before they go into the `main` branch. If you run into issues like merge conflicts or don't know how to open a pull request, check out [GitHub's pull request tutorial](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests). 
+At last, time to open a pull request (PR) to our repo. For major features, we first merge them into the `deploy/dev` branch for testing, before they go into the `main` branch. If you run into issues like merge conflicts or don't know how to open a pull request, check out [GitHub's pull request tutorial](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests).
 
 And that's it! Once your PR is merged, you will be featured as a contributor in our [README](https://github.com/langgenius/dify/blob/main/README.md).
 
 ## Getting Help
 
-If you ever get stuck or got a burning question while contributing, simply shoot your queries our way via the related GitHub issue, or hop onto our [Discord](https://discord.gg/8Tpq4AcN9c) for a quick chat. 
+If you ever get stuck or got a burning question while contributing, simply shoot your queries our way via the related GitHub issue, or hop onto our [Discord](https://discord.gg/8Tpq4AcN9c) for a quick chat.

CONTRIBUTING_CN.md

@@ -71,7 +71,7 @@ Dify 依赖以下工具和库：
 - [Docker Compose](https://docs.docker.com/compose/install/)
 - [Node.js v18.x (LTS)](http://nodejs.org)
 - [npm](https://www.npmjs.com/) version 8.x.x or [Yarn](https://yarnpkg.com/)
-- [Python](https://www.python.org/) version 3.10.x
+- [Python](https://www.python.org/) version 3.11.x or 3.12.x
 
 ### 4. 安装
 

CONTRIBUTING_JA.md

@@ -74,7 +74,7 @@ Dify を構築するには次の依存関係が必要です。それらがシス
 - [Docker Compose](https://docs.docker.com/compose/install/)
 - [Node.js v18.x (LTS)](http://nodejs.org)
 - [npm](https://www.npmjs.com/) version 8.x.x or [Yarn](https://yarnpkg.com/)
-- [Python](https://www.python.org/) version 3.10.x
+- [Python](https://www.python.org/) version 3.11.x or 3.12.x
 
 ### 4. インストール
 

CONTRIBUTING_VI.md

@@ -73,7 +73,7 @@ Dify yêu cầu các phụ thuộc sau để build, hãy đảm bảo chúng đ
 - [Docker Compose](https://docs.docker.com/compose/install/)
 - [Node.js v18.x (LTS)](http://nodejs.org)
 - [npm](https://www.npmjs.com/) phiên bản 8.x.x hoặc [Yarn](https://yarnpkg.com/)
-- [Python](https://www.python.org/) phiên bản 3.10.x
+- [Python](https://www.python.org/) phiên bản 3.11.x hoặc 3.12.x
 
 ### 4. Cài đặt
 
@@ -153,4 +153,4 @@ Và thế là xong! Khi PR của bạn được merge, bạn sẽ được giớ
 
 ## Nhận trợ giúp
 
-Nếu bạn gặp khó khăn hoặc có câu hỏi cấp bách trong quá trình đóng góp, hãy đặt câu hỏi của bạn trong vấn đề GitHub liên quan, hoặc tham gia [Discord](https://discord.gg/8Tpq4AcN9c) của chúng tôi để trò chuyện nhanh chóng.
+Nếu bạn gặp khó khăn hoặc có câu hỏi cấp bách trong quá trình đóng góp, hãy đặt câu hỏi của bạn trong vấn đề GitHub liên quan, hoặc tham gia [Discord](https://discord.gg/8Tpq4AcN9c) của chúng tôi để trò chuyện nhanh chóng.

api/Dockerfile

@@ -1,5 +1,5 @@
 # base image
-FROM python:3.10-slim-bookworm AS base
+FROM python:3.12-slim-bookworm AS base
 
 WORKDIR /app/api
 

api/README.md

@@ -42,7 +42,7 @@
 5. Install dependencies
 
    ```bash
-   poetry env use 3.10
+   poetry env use 3.12
    poetry install
    ```
 
@@ -81,5 +81,3 @@
    ```bash
    poetry run -C api bash dev/pytest/pytest_all_tests.sh
    ```
-
-

api/app.py

@@ -1,6 +1,11 @@
 import os
 import sys
 
+python_version = sys.version_info
+if not ((3, 11) <= python_version < (3, 13)):
+    print(f"Python 3.11 or 3.12 is required, current version is {python_version.major}.{python_version.minor}")
+    raise SystemExit(1)
+
 from configs import dify_config
 
 if not dify_config.DEBUG:
@@ -30,9 +35,6 @@ from models import account, dataset, model, source, task, tool, tools, web  # no
 
 # DO NOT REMOVE ABOVE
 
-if sys.version_info[:2] == (3, 10):
-    print("Warning: Python 3.10 will not be supported in the next version.")
-
 
 warnings.simplefilter("ignore", ResourceWarning)
 

api/configs/app_config.py

@@ -27,7 +27,6 @@ class DifyConfig(
         # read from dotenv format config file
         env_file=".env",
         env_file_encoding="utf-8",
-        frozen=True,
         # ignore extra attributes
         extra="ignore",
     )

api/controllers/console/__init__.py

@@ -2,6 +2,7 @@ from flask import Blueprint
 
 from libs.external_api import ExternalApi
 
+from .app.app_import import AppImportApi, AppImportConfirmApi
 from .files import FileApi, FilePreviewApi, FileSupportTypeApi
 from .remote_files import RemoteFileInfoApi, RemoteFileUploadApi
 
@@ -17,6 +18,10 @@ api.add_resource(FileSupportTypeApi, "/files/support-type")
 api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")
 api.add_resource(RemoteFileUploadApi, "/remote-files/upload")
 
+# Import App
+api.add_resource(AppImportApi, "/apps/imports")
+api.add_resource(AppImportConfirmApi, "/apps/imports/<string:import_id>/confirm")
+
 # Import other controllers
 from . import admin, apikey, extension, feature, ping, setup, version
 

api/controllers/console/app/app.py

@@ -1,7 +1,10 @@
 import uuid
+from typing import cast
 
 from flask_login import current_user
 from flask_restful import Resource, inputs, marshal, marshal_with, reqparse
+from sqlalchemy import select
+from sqlalchemy.orm import Session
 from werkzeug.exceptions import BadRequest, Forbidden, abort
 
 from controllers.console import api
@@ -13,13 +16,15 @@ from controllers.console.wraps import (
     setup_required,
 )
 from core.ops.ops_trace_manager import OpsTraceManager
+from extensions.ext_database import db
 from fields.app_fields import (
     app_detail_fields,
     app_detail_fields_with_site,
     app_pagination_fields,
 )
 from libs.login import login_required
-from services.app_dsl_service import AppDslService
+from models import Account, App
+from services.app_dsl_service import AppDslService, ImportMode
 from services.app_service import AppService
 
 ALLOW_CREATE_APP_MODES = ["chat", "agent-chat", "advanced-chat", "workflow", "completion"]
@@ -92,61 +97,6 @@ class AppListApi(Resource):
         return app, 201
 
 
-class AppImportApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    @marshal_with(app_detail_fields_with_site)
-    @cloud_edition_billing_resource_check("apps")
-    def post(self):
-        """Import 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("data", type=str, required=True, nullable=False, location="json")
-        parser.add_argument("name", type=str, location="json")
-        parser.add_argument("description", type=str, location="json")
-        parser.add_argument("icon_type", type=str, location="json")
-        parser.add_argument("icon", type=str, location="json")
-        parser.add_argument("icon_background", type=str, location="json")
-        args = parser.parse_args()
-
-        app = AppDslService.import_and_create_new_app(
-            tenant_id=current_user.current_tenant_id, data=args["data"], args=args, account=current_user
-        )
-
-        return app, 201
-
-
-class AppImportFromUrlApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    @marshal_with(app_detail_fields_with_site)
-    @cloud_edition_billing_resource_check("apps")
-    def post(self):
-        """Import app from url"""
-        # 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("url", type=str, required=True, nullable=False, location="json")
-        parser.add_argument("name", type=str, location="json")
-        parser.add_argument("description", type=str, location="json")
-        parser.add_argument("icon", type=str, location="json")
-        parser.add_argument("icon_background", type=str, location="json")
-        args = parser.parse_args()
-
-        app = AppDslService.import_and_create_new_app_from_url(
-            tenant_id=current_user.current_tenant_id, url=args["url"], args=args, account=current_user
-        )
-
-        return app, 201
-
-
 class AppApi(Resource):
     @setup_required
     @login_required
@@ -224,10 +174,24 @@ class AppCopyApi(Resource):
         parser.add_argument("icon_background", type=str, location="json")
         args = parser.parse_args()
 
-        data = AppDslService.export_dsl(app_model=app_model, include_secret=True)
+        with Session(db.engine) as session:
-        app = AppDslService.import_and_create_new_app(
+            import_service = AppDslService(session)
-            tenant_id=current_user.current_tenant_id, data=data, args=args, account=current_user
+            yaml_content = import_service.export_dsl(app_model=app_model, include_secret=True)
-        )
+            account = cast(Account, current_user)
+            result = import_service.import_app(
+                account=account,
+                import_mode=ImportMode.YAML_CONTENT.value,
+                yaml_content=yaml_content,
+                name=args.get("name"),
+                description=args.get("description"),
+                icon_type=args.get("icon_type"),
+                icon=args.get("icon"),
+                icon_background=args.get("icon_background"),
+            )
+            session.commit()
+
+            stmt = select(App).where(App.id == result.app.id)
+            app = session.scalar(stmt)
 
         return app, 201
 
@@ -368,8 +332,6 @@ class AppTraceApi(Resource):
 
 
 api.add_resource(AppListApi, "/apps")
-api.add_resource(AppImportApi, "/apps/import")
-api.add_resource(AppImportFromUrlApi, "/apps/import/url")
 api.add_resource(AppApi, "/apps/<uuid:app_id>")
 api.add_resource(AppCopyApi, "/apps/<uuid:app_id>/copy")
 api.add_resource(AppExportApi, "/apps/<uuid:app_id>/export")

api/controllers/console/app/app_import.py

@@ -0,0 +1,90 @@
+from typing import cast
+
+from flask_login import current_user
+from flask_restful import Resource, marshal_with, reqparse
+from sqlalchemy.orm import Session
+from werkzeug.exceptions import Forbidden
+
+from controllers.console.wraps import (
+    account_initialization_required,
+    setup_required,
+)
+from extensions.ext_database import db
+from fields.app_fields import app_import_fields
+from libs.login import login_required
+from models import Account
+from services.app_dsl_service import AppDslService, ImportStatus
+
+
+class AppImportApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(app_import_fields)
+    def post(self):
+        # Check user role first
+        if not current_user.is_editor:
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("mode", type=str, required=True, location="json")
+        parser.add_argument("yaml_content", type=str, location="json")
+        parser.add_argument("yaml_url", type=str, location="json")
+        parser.add_argument("name", type=str, location="json")
+        parser.add_argument("description", type=str, location="json")
+        parser.add_argument("icon_type", type=str, location="json")
+        parser.add_argument("icon", type=str, location="json")
+        parser.add_argument("icon_background", type=str, location="json")
+        parser.add_argument("app_id", type=str, location="json")
+        args = parser.parse_args()
+
+        # Create service with session
+        with Session(db.engine) as session:
+            import_service = AppDslService(session)
+            # Import app
+            account = cast(Account, current_user)
+            result = import_service.import_app(
+                account=account,
+                import_mode=args["mode"],
+                yaml_content=args.get("yaml_content"),
+                yaml_url=args.get("yaml_url"),
+                name=args.get("name"),
+                description=args.get("description"),
+                icon_type=args.get("icon_type"),
+                icon=args.get("icon"),
+                icon_background=args.get("icon_background"),
+                app_id=args.get("app_id"),
+            )
+            session.commit()
+
+        # Return appropriate status code based on result
+        status = result.status
+        if status == ImportStatus.FAILED.value:
+            return result.model_dump(mode="json"), 400
+        elif status == ImportStatus.PENDING.value:
+            return result.model_dump(mode="json"), 202
+        return result.model_dump(mode="json"), 200
+
+
+class AppImportConfirmApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(app_import_fields)
+    def post(self, import_id):
+        # Check user role first
+        if not current_user.is_editor:
+            raise Forbidden()
+
+        # Create service with session
+        with Session(db.engine) as session:
+            import_service = AppDslService(session)
+            # Confirm import
+            account = cast(Account, current_user)
+            result = import_service.confirm_import(import_id=import_id, account=account)
+            session.commit()
+
+        # Return appropriate status code based on result
+        if result.status == ImportStatus.FAILED.value:
+            return result.model_dump(mode="json"), 400
+        return result.model_dump(mode="json"), 200

api/controllers/console/app/conversation.py

@@ -1,4 +1,4 @@
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 
 import pytz
 from flask_login import current_user
@@ -314,7 +314,7 @@ def _get_conversation(app_model, conversation_id):
         raise NotFound("Conversation Not Exists.")
 
     if not conversation.read_at:
-        conversation.read_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        conversation.read_at = datetime.now(UTC).replace(tzinfo=None)
         conversation.read_account_id = current_user.id
         db.session.commit()
 

api/controllers/console/app/site.py

@@ -1,4 +1,4 @@
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 
 from flask_login import current_user
 from flask_restful import Resource, marshal_with, reqparse
@@ -75,7 +75,7 @@ class AppSite(Resource):
                 setattr(site, attr_name, value)
 
         site.updated_by = current_user.id
-        site.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        site.updated_at = datetime.now(UTC).replace(tzinfo=None)
         db.session.commit()
 
         return site
@@ -99,7 +99,7 @@ class AppSiteAccessTokenReset(Resource):
 
         site.code = Site.generate_code(16)
         site.updated_by = current_user.id
-        site.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        site.updated_at = datetime.now(UTC).replace(tzinfo=None)
         db.session.commit()
 
         return site

api/controllers/console/app/workflow.py

@@ -20,7 +20,6 @@ from libs.helper import TimestampField, uuid_value
 from libs.login import current_user, login_required
 from models import App
 from models.model import AppMode
-from services.app_dsl_service import AppDslService
 from services.app_generate_service import AppGenerateService
 from services.errors.app import WorkflowHashNotEqualError
 from services.workflow_service import WorkflowService
@@ -126,31 +125,6 @@ class DraftWorkflowApi(Resource):
         }
 
 
-class DraftWorkflowImportApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
-    @marshal_with(workflow_fields)
-    def post(self, app_model: App):
-        """
-        Import 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("data", type=str, required=True, nullable=False, location="json")
-        args = parser.parse_args()
-
-        workflow = AppDslService.import_and_overwrite_workflow(
-            app_model=app_model, data=args["data"], account=current_user
-        )
-
-        return workflow
-
-
 class AdvancedChatDraftWorkflowRunApi(Resource):
     @setup_required
     @login_required
@@ -453,7 +427,6 @@ class ConvertToWorkflowApi(Resource):
 
 
 api.add_resource(DraftWorkflowApi, "/apps/<uuid:app_id>/workflows/draft")
-api.add_resource(DraftWorkflowImportApi, "/apps/<uuid:app_id>/workflows/draft/import")
 api.add_resource(AdvancedChatDraftWorkflowRunApi, "/apps/<uuid:app_id>/advanced-chat/workflows/draft/run")
 api.add_resource(DraftWorkflowRunApi, "/apps/<uuid:app_id>/workflows/draft/run")
 api.add_resource(WorkflowTaskStopApi, "/apps/<uuid:app_id>/workflow-runs/tasks/<string:task_id>/stop")

api/controllers/console/auth/activate.py

@@ -65,7 +65,7 @@ class ActivateApi(Resource):
         account.timezone = args["timezone"]
         account.interface_theme = "light"
         account.status = AccountStatus.ACTIVE.value
-        account.initialized_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+        account.initialized_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
         db.session.commit()
 
         token_pair = AccountService.login(account, ip_address=extract_remote_ip(request))

api/controllers/console/auth/oauth.py

@@ -1,5 +1,5 @@
 import logging
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from typing import Optional
 
 import requests
@@ -106,7 +106,7 @@ class OAuthCallback(Resource):
 
         if account.status == AccountStatus.PENDING.value:
             account.status = AccountStatus.ACTIVE.value
-            account.initialized_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            account.initialized_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
         try:

api/controllers/console/datasets/data_source.py

@@ -83,7 +83,7 @@ class DataSourceApi(Resource):
         if action == "enable":
             if data_source_binding.disabled:
                 data_source_binding.disabled = False
-                data_source_binding.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+                data_source_binding.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
                 db.session.add(data_source_binding)
                 db.session.commit()
             else:
@@ -92,7 +92,7 @@ class DataSourceApi(Resource):
         if action == "disable":
             if not data_source_binding.disabled:
                 data_source_binding.disabled = True
-                data_source_binding.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+                data_source_binding.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
                 db.session.add(data_source_binding)
                 db.session.commit()
             else:

api/controllers/console/datasets/datasets_document.py

@@ -1,6 +1,6 @@
 import logging
 from argparse import ArgumentTypeError
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 
 from flask import request
 from flask_login import current_user
@@ -665,7 +665,7 @@ class DocumentProcessingApi(DocumentResource):
                 raise InvalidActionError("Document not in indexing state.")
 
             document.paused_by = current_user.id
-            document.paused_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.paused_at = datetime.now(UTC).replace(tzinfo=None)
             document.is_paused = True
             db.session.commit()
 
@@ -745,7 +745,7 @@ class DocumentMetadataApi(DocumentResource):
                     document.doc_metadata[key] = value
 
         document.doc_type = doc_type
-        document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        document.updated_at = datetime.now(UTC).replace(tzinfo=None)
         db.session.commit()
 
         return {"result": "success", "message": "Document metadata updated."}, 200
@@ -787,7 +787,7 @@ class DocumentStatusApi(DocumentResource):
             document.enabled = True
             document.disabled_at = None
             document.disabled_by = None
-            document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.updated_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
             # Set cache to prevent indexing the same document multiple times
@@ -804,9 +804,9 @@ class DocumentStatusApi(DocumentResource):
                 raise InvalidActionError("Document already disabled.")
 
             document.enabled = False
-            document.disabled_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.disabled_at = datetime.now(UTC).replace(tzinfo=None)
             document.disabled_by = current_user.id
-            document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.updated_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
             # Set cache to prevent indexing the same document multiple times
@@ -821,9 +821,9 @@ class DocumentStatusApi(DocumentResource):
                 raise InvalidActionError("Document already archived.")
 
             document.archived = True
-            document.archived_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.archived_at = datetime.now(UTC).replace(tzinfo=None)
             document.archived_by = current_user.id
-            document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.updated_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
             if document.enabled:
@@ -840,7 +840,7 @@ class DocumentStatusApi(DocumentResource):
             document.archived = False
             document.archived_at = None
             document.archived_by = None
-            document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.updated_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
             # Set cache to prevent indexing the same document multiple times

api/controllers/console/datasets/datasets_segments.py

@@ -1,5 +1,5 @@
 import uuid
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 
 import pandas as pd
 from flask import request
@@ -188,7 +188,7 @@ class DatasetDocumentSegmentApi(Resource):
                 raise InvalidActionError("Segment is already disabled.")
 
             segment.enabled = False
-            segment.disabled_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            segment.disabled_at = datetime.now(UTC).replace(tzinfo=None)
             segment.disabled_by = current_user.id
             db.session.commit()
 

api/controllers/console/explore/completion.py

@@ -1,5 +1,5 @@
 import logging
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 
 from flask_login import current_user
 from flask_restful import reqparse
@@ -46,7 +46,7 @@ class CompletionApi(InstalledAppResource):
         streaming = args["response_mode"] == "streaming"
         args["auto_generate_name"] = False
 
-        installed_app.last_used_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        installed_app.last_used_at = datetime.now(UTC).replace(tzinfo=None)
         db.session.commit()
 
         try:
@@ -106,7 +106,7 @@ class ChatApi(InstalledAppResource):
 
         args["auto_generate_name"] = False
 
-        installed_app.last_used_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        installed_app.last_used_at = datetime.now(UTC).replace(tzinfo=None)
         db.session.commit()
 
         try:

api/controllers/console/explore/installed_app.py

@@ -1,4 +1,4 @@
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 
 from flask_login import current_user
 from flask_restful import Resource, inputs, marshal_with, reqparse
@@ -81,7 +81,7 @@ class InstalledAppsListApi(Resource):
                 tenant_id=current_tenant_id,
                 app_owner_tenant_id=app.tenant_id,
                 is_pinned=False,
-                last_used_at=datetime.now(timezone.utc).replace(tzinfo=None),
+                last_used_at=datetime.now(UTC).replace(tzinfo=None),
             )
             db.session.add(new_installed_app)
             db.session.commit()

api/controllers/console/workspace/account.py

@@ -60,7 +60,7 @@ class AccountInitApi(Resource):
                 raise InvalidInvitationCodeError()
 
             invitation_code.status = "used"
-            invitation_code.used_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            invitation_code.used_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             invitation_code.used_by_tenant_id = account.current_tenant_id
             invitation_code.used_by_account_id = account.id
 
@@ -68,7 +68,7 @@ class AccountInitApi(Resource):
         account.timezone = args["timezone"]
         account.interface_theme = "light"
         account.status = "active"
-        account.initialized_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+        account.initialized_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
         db.session.commit()
 
         return {"result": "success"}

api/controllers/service_api/wraps.py

@@ -1,5 +1,5 @@
 from collections.abc import Callable
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from enum import Enum
 from functools import wraps
 from typing import Optional
@@ -198,7 +198,7 @@ def validate_and_get_api_token(scope=None):
     if not api_token:
         raise Unauthorized("Access token is invalid")
 
-    api_token.last_used_at = datetime.now(timezone.utc).replace(tzinfo=None)
+    api_token.last_used_at = datetime.now(UTC).replace(tzinfo=None)
     db.session.commit()
 
     return api_token

api/core/agent/base_agent_runner.py

@@ -2,7 +2,7 @@ import json
 import logging
 import uuid
 from collections.abc import Mapping, Sequence
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from typing import Optional, Union, cast
 
 from core.agent.entities import AgentEntity, AgentToolEntity
@@ -412,7 +412,7 @@ class BaseAgentRunner(AppRunner):
             .first()
         )
 
-        db_variables.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        db_variables.updated_at = datetime.now(UTC).replace(tzinfo=None)
         db_variables.variables_str = json.dumps(jsonable_encoder(tool_variables.pool))
         db.session.commit()
         db.session.close()

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

@@ -1,3 +1,4 @@
+import uuid
 from typing import Optional
 
 from core.app.app_config.entities import DatasetEntity, DatasetRetrieveConfigEntity

api/core/app/app_config/easy_ui_based_app/model_config/converter.py

@@ -11,7 +11,7 @@ from core.provider_manager import ProviderManager
 
 class ModelConfigConverter:
     @classmethod
-    def convert(cls, app_config: EasyUIBasedAppConfig, skip_check: bool = False) -> ModelConfigWithCredentialsEntity:
+    def convert(cls, app_config: EasyUIBasedAppConfig) -> ModelConfigWithCredentialsEntity:
         """
         Convert app model config dict to entity.
         :param app_config: app config
@@ -38,27 +38,23 @@ class ModelConfigConverter:
         )
 
         if model_credentials is None:
-            if not skip_check:
+            raise ProviderTokenNotInitError(f"Model {model_name} credentials is not initialized.")
-                raise ProviderTokenNotInitError(f"Model {model_name} credentials is not initialized.")
-            else:
-                model_credentials = {}
 
-        if not skip_check:
+        # check model
-            # check model
+        provider_model = provider_model_bundle.configuration.get_provider_model(
-            provider_model = provider_model_bundle.configuration.get_provider_model(
+            model=model_config.model, model_type=ModelType.LLM
-                model=model_config.model, model_type=ModelType.LLM
+        )
-            )
 
-            if provider_model is None:
+        if provider_model is None:
-                model_name = model_config.model
+            model_name = model_config.model
-                raise ValueError(f"Model {model_name} not exist.")
+            raise ValueError(f"Model {model_name} not exist.")
 
-            if provider_model.status == ModelStatus.NO_CONFIGURE:
+        if provider_model.status == ModelStatus.NO_CONFIGURE:
-                raise ProviderTokenNotInitError(f"Model {model_name} credentials is not initialized.")
+            raise ProviderTokenNotInitError(f"Model {model_name} credentials is not initialized.")
-            elif provider_model.status == ModelStatus.NO_PERMISSION:
+        elif provider_model.status == ModelStatus.NO_PERMISSION:
-                raise ModelCurrentlyNotSupportError(f"Dify Hosted OpenAI {model_name} currently not support.")
+            raise ModelCurrentlyNotSupportError(f"Dify Hosted OpenAI {model_name} currently not support.")
-            elif provider_model.status == ModelStatus.QUOTA_EXCEEDED:
+        elif provider_model.status == ModelStatus.QUOTA_EXCEEDED:
-                raise QuotaExceededError(f"Model provider {provider_name} quota exceeded.")
+            raise QuotaExceededError(f"Model provider {provider_name} quota exceeded.")
 
         # model config
         completion_params = model_config.parameters
@@ -76,7 +72,7 @@ class ModelConfigConverter:
 
         model_schema = model_type_instance.get_model_schema(model_config.model, model_credentials)
 
-        if not skip_check and not model_schema:
+        if not model_schema:
             raise ValueError(f"Model {model_name} not exist.")
 
         return ModelConfigWithCredentialsEntity(

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

@@ -1,4 +1,5 @@
 from core.app.app_config.entities import (
+    AdvancedChatMessageEntity,
     AdvancedChatPromptTemplateEntity,
     AdvancedCompletionPromptTemplateEntity,
     PromptTemplateEntity,
@@ -25,7 +26,9 @@ class PromptTemplateConfigManager:
                 chat_prompt_messages = []
                 for message in chat_prompt_config.get("prompt", []):
                     chat_prompt_messages.append(
-                        {"text": message["text"], "role": PromptMessageRole.value_of(message["role"])}
+                        AdvancedChatMessageEntity(
+                            **{"text": message["text"], "role": PromptMessageRole.value_of(message["role"])}
+                        )
                     )
 
                 advanced_chat_prompt_template = AdvancedChatPromptTemplateEntity(messages=chat_prompt_messages)

api/core/app/app_config/entities.py

@@ -1,5 +1,5 @@
 from collections.abc import Sequence
-from enum import Enum
+from enum import Enum, StrEnum
 from typing import Any, Optional
 
 from pydantic import BaseModel, Field, field_validator
@@ -88,7 +88,7 @@ class PromptTemplateEntity(BaseModel):
     advanced_completion_prompt_template: Optional[AdvancedCompletionPromptTemplateEntity] = None
 
 
-class VariableEntityType(str, Enum):
+class VariableEntityType(StrEnum):
     TEXT_INPUT = "text-input"
     SELECT = "select"
     PARAGRAPH = "paragraph"

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

@@ -127,7 +127,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             conversation_id=conversation.id if conversation else None,
             inputs=conversation.inputs
             if conversation
-            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            else self._prepare_user_inputs(user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.id),
             query=query,
             files=file_objs,
             parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,

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

@@ -134,7 +134,7 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
             conversation_id=conversation.id if conversation else None,
             inputs=conversation.inputs
             if conversation
-            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            else self._prepare_user_inputs(user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.id),
             query=query,
             files=file_objs,
             parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,

api/core/app/apps/base_app_generator.py

@@ -1,4 +1,4 @@
-from collections.abc import Mapping
+from collections.abc import Mapping, Sequence
 from typing import TYPE_CHECKING, Any, Optional
 
 from core.app.app_config.entities import VariableEntityType
@@ -6,7 +6,7 @@ from core.file import File, FileUploadConfig
 from factories import file_factory
 
 if TYPE_CHECKING:
-    from core.app.app_config.entities import AppConfig, VariableEntity
+    from core.app.app_config.entities import VariableEntity
 
 
 class BaseAppGenerator:
@@ -14,23 +14,23 @@ class BaseAppGenerator:
         self,
         *,
         user_inputs: Optional[Mapping[str, Any]],
-        app_config: "AppConfig",
+        variables: Sequence["VariableEntity"],
+        tenant_id: str,
     ) -> Mapping[str, Any]:
         user_inputs = user_inputs or {}
         # Filter input variables from form configuration, handle required fields, default values, and option values
-        variables = app_config.variables
         user_inputs = {
             var.variable: self._validate_inputs(value=user_inputs.get(var.variable), variable_entity=var)
             for var in variables
         }
         user_inputs = {k: self._sanitize_value(v) for k, v in user_inputs.items()}
         # Convert files in inputs to File
-        entity_dictionary = {item.variable: item for item in app_config.variables}
+        entity_dictionary = {item.variable: item for item in variables}
         # Convert single file to File
         files_inputs = {
             k: file_factory.build_from_mapping(
                 mapping=v,
-                tenant_id=app_config.tenant_id,
+                tenant_id=tenant_id,
                 config=FileUploadConfig(
                     allowed_file_types=entity_dictionary[k].allowed_file_types,
                     allowed_file_extensions=entity_dictionary[k].allowed_file_extensions,
@@ -44,7 +44,7 @@ class BaseAppGenerator:
         file_list_inputs = {
             k: file_factory.build_from_mappings(
                 mappings=v,
-                tenant_id=app_config.tenant_id,
+                tenant_id=tenant_id,
                 config=FileUploadConfig(
                     allowed_file_types=entity_dictionary[k].allowed_file_types,
                     allowed_file_extensions=entity_dictionary[k].allowed_file_extensions,

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

@@ -132,7 +132,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             conversation_id=conversation.id if conversation else None,
             inputs=conversation.inputs
             if conversation
-            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            else self._prepare_user_inputs(user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.id),
             query=query,
             files=file_objs,
             parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,

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

@@ -113,7 +113,9 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
             app_config=app_config,
             model_conf=ModelConfigConverter.convert(app_config),
             file_upload_config=file_extra_config,
-            inputs=self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            inputs=self._prepare_user_inputs(
+                user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.id
+            ),
             query=query,
             files=file_objs,
             user_id=user.id,

api/core/app/apps/message_based_app_generator.py

@@ -1,7 +1,7 @@
 import json
 import logging
 from collections.abc import Generator
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from typing import Optional, Union
 
 from sqlalchemy import and_
@@ -200,7 +200,7 @@ class MessageBasedAppGenerator(BaseAppGenerator):
             db.session.commit()
             db.session.refresh(conversation)
         else:
-            conversation.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            conversation.updated_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
         message = Message(

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

@@ -96,7 +96,9 @@ class WorkflowAppGenerator(BaseAppGenerator):
             task_id=str(uuid.uuid4()),
             app_config=app_config,
             file_upload_config=file_extra_config,
-            inputs=self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            inputs=self._prepare_user_inputs(
+                user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
+            ),
             files=system_files,
             user_id=user.id,
             stream=stream,

api/core/app/apps/workflow_app_runner.py

@@ -43,7 +43,6 @@ from core.workflow.graph_engine.entities.event import (
 )
 from core.workflow.graph_engine.entities.graph import Graph
 from core.workflow.nodes import NodeType
-from core.workflow.nodes.iteration import IterationNodeData
 from core.workflow.nodes.node_mapping import node_type_classes_mapping
 from core.workflow.workflow_entry import WorkflowEntry
 from extensions.ext_database import db
@@ -160,8 +159,6 @@ class WorkflowBasedAppRunner(AppRunner):
             user_inputs=user_inputs,
             variable_pool=variable_pool,
             tenant_id=workflow.tenant_id,
-            node_type=node_type,
-            node_data=IterationNodeData(**iteration_node_config.get("data", {})),
         )
 
         return graph, variable_pool

api/core/app/entities/queue_entities.py

@@ -1,5 +1,5 @@
 from datetime import datetime
-from enum import Enum
+from enum import Enum, StrEnum
 from typing import Any, Optional
 
 from pydantic import BaseModel, field_validator
@@ -11,7 +11,7 @@ from core.workflow.nodes import NodeType
 from core.workflow.nodes.base import BaseNodeData
 
 
-class QueueEvent(str, Enum):
+class QueueEvent(StrEnum):
     """
     QueueEvent enum
     """

api/core/app/task_pipeline/workflow_cycle_manage.py

@@ -1,7 +1,7 @@
 import json
 import time
 from collections.abc import Mapping, Sequence
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from typing import Any, Optional, Union, cast
 
 from sqlalchemy.orm import Session
@@ -144,7 +144,7 @@ class WorkflowCycleManage:
         workflow_run.elapsed_time = time.perf_counter() - start_at
         workflow_run.total_tokens = total_tokens
         workflow_run.total_steps = total_steps
-        workflow_run.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        workflow_run.finished_at = datetime.now(UTC).replace(tzinfo=None)
 
         db.session.commit()
         db.session.refresh(workflow_run)
@@ -191,7 +191,7 @@ class WorkflowCycleManage:
         workflow_run.elapsed_time = time.perf_counter() - start_at
         workflow_run.total_tokens = total_tokens
         workflow_run.total_steps = total_steps
-        workflow_run.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        workflow_run.finished_at = datetime.now(UTC).replace(tzinfo=None)
 
         db.session.commit()
 
@@ -211,15 +211,18 @@ class WorkflowCycleManage:
         for workflow_node_execution in running_workflow_node_executions:
             workflow_node_execution.status = WorkflowNodeExecutionStatus.FAILED.value
             workflow_node_execution.error = error
-            workflow_node_execution.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            workflow_node_execution.finished_at = datetime.now(UTC).replace(tzinfo=None)
             workflow_node_execution.elapsed_time = (
                 workflow_node_execution.finished_at - workflow_node_execution.created_at
             ).total_seconds()
             db.session.commit()
 
-        db.session.refresh(workflow_run)
         db.session.close()
 
+        with Session(db.engine, expire_on_commit=False) as session:
+            session.add(workflow_run)
+            session.refresh(workflow_run)
+
         if trace_manager:
             trace_manager.add_trace_task(
                 TraceTask(
@@ -259,7 +262,7 @@ class WorkflowCycleManage:
                     NodeRunMetadataKey.ITERATION_ID: event.in_iteration_id,
                 }
             )
-            workflow_node_execution.created_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            workflow_node_execution.created_at = datetime.now(UTC).replace(tzinfo=None)
 
             session.add(workflow_node_execution)
             session.commit()
@@ -282,7 +285,7 @@ class WorkflowCycleManage:
         execution_metadata = (
             json.dumps(jsonable_encoder(event.execution_metadata)) if event.execution_metadata else None
         )
-        finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        finished_at = datetime.now(UTC).replace(tzinfo=None)
         elapsed_time = (finished_at - event.start_at).total_seconds()
 
         db.session.query(WorkflowNodeExecution).filter(WorkflowNodeExecution.id == workflow_node_execution.id).update(
@@ -326,7 +329,7 @@ class WorkflowCycleManage:
         inputs = WorkflowEntry.handle_special_values(event.inputs)
         process_data = WorkflowEntry.handle_special_values(event.process_data)
         outputs = WorkflowEntry.handle_special_values(event.outputs)
-        finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        finished_at = datetime.now(UTC).replace(tzinfo=None)
         elapsed_time = (finished_at - event.start_at).total_seconds()
         execution_metadata = (
             json.dumps(jsonable_encoder(event.execution_metadata)) if event.execution_metadata else None
@@ -654,7 +657,7 @@ class WorkflowCycleManage:
                 if event.error is None
                 else WorkflowNodeExecutionStatus.FAILED,
                 error=None,
-                elapsed_time=(datetime.now(timezone.utc).replace(tzinfo=None) - event.start_at).total_seconds(),
+                elapsed_time=(datetime.now(UTC).replace(tzinfo=None) - event.start_at).total_seconds(),
                 total_tokens=event.metadata.get("total_tokens", 0) if event.metadata else 0,
                 execution_metadata=event.metadata,
                 finished_at=int(time.time()),

api/core/entities/provider_configuration.py

@@ -240,7 +240,7 @@ class ProviderConfiguration(BaseModel):
         if provider_record:
             provider_record.encrypted_config = json.dumps(credentials)
             provider_record.is_valid = True
-            provider_record.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            provider_record.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         else:
             provider_record = Provider(
@@ -394,7 +394,7 @@ class ProviderConfiguration(BaseModel):
         if provider_model_record:
             provider_model_record.encrypted_config = json.dumps(credentials)
             provider_model_record.is_valid = True
-            provider_model_record.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            provider_model_record.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         else:
             provider_model_record = ProviderModel(
@@ -468,7 +468,7 @@ class ProviderConfiguration(BaseModel):
 
         if model_setting:
             model_setting.enabled = True
-            model_setting.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            model_setting.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         else:
             model_setting = ProviderModelSetting(
@@ -503,7 +503,7 @@ class ProviderConfiguration(BaseModel):
 
         if model_setting:
             model_setting.enabled = False
-            model_setting.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            model_setting.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         else:
             model_setting = ProviderModelSetting(
@@ -570,7 +570,7 @@ class ProviderConfiguration(BaseModel):
 
         if model_setting:
             model_setting.load_balancing_enabled = True
-            model_setting.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            model_setting.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         else:
             model_setting = ProviderModelSetting(
@@ -605,7 +605,7 @@ class ProviderConfiguration(BaseModel):
 
         if model_setting:
             model_setting.load_balancing_enabled = False
-            model_setting.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            model_setting.updated_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         else:
             model_setting = ProviderModelSetting(

api/core/file/enums.py

@@ -1,7 +1,7 @@
-from enum import Enum
+from enum import StrEnum
 
 
-class FileType(str, Enum):
+class FileType(StrEnum):
     IMAGE = "image"
     DOCUMENT = "document"
     AUDIO = "audio"
@@ -16,7 +16,7 @@ class FileType(str, Enum):
         raise ValueError(f"No matching enum found for value '{value}'")
 
 
-class FileTransferMethod(str, Enum):
+class FileTransferMethod(StrEnum):
     REMOTE_URL = "remote_url"
     LOCAL_FILE = "local_file"
     TOOL_FILE = "tool_file"
@@ -29,7 +29,7 @@ class FileTransferMethod(str, Enum):
         raise ValueError(f"No matching enum found for value '{value}'")
 
 
-class FileBelongsTo(str, Enum):
+class FileBelongsTo(StrEnum):
     USER = "user"
     ASSISTANT = "assistant"
 
@@ -41,7 +41,7 @@ class FileBelongsTo(str, Enum):
         raise ValueError(f"No matching enum found for value '{value}'")
 
 
-class FileAttribute(str, Enum):
+class FileAttribute(StrEnum):
     TYPE = "type"
     SIZE = "size"
     NAME = "name"
@@ -51,5 +51,5 @@ class FileAttribute(str, Enum):
     EXTENSION = "extension"
 
 
-class ArrayFileAttribute(str, Enum):
+class ArrayFileAttribute(StrEnum):
     LENGTH = "length"

api/core/file/file_manager.py

@@ -3,7 +3,12 @@ import base64
 from configs import dify_config
 from core.file import file_repository
 from core.helper import ssrf_proxy
-from core.model_runtime.entities import AudioPromptMessageContent, ImagePromptMessageContent, VideoPromptMessageContent
+from core.model_runtime.entities import (
+    AudioPromptMessageContent,
+    DocumentPromptMessageContent,
+    ImagePromptMessageContent,
+    VideoPromptMessageContent,
+)
 from extensions.ext_database import db
 from extensions.ext_storage import storage
 
@@ -29,35 +34,17 @@ def get_attr(*, file: File, attr: FileAttribute):
             return file.remote_url
         case FileAttribute.EXTENSION:
             return file.extension
-        case _:
-            raise ValueError(f"Invalid file attribute: {attr}")
 
 
 def to_prompt_message_content(
     f: File,
     /,
     *,
-    image_detail_config: ImagePromptMessageContent.DETAIL = ImagePromptMessageContent.DETAIL.LOW,
+    image_detail_config: ImagePromptMessageContent.DETAIL | None = None,
 ):
-    """
-    Convert a File object to an ImagePromptMessageContent or AudioPromptMessageContent object.
-
-    This function takes a File object and converts it to an appropriate PromptMessageContent
-    object, which can be used as a prompt for image or audio-based AI models.
-
-    Args:
-        f (File): The File object to convert.
-        detail (Optional[ImagePromptMessageContent.DETAIL]): The detail level for image prompts.
-            If not provided, defaults to ImagePromptMessageContent.DETAIL.LOW.
-
-    Returns:
-        Union[ImagePromptMessageContent, AudioPromptMessageContent]: An object containing the file data and detail level
-
-    Raises:
-        ValueError: If the file type is not supported or if required data is missing.
-    """
     match f.type:
         case FileType.IMAGE:
+            image_detail_config = image_detail_config or ImagePromptMessageContent.DETAIL.LOW
             if dify_config.MULTIMODAL_SEND_IMAGE_FORMAT == "url":
                 data = _to_url(f)
             else:
@@ -65,7 +52,7 @@ def to_prompt_message_content(
 
             return ImagePromptMessageContent(data=data, detail=image_detail_config)
         case FileType.AUDIO:
-            encoded_string = _file_to_encoded_string(f)
+            encoded_string = _get_encoded_string(f)
             if f.extension is None:
                 raise ValueError("Missing file extension")
             return AudioPromptMessageContent(data=encoded_string, format=f.extension.lstrip("."))
@@ -74,9 +61,20 @@ def to_prompt_message_content(
                 data = _to_url(f)
             else:
                 data = _to_base64_data_string(f)
+            if f.extension is None:
+                raise ValueError("Missing file extension")
             return VideoPromptMessageContent(data=data, format=f.extension.lstrip("."))
+        case FileType.DOCUMENT:
+            data = _get_encoded_string(f)
+            if f.mime_type is None:
+                raise ValueError("Missing file mime_type")
+            return DocumentPromptMessageContent(
+                encode_format="base64",
+                mime_type=f.mime_type,
+                data=data,
+            )
         case _:
-            raise ValueError("file type f.type is not supported")
+            raise ValueError(f"file type {f.type} is not supported")
 
 
 def download(f: File, /):
@@ -118,21 +116,16 @@ def _get_encoded_string(f: File, /):
         case FileTransferMethod.REMOTE_URL:
             response = ssrf_proxy.get(f.remote_url, follow_redirects=True)
             response.raise_for_status()
-            content = response.content
+            data = response.content
-            encoded_string = base64.b64encode(content).decode("utf-8")
-            return encoded_string
         case FileTransferMethod.LOCAL_FILE:
             upload_file = file_repository.get_upload_file(session=db.session(), file=f)
             data = _download_file_content(upload_file.key)
-            encoded_string = base64.b64encode(data).decode("utf-8")
-            return encoded_string
         case FileTransferMethod.TOOL_FILE:
             tool_file = file_repository.get_tool_file(session=db.session(), file=f)
             data = _download_file_content(tool_file.file_key)
-            encoded_string = base64.b64encode(data).decode("utf-8")
+
-            return encoded_string
+    encoded_string = base64.b64encode(data).decode("utf-8")
-        case _:
+    return encoded_string
-            raise ValueError(f"Unsupported transfer method: {f.transfer_method}")
 
 
 def _to_base64_data_string(f: File, /):
@@ -140,18 +133,6 @@ def _to_base64_data_string(f: File, /):
     return f"data:{f.mime_type};base64,{encoded_string}"
 
 
-def _file_to_encoded_string(f: File, /):
-    match f.type:
-        case FileType.IMAGE:
-            return _to_base64_data_string(f)
-        case FileType.VIDEO:
-            return _to_base64_data_string(f)
-        case FileType.AUDIO:
-            return _get_encoded_string(f)
-        case _:
-            raise ValueError(f"file type {f.type} is not supported")
-
-
 def _to_url(f: File, /):
     if f.transfer_method == FileTransferMethod.REMOTE_URL:
         if f.remote_url is None:

api/core/helper/code_executor/code_executor.py

@@ -1,6 +1,6 @@
 import logging
 from collections.abc import Mapping
-from enum import Enum
+from enum import StrEnum
 from threading import Lock
 from typing import Any, Optional
 
@@ -31,7 +31,7 @@ class CodeExecutionResponse(BaseModel):
     data: Data
 
 
-class CodeLanguage(str, Enum):
+class CodeLanguage(StrEnum):
     PYTHON3 = "python3"
     JINJA2 = "jinja2"
     JAVASCRIPT = "javascript"

api/core/indexing_runner.py

@@ -86,7 +86,7 @@ class IndexingRunner:
             except ProviderTokenNotInitError as e:
                 dataset_document.indexing_status = "error"
                 dataset_document.error = str(e.description)
-                dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+                dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
                 db.session.commit()
             except ObjectDeletedError:
                 logging.warning("Document deleted, document id: {}".format(dataset_document.id))
@@ -94,7 +94,7 @@ class IndexingRunner:
                 logging.exception("consume document failed")
                 dataset_document.indexing_status = "error"
                 dataset_document.error = str(e)
-                dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+                dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
                 db.session.commit()
 
     def run_in_splitting_status(self, dataset_document: DatasetDocument):
@@ -142,13 +142,13 @@ class IndexingRunner:
         except ProviderTokenNotInitError as e:
             dataset_document.indexing_status = "error"
             dataset_document.error = str(e.description)
-            dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         except Exception as e:
             logging.exception("consume document failed")
             dataset_document.indexing_status = "error"
             dataset_document.error = str(e)
-            dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
 
     def run_in_indexing_status(self, dataset_document: DatasetDocument):
@@ -200,13 +200,13 @@ class IndexingRunner:
         except ProviderTokenNotInitError as e:
             dataset_document.indexing_status = "error"
             dataset_document.error = str(e.description)
-            dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         except Exception as e:
             logging.exception("consume document failed")
             dataset_document.indexing_status = "error"
             dataset_document.error = str(e)
-            dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
 
     def indexing_estimate(
@@ -372,7 +372,7 @@ class IndexingRunner:
             after_indexing_status="splitting",
             extra_update_params={
                 DatasetDocument.word_count: sum(len(text_doc.page_content) for text_doc in text_docs),
-                DatasetDocument.parsing_completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                DatasetDocument.parsing_completed_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
             },
         )
 
@@ -464,7 +464,7 @@ class IndexingRunner:
         doc_store.add_documents(documents)
 
         # update document status to indexing
-        cur_time = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+        cur_time = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
         self._update_document_index_status(
             document_id=dataset_document.id,
             after_indexing_status="indexing",
@@ -479,7 +479,7 @@ class IndexingRunner:
             dataset_document_id=dataset_document.id,
             update_params={
                 DocumentSegment.status: "indexing",
-                DocumentSegment.indexing_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                DocumentSegment.indexing_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
             },
         )
 
@@ -680,7 +680,7 @@ class IndexingRunner:
             after_indexing_status="completed",
             extra_update_params={
                 DatasetDocument.tokens: tokens,
-                DatasetDocument.completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                DatasetDocument.completed_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
                 DatasetDocument.indexing_latency: indexing_end_at - indexing_start_at,
                 DatasetDocument.error: None,
             },
@@ -705,7 +705,7 @@ class IndexingRunner:
                     {
                         DocumentSegment.status: "completed",
                         DocumentSegment.enabled: True,
-                        DocumentSegment.completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                        DocumentSegment.completed_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
                     }
                 )
 
@@ -720,10 +720,8 @@ class IndexingRunner:
 
             tokens = 0
             if embedding_model_instance:
-                tokens += sum(
+                page_content_list = [document.page_content for document in chunk_documents]
-                    embedding_model_instance.get_text_embedding_num_tokens([document.page_content])
+                tokens += sum(embedding_model_instance.get_text_embedding_num_tokens(page_content_list))
-                    for document in chunk_documents
-                )
 
             # load index
             index_processor.load(dataset, chunk_documents, with_keywords=False)
@@ -738,7 +736,7 @@ class IndexingRunner:
                 {
                     DocumentSegment.status: "completed",
                     DocumentSegment.enabled: True,
-                    DocumentSegment.completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                    DocumentSegment.completed_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
                 }
             )
 
@@ -849,7 +847,7 @@ class IndexingRunner:
         doc_store.add_documents(documents)
 
         # update document status to indexing
-        cur_time = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+        cur_time = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
         self._update_document_index_status(
             document_id=dataset_document.id,
             after_indexing_status="indexing",
@@ -864,7 +862,7 @@ class IndexingRunner:
             dataset_document_id=dataset_document.id,
             update_params={
                 DocumentSegment.status: "indexing",
-                DocumentSegment.indexing_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                DocumentSegment.indexing_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
             },
         )
         pass

api/core/memory/token_buffer_memory.py

@@ -1,8 +1,8 @@
+from collections.abc import Sequence
 from typing import Optional
 
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.file import file_manager
-from core.file.models import FileType
 from core.model_manager import ModelInstance
 from core.model_runtime.entities import (
     AssistantPromptMessage,
@@ -27,7 +27,7 @@ class TokenBufferMemory:
 
     def get_history_prompt_messages(
         self, max_token_limit: int = 2000, message_limit: Optional[int] = None
-    ) -> list[PromptMessage]:
+    ) -> Sequence[PromptMessage]:
         """
         Get history prompt messages.
         :param max_token_limit: max token limit
@@ -102,12 +102,11 @@ class TokenBufferMemory:
                     prompt_message_contents: list[PromptMessageContent] = []
                     prompt_message_contents.append(TextPromptMessageContent(data=message.query))
                     for file in file_objs:
-                        if file.type in {FileType.IMAGE, FileType.AUDIO}:
+                        prompt_message = file_manager.to_prompt_message_content(
-                            prompt_message = file_manager.to_prompt_message_content(
+                            file,
-                                file,
+                            image_detail_config=detail,
-                                image_detail_config=detail,
+                        )
-                            )
+                        prompt_message_contents.append(prompt_message)
-                            prompt_message_contents.append(prompt_message)
 
                     prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
 

api/core/model_manager.py

@@ -100,10 +100,10 @@ class ModelInstance:
 
     def invoke_llm(
         self,
-        prompt_messages: list[PromptMessage],
+        prompt_messages: Sequence[PromptMessage],
         model_parameters: Optional[dict] = None,
         tools: Sequence[PromptMessageTool] | None = None,
-        stop: Optional[list[str]] = None,
+        stop: Optional[Sequence[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
         callbacks: Optional[list[Callback]] = None,
@@ -183,7 +183,7 @@ class ModelInstance:
             input_type=input_type,
         )
 
-    def get_text_embedding_num_tokens(self, texts: list[str]) -> int:
+    def get_text_embedding_num_tokens(self, texts: list[str]) -> list[int]:
         """
         Get number of tokens for text embedding
 

api/core/model_runtime/callbacks/base_callback.py

@@ -1,4 +1,5 @@
 from abc import ABC, abstractmethod
+from collections.abc import Sequence
 from typing import Optional
 
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk
@@ -31,7 +32,7 @@ class Callback(ABC):
         prompt_messages: list[PromptMessage],
         model_parameters: dict,
         tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
+        stop: Optional[Sequence[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
     ) -> None:
@@ -60,7 +61,7 @@ class Callback(ABC):
         prompt_messages: list[PromptMessage],
         model_parameters: dict,
         tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
+        stop: Optional[Sequence[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
     ):
@@ -90,7 +91,7 @@ class Callback(ABC):
         prompt_messages: list[PromptMessage],
         model_parameters: dict,
         tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
+        stop: Optional[Sequence[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
     ) -> None:
@@ -120,7 +121,7 @@ class Callback(ABC):
         prompt_messages: list[PromptMessage],
         model_parameters: dict,
         tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
+        stop: Optional[Sequence[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
     ) -> None:

api/core/model_runtime/entities/__init__.py

@@ -2,6 +2,7 @@ from .llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsa
 from .message_entities import (
     AssistantPromptMessage,
     AudioPromptMessageContent,
+    DocumentPromptMessageContent,
     ImagePromptMessageContent,
     PromptMessage,
     PromptMessageContent,
@@ -37,4 +38,5 @@ __all__ = [
     "LLMResultChunk",
     "LLMResultChunkDelta",
     "AudioPromptMessageContent",
+    "DocumentPromptMessageContent",
 ]

api/core/model_runtime/entities/message_entities.py

@@ -1,6 +1,7 @@
 from abc import ABC
-from enum import Enum
+from collections.abc import Sequence
-from typing import Optional
+from enum import Enum, StrEnum
+from typing import Literal, Optional
 
 from pydantic import BaseModel, Field, field_validator
 
@@ -48,7 +49,7 @@ class PromptMessageFunction(BaseModel):
     function: PromptMessageTool
 
 
-class PromptMessageContentType(Enum):
+class PromptMessageContentType(StrEnum):
     """
     Enum class for prompt message content type.
     """
@@ -57,6 +58,7 @@ class PromptMessageContentType(Enum):
     IMAGE = "image"
     AUDIO = "audio"
     VIDEO = "video"
+    DOCUMENT = "document"
 
 
 class PromptMessageContent(BaseModel):
@@ -93,7 +95,7 @@ class ImagePromptMessageContent(PromptMessageContent):
     Model class for image prompt message content.
     """
 
-    class DETAIL(str, Enum):
+    class DETAIL(StrEnum):
         LOW = "low"
         HIGH = "high"
 
@@ -101,13 +103,20 @@ class ImagePromptMessageContent(PromptMessageContent):
     detail: DETAIL = DETAIL.LOW
 
 
+class DocumentPromptMessageContent(PromptMessageContent):
+    type: PromptMessageContentType = PromptMessageContentType.DOCUMENT
+    encode_format: Literal["base64"]
+    mime_type: str
+    data: str
+
+
 class PromptMessage(ABC, BaseModel):
     """
     Model class for prompt message.
     """
 
     role: PromptMessageRole
-    content: Optional[str | list[PromptMessageContent]] = None
+    content: Optional[str | Sequence[PromptMessageContent]] = None
     name: Optional[str] = None
 
     def is_empty(self) -> bool:

api/core/model_runtime/entities/model_entities.py

@@ -1,5 +1,5 @@
 from decimal import Decimal
-from enum import Enum
+from enum import Enum, StrEnum
 from typing import Any, Optional
 
 from pydantic import BaseModel, ConfigDict
@@ -87,9 +87,12 @@ class ModelFeature(Enum):
     AGENT_THOUGHT = "agent-thought"
     VISION = "vision"
     STREAM_TOOL_CALL = "stream-tool-call"
+    DOCUMENT = "document"
+    VIDEO = "video"
+    AUDIO = "audio"
 
 
-class DefaultParameterName(str, Enum):
+class DefaultParameterName(StrEnum):
     """
     Enum class for parameter template variable.
     """

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

@@ -2,7 +2,7 @@ import logging
 import re
 import time
 from abc import abstractmethod
-from collections.abc import Generator, Mapping
+from collections.abc import Generator, Mapping, Sequence
 from typing import Optional, Union
 
 from pydantic import ConfigDict
@@ -48,7 +48,7 @@ class LargeLanguageModel(AIModel):
         prompt_messages: list[PromptMessage],
         model_parameters: Optional[dict] = None,
         tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
+        stop: Optional[Sequence[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
         callbacks: Optional[list[Callback]] = None,
@@ -169,7 +169,7 @@ class LargeLanguageModel(AIModel):
         prompt_messages: list[PromptMessage],
         model_parameters: dict,
         tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
+        stop: Optional[Sequence[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
         callbacks: Optional[list[Callback]] = None,
@@ -212,7 +212,7 @@ if you are not sure about the structure.
             )
 
         model_parameters.pop("response_format")
-        stop = stop or []
+        stop = list(stop) if stop is not None else []
         stop.extend(["\n```", "```\n"])
         block_prompts = block_prompts.replace("{{block}}", code_block)
 
@@ -408,7 +408,7 @@ if you are not sure about the structure.
         prompt_messages: list[PromptMessage],
         model_parameters: dict,
         tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
+        stop: Optional[Sequence[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
         callbacks: Optional[list[Callback]] = None,
@@ -479,7 +479,7 @@ if you are not sure about the structure.
         prompt_messages: list[PromptMessage],
         model_parameters: dict,
         tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
+        stop: Optional[Sequence[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
     ) -> Union[LLMResult, Generator]:
@@ -601,7 +601,7 @@ if you are not sure about the structure.
         prompt_messages: list[PromptMessage],
         model_parameters: dict,
         tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
+        stop: Optional[Sequence[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
         callbacks: Optional[list[Callback]] = None,
@@ -647,7 +647,7 @@ if you are not sure about the structure.
         prompt_messages: list[PromptMessage],
         model_parameters: dict,
         tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
+        stop: Optional[Sequence[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
         callbacks: Optional[list[Callback]] = None,
@@ -694,7 +694,7 @@ if you are not sure about the structure.
         prompt_messages: list[PromptMessage],
         model_parameters: dict,
         tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
+        stop: Optional[Sequence[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
         callbacks: Optional[list[Callback]] = None,
@@ -742,7 +742,7 @@ if you are not sure about the structure.
         prompt_messages: list[PromptMessage],
         model_parameters: dict,
         tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
+        stop: Optional[Sequence[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
         callbacks: Optional[list[Callback]] = None,

api/core/model_runtime/model_providers/anthropic/llm/claude-3-5-sonnet-20240620.yaml

@@ -7,6 +7,7 @@ features:
   - vision
   - tool-call
   - stream-tool-call
+  - document
 model_properties:
   mode: chat
   context_size: 200000

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

@@ -7,6 +7,7 @@ features:
   - vision
   - tool-call
   - stream-tool-call
+  - document
 model_properties:
   mode: chat
   context_size: 200000

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

@@ -1,7 +1,7 @@
 import base64
 import io
 import json
-from collections.abc import Generator
+from collections.abc import Generator, Sequence
 from typing import Optional, Union, cast
 
 import anthropic
@@ -21,9 +21,9 @@ from httpx import Timeout
 from PIL import Image
 
 from core.model_runtime.callbacks.base_callback import Callback
-from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta
+from core.model_runtime.entities import (
-from core.model_runtime.entities.message_entities import (
     AssistantPromptMessage,
+    DocumentPromptMessageContent,
     ImagePromptMessageContent,
     PromptMessage,
     PromptMessageContentType,
@@ -33,6 +33,7 @@ from core.model_runtime.entities.message_entities import (
     ToolPromptMessage,
     UserPromptMessage,
 )
+from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta
 from core.model_runtime.errors.invoke import (
     InvokeAuthorizationError,
     InvokeBadRequestError,
@@ -86,10 +87,10 @@ class AnthropicLargeLanguageModel(LargeLanguageModel):
         self,
         model: str,
         credentials: dict,
-        prompt_messages: list[PromptMessage],
+        prompt_messages: Sequence[PromptMessage],
         model_parameters: dict,
         tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
+        stop: Optional[Sequence[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
     ) -> Union[LLMResult, Generator]:
@@ -130,9 +131,17 @@ class AnthropicLargeLanguageModel(LargeLanguageModel):
         # Add the new header for claude-3-5-sonnet-20240620 model
         extra_headers = {}
         if model == "claude-3-5-sonnet-20240620":
-            if model_parameters.get("max_tokens") > 4096:
+            if model_parameters.get("max_tokens", 0) > 4096:
                 extra_headers["anthropic-beta"] = "max-tokens-3-5-sonnet-2024-07-15"
 
+        if any(
+            isinstance(content, DocumentPromptMessageContent)
+            for prompt_message in prompt_messages
+            if isinstance(prompt_message.content, list)
+            for content in prompt_message.content
+        ):
+            extra_headers["anthropic-beta"] = "pdfs-2024-09-25"
+
         if tools:
             extra_model_kwargs["tools"] = [self._transform_tool_prompt(tool) for tool in tools]
             response = client.beta.tools.messages.create(
@@ -504,6 +513,21 @@ class AnthropicLargeLanguageModel(LargeLanguageModel):
                                     "source": {"type": "base64", "media_type": mime_type, "data": base64_data},
                                 }
                                 sub_messages.append(sub_message_dict)
+                            elif isinstance(message_content, DocumentPromptMessageContent):
+                                if message_content.mime_type != "application/pdf":
+                                    raise ValueError(
+                                        f"Unsupported document type {message_content.mime_type}, "
+                                        "only support application/pdf"
+                                    )
+                                sub_message_dict = {
+                                    "type": "document",
+                                    "source": {
+                                        "type": message_content.encode_format,
+                                        "media_type": message_content.mime_type,
+                                        "data": message_content.data,
+                                    },
+                                }
+                                sub_messages.append(sub_message_dict)
                         prompt_message_dicts.append({"role": "user", "content": sub_messages})
                 elif isinstance(message, AssistantPromptMessage):
                     message = cast(AssistantPromptMessage, message)

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

@@ -15,9 +15,9 @@ parameter_rules:
     use_template: max_tokens
     required: true
     type: int
-    default: 4096
+    default: 8192
     min: 1
-    max: 4096
+    max: 8192
     help:
       zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
       en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.

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

@@ -16,9 +16,9 @@ parameter_rules:
     use_template: max_tokens
     required: true
     type: int
-    default: 4096
+    default: 8192
     min: 1
-    max: 4096
+    max: 8192
     help:
       zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
       en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.

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

@@ -5,6 +5,7 @@ label:
 model_type: llm
 features:
   - agent-thought
+  - tool-call
   - multi-tool-call
   - stream-tool-call
 model_properties:
@@ -72,7 +73,7 @@ parameter_rules:
       - text
       - json_object
 pricing:
-  input: '1'
+  input: "1"
-  output: '2'
+  output: "2"
-  unit: '0.000001'
+  unit: "0.000001"
   currency: RMB

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

@@ -5,6 +5,7 @@ label:
 model_type: llm
 features:
   - agent-thought
+  - tool-call
   - multi-tool-call
   - stream-tool-call
 model_properties:

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

@@ -1,18 +1,17 @@
 from collections.abc import Generator
 from typing import Optional, Union
-from urllib.parse import urlparse
 
-import tiktoken
+from yarl import URL
 
-from core.model_runtime.entities.llm_entities import LLMResult
+from core.model_runtime.entities.llm_entities import LLMMode, LLMResult
 from core.model_runtime.entities.message_entities import (
     PromptMessage,
     PromptMessageTool,
 )
-from core.model_runtime.model_providers.openai.llm.llm import OpenAILargeLanguageModel
+from core.model_runtime.model_providers.openai_api_compatible.llm.llm import OAIAPICompatLargeLanguageModel
 
 
-class DeepSeekLargeLanguageModel(OpenAILargeLanguageModel):
+class DeepseekLargeLanguageModel(OAIAPICompatLargeLanguageModel):
     def _invoke(
         self,
         model: str,
@@ -25,92 +24,15 @@ class DeepSeekLargeLanguageModel(OpenAILargeLanguageModel):
         user: Optional[str] = None,
     ) -> Union[LLMResult, Generator]:
         self._add_custom_parameters(credentials)
-
+        return super()._invoke(model, credentials, prompt_messages, model_parameters, tools, stop, stream)
-        return super()._invoke(model, credentials, prompt_messages, model_parameters, tools, stop, stream, user)
 
     def validate_credentials(self, model: str, credentials: dict) -> None:
         self._add_custom_parameters(credentials)
         super().validate_credentials(model, credentials)
 
-    # refactored from openai model runtime, use cl100k_base for calculate token number
-    def _num_tokens_from_string(self, model: str, text: str, tools: Optional[list[PromptMessageTool]] = None) -> int:
-        """
-        Calculate num tokens for text completion model with tiktoken package.
-
-        :param model: model name
-        :param text: prompt text
-        :param tools: tools for tool calling
-        :return: number of tokens
-        """
-        encoding = tiktoken.get_encoding("cl100k_base")
-        num_tokens = len(encoding.encode(text))
-
-        if tools:
-            num_tokens += self._num_tokens_for_tools(encoding, tools)
-
-        return num_tokens
-
-    # refactored from openai model runtime, use cl100k_base for calculate token number
-    def _num_tokens_from_messages(
-        self, model: str, messages: list[PromptMessage], tools: Optional[list[PromptMessageTool]] = None
-    ) -> int:
-        """Calculate num tokens for gpt-3.5-turbo and gpt-4 with tiktoken package.
-
-        Official documentation: https://github.com/openai/openai-cookbook/blob/
-        main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb"""
-        encoding = tiktoken.get_encoding("cl100k_base")
-        tokens_per_message = 3
-        tokens_per_name = 1
-
-        num_tokens = 0
-        messages_dict = [self._convert_prompt_message_to_dict(m) for m in messages]
-        for message in messages_dict:
-            num_tokens += tokens_per_message
-            for key, value in message.items():
-                # Cast str(value) in case the message value is not a string
-                # This occurs with function messages
-                # TODO: The current token calculation method for the image type is not implemented,
-                #  which need to download the image and then get the resolution for calculation,
-                #  and will increase the request delay
-                if isinstance(value, list):
-                    text = ""
-                    for item in value:
-                        if isinstance(item, dict) and item["type"] == "text":
-                            text += item["text"]
-
-                    value = text
-
-                if key == "tool_calls":
-                    for tool_call in value:
-                        for t_key, t_value in tool_call.items():
-                            num_tokens += len(encoding.encode(t_key))
-                            if t_key == "function":
-                                for f_key, f_value in t_value.items():
-                                    num_tokens += len(encoding.encode(f_key))
-                                    num_tokens += len(encoding.encode(f_value))
-                            else:
-                                num_tokens += len(encoding.encode(t_key))
-                                num_tokens += len(encoding.encode(t_value))
-                else:
-                    num_tokens += len(encoding.encode(str(value)))
-
-                if key == "name":
-                    num_tokens += tokens_per_name
-
-        # every reply is primed with <im_start>assistant
-        num_tokens += 3
-
-        if tools:
-            num_tokens += self._num_tokens_for_tools(encoding, tools)
-
-        return num_tokens
-
     @staticmethod
-    def _add_custom_parameters(credentials: dict) -> None:
+    def _add_custom_parameters(credentials) -> None:
-        credentials["mode"] = "chat"
+        credentials["endpoint_url"] = str(URL(credentials.get("endpoint_url", "https://api.deepseek.com")))
-        credentials["openai_api_key"] = credentials["api_key"]
+        credentials["mode"] = LLMMode.CHAT.value
-        if "endpoint_url" not in credentials or credentials["endpoint_url"] == "":
+        credentials["function_calling_type"] = "tool_call"
-            credentials["openai_api_base"] = "https://api.deepseek.com"
+        credentials["stream_function_calling"] = "support"
-        else:
-            parsed_url = urlparse(credentials["endpoint_url"])
-            credentials["openai_api_base"] = f"{parsed_url.scheme}://{parsed_url.netloc}"

api/core/model_runtime/model_providers/fishaudio/fishaudio.py

@@ -18,7 +18,8 @@ class FishAudioProvider(ModelProvider):
         """
         try:
             model_instance = self.get_model_instance(ModelType.TTS)
-            model_instance.validate_credentials(credentials=credentials)
+            # FIXME fish tts do not have model for now, so set it to empty string instead
+            model_instance.validate_credentials(model="", credentials=credentials)
         except CredentialsValidateFailedError as ex:
             raise ex
         except Exception as ex:

api/core/model_runtime/model_providers/fishaudio/tts/tts.py

@@ -66,7 +66,7 @@ class FishAudioText2SpeechModel(TTSModel):
             voice=voice,
         )
 
-    def validate_credentials(self, credentials: dict, user: Optional[str] = None) -> None:
+    def validate_credentials(self, model: str, credentials: dict, user: Optional[str] = None) -> None:
         """
         Validate credentials for text2speech model
 
@@ -76,7 +76,7 @@ class FishAudioText2SpeechModel(TTSModel):
 
         try:
             self.get_tts_model_voices(
-                None,
+                "",
                 credentials={
                     "api_key": credentials["api_key"],
                     "api_base": credentials["api_base"],

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

@@ -7,6 +7,7 @@ features:
   - vision
   - tool-call
   - stream-tool-call
+  - document
 model_properties:
   mode: chat
   context_size: 1048576

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

@@ -7,6 +7,7 @@ features:
   - vision
   - tool-call
   - stream-tool-call
+  - document
 model_properties:
   mode: chat
   context_size: 1048576

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

@@ -7,6 +7,7 @@ features:
   - vision
   - tool-call
   - stream-tool-call
+  - document
 model_properties:
   mode: chat
   context_size: 1048576

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

@@ -7,6 +7,7 @@ features:
   - vision
   - tool-call
   - stream-tool-call
+  - document
 model_properties:
   mode: chat
   context_size: 1048576

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

@@ -7,6 +7,7 @@ features:
   - vision
   - tool-call
   - stream-tool-call
+  - document
 model_properties:
   mode: chat
   context_size: 1048576

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

@@ -7,6 +7,7 @@ features:
   - vision
   - tool-call
   - stream-tool-call
+  - document
 model_properties:
   mode: chat
   context_size: 1048576

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

@@ -7,6 +7,7 @@ features:
   - vision
   - tool-call
   - stream-tool-call
+  - document
 model_properties:
   mode: chat
   context_size: 1048576

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

@@ -7,6 +7,7 @@ features:
   - vision
   - tool-call
   - stream-tool-call
+  - document
 model_properties:
   mode: chat
   context_size: 2097152

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

@@ -7,6 +7,7 @@ features:
   - vision
   - tool-call
   - stream-tool-call
+  - document
 model_properties:
   mode: chat
   context_size: 2097152

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

@@ -7,6 +7,7 @@ features:
   - vision
   - tool-call
   - stream-tool-call
+  - document
 model_properties:
   mode: chat
   context_size: 2097152

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

@@ -7,6 +7,7 @@ features:
   - vision
   - tool-call
   - stream-tool-call
+  - document
 model_properties:
   mode: chat
   context_size: 2097152

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

@@ -7,6 +7,7 @@ features:
   - vision
   - tool-call
   - stream-tool-call
+  - document
 model_properties:
   mode: chat
   context_size: 2097152

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

@@ -7,6 +7,7 @@ features:
   - vision
   - tool-call
   - stream-tool-call
+  - document
 model_properties:
   mode: chat
   context_size: 2097152

api/core/model_runtime/model_providers/google/llm/gemini-exp-1114.yaml

@@ -7,9 +7,10 @@ features:
   - vision
   - tool-call
   - stream-tool-call
+  - document
 model_properties:
   mode: chat
-  context_size: 2097152
+  context_size: 32767
 parameter_rules:
   - name: temperature
     use_template: temperature

api/core/model_runtime/model_providers/google/llm/gemini-exp-1121.yaml

@@ -0,0 +1,38 @@
+model: gemini-exp-1121
+label:
+  en_US: Gemini exp 1121
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 32767
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_output_tokens
+    use_template: max_tokens
+    default: 8192
+    min: 1
+    max: 8192
+  - name: json_schema
+    use_template: json_schema
+pricing:
+  input: '0.00'
+  output: '0.00'
+  unit: '0.000001'
+  currency: USD

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

@@ -0,0 +1,38 @@
+model: learnlm-1.5-pro-experimental
+label:
+  en_US: LearnLM 1.5 Pro Experimental
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 32767
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_output_tokens
+    use_template: max_tokens
+    default: 8192
+    min: 1
+    max: 8192
+  - name: json_schema
+    use_template: json_schema
+pricing:
+  input: '0.00'
+  output: '0.00'
+  unit: '0.000001'
+  currency: USD

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

@@ -16,6 +16,7 @@ from PIL import Image
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta
 from core.model_runtime.entities.message_entities import (
     AssistantPromptMessage,
+    DocumentPromptMessageContent,
     ImagePromptMessageContent,
     PromptMessage,
     PromptMessageContentType,
@@ -35,6 +36,21 @@ 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
 
+GOOGLE_AVAILABLE_MIMETYPE = [
+    "application/pdf",
+    "application/x-javascript",
+    "text/javascript",
+    "application/x-python",
+    "text/x-python",
+    "text/plain",
+    "text/html",
+    "text/css",
+    "text/md",
+    "text/csv",
+    "text/xml",
+    "text/rtf",
+]
+
 
 class GoogleLargeLanguageModel(LargeLanguageModel):
     def _invoke(
@@ -370,6 +386,12 @@ class GoogleLargeLanguageModel(LargeLanguageModel):
                                 raise ValueError(f"Failed to fetch image data from url {message_content.data}, {ex}")
                         blob = {"inline_data": {"mime_type": mime_type, "data": base64_data}}
                         glm_content["parts"].append(blob)
+                    elif c.type == PromptMessageContentType.DOCUMENT:
+                        message_content = cast(DocumentPromptMessageContent, c)
+                        if message_content.mime_type not in GOOGLE_AVAILABLE_MIMETYPE:
+                            raise ValueError(f"Unsupported mime type {message_content.mime_type}")
+                        blob = {"inline_data": {"mime_type": message_content.mime_type, "data": message_content.data}}
+                        glm_content["parts"].append(blob)
 
             return glm_content
         elif isinstance(message, AssistantPromptMessage):

api/core/model_runtime/model_providers/huggingface_tei/huggingface_tei.yaml

@@ -34,3 +34,11 @@ model_credential_schema:
       placeholder:
         zh_Hans: 在此输入Text Embedding Inference的服务器地址，如 http://192.168.1.100:8080
         en_US: Enter the url of your Text Embedding Inference, e.g. http://192.168.1.100:8080
+    - variable: api_key
+      label:
+        en_US: API Key
+      type: secret-input
+      required: false
+      placeholder:
+        zh_Hans: 在此输入您的 API Key
+        en_US: Enter your API Key

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

@@ -51,8 +51,13 @@ class HuggingfaceTeiRerankModel(RerankModel):
 
         server_url = server_url.removesuffix("/")
 
+        headers = {"Content-Type": "application/json"}
+        api_key = credentials.get("api_key")
+        if api_key:
+            headers["Authorization"] = f"Bearer {api_key}"
+
         try:
-            results = TeiHelper.invoke_rerank(server_url, query, docs)
+            results = TeiHelper.invoke_rerank(server_url, query, docs, headers)
 
             rerank_documents = []
             for result in results:
@@ -80,7 +85,11 @@ class HuggingfaceTeiRerankModel(RerankModel):
         """
         try:
             server_url = credentials["server_url"]
-            extra_args = TeiHelper.get_tei_extra_parameter(server_url, model)
+            headers = {"Content-Type": "application/json"}
+            api_key = credentials.get("api_key")
+            if api_key:
+                headers["Authorization"] = f"Bearer {api_key}"
+            extra_args = TeiHelper.get_tei_extra_parameter(server_url, model, headers)
             if extra_args.model_type != "reranker":
                 raise CredentialsValidateFailedError("Current model is not a rerank model")
 

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

@@ -26,13 +26,15 @@ cache_lock = Lock()
 
 class TeiHelper:
     @staticmethod
-    def get_tei_extra_parameter(server_url: str, model_name: str) -> TeiModelExtraParameter:
+    def get_tei_extra_parameter(
+        server_url: str, model_name: str, headers: Optional[dict] = None
+    ) -> TeiModelExtraParameter:
         TeiHelper._clean_cache()
         with cache_lock:
             if model_name not in cache:
                 cache[model_name] = {
                     "expires": time() + 300,
-                    "value": TeiHelper._get_tei_extra_parameter(server_url),
+                    "value": TeiHelper._get_tei_extra_parameter(server_url, headers),
                 }
             return cache[model_name]["value"]
 
@@ -47,7 +49,7 @@ class TeiHelper:
             pass
 
     @staticmethod
-    def _get_tei_extra_parameter(server_url: str) -> TeiModelExtraParameter:
+    def _get_tei_extra_parameter(server_url: str, headers: Optional[dict] = None) -> TeiModelExtraParameter:
         """
         get tei model extra parameter like model_type, max_input_length, max_batch_requests
         """
@@ -61,7 +63,7 @@ class TeiHelper:
         session.mount("https://", HTTPAdapter(max_retries=3))
 
         try:
-            response = session.get(url, timeout=10)
+            response = session.get(url, headers=headers, timeout=10)
         except (MissingSchema, ConnectionError, Timeout) as e:
             raise RuntimeError(f"get tei model extra parameter failed, url: {url}, error: {e}")
         if response.status_code != 200:
@@ -86,7 +88,7 @@ class TeiHelper:
         )
 
     @staticmethod
-    def invoke_tokenize(server_url: str, texts: list[str]) -> list[list[dict]]:
+    def invoke_tokenize(server_url: str, texts: list[str], headers: Optional[dict] = None) -> list[list[dict]]:
         """
         Invoke tokenize endpoint
 
@@ -114,15 +116,15 @@ class TeiHelper:
         :param server_url: server url
         :param texts: texts to tokenize
         """
-        resp = httpx.post(
+        url = f"{server_url}/tokenize"
-            f"{server_url}/tokenize",
+        json_data = {"inputs": texts}
-            json={"inputs": texts},
+        resp = httpx.post(url, json=json_data, headers=headers)
-        )
+
         resp.raise_for_status()
         return resp.json()
 
     @staticmethod
-    def invoke_embeddings(server_url: str, texts: list[str]) -> dict:
+    def invoke_embeddings(server_url: str, texts: list[str], headers: Optional[dict] = None) -> dict:
         """
         Invoke embeddings endpoint
 
@@ -147,15 +149,14 @@ class TeiHelper:
         :param texts: texts to embed
         """
         # Use OpenAI compatible API here, which has usage tracking
-        resp = httpx.post(
+        url = f"{server_url}/v1/embeddings"
-            f"{server_url}/v1/embeddings",
+        json_data = {"input": texts}
-            json={"input": texts},
+        resp = httpx.post(url, json=json_data, headers=headers)
-        )
         resp.raise_for_status()
         return resp.json()
 
     @staticmethod
-    def invoke_rerank(server_url: str, query: str, docs: list[str]) -> list[dict]:
+    def invoke_rerank(server_url: str, query: str, docs: list[str], headers: Optional[dict] = None) -> list[dict]:
         """
         Invoke rerank endpoint
 
@@ -173,10 +174,7 @@ class TeiHelper:
         :param candidates: candidates to rerank
         """
         params = {"query": query, "texts": docs, "return_text": True}
-
+        url = f"{server_url}/rerank"
-        response = httpx.post(
+        response = httpx.post(url, json=params, headers=headers)
-            server_url + "/rerank",
-            json=params,
-        )
         response.raise_for_status()
         return response.json()

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

@@ -51,6 +51,10 @@ class HuggingfaceTeiTextEmbeddingModel(TextEmbeddingModel):
 
         server_url = server_url.removesuffix("/")
 
+        headers = {"Content-Type": "application/json"}
+        api_key = credentials["api_key"]
+        if api_key:
+            headers["Authorization"] = f"Bearer {api_key}"
         # get model properties
         context_size = self._get_context_size(model, credentials)
         max_chunks = self._get_max_chunks(model, credentials)
@@ -60,7 +64,7 @@ class HuggingfaceTeiTextEmbeddingModel(TextEmbeddingModel):
         used_tokens = 0
 
         # get tokenized results from TEI
-        batched_tokenize_result = TeiHelper.invoke_tokenize(server_url, texts)
+        batched_tokenize_result = TeiHelper.invoke_tokenize(server_url, texts, headers)
 
         for i, (text, tokenize_result) in enumerate(zip(texts, batched_tokenize_result)):
             # Check if the number of tokens is larger than the context size
@@ -97,7 +101,7 @@ class HuggingfaceTeiTextEmbeddingModel(TextEmbeddingModel):
             used_tokens = 0
             for i in _iter:
                 iter_texts = inputs[i : i + max_chunks]
-                results = TeiHelper.invoke_embeddings(server_url, iter_texts)
+                results = TeiHelper.invoke_embeddings(server_url, iter_texts, headers)
                 embeddings = results["data"]
                 embeddings = [embedding["embedding"] for embedding in embeddings]
                 batched_embeddings.extend(embeddings)
@@ -127,7 +131,11 @@ class HuggingfaceTeiTextEmbeddingModel(TextEmbeddingModel):
 
         server_url = server_url.removesuffix("/")
 
-        batch_tokens = TeiHelper.invoke_tokenize(server_url, texts)
+        headers = {
+            "Authorization": f"Bearer {credentials.get('api_key')}",
+        }
+
+        batch_tokens = TeiHelper.invoke_tokenize(server_url, texts, headers)
         num_tokens = sum(len(tokens) for tokens in batch_tokens)
         return num_tokens
 
@@ -141,7 +149,14 @@ class HuggingfaceTeiTextEmbeddingModel(TextEmbeddingModel):
         """
         try:
             server_url = credentials["server_url"]
-            extra_args = TeiHelper.get_tei_extra_parameter(server_url, model)
+            headers = {"Content-Type": "application/json"}
+
+            api_key = credentials.get("api_key")
+
+            if api_key:
+                headers["Authorization"] = f"Bearer {api_key}"
+
+            extra_args = TeiHelper.get_tei_extra_parameter(server_url, model, headers)
             print(extra_args)
             if extra_args.model_type != "embedding":
                 raise CredentialsValidateFailedError("Current model is not a embedding model")

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

@@ -3,6 +3,7 @@
 - gpt-4o
 - gpt-4o-2024-05-13
 - gpt-4o-2024-08-06
+- gpt-4o-2024-11-20
 - chatgpt-4o-latest
 - gpt-4o-mini
 - gpt-4o-mini-2024-07-18

api/core/model_runtime/model_providers/openai/llm/gpt-4o-2024-11-20.yaml

@@ -0,0 +1,47 @@
+model: gpt-4o-2024-11-20
+label:
+  zh_Hans: gpt-4o-2024-11-20
+  en_US: gpt-4o-2024-11-20
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+  - vision
+model_properties:
+  mode: chat
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+  - name: max_tokens
+    use_template: max_tokens
+    default: 512
+    min: 1
+    max: 16384
+  - name: response_format
+    label:
+      zh_Hans: 回复格式
+      en_US: Response Format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
+      - json_schema
+  - name: json_schema
+    use_template: json_schema
+pricing:
+  input: '2.50'
+  output: '10.00'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/openai/llm/gpt-4o-audio-preview.yaml

@@ -7,7 +7,7 @@ features:
   - multi-tool-call
   - agent-thought
   - stream-tool-call
-  - vision
+  - audio
 model_properties:
   mode: chat
   context_size: 128000

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

@@ -64,7 +64,7 @@ class OAICompatRerankModel(RerankModel):
 
         # TODO: Do we need truncate docs to avoid llama.cpp return error?
 
-        data = {"model": model_name, "query": query, "documents": docs, "top_n": top_n}
+        data = {"model": model_name, "query": query, "documents": docs, "top_n": top_n, "return_documents": True}
 
         try:
             response = post(str(URL(url) / "rerank"), headers=headers, data=dumps(data), timeout=60)
@@ -83,7 +83,13 @@ class OAICompatRerankModel(RerankModel):
                 index = result["index"]
 
                 # Retrieve document text (fallback if llama.cpp rerank doesn't return it)
-                text = result.get("document", {}).get("text", docs[index])
+                text = docs[index]
+                document = result.get("document", {})
+                if document:
+                    if isinstance(document, dict):
+                        text = document.get("text", docs[index])
+                    elif isinstance(document, str):
+                        text = document
 
                 # Normalize the score
                 normalized_score = (result["relevance_score"] - min_score) / score_range

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

@@ -24,4 +24,3 @@
 - meta-llama/Meta-Llama-3.1-8B-Instruct
 - google/gemma-2-27b-it
 - google/gemma-2-9b-it
-- deepseek-ai/DeepSeek-V2-Chat

api/core/model_runtime/model_providers/siliconflow/siliconflow.yaml

@@ -18,6 +18,7 @@ supported_model_types:
   - text-embedding
   - rerank
   - speech2text
+  - tts
 configurate_methods:
   - predefined-model
   - customizable-model

api/core/model_runtime/model_providers/siliconflow/tts/fish-speech-1.4.yaml

@@ -0,0 +1,37 @@
+model: fishaudio/fish-speech-1.4
+model_type: tts
+model_properties:
+  default_voice: 'fishaudio/fish-speech-1.4:alex'
+  voices:
+    - mode: "fishaudio/fish-speech-1.4:alex"
+      name: "Alex（男声）"
+      language: [ "zh-Hans", "en-US" ]
+    - mode: "fishaudio/fish-speech-1.4:benjamin"
+      name: "Benjamin（男声）"
+      language: [ "zh-Hans", "en-US" ]
+    - mode: "fishaudio/fish-speech-1.4:charles"
+      name: "Charles（男声）"
+      language: [ "zh-Hans", "en-US" ]
+    - mode: "fishaudio/fish-speech-1.4:david"
+      name: "David（男声）"
+      language: [ "zh-Hans", "en-US" ]
+    - mode: "fishaudio/fish-speech-1.4:anna"
+      name: "Anna（女声）"
+      language: [ "zh-Hans", "en-US" ]
+    - mode: "fishaudio/fish-speech-1.4:bella"
+      name: "Bella（女声）"
+      language: [ "zh-Hans", "en-US" ]
+    - mode: "fishaudio/fish-speech-1.4:claire"
+      name: "Claire（女声）"
+      language: [ "zh-Hans", "en-US" ]
+    - mode: "fishaudio/fish-speech-1.4:diana"
+      name: "Diana（女声）"
+      language: [ "zh-Hans", "en-US" ]
+  audio_type: 'mp3'
+  max_workers: 5
+  # stream: false
+pricing:
+  input: '0.015'
+  output: '0'
+  unit: '0.001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/tts/tts.py

@@ -0,0 +1,105 @@
+import concurrent.futures
+from typing import Any, Optional
+
+from openai import OpenAI
+
+from core.model_runtime.errors.invoke import InvokeBadRequestError
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.model_runtime.model_providers.__base.tts_model import TTSModel
+from core.model_runtime.model_providers.openai._common import _CommonOpenAI
+
+
+class SiliconFlowText2SpeechModel(_CommonOpenAI, TTSModel):
+    """
+    Model class for SiliconFlow Speech to text model.
+    """
+
+    def _invoke(
+        self, model: str, tenant_id: str, credentials: dict, content_text: str, voice: str, user: Optional[str] = None
+    ) -> Any:
+        """
+        _invoke text2speech model
+
+        :param model: model name
+        :param tenant_id: user tenant id
+        :param credentials: model credentials
+        :param content_text: text content to be translated
+        :param voice: model timbre
+        :param user: unique user id
+        :return: text translated to audio file
+        """
+        if not voice or voice not in [
+            d["value"] for d in self.get_tts_model_voices(model=model, credentials=credentials)
+        ]:
+            voice = self._get_model_default_voice(model, credentials)
+        # if streaming:
+        return self._tts_invoke_streaming(model=model, credentials=credentials, content_text=content_text, voice=voice)
+
+    def validate_credentials(self, model: str, credentials: dict, user: Optional[str] = None) -> None:
+        """
+        validate credentials text2speech model
+
+        :param model: model name
+        :param credentials: model credentials
+        :param user: unique user id
+        :return: text translated to audio file
+        """
+        try:
+            self._tts_invoke_streaming(
+                model=model,
+                credentials=credentials,
+                content_text="Hello SiliconFlow!",
+                voice=self._get_model_default_voice(model, credentials),
+            )
+        except Exception as ex:
+            raise CredentialsValidateFailedError(str(ex))
+
+    def _tts_invoke_streaming(self, model: str, credentials: dict, content_text: str, voice: str) -> Any:
+        """
+        _tts_invoke_streaming text2speech model
+
+        :param model: model name
+        :param credentials: model credentials
+        :param content_text: text content to be translated
+        :param voice: model timbre
+        :return: text translated to audio file
+        """
+        try:
+            # doc: https://docs.siliconflow.cn/capabilities/text-to-speech
+            self._add_custom_parameters(credentials)
+            credentials_kwargs = self._to_credential_kwargs(credentials)
+            client = OpenAI(**credentials_kwargs)
+            model_support_voice = [
+                x.get("value") for x in self.get_tts_model_voices(model=model, credentials=credentials)
+            ]
+            if not voice or voice not in model_support_voice:
+                voice = self._get_model_default_voice(model, credentials)
+            if len(content_text) > 4096:
+                sentences = self._split_text_into_sentences(content_text, max_length=4096)
+                executor = concurrent.futures.ThreadPoolExecutor(max_workers=min(3, len(sentences)))
+                futures = [
+                    executor.submit(
+                        client.audio.speech.with_streaming_response.create,
+                        model=model,
+                        response_format="mp3",
+                        input=sentences[i],
+                        voice=voice,
+                    )
+                    for i in range(len(sentences))
+                ]
+                for future in futures:
+                    yield from future.result().__enter__().iter_bytes(1024)  # noqa:PLC2801
+
+            else:
+                response = client.audio.speech.with_streaming_response.create(
+                    model=model, voice=voice, response_format="mp3", input=content_text.strip()
+                )
+
+                yield from response.__enter__().iter_bytes(1024)  # noqa:PLC2801
+        except Exception as ex:
+            raise InvokeBadRequestError(str(ex))
+
+    @classmethod
+    def _add_custom_parameters(cls, credentials: dict) -> None:
+        credentials["openai_api_base"] = "https://api.siliconflow.cn"
+        credentials["openai_api_key"] = credentials["api_key"]

api/core/model_runtime/model_providers/tongyi/llm/qwen-vl-max-0809.yaml

@@ -6,6 +6,7 @@ model_type: llm
 features:
   - vision
   - agent-thought
+  - video
 model_properties:
   mode: chat
   context_size: 32000

api/core/model_runtime/model_providers/tongyi/llm/qwen-vl-max.yaml

@@ -6,6 +6,7 @@ model_type: llm
 features:
   - vision
   - agent-thought
+  - video
 model_properties:
   mode: chat
   context_size: 32000

api/core/model_runtime/model_providers/tongyi/llm/qwen-vl-plus-0809.yaml

@@ -6,6 +6,7 @@ model_type: llm
 features:
   - vision
   - agent-thought
+  - video
 model_properties:
   mode: chat
   context_size: 32768

api/core/model_runtime/model_providers/tongyi/llm/qwen-vl-plus.yaml

@@ -6,6 +6,7 @@ model_type: llm
 features:
   - vision
   - agent-thought
+  - video
 model_properties:
   mode: chat
   context_size: 8000

api/core/model_runtime/model_providers/volcengine_maas/text_embedding/models.py

@@ -22,7 +22,7 @@ def get_model_config(credentials: dict) -> ModelConfig:
         return ModelConfig(
             properties=ModelProperties(
                 context_size=int(credentials.get("context_size", 0)),
-                max_chunks=int(credentials.get("max_chunks", 0)),
+                max_chunks=int(credentials.get("max_chunks", 1)),
             )
         )
     return model_configs