add download file method

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

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 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
+* [Docker](https://www.docker.com/)
+* [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 3.11.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.

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/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
 
@@ -57,6 +62,7 @@ from .datasets import (
     external,
     hit_testing,
     website,
+    fta_test,
 )
 
 # Import explore controllers

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)
-        app = AppDslService.import_and_create_new_app(
-            tenant_id=current_user.current_tenant_id, data=data, args=args, account=current_user
-        )
+        with Session(db.engine) as session:
+            import_service = AppDslService(session)
+            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/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/datasets/fta_test.py

@@ -0,0 +1,145 @@
+import json
+
+import requests
+from flask import Response
+from flask_restful import Resource, reqparse
+from sqlalchemy import text
+
+from controllers.console import api
+from extensions.ext_database import db
+from extensions.ext_storage import storage
+from models.fta import ComponentFailure, ComponentFailureStats
+
+
+class FATTestApi(Resource):
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("log_process_data", nullable=False, required=True, type=str, location="args")
+        args = parser.parse_args()
+        print(args["log_process_data"])
+        # Extract the JSON string from the text field
+        json_str = args["log_process_data"].strip("```json\\n").strip("```").strip().replace("\\n", "")
+        log_data = json.loads(json_str)
+        db.session.query(ComponentFailure).delete()
+        for data in log_data:
+            if not isinstance(data, dict):
+                raise TypeError("Data must be a dictionary.")
+
+            required_keys = {"Date", "Component", "FailureMode", "Cause", "RepairAction", "Technician"}
+            if not required_keys.issubset(data.keys()):
+                raise ValueError(f"Data dictionary must contain the following keys: {required_keys}")
+
+            try:
+                # Clear existing stats
+                component_failure = ComponentFailure(
+                    Date=data["Date"],
+                    Component=data["Component"],
+                    FailureMode=data["FailureMode"],
+                    Cause=data["Cause"],
+                    RepairAction=data["RepairAction"],
+                    Technician=data["Technician"],
+                )
+                db.session.add(component_failure)
+                db.session.commit()
+            except Exception as e:
+                print(e)
+        # Clear existing stats
+        db.session.query(ComponentFailureStats).delete()
+
+        # Insert calculated statistics
+        try:
+            db.session.execute(
+                text("""
+                    INSERT INTO component_failure_stats ("Component", "FailureMode", "Cause", "PossibleAction", "Probability", "MTBF")
+                    SELECT 
+                        cf."Component",
+                        cf."FailureMode",
+                        cf."Cause",
+                        cf."RepairAction" as "PossibleAction",
+                        COUNT(*) * 1.0 / (SELECT COUNT(*) FROM component_failure WHERE "Component" = cf."Component") AS "Probability",
+                        COALESCE(AVG(EXTRACT(EPOCH FROM (next_failure_date::timestamp - cf."Date"::timestamp)) / 86400.0),0)AS "MTBF"
+                    FROM (
+                        SELECT 
+                            "Component",
+                            "FailureMode",
+                            "Cause",
+                            "RepairAction",
+                            "Date", 
+                            LEAD("Date") OVER (PARTITION BY "Component", "FailureMode", "Cause" ORDER BY "Date") AS next_failure_date
+                        FROM 
+                            component_failure
+                    ) cf
+                    GROUP BY 
+                        cf."Component", cf."FailureMode", cf."Cause", cf."RepairAction";
+            """)
+            )
+            db.session.commit()
+        except Exception as e:
+            db.session.rollback()
+            print(f"Error during stats calculation: {e}")
+        # output format
+        # [
+        #     (17, 'Hydraulic system', 'Leak', 'Hose rupture', 'Replaced hydraulic hose', 0.3333333333333333, None),
+        #     (18, 'Hydraulic system', 'Leak', 'Seal Wear', 'Replaced the faulty seal', 0.3333333333333333, None),
+        #     (19, 'Hydraulic system', 'Pressure drop', 'Fluid leak', 'Replaced hydraulic fluid and seals', 0.3333333333333333, None)
+        # ]
+
+        component_failure_stats = db.session.query(ComponentFailureStats).all()
+        # Convert stats to list of tuples format
+        stats_list = []
+        for stat in component_failure_stats:
+            stats_list.append(
+                (
+                    stat.StatID,
+                    stat.Component,
+                    stat.FailureMode,
+                    stat.Cause,
+                    stat.PossibleAction,
+                    stat.Probability,
+                    stat.MTBF,
+                )
+            )
+        return {"data": stats_list}, 200
+
+
+# generate-fault-tree
+class GenerateFaultTreeApi(Resource):
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("llm_text", nullable=False, required=True, type=str, location="args")
+        args = parser.parse_args()
+        entities = args["llm_text"].replace("```", "").replace("\\n", "\n")
+        print(entities)
+        request_data = {"fault_tree_text": entities}
+        url = "https://fta.cognitech-dev.live/generate-fault-tree"
+        headers = {"accept": "application/json", "Content-Type": "application/json"}
+
+        response = requests.post(url, json=request_data, headers=headers)
+        print(response.json())
+        return {"data": response.json()}, 200
+
+
+class ExtractSVGApi(Resource):
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("svg_text", nullable=False, required=True, type=str, location="args")
+        args = parser.parse_args()
+        # svg_text = ''.join(args["svg_text"].splitlines())
+        svg_text = args["svg_text"].replace("\n", "")
+        svg_text = svg_text.replace('"', '"')
+        print(svg_text)
+        svg_text_json = json.loads(svg_text)
+        svg_content = svg_text_json.get("data").get("svg_content")[0]
+        svg_content = svg_content.replace("\n", "").replace('"', '"')
+        file_key = "fta_svg/" + "fat.svg"
+        if storage.exists(file_key):
+            storage.delete(file_key)
+        storage.save(file_key, svg_content.encode("utf-8"))
+        generator = storage.load(file_key, stream=True)
+
+        return Response(generator, mimetype="image/svg+xml")
+
+
+api.add_resource(FATTestApi, "/fta/db-handler")
+api.add_resource(GenerateFaultTreeApi, "/fta/generate-fault-tree")
+api.add_resource(ExtractSVGApi, "/fta/extract-svg")

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.")
-            else:
-                model_credentials = {}
+            raise ProviderTokenNotInitError(f"Model {model_name} credentials is not initialized.")
 
-        if not skip_check:
-            # check model
-            provider_model = provider_model_bundle.configuration.get_provider_model(
-                model=model_config.model, model_type=ModelType.LLM
-            )
+        # check model
+        provider_model = provider_model_bundle.configuration.get_provider_model(
+            model=model_config.model, model_type=ModelType.LLM
+        )
 
-            if provider_model is None:
-                model_name = model_config.model
-                raise ValueError(f"Model {model_name} not exist.")
+        if provider_model is None:
+            model_name = model_config.model
+            raise ValueError(f"Model {model_name} not exist.")
 
-            if provider_model.status == ModelStatus.NO_CONFIGURE:
-                raise ProviderTokenNotInitError(f"Model {model_name} credentials is not initialized.")
-            elif provider_model.status == ModelStatus.NO_PERMISSION:
-                raise ModelCurrentlyNotSupportError(f"Dify Hosted OpenAI {model_name} currently not support.")
-            elif provider_model.status == ModelStatus.QUOTA_EXCEEDED:
-                raise QuotaExceededError(f"Model provider {provider_name} quota exceeded.")
+        if provider_model.status == ModelStatus.NO_CONFIGURE:
+            raise ProviderTokenNotInitError(f"Model {model_name} credentials is not initialized.")
+        elif provider_model.status == ModelStatus.NO_PERMISSION:
+            raise ModelCurrentlyNotSupportError(f"Dify Hosted OpenAI {model_name} currently not support.")
+        elif provider_model.status == ModelStatus.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/task_pipeline/workflow_cycle_manage.py

@@ -217,9 +217,12 @@ class WorkflowCycleManage:
             ).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(

api/core/file/file_manager.py

@@ -1,9 +1,16 @@
 import base64
+import tempfile
+from pathlib import Path
 
 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
 
@@ -13,6 +20,38 @@ from .models import File, FileTransferMethod, FileType
 from .tool_file_parser import ToolFileParser
 
 
+def download_to_target_path(f: File, temp_dir: str, /):
+    if f.transfer_method == FileTransferMethod.TOOL_FILE:
+        tool_file = file_repository.get_tool_file(session=db.session(), file=f)
+        suffix = Path(tool_file.file_key).suffix
+        target_path = f"{temp_dir}/{next(tempfile._get_candidate_names())}{suffix}"
+        _download_file_to_target_path(tool_file.file_key, target_path)
+        return target_path
+    elif f.transfer_method == FileTransferMethod.LOCAL_FILE:
+        upload_file = file_repository.get_upload_file(session=db.session(), file=f)
+        suffix = Path(upload_file.key).suffix
+        target_path = f"{temp_dir}/{next(tempfile._get_candidate_names())}{suffix}"
+        _download_file_to_target_path(upload_file.key, target_path)
+        return target_path
+    else:
+        raise ValueError(f"Unsupported transfer method: {f.transfer_method}")
+
+
+def _download_file_to_target_path(path: str, target_path: str, /):
+    """
+    Download and return the contents of a file as bytes.
+
+    This function loads the file from storage and ensures it's in bytes format.
+
+    Args:
+        path (str): The path to the file in storage.
+        target_path (str): The path to the target file.
+    Raises:
+        ValueError: If the loaded file is not a bytes object.
+    """
+    storage.download(path, target_path)
+
+
 def get_attr(*, file: File, attr: FileAttribute):
     match attr:
         case FileAttribute.TYPE:
@@ -29,35 +68,17 @@ 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 +86,7 @@ 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 +95,20 @@ 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 +150,16 @@ 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
-            encoded_string = base64.b64encode(content).decode("utf-8")
-            return encoded_string
+            data = response.content
         case FileTransferMethod.LOCAL_FILE:
             upload_file = file_repository.get_upload_file(session=db.session(), file=f)
             data = _download_file_content(upload_file.key)
-            encoded_string = base64.b64encode(data).decode("utf-8")
-            return encoded_string
         case FileTransferMethod.TOOL_FILE:
             tool_file = file_repository.get_tool_file(session=db.session(), file=f)
             data = _download_file_content(tool_file.file_key)
-            encoded_string = base64.b64encode(data).decode("utf-8")
-            return encoded_string
-        case _:
-            raise ValueError(f"Unsupported transfer method: {f.transfer_method}")
+
+    encoded_string = base64.b64encode(data).decode("utf-8")
+    return encoded_string
 
 
 def _to_base64_data_string(f: File, /):
@@ -140,18 +167,6 @@ 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/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(
-                                file,
-                                image_detail_config=detail,
-                            )
-                            prompt_message_contents.append(prompt_message)
+                        prompt_message = file_manager.to_prompt_message_content(
+                            file,
+                            image_detail_config=detail,
+                        )
+                        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,

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 collections.abc import Sequence
 from enum import Enum
-from typing import Optional
+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(str, Enum):
     """
     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):
@@ -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

@@ -87,6 +87,9 @@ 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):

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.message_entities import (
+from core.model_runtime.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/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/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/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

api/core/model_runtime/model_providers/zhipuai/llm/glm_4v_plus.yaml

@@ -6,6 +6,7 @@ model_properties:
   mode: chat
 features:
   - vision
+  - video
 parameter_rules:
   - name: temperature
     use_template: temperature

api/core/prompt/utils/prompt_message_util.py

@@ -1,3 +1,4 @@
+from collections.abc import Sequence
 from typing import cast
 
 from core.model_runtime.entities import (
@@ -14,7 +15,7 @@ from core.prompt.simple_prompt_transform import ModelMode
 
 class PromptMessageUtil:
     @staticmethod
-    def prompt_messages_to_prompt_for_saving(model_mode: str, prompt_messages: list[PromptMessage]) -> list[dict]:
+    def prompt_messages_to_prompt_for_saving(model_mode: str, prompt_messages: Sequence[PromptMessage]) -> list[dict]:
         """
         Prompt messages to prompt for saving.
         :param model_mode: model mode

api/core/rag/cleaner/clean_processor.py

@@ -12,7 +12,7 @@ class CleanProcessor:
         # Unicode  U+FFFE
         text = re.sub("\ufffe", "", text)
 
-        rules = process_rule["rules"] if process_rule else None
+        rules = process_rule["rules"] if process_rule else {}
         if "pre_processing_rules" in rules:
             pre_processing_rules = rules["pre_processing_rules"]
             for pre_processing_rule in pre_processing_rules:

api/core/rag/rerank/rerank_model.py

@@ -27,11 +27,11 @@ class RerankModelRunner(BaseRerankRunner):
         :return:
         """
         docs = []
-        doc_id = set()
+        doc_ids = set()
         unique_documents = []
         for document in documents:
-            if document.provider == "dify" and document.metadata["doc_id"] not in doc_id:
-                doc_id.add(document.metadata["doc_id"])
+            if document.provider == "dify" and document.metadata["doc_id"] not in doc_ids:
+                doc_ids.add(document.metadata["doc_id"])
                 docs.append(document.page_content)
                 unique_documents.append(document)
             elif document.provider == "external":

api/core/rag/rerank/weight_rerank.py

@@ -37,11 +37,10 @@ class WeightRerankRunner(BaseRerankRunner):
         :return:
         """
         unique_documents = []
-        doc_id = set()
+        doc_ids = set()
         for document in documents:
-            doc_id = document.metadata.get("doc_id")
-            if doc_id not in doc_id:
-                doc_id.add(doc_id)
+            if document.metadata["doc_id"] not in doc_ids:
+                doc_ids.add(document.metadata["doc_id"])
                 unique_documents.append(document)
 
         documents = unique_documents

api/core/tools/provider/builtin/bing/tools/bing_web_search.py

@@ -66,6 +66,41 @@ class BingSearchTool(BuiltinTool):
                     results.append(self.create_text_message(text=f'{related.get("displayText", "")}{url}'))
 
             return results
+        elif result_type == "json":
+            result = {}
+            if search_results:
+                result["organic"] = [
+                    {
+                        "title": item.get("name", ""),
+                        "snippet": item.get("snippet", ""),
+                        "url": item.get("url", ""),
+                        "siteName": item.get("siteName", ""),
+                    }
+                    for item in search_results
+                ]
+
+            if computation and "expression" in computation and "value" in computation:
+                result["computation"] = {"expression": computation["expression"], "value": computation["value"]}
+
+            if entities:
+                result["entities"] = [
+                    {
+                        "name": item.get("name", ""),
+                        "url": item.get("url", ""),
+                        "description": item.get("description", ""),
+                    }
+                    for item in entities
+                ]
+
+            if news:
+                result["news"] = [{"name": item.get("name", ""), "url": item.get("url", "")} for item in news]
+
+            if related_searches:
+                result["related searches"] = [
+                    {"displayText": item.get("displayText", ""), "url": item.get("webSearchUrl", "")} for item in news
+                ]
+
+            return self.create_json_message(result)
         else:
             # construct text
             text = ""

api/core/tools/provider/builtin/bing/tools/bing_web_search.yaml

@@ -113,9 +113,9 @@ parameters:
       zh_Hans: 结果类型
       pt_BR: result type
     human_description:
-      en_US: return a list of links or texts
-      zh_Hans: 返回一个连接列表还是纯文本内容
-      pt_BR: return a list of links or texts
+      en_US: return a list of links, json or texts
+      zh_Hans: 返回一个列表，内容是链接、json还是纯文本
+      pt_BR: return a list of links, json or texts
     default: text
     options:
       - value: link
@@ -123,6 +123,11 @@ parameters:
           en_US: Link
           zh_Hans: 链接
           pt_BR: Link
+      - value: json
+        label:
+          en_US: JSON
+          zh_Hans: JSON
+          pt_BR: JSON
       - value: text
         label:
           en_US: Text

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

@@ -0,0 +1,8 @@
+from typing import Any
+
+from core.tools.provider.builtin_tool_provider import BuiltinToolProviderController
+
+
+class FileExtractorProvider(BuiltinToolProviderController):
+    def _validate_credentials(self, credentials: dict[str, Any]) -> None:
+        pass

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

@@ -0,0 +1,15 @@
+identity:
+  author: Jyong
+  name: file_extractor
+  label:
+    en_US: File Extractor
+    zh_Hans: 文件提取
+    pt_BR: File Extractor
+  description:
+    en_US: Extract text from file
+    zh_Hans: 从文件中提取文本
+    pt_BR: Extract text from file
+  icon: icon.png
+  tags:
+    - utilities
+    - productivity

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

@@ -0,0 +1,45 @@
+import tempfile
+from typing import Any, Union
+
+from core.file.enums import FileType
+from core.file.file_manager import download_to_target_path
+from core.rag.extractor.text_extractor import TextExtractor
+from core.rag.splitter.fixed_text_splitter import FixedRecursiveCharacterTextSplitter
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.errors import ToolParameterValidationError
+from core.tools.tool.builtin_tool import BuiltinTool
+
+
+class FileExtractorTool(BuiltinTool):
+    def _invoke(
+        self,
+        user_id: str,
+        tool_parameters: dict[str, Any],
+    ) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
+        """
+        invoke tools
+        """
+        # image file for workflow mode
+        file = tool_parameters.get("text_file")
+        if file and file.type != FileType.DOCUMENT:
+            raise ToolParameterValidationError("Not a valid document")
+
+        if file:
+            with tempfile.TemporaryDirectory() as temp_dir:
+                file_path = download_to_target_path(file, temp_dir)
+                extractor = TextExtractor(file_path, autodetect_encoding=True)
+                documents = extractor.extract()
+                character_splitter = FixedRecursiveCharacterTextSplitter.from_encoder(
+                    chunk_size=tool_parameters.get("max_token", 500),
+                    chunk_overlap=0,
+                    fixed_separator=tool_parameters.get("separator", "\n\n"),
+                    separators=["\n\n", "。", ". ", " ", ""],
+                    embedding_model_instance=None,
+                )
+                chunks = character_splitter.split_documents(documents)
+
+                content = "\n".join([chunk.page_content for chunk in chunks])
+                return self.create_text_message(content)
+
+        else:
+            raise ToolParameterValidationError("Please provide either file")

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

@@ -0,0 +1,49 @@
+identity:
+  name: text extractor
+  author: Jyong
+  label:
+    en_US: Text extractor
+    zh_Hans: Text 文本解析
+  description:
+    en_US: Extract content from text file and support split to chunks by split characters and token length
+    zh_Hans: 支持从文本文件中提取内容并支持通过分割字符和令牌长度分割成块
+    pt_BR: Extract content from text file and support split to chunks by split characters and token length
+description:
+  human:
+    en_US: Text extractor is a text extract tool
+    zh_Hans: Text extractor 是一个文本提取工具
+    pt_BR: Text extractor is a text extract tool
+  llm: Text extractor is a tool used to extract text file
+parameters:
+  - name: text_file
+    type: file
+    label:
+      en_US: Text file
+    human_description:
+      en_US: The text file to be extracted.
+      zh_Hans: 要提取的 text 文档。
+    llm_description: you should not input this parameter. just input the image_id.
+    form: llm
+  - name: separator
+    type: string
+    required: false
+    label:
+      en_US: split character
+      zh_Hans: 分隔符号
+    human_description:
+      en_US: Text content split character
+      zh_Hans: 用于文档分隔的符号
+    llm_description: it is used for split content to chunks
+    form: form
+  - name: max_token
+    type: number
+    required: false
+    label:
+      en_US: Maximum chunk length
+      zh_Hans: 最大分段长度
+    human_description:
+      en_US: Maximum chunk length
+      zh_Hans: 最大分段长度
+    llm_description: it is used for limit chunk's max length
+    form: form
+

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

@@ -12,7 +12,7 @@ class NovitaAiToolBase:
         if not loras_str:
             return []
 
-        loras_ori_list = lora_str.strip().split(";")
+        loras_ori_list = loras_str.strip().split(";")
         result_list = []
         for lora_str in loras_ori_list:
             lora_info = lora_str.strip().split(",")

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

@@ -0,0 +1,28 @@
+from typing import Any
+
+import requests
+from yarl import URL
+
+from core.tools.errors import ToolProviderCredentialValidationError
+from core.tools.provider.builtin_tool_provider import BuiltinToolProviderController
+
+
+class SlideSpeakProvider(BuiltinToolProviderController):
+    def _validate_credentials(self, credentials: dict[str, Any]) -> None:
+        api_key = credentials.get("slidespeak_api_key")
+        base_url = credentials.get("base_url")
+
+        if not api_key:
+            raise ToolProviderCredentialValidationError("API key is missing")
+
+        if base_url:
+            base_url = str(URL(base_url) / "v1")
+
+        headers = {"Content-Type": "application/json", "X-API-Key": api_key}
+
+        test_task_id = "xxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
+        url = f"{base_url or 'https://api.slidespeak.co/api/v1'}/task_status/{test_task_id}"
+
+        response = requests.get(url, headers=headers)
+        if response.status_code != 200:
+            raise ToolProviderCredentialValidationError("Invalid SlidePeak API key")

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

@@ -0,0 +1,22 @@
+identity:
+  author: Kalo Chin
+  name: slidespeak
+  label:
+    en_US: SlideSpeak
+    zh_Hans: SlideSpeak
+  description:
+    en_US: Generate presentation slides using SlideSpeak API
+    zh_Hans: 使用 SlideSpeak API 生成演示幻灯片
+  icon: icon.png
+
+credentials_for_provider:
+  slidespeak_api_key:
+    type: secret-input
+    required: true
+    label:
+      en_US: API Key
+      zh_Hans: API 密钥
+    placeholder:
+      en_US: Enter your SlideSpeak API key
+      zh_Hans: 输入您的 SlideSpeak API 密钥
+    url: https://app.slidespeak.co/settings/developer

api/core/tools/provider/builtin/slidespeak/tools/slides_generator.py

@@ -0,0 +1,163 @@
+import asyncio
+from dataclasses import asdict, dataclass
+from enum import Enum
+from typing import Any, Optional, Union
+
+import aiohttp
+from pydantic import ConfigDict
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.errors import ToolProviderCredentialValidationError
+from core.tools.tool.builtin_tool import BuiltinTool
+
+
+class SlidesGeneratorTool(BuiltinTool):
+    """
+    Tool for generating presentations using the SlideSpeak API.
+    """
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+    headers: Optional[dict[str, str]] = None
+    base_url: Optional[str] = None
+    timeout: Optional[aiohttp.ClientTimeout] = None
+    poll_interval: Optional[int] = None
+
+    class TaskState(Enum):
+        FAILURE = "FAILURE"
+        REVOKED = "REVOKED"
+        SUCCESS = "SUCCESS"
+        PENDING = "PENDING"
+        RECEIVED = "RECEIVED"
+        STARTED = "STARTED"
+
+    @dataclass
+    class PresentationRequest:
+        plain_text: str
+        length: Optional[int] = None
+        theme: Optional[str] = None
+
+    async def _generate_presentation(
+        self,
+        session: aiohttp.ClientSession,
+        request: PresentationRequest,
+    ) -> dict[str, Any]:
+        """Generate a new presentation asynchronously"""
+        async with session.post(
+            f"{self.base_url}/presentation/generate",
+            headers=self.headers,
+            json=asdict(request),
+            timeout=self.timeout,
+        ) as response:
+            response.raise_for_status()
+            return await response.json()
+
+    async def _get_task_status(
+        self,
+        session: aiohttp.ClientSession,
+        task_id: str,
+    ) -> dict[str, Any]:
+        """Get the status of a task asynchronously"""
+        async with session.get(
+            f"{self.base_url}/task_status/{task_id}",
+            headers=self.headers,
+            timeout=self.timeout,
+        ) as response:
+            response.raise_for_status()
+            return await response.json()
+
+    async def _wait_for_completion(
+        self,
+        session: aiohttp.ClientSession,
+        task_id: str,
+    ) -> str:
+        """Wait for task completion and return download URL"""
+        while True:
+            status = await self._get_task_status(session, task_id)
+            task_status = self.TaskState(status["task_status"])
+            if task_status == self.TaskState.SUCCESS:
+                return status["task_result"]["url"]
+            if task_status in [self.TaskState.FAILURE, self.TaskState.REVOKED]:
+                raise Exception(f"Task failed with status: {task_status.value}")
+            await asyncio.sleep(self.poll_interval)
+
+    async def _generate_slides(
+        self,
+        plain_text: str,
+        length: Optional[int],
+        theme: Optional[str],
+    ) -> str:
+        """Generate slides and return the download URL"""
+        async with aiohttp.ClientSession() as session:
+            request = self.PresentationRequest(
+                plain_text=plain_text,
+                length=length,
+                theme=theme,
+            )
+            result = await self._generate_presentation(session, request)
+            task_id = result["task_id"]
+            download_url = await self._wait_for_completion(session, task_id)
+            return download_url
+
+    async def _fetch_presentation(
+        self,
+        session: aiohttp.ClientSession,
+        download_url: str,
+    ) -> bytes:
+        """Fetch the presentation file from the download URL"""
+        async with session.get(download_url, timeout=self.timeout) as response:
+            response.raise_for_status()
+            return await response.read()
+
+    def _invoke(
+        self,
+        user_id: str,
+        tool_parameters: dict[str, Any],
+    ) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
+        """Synchronous invoke method that runs asynchronous code"""
+
+        async def async_invoke():
+            # Extract parameters
+            plain_text = tool_parameters.get("plain_text", "")
+            length = tool_parameters.get("length")
+            theme = tool_parameters.get("theme")
+
+            # Ensure runtime and credentials
+            if not self.runtime or not self.runtime.credentials:
+                raise ToolProviderCredentialValidationError("Tool runtime or credentials are missing")
+
+            # Get API key from credentials
+            api_key = self.runtime.credentials.get("slidespeak_api_key")
+            if not api_key:
+                raise ToolProviderCredentialValidationError("SlideSpeak API key is missing")
+
+            # Set configuration
+            self.headers = {
+                "Content-Type": "application/json",
+                "X-API-Key": api_key,
+            }
+            self.base_url = "https://api.slidespeak.co/api/v1"
+            self.timeout = aiohttp.ClientTimeout(total=30)
+            self.poll_interval = 2
+
+            # Run the asynchronous slide generation
+            try:
+                download_url = await self._generate_slides(plain_text, length, theme)
+
+                # Fetch the presentation file
+                async with aiohttp.ClientSession() as session:
+                    presentation_bytes = await self._fetch_presentation(session, download_url)
+
+                return [
+                    self.create_text_message("Presentation generated successfully"),
+                    self.create_blob_message(
+                        blob=presentation_bytes,
+                        meta={"mime_type": "application/vnd.openxmlformats-officedocument.presentationml.presentation"},
+                    ),
+                ]
+            except Exception as e:
+                return [self.create_text_message(f"An error occurred: {str(e)}")]
+
+        # Run the asynchronous code synchronously
+        result = asyncio.run(async_invoke())
+        return result

api/core/tools/provider/builtin/slidespeak/tools/slides_generator.yaml

@@ -0,0 +1,102 @@
+identity:
+  name: slide_generator
+  author: Kalo Chin
+  label:
+    en_US: Slides Generator
+    zh_Hans: 幻灯片生成器
+description:
+  human:
+    en_US: Generate presentation slides from text using SlideSpeak API.
+    zh_Hans: 使用 SlideSpeak API 从文本生成演示幻灯片。
+  llm: This tool converts text input into a presentation using the SlideSpeak API service, with options for slide length and theme.
+parameters:
+  - name: plain_text
+    type: string
+    required: true
+    label:
+      en_US: Topic or Content
+      zh_Hans: 主题或内容
+    human_description:
+      en_US: The topic or content to be converted into presentation slides.
+      zh_Hans: 需要转换为幻灯片的内容或主题。
+    llm_description: A string containing the topic or content to be transformed into presentation slides.
+    form: llm
+  - name: length
+    type: number
+    required: false
+    label:
+      en_US: Number of Slides
+      zh_Hans: 幻灯片数量
+    human_description:
+      en_US: The desired number of slides in the presentation (optional).
+      zh_Hans: 演示文稿中所需的幻灯片数量（可选）。
+    llm_description: Optional parameter specifying the number of slides to generate.
+    form: form
+  - name: theme
+    type: select
+    required: false
+    label:
+      en_US: Presentation Theme
+      zh_Hans: 演示主题
+    human_description:
+      en_US: The visual theme for the presentation (optional).
+      zh_Hans: 演示文稿的视觉主题（可选）。
+    llm_description: Optional parameter specifying the presentation theme.
+    options:
+      - label:
+          en_US: Adam
+          zh_Hans: Adam
+        value: adam
+      - label:
+          en_US: Aurora
+          zh_Hans: Aurora
+        value: aurora
+      - label:
+          en_US: Bruno
+          zh_Hans: Bruno
+        value: bruno
+      - label:
+          en_US: Clyde
+          zh_Hans: Clyde
+        value: clyde
+      - label:
+          en_US: Daniel
+          zh_Hans: Daniel
+        value: daniel
+      - label:
+          en_US: Default
+          zh_Hans: Default
+        value: default
+      - label:
+          en_US: Eddy
+          zh_Hans: Eddy
+        value: eddy
+      - label:
+          en_US: Felix
+          zh_Hans: Felix
+        value: felix
+      - label:
+          en_US: Gradient
+          zh_Hans: Gradient
+        value: gradient
+      - label:
+          en_US: Iris
+          zh_Hans: Iris
+        value: iris
+      - label:
+          en_US: Lavender
+          zh_Hans: Lavender
+        value: lavender
+      - label:
+          en_US: Monolith
+          zh_Hans: Monolith
+        value: monolith
+      - label:
+          en_US: Nebula
+          zh_Hans: Nebula
+        value: nebula
+      - label:
+          en_US: Nexus
+          zh_Hans: Nexus
+        value: nexus
+    form: form

api/core/variables/segments.py

@@ -118,11 +118,11 @@ class FileSegment(Segment):
 
     @property
     def log(self) -> str:
-        return str(self.value)
+        return ""
 
     @property
     def text(self) -> str:
-        return str(self.value)
+        return ""
 
 
 class ArrayAnySegment(ArraySegment):
@@ -155,3 +155,11 @@ class ArrayFileSegment(ArraySegment):
         for item in self.value:
             items.append(item.markdown)
         return "\n".join(items)
+
+    @property
+    def log(self) -> str:
+        return ""
+
+    @property
+    def text(self) -> str:
+        return ""

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

@@ -39,7 +39,14 @@ class VisionConfig(BaseModel):
 
 
 class PromptConfig(BaseModel):
-    jinja2_variables: Optional[list[VariableSelector]] = None
+    jinja2_variables: Sequence[VariableSelector] = Field(default_factory=list)
+
+    @field_validator("jinja2_variables", mode="before")
+    @classmethod
+    def convert_none_jinja2_variables(cls, v: Any):
+        if v is None:
+            return []
+        return v
 
 
 class LLMNodeChatModelMessage(ChatModelMessage):
@@ -53,7 +60,14 @@ class LLMNodeCompletionModelPromptTemplate(CompletionModelPromptTemplate):
 class LLMNodeData(BaseNodeData):
     model: ModelConfig
     prompt_template: Sequence[LLMNodeChatModelMessage] | LLMNodeCompletionModelPromptTemplate
-    prompt_config: Optional[PromptConfig] = None
+    prompt_config: PromptConfig = Field(default_factory=PromptConfig)
     memory: Optional[MemoryConfig] = None
     context: ContextConfig
     vision: VisionConfig = Field(default_factory=VisionConfig)
+
+    @field_validator("prompt_config", mode="before")
+    @classmethod
+    def convert_none_prompt_config(cls, v: Any):
+        if v is None:
+            return PromptConfig()
+        return v

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

@@ -24,3 +24,17 @@ class LLMModeRequiredError(LLMNodeError):
 
 class NoPromptFoundError(LLMNodeError):
     """Raised when no prompt is found in the LLM configuration."""
+
+
+class TemplateTypeNotSupportError(LLMNodeError):
+    def __init__(self, *, type_name: str):
+        super().__init__(f"Prompt type {type_name} is not supported.")
+
+
+class MemoryRolePrefixRequiredError(LLMNodeError):
+    """Raised when memory role prefix is required for completion model."""
+
+
+class FileTypeNotSupportError(LLMNodeError):
+    def __init__(self, *, type_name: str):
+        super().__init__(f"{type_name} type is not supported by this model")

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

@@ -1,4 +1,5 @@
 import json
+import logging
 from collections.abc import Generator, Mapping, Sequence
 from typing import TYPE_CHECKING, Any, Optional, cast
 
@@ -6,21 +7,26 @@ from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEnti
 from core.entities.model_entities import ModelStatus
 from core.entities.provider_entities import QuotaUnit
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
+from core.file import FileType, file_manager
+from core.helper.code_executor import CodeExecutor, CodeLanguage
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance, ModelManager
 from core.model_runtime.entities import (
-    AudioPromptMessageContent,
     ImagePromptMessageContent,
     PromptMessage,
     PromptMessageContentType,
     TextPromptMessageContent,
-    VideoPromptMessageContent,
 )
 from core.model_runtime.entities.llm_entities import LLMResult, LLMUsage
-from core.model_runtime.entities.model_entities import ModelType
+from core.model_runtime.entities.message_entities import (
+    AssistantPromptMessage,
+    PromptMessageRole,
+    SystemPromptMessage,
+    UserPromptMessage,
+)
+from core.model_runtime.entities.model_entities import ModelFeature, ModelPropertyKey, ModelType
 from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
 from core.model_runtime.utils.encoders import jsonable_encoder
-from core.prompt.advanced_prompt_transform import AdvancedPromptTransform
 from core.prompt.entities.advanced_prompt_entities import CompletionModelPromptTemplate, MemoryConfig
 from core.prompt.utils.prompt_message_util import PromptMessageUtil
 from core.variables import (
@@ -32,8 +38,9 @@ from core.variables import (
     ObjectSegment,
     StringSegment,
 )
-from core.workflow.constants import SYSTEM_VARIABLE_NODE_ID
 from core.workflow.entities.node_entities import NodeRunMetadataKey, NodeRunResult
+from core.workflow.entities.variable_entities import VariableSelector
+from core.workflow.entities.variable_pool import VariablePool
 from core.workflow.enums import SystemVariableKey
 from core.workflow.graph_engine.entities.event import InNodeEvent
 from core.workflow.nodes.base import BaseNode
@@ -58,18 +65,23 @@ from .entities import (
     ModelConfig,
 )
 from .exc import (
+    FileTypeNotSupportError,
     InvalidContextStructureError,
     InvalidVariableTypeError,
     LLMModeRequiredError,
     LLMNodeError,
+    MemoryRolePrefixRequiredError,
     ModelNotExistError,
     NoPromptFoundError,
+    TemplateTypeNotSupportError,
     VariableNotFoundError,
 )
 
 if TYPE_CHECKING:
     from core.file.models import File
 
+logger = logging.getLogger(__name__)
+
 
 class LLMNode(BaseNode[LLMNodeData]):
     _node_data_cls = LLMNodeData
@@ -123,17 +135,13 @@ class LLMNode(BaseNode[LLMNodeData]):
 
             # fetch prompt messages
             if self.node_data.memory:
-                query = self.graph_runtime_state.variable_pool.get((SYSTEM_VARIABLE_NODE_ID, SystemVariableKey.QUERY))
-                if not query:
-                    raise VariableNotFoundError("Query not found")
-                query = query.text
+                query = self.node_data.memory.query_prompt_template
             else:
                 query = None
 
             prompt_messages, stop = self._fetch_prompt_messages(
-                system_query=query,
-                inputs=inputs,
-                files=files,
+                user_query=query,
+                user_files=files,
                 context=context,
                 memory=memory,
                 model_config=model_config,
@@ -141,6 +149,8 @@ class LLMNode(BaseNode[LLMNodeData]):
                 memory_config=self.node_data.memory,
                 vision_enabled=self.node_data.vision.enabled,
                 vision_detail=self.node_data.vision.configs.detail,
+                variable_pool=self.graph_runtime_state.variable_pool,
+                jinja2_variables=self.node_data.prompt_config.jinja2_variables,
             )
 
             process_data = {
@@ -181,6 +191,17 @@ class LLMNode(BaseNode[LLMNodeData]):
                 )
             )
             return
+        except Exception as e:
+            logger.exception(f"Node {self.node_id} failed to run")
+            yield RunCompletedEvent(
+                run_result=NodeRunResult(
+                    status=WorkflowNodeExecutionStatus.FAILED,
+                    error=str(e),
+                    inputs=node_inputs,
+                    process_data=process_data,
+                )
+            )
+            return
 
         outputs = {"text": result_text, "usage": jsonable_encoder(usage), "finish_reason": finish_reason}
 
@@ -203,8 +224,8 @@ class LLMNode(BaseNode[LLMNodeData]):
         self,
         node_data_model: ModelConfig,
         model_instance: ModelInstance,
-        prompt_messages: list[PromptMessage],
-        stop: Optional[list[str]] = None,
+        prompt_messages: Sequence[PromptMessage],
+        stop: Optional[Sequence[str]] = None,
     ) -> Generator[NodeEvent, None, None]:
         db.session.close()
 
@@ -519,9 +540,8 @@ class LLMNode(BaseNode[LLMNodeData]):
     def _fetch_prompt_messages(
         self,
         *,
-        system_query: str | None = None,
-        inputs: dict[str, str] | None = None,
-        files: Sequence["File"],
+        user_query: str | None = None,
+        user_files: Sequence["File"],
         context: str | None = None,
         memory: TokenBufferMemory | None = None,
         model_config: ModelConfigWithCredentialsEntity,
@@ -529,58 +549,144 @@ class LLMNode(BaseNode[LLMNodeData]):
         memory_config: MemoryConfig | None = None,
         vision_enabled: bool = False,
         vision_detail: ImagePromptMessageContent.DETAIL,
-    ) -> tuple[list[PromptMessage], Optional[list[str]]]:
-        inputs = inputs or {}
+        variable_pool: VariablePool,
+        jinja2_variables: Sequence[VariableSelector],
+    ) -> tuple[Sequence[PromptMessage], Optional[Sequence[str]]]:
+        prompt_messages = []
 
-        prompt_transform = AdvancedPromptTransform(with_variable_tmpl=True)
-        prompt_messages = prompt_transform.get_prompt(
-            prompt_template=prompt_template,
-            inputs=inputs,
-            query=system_query or "",
-            files=files,
-            context=context,
-            memory_config=memory_config,
-            memory=memory,
-            model_config=model_config,
-        )
-        stop = model_config.stop
+        if isinstance(prompt_template, list):
+            # For chat model
+            prompt_messages.extend(
+                _handle_list_messages(
+                    messages=prompt_template,
+                    context=context,
+                    jinja2_variables=jinja2_variables,
+                    variable_pool=variable_pool,
+                    vision_detail_config=vision_detail,
+                )
+            )
+
+            # Get memory messages for chat mode
+            memory_messages = _handle_memory_chat_mode(
+                memory=memory,
+                memory_config=memory_config,
+                model_config=model_config,
+            )
+            # Extend prompt_messages with memory messages
+            prompt_messages.extend(memory_messages)
+
+            # Add current query to the prompt messages
+            if user_query:
+                message = LLMNodeChatModelMessage(
+                    text=user_query,
+                    role=PromptMessageRole.USER,
+                    edition_type="basic",
+                )
+                prompt_messages.extend(
+                    _handle_list_messages(
+                        messages=[message],
+                        context="",
+                        jinja2_variables=[],
+                        variable_pool=variable_pool,
+                        vision_detail_config=vision_detail,
+                    )
+                )
+
+        elif isinstance(prompt_template, LLMNodeCompletionModelPromptTemplate):
+            # For completion model
+            prompt_messages.extend(
+                _handle_completion_template(
+                    template=prompt_template,
+                    context=context,
+                    jinja2_variables=jinja2_variables,
+                    variable_pool=variable_pool,
+                )
+            )
+
+            # Get memory text for completion model
+            memory_text = _handle_memory_completion_mode(
+                memory=memory,
+                memory_config=memory_config,
+                model_config=model_config,
+            )
+            # Insert histories into the prompt
+            prompt_content = prompt_messages[0].content
+            if "#histories#" in prompt_content:
+                prompt_content = prompt_content.replace("#histories#", memory_text)
+            else:
+                prompt_content = memory_text + "\n" + prompt_content
+            prompt_messages[0].content = prompt_content
+
+            # Add current query to the prompt message
+            if user_query:
+                prompt_content = prompt_messages[0].content.replace("#sys.query#", user_query)
+                prompt_messages[0].content = prompt_content
+        else:
+            raise TemplateTypeNotSupportError(type_name=str(type(prompt_template)))
+
+        if vision_enabled and user_files:
+            file_prompts = []
+            for file in user_files:
+                file_prompt = file_manager.to_prompt_message_content(file, image_detail_config=vision_detail)
+                file_prompts.append(file_prompt)
+            if (
+                len(prompt_messages) > 0
+                and isinstance(prompt_messages[-1], UserPromptMessage)
+                and isinstance(prompt_messages[-1].content, list)
+            ):
+                prompt_messages[-1] = UserPromptMessage(content=prompt_messages[-1].content + file_prompts)
+            else:
+                prompt_messages.append(UserPromptMessage(content=file_prompts))
+
+        # Filter prompt messages
         filtered_prompt_messages = []
         for prompt_message in prompt_messages:
-            if prompt_message.is_empty():
-                continue
-
-            if not isinstance(prompt_message.content, str):
+            if isinstance(prompt_message.content, list):
                 prompt_message_content = []
-                for content_item in prompt_message.content or []:
-                    # Skip image if vision is disabled
-                    if not vision_enabled and content_item.type == PromptMessageContentType.IMAGE:
+                for content_item in prompt_message.content:
+                    # Skip content if features are not defined
+                    if not model_config.model_schema.features:
+                        if content_item.type != PromptMessageContentType.TEXT:
+                            continue
+                        prompt_message_content.append(content_item)
                         continue
 
-                    if isinstance(content_item, ImagePromptMessageContent):
-                        # Override vision config if LLM node has vision config,
-                        # cuz vision detail is related to the configuration from FileUpload feature.
-                        content_item.detail = vision_detail
-                        prompt_message_content.append(content_item)
-                    elif isinstance(
-                        content_item, TextPromptMessageContent | AudioPromptMessageContent | VideoPromptMessageContent
+                    # Skip content if corresponding feature is not supported
+                    if (
+                        (
+                            content_item.type == PromptMessageContentType.IMAGE
+                            and ModelFeature.VISION not in model_config.model_schema.features
+                        )
+                        or (
+                            content_item.type == PromptMessageContentType.DOCUMENT
+                            and ModelFeature.DOCUMENT not in model_config.model_schema.features
+                        )
+                        or (
+                            content_item.type == PromptMessageContentType.VIDEO
+                            and ModelFeature.VIDEO not in model_config.model_schema.features
+                        )
+                        or (
+                            content_item.type == PromptMessageContentType.AUDIO
+                            and ModelFeature.AUDIO not in model_config.model_schema.features
+                        )
                     ):
-                        prompt_message_content.append(content_item)
-
-                if len(prompt_message_content) > 1:
-                    prompt_message.content = prompt_message_content
-                elif (
-                    len(prompt_message_content) == 1 and prompt_message_content[0].type == PromptMessageContentType.TEXT
-                ):
+                        raise FileTypeNotSupportError(type_name=content_item.type)
+                    prompt_message_content.append(content_item)
+                if len(prompt_message_content) == 1 and prompt_message_content[0].type == PromptMessageContentType.TEXT:
                     prompt_message.content = prompt_message_content[0].data
-
+                else:
+                    prompt_message.content = prompt_message_content
+            if prompt_message.is_empty():
+                continue
             filtered_prompt_messages.append(prompt_message)
 
-        if not filtered_prompt_messages:
+        if len(filtered_prompt_messages) == 0:
             raise NoPromptFoundError(
                 "No prompt found in the LLM configuration. "
                 "Please ensure a prompt is properly configured before proceeding."
             )
 
+        stop = model_config.stop
         return filtered_prompt_messages, stop
 
     @classmethod
@@ -715,3 +821,198 @@ class LLMNode(BaseNode[LLMNodeData]):
                 }
             },
         }
+
+
+def _combine_text_message_with_role(*, text: str, role: PromptMessageRole):
+    match role:
+        case PromptMessageRole.USER:
+            return UserPromptMessage(content=[TextPromptMessageContent(data=text)])
+        case PromptMessageRole.ASSISTANT:
+            return AssistantPromptMessage(content=[TextPromptMessageContent(data=text)])
+        case PromptMessageRole.SYSTEM:
+            return SystemPromptMessage(content=[TextPromptMessageContent(data=text)])
+    raise NotImplementedError(f"Role {role} is not supported")
+
+
+def _render_jinja2_message(
+    *,
+    template: str,
+    jinjia2_variables: Sequence[VariableSelector],
+    variable_pool: VariablePool,
+):
+    if not template:
+        return ""
+
+    jinjia2_inputs = {}
+    for jinja2_variable in jinjia2_variables:
+        variable = variable_pool.get(jinja2_variable.value_selector)
+        jinjia2_inputs[jinja2_variable.variable] = variable.to_object() if variable else ""
+    code_execute_resp = CodeExecutor.execute_workflow_code_template(
+        language=CodeLanguage.JINJA2,
+        code=template,
+        inputs=jinjia2_inputs,
+    )
+    result_text = code_execute_resp["result"]
+    return result_text
+
+
+def _handle_list_messages(
+    *,
+    messages: Sequence[LLMNodeChatModelMessage],
+    context: Optional[str],
+    jinja2_variables: Sequence[VariableSelector],
+    variable_pool: VariablePool,
+    vision_detail_config: ImagePromptMessageContent.DETAIL,
+) -> Sequence[PromptMessage]:
+    prompt_messages = []
+    for message in messages:
+        if message.edition_type == "jinja2":
+            result_text = _render_jinja2_message(
+                template=message.jinja2_text or "",
+                jinjia2_variables=jinja2_variables,
+                variable_pool=variable_pool,
+            )
+            prompt_message = _combine_text_message_with_role(text=result_text, role=message.role)
+            prompt_messages.append(prompt_message)
+        else:
+            # Get segment group from basic message
+            if context:
+                template = message.text.replace("{#context#}", context)
+            else:
+                template = message.text
+            segment_group = variable_pool.convert_template(template)
+
+            # Process segments for images
+            file_contents = []
+            for segment in segment_group.value:
+                if isinstance(segment, ArrayFileSegment):
+                    for file in segment.value:
+                        if file.type in {FileType.IMAGE, FileType.VIDEO, FileType.AUDIO, FileType.DOCUMENT}:
+                            file_content = file_manager.to_prompt_message_content(
+                                file, image_detail_config=vision_detail_config
+                            )
+                            file_contents.append(file_content)
+                if isinstance(segment, FileSegment):
+                    file = segment.value
+                    if file.type in {FileType.IMAGE, FileType.VIDEO, FileType.AUDIO, FileType.DOCUMENT}:
+                        file_content = file_manager.to_prompt_message_content(
+                            file, image_detail_config=vision_detail_config
+                        )
+                        file_contents.append(file_content)
+
+            # Create message with text from all segments
+            plain_text = segment_group.text
+            if plain_text:
+                prompt_message = _combine_text_message_with_role(text=plain_text, role=message.role)
+                prompt_messages.append(prompt_message)
+
+            if file_contents:
+                # Create message with image contents
+                prompt_message = UserPromptMessage(content=file_contents)
+                prompt_messages.append(prompt_message)
+
+    return prompt_messages
+
+
+def _calculate_rest_token(
+    *, prompt_messages: list[PromptMessage], model_config: ModelConfigWithCredentialsEntity
+) -> int:
+    rest_tokens = 2000
+
+    model_context_tokens = model_config.model_schema.model_properties.get(ModelPropertyKey.CONTEXT_SIZE)
+    if model_context_tokens:
+        model_instance = ModelInstance(
+            provider_model_bundle=model_config.provider_model_bundle, model=model_config.model
+        )
+
+        curr_message_tokens = model_instance.get_llm_num_tokens(prompt_messages)
+
+        max_tokens = 0
+        for parameter_rule in model_config.model_schema.parameter_rules:
+            if parameter_rule.name == "max_tokens" or (
+                parameter_rule.use_template and parameter_rule.use_template == "max_tokens"
+            ):
+                max_tokens = (
+                    model_config.parameters.get(parameter_rule.name)
+                    or model_config.parameters.get(str(parameter_rule.use_template))
+                    or 0
+                )
+
+        rest_tokens = model_context_tokens - max_tokens - curr_message_tokens
+        rest_tokens = max(rest_tokens, 0)
+
+    return rest_tokens
+
+
+def _handle_memory_chat_mode(
+    *,
+    memory: TokenBufferMemory | None,
+    memory_config: MemoryConfig | None,
+    model_config: ModelConfigWithCredentialsEntity,
+) -> Sequence[PromptMessage]:
+    memory_messages = []
+    # Get messages from memory for chat model
+    if memory and memory_config:
+        rest_tokens = _calculate_rest_token(prompt_messages=[], model_config=model_config)
+        memory_messages = memory.get_history_prompt_messages(
+            max_token_limit=rest_tokens,
+            message_limit=memory_config.window.size if memory_config.window.enabled else None,
+        )
+    return memory_messages
+
+
+def _handle_memory_completion_mode(
+    *,
+    memory: TokenBufferMemory | None,
+    memory_config: MemoryConfig | None,
+    model_config: ModelConfigWithCredentialsEntity,
+) -> str:
+    memory_text = ""
+    # Get history text from memory for completion model
+    if memory and memory_config:
+        rest_tokens = _calculate_rest_token(prompt_messages=[], model_config=model_config)
+        if not memory_config.role_prefix:
+            raise MemoryRolePrefixRequiredError("Memory role prefix is required for completion model.")
+        memory_text = memory.get_history_prompt_text(
+            max_token_limit=rest_tokens,
+            message_limit=memory_config.window.size if memory_config.window.enabled else None,
+            human_prefix=memory_config.role_prefix.user,
+            ai_prefix=memory_config.role_prefix.assistant,
+        )
+    return memory_text
+
+
+def _handle_completion_template(
+    *,
+    template: LLMNodeCompletionModelPromptTemplate,
+    context: Optional[str],
+    jinja2_variables: Sequence[VariableSelector],
+    variable_pool: VariablePool,
+) -> Sequence[PromptMessage]:
+    """Handle completion template processing outside of LLMNode class.
+
+    Args:
+        template: The completion model prompt template
+        context: Optional context string
+        jinja2_variables: Variables for jinja2 template rendering
+        variable_pool: Variable pool for template conversion
+
+    Returns:
+        Sequence of prompt messages
+    """
+    prompt_messages = []
+    if template.edition_type == "jinja2":
+        result_text = _render_jinja2_message(
+            template=template.jinja2_text or "",
+            jinjia2_variables=jinja2_variables,
+            variable_pool=variable_pool,
+        )
+    else:
+        if context:
+            template_text = template.text.replace("{#context#}", context)
+        else:
+            template_text = template.text
+        result_text = variable_pool.convert_template(template_text).text
+    prompt_message = _combine_text_message_with_role(text=result_text, role=PromptMessageRole.USER)
+    prompt_messages.append(prompt_message)
+    return prompt_messages

api/core/workflow/nodes/question_classifier/question_classifier_node.py

@@ -86,12 +86,14 @@ class QuestionClassifierNode(LLMNode):
         )
         prompt_messages, stop = self._fetch_prompt_messages(
             prompt_template=prompt_template,
-            system_query=query,
+            user_query=query,
             memory=memory,
             model_config=model_config,
-            files=files,
+            user_files=files,
             vision_enabled=node_data.vision.enabled,
             vision_detail=node_data.vision.configs.detail,
+            variable_pool=variable_pool,
+            jinja2_variables=[],
         )
 
         # handle invoke result

api/fields/app_fields.py

@@ -190,3 +190,12 @@ app_site_fields = {
     "show_workflow_steps": fields.Boolean,
     "use_icon_as_answer_icon": fields.Boolean,
 }
+
+app_import_fields = {
+    "id": fields.String,
+    "status": fields.String,
+    "app_id": fields.String,
+    "current_dsl_version": fields.String,
+    "imported_dsl_version": fields.String,
+    "error": fields.String,
+}

api/fields/dataset_fields.py

@@ -41,6 +41,7 @@ dataset_retrieval_model_fields = {
 external_retrieval_model_fields = {
     "top_k": fields.Integer,
     "score_threshold": fields.Float,
+    "score_threshold_enabled": fields.Boolean,
 }
 
 tag_fields = {"id": fields.String, "name": fields.String, "type": fields.String}

api/libs/helper.py

@@ -31,9 +31,12 @@ class AppIconUrlField(fields.Raw):
         if obj is None:
             return None
 
-        from models.model import IconType
+        from models.model import App, IconType
 
-        if obj.icon_type == IconType.IMAGE.value:
+        if isinstance(obj, dict) and "app" in obj:
+            obj = obj["app"]
+
+        if isinstance(obj, App) and obj.icon_type == IconType.IMAGE.value:
             return file_helpers.get_signed_file_url(obj.icon)
         return None
 

api/models/fta.py

@@ -0,0 +1,78 @@
+from extensions.ext_database import db
+
+
+class ComponentFailure(db.Model):
+    __tablename__ = "component_failure"
+    __table_args__ = (
+        db.UniqueConstraint("Date", "Component", "FailureMode", "Cause", "Technician", name="unique_failure_entry"),
+    )
+
+    FailureID = db.Column(db.Integer, primary_key=True, autoincrement=True)
+    Date = db.Column(db.Date, nullable=False)
+    Component = db.Column(db.String(255), nullable=False)
+    FailureMode = db.Column(db.String(255), nullable=False)
+    Cause = db.Column(db.String(255), nullable=False)
+    RepairAction = db.Column(db.Text, nullable=True)
+    Technician = db.Column(db.String(255), nullable=False)
+
+
+class Maintenance(db.Model):
+    __tablename__ = "maintenance"
+
+    MaintenanceID = db.Column(db.Integer, primary_key=True, autoincrement=True)
+    MaintenanceType = db.Column(db.String(255), nullable=False)
+    MaintenanceDate = db.Column(db.Date, nullable=False)
+    ServiceDescription = db.Column(db.Text, nullable=True)
+    PartsReplaced = db.Column(db.Text, nullable=True)
+    Technician = db.Column(db.String(255), nullable=False)
+
+
+class OperationalData(db.Model):
+    __tablename__ = "operational_data"
+
+    OperationID = db.Column(db.Integer, primary_key=True, autoincrement=True)
+    CraneUsage = db.Column(db.Integer, nullable=False)
+    LoadWeight = db.Column(db.Float, nullable=False)
+    LoadFrequency = db.Column(db.Integer, nullable=False)
+    EnvironmentalConditions = db.Column(db.Text, nullable=True)
+
+
+class IncidentData(db.Model):
+    __tablename__ = "incident_data"
+
+    IncidentID = db.Column(db.Integer, primary_key=True, autoincrement=True)
+    IncidentDescription = db.Column(db.Text, nullable=False)
+    IncidentDate = db.Column(db.Date, nullable=False)
+    Consequences = db.Column(db.Text, nullable=True)
+    ResponseActions = db.Column(db.Text, nullable=True)
+
+
+class ReliabilityData(db.Model):
+    __tablename__ = "reliability_data"
+
+    ComponentID = db.Column(db.Integer, primary_key=True, autoincrement=True)
+    ComponentName = db.Column(db.String(255), nullable=False)
+    MTBF = db.Column(db.Float, nullable=False)
+    FailureRate = db.Column(db.Float, nullable=False)
+
+
+class SafetyData(db.Model):
+    __tablename__ = "safety_data"
+
+    SafetyID = db.Column(db.Integer, primary_key=True, autoincrement=True)
+    SafetyInspectionDate = db.Column(db.Date, nullable=False)
+    SafetyFindings = db.Column(db.Text, nullable=True)
+    SafetyIncidentDescription = db.Column(db.Text, nullable=True)
+    ComplianceStatus = db.Column(db.String(50), nullable=False)
+
+
+class ComponentFailureStats(db.Model):
+    __tablename__ = "component_failure_stats"
+
+    StatID = db.Column(db.Integer, primary_key=True, autoincrement=True)
+    Component = db.Column(db.String(255), nullable=False)
+    FailureMode = db.Column(db.String(255), nullable=False)
+    Cause = db.Column(db.String(255), nullable=False)
+    PossibleAction = db.Column(db.Text, nullable=True)
+    Probability = db.Column(db.Float, nullable=False)
+    MTBF = db.Column(db.Float, nullable=False)

api/models/model.py

@@ -68,7 +68,7 @@ class App(db.Model):
     name = db.Column(db.String(255), nullable=False)
     description = db.Column(db.Text, nullable=False, server_default=db.text("''::character varying"))
     mode = db.Column(db.String(255), nullable=False)
-    icon_type = db.Column(db.String(255), nullable=True)
+    icon_type = db.Column(db.String(255), nullable=True)  # image, emoji
     icon = db.Column(db.String(255))
     icon_background = db.Column(db.String(255))
     app_model_config_id = db.Column(StringUUID, nullable=True)
@@ -255,7 +255,7 @@ class AppModelConfig(db.Model):
 
     @property
     def model_dict(self) -> dict:
-        return json.loads(self.model) if self.model else None
+        return json.loads(self.model) if self.model else {}
 
     @property
     def suggested_questions_list(self) -> list:
@@ -600,8 +600,8 @@ class Conversation(db.Model):
                 app_model_config = (
                     db.session.query(AppModelConfig).filter(AppModelConfig.id == self.app_model_config_id).first()
                 )
-
-                model_config = app_model_config.to_dict()
+                if app_model_config:
+                    model_config = app_model_config.to_dict()
 
         model_config["model_id"] = self.model_id
         model_config["provider"] = self.model_provider

api/poetry.lock

@@ -2423,6 +2423,21 @@ files = [
 [package.extras]
 test = ["pytest (>=6)"]
 
+[[package]]
+name = "faker"
+version = "32.1.0"
+description = "Faker is a Python package that generates fake data for you."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "Faker-32.1.0-py3-none-any.whl", hash = "sha256:c77522577863c264bdc9dad3a2a750ad3f7ee43ff8185072e482992288898814"},
+    {file = "faker-32.1.0.tar.gz", hash = "sha256:aac536ba04e6b7beb2332c67df78485fc29c1880ff723beac6d1efd45e2f10f5"},
+]
+
+[package.dependencies]
+python-dateutil = ">=2.4"
+typing-extensions = "*"
+
 [[package]]
 name = "fal-client"
 version = "0.5.6"
@@ -3030,59 +3045,54 @@ files = [
 
 [[package]]
 name = "gevent"
-version = "23.9.1"
+version = "24.11.1"
 description = "Coroutine-based network library"
 optional = false
-python-versions = ">=3.8"
+python-versions = ">=3.9"
 files = [
-    {file = "gevent-23.9.1-cp310-cp310-macosx_11_0_universal2.whl", hash = "sha256:a3c5e9b1f766a7a64833334a18539a362fb563f6c4682f9634dea72cbe24f771"},
-    {file = "gevent-23.9.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b101086f109168b23fa3586fccd1133494bdb97f86920a24dc0b23984dc30b69"},
-    {file = "gevent-23.9.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:36a549d632c14684bcbbd3014a6ce2666c5f2a500f34d58d32df6c9ea38b6535"},
-    {file = "gevent-23.9.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:272cffdf535978d59c38ed837916dfd2b5d193be1e9e5dcc60a5f4d5025dd98a"},
-    {file = "gevent-23.9.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dcb8612787a7f4626aa881ff15ff25439561a429f5b303048f0fca8a1c781c39"},
-    {file = "gevent-23.9.1-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:d57737860bfc332b9b5aa438963986afe90f49645f6e053140cfa0fa1bdae1ae"},
-    {file = "gevent-23.9.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:5f3c781c84794926d853d6fb58554dc0dcc800ba25c41d42f6959c344b4db5a6"},
-    {file = "gevent-23.9.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:dbb22a9bbd6a13e925815ce70b940d1578dbe5d4013f20d23e8a11eddf8d14a7"},
-    {file = "gevent-23.9.1-cp310-cp310-win_amd64.whl", hash = "sha256:707904027d7130ff3e59ea387dddceedb133cc742b00b3ffe696d567147a9c9e"},
-    {file = "gevent-23.9.1-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:45792c45d60f6ce3d19651d7fde0bc13e01b56bb4db60d3f32ab7d9ec467374c"},
-    {file = "gevent-23.9.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4e24c2af9638d6c989caffc691a039d7c7022a31c0363da367c0d32ceb4a0648"},
-    {file = "gevent-23.9.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e1ead6863e596a8cc2a03e26a7a0981f84b6b3e956101135ff6d02df4d9a6b07"},
-    {file = "gevent-23.9.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:65883ac026731ac112184680d1f0f1e39fa6f4389fd1fc0bf46cc1388e2599f9"},
-    {file = "gevent-23.9.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bf7af500da05363e66f122896012acb6e101a552682f2352b618e541c941a011"},
-    {file = "gevent-23.9.1-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:c3e5d2fa532e4d3450595244de8ccf51f5721a05088813c1abd93ad274fe15e7"},
-    {file = "gevent-23.9.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:c84d34256c243b0a53d4335ef0bc76c735873986d478c53073861a92566a8d71"},
-    {file = "gevent-23.9.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:ada07076b380918829250201df1d016bdafb3acf352f35e5693b59dceee8dd2e"},
-    {file = "gevent-23.9.1-cp311-cp311-win_amd64.whl", hash = "sha256:921dda1c0b84e3d3b1778efa362d61ed29e2b215b90f81d498eb4d8eafcd0b7a"},
-    {file = "gevent-23.9.1-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:ed7a048d3e526a5c1d55c44cb3bc06cfdc1947d06d45006cc4cf60dedc628904"},
-    {file = "gevent-23.9.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7c1abc6f25f475adc33e5fc2dbcc26a732608ac5375d0d306228738a9ae14d3b"},
-    {file = "gevent-23.9.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4368f341a5f51611411ec3fc62426f52ac3d6d42eaee9ed0f9eebe715c80184e"},
-    {file = "gevent-23.9.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:52b4abf28e837f1865a9bdeef58ff6afd07d1d888b70b6804557e7908032e599"},
-    {file = "gevent-23.9.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:52e9f12cd1cda96603ce6b113d934f1aafb873e2c13182cf8e86d2c5c41982ea"},
-    {file = "gevent-23.9.1-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:de350fde10efa87ea60d742901e1053eb2127ebd8b59a7d3b90597eb4e586599"},
-    {file = "gevent-23.9.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:fde6402c5432b835fbb7698f1c7f2809c8d6b2bd9d047ac1f5a7c1d5aa569303"},
-    {file = "gevent-23.9.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:dd6c32ab977ecf7c7b8c2611ed95fa4aaebd69b74bf08f4b4960ad516861517d"},
-    {file = "gevent-23.9.1-cp312-cp312-win_amd64.whl", hash = "sha256:455e5ee8103f722b503fa45dedb04f3ffdec978c1524647f8ba72b4f08490af1"},
-    {file = "gevent-23.9.1-cp38-cp38-macosx_11_0_universal2.whl", hash = "sha256:7ccf0fd378257cb77d91c116e15c99e533374a8153632c48a3ecae7f7f4f09fe"},
-    {file = "gevent-23.9.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d163d59f1be5a4c4efcdd13c2177baaf24aadf721fdf2e1af9ee54a998d160f5"},
-    {file = "gevent-23.9.1-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:7532c17bc6c1cbac265e751b95000961715adef35a25d2b0b1813aa7263fb397"},
-    {file = "gevent-23.9.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:78eebaf5e73ff91d34df48f4e35581ab4c84e22dd5338ef32714264063c57507"},
-    {file = "gevent-23.9.1-cp38-cp38-win32.whl", hash = "sha256:f632487c87866094546a74eefbca2c74c1d03638b715b6feb12e80120960185a"},
-    {file = "gevent-23.9.1-cp38-cp38-win_amd64.whl", hash = "sha256:62d121344f7465e3739989ad6b91f53a6ca9110518231553fe5846dbe1b4518f"},
-    {file = "gevent-23.9.1-cp39-cp39-macosx_11_0_universal2.whl", hash = "sha256:bf456bd6b992eb0e1e869e2fd0caf817f0253e55ca7977fd0e72d0336a8c1c6a"},
-    {file = "gevent-23.9.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:43daf68496c03a35287b8b617f9f91e0e7c0d042aebcc060cadc3f049aadd653"},
-    {file = "gevent-23.9.1-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:7c28e38dcde327c217fdafb9d5d17d3e772f636f35df15ffae2d933a5587addd"},
-    {file = "gevent-23.9.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:fae8d5b5b8fa2a8f63b39f5447168b02db10c888a3e387ed7af2bd1b8612e543"},
-    {file = "gevent-23.9.1-cp39-cp39-win32.whl", hash = "sha256:2c7b5c9912378e5f5ccf180d1fdb1e83f42b71823483066eddbe10ef1a2fcaa2"},
-    {file = "gevent-23.9.1-cp39-cp39-win_amd64.whl", hash = "sha256:a2898b7048771917d85a1d548fd378e8a7b2ca963db8e17c6d90c76b495e0e2b"},
-    {file = "gevent-23.9.1.tar.gz", hash = "sha256:72c002235390d46f94938a96920d8856d4ffd9ddf62a303a0d7c118894097e34"},
+    {file = "gevent-24.11.1-cp310-cp310-macosx_11_0_universal2.whl", hash = "sha256:92fe5dfee4e671c74ffaa431fd7ffd0ebb4b339363d24d0d944de532409b935e"},
+    {file = "gevent-24.11.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b7bfcfe08d038e1fa6de458891bca65c1ada6d145474274285822896a858c870"},
+    {file = "gevent-24.11.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7398c629d43b1b6fd785db8ebd46c0a353880a6fab03d1cf9b6788e7240ee32e"},
+    {file = "gevent-24.11.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d7886b63ebfb865178ab28784accd32f287d5349b3ed71094c86e4d3ca738af5"},
+    {file = "gevent-24.11.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d9ca80711e6553880974898d99357fb649e062f9058418a92120ca06c18c3c59"},
+    {file = "gevent-24.11.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:e24181d172f50097ac8fc272c8c5b030149b630df02d1c639ee9f878a470ba2b"},
+    {file = "gevent-24.11.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:1d4fadc319b13ef0a3c44d2792f7918cf1bca27cacd4d41431c22e6b46668026"},
+    {file = "gevent-24.11.1-cp310-cp310-win_amd64.whl", hash = "sha256:3d882faa24f347f761f934786dde6c73aa6c9187ee710189f12dcc3a63ed4a50"},
+    {file = "gevent-24.11.1-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:351d1c0e4ef2b618ace74c91b9b28b3eaa0dd45141878a964e03c7873af09f62"},
+    {file = "gevent-24.11.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b5efe72e99b7243e222ba0c2c2ce9618d7d36644c166d63373af239da1036bab"},
+    {file = "gevent-24.11.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9d3b249e4e1f40c598ab8393fc01ae6a3b4d51fc1adae56d9ba5b315f6b2d758"},
+    {file = "gevent-24.11.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81d918e952954675f93fb39001da02113ec4d5f4921bf5a0cc29719af6824e5d"},
+    {file = "gevent-24.11.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c9c935b83d40c748b6421625465b7308d87c7b3717275acd587eef2bd1c39546"},
+    {file = "gevent-24.11.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:ff96c5739834c9a594db0e12bf59cb3fa0e5102fc7b893972118a3166733d61c"},
+    {file = "gevent-24.11.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:d6c0a065e31ef04658f799215dddae8752d636de2bed61365c358f9c91e7af61"},
+    {file = "gevent-24.11.1-cp311-cp311-win_amd64.whl", hash = "sha256:97e2f3999a5c0656f42065d02939d64fffaf55861f7d62b0107a08f52c984897"},
+    {file = "gevent-24.11.1-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:a3d75fa387b69c751a3d7c5c3ce7092a171555126e136c1d21ecd8b50c7a6e46"},
+    {file = "gevent-24.11.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:beede1d1cff0c6fafae3ab58a0c470d7526196ef4cd6cc18e7769f207f2ea4eb"},
+    {file = "gevent-24.11.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:85329d556aaedced90a993226d7d1186a539c843100d393f2349b28c55131c85"},
+    {file = "gevent-24.11.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:816b3883fa6842c1cf9d2786722014a0fd31b6312cca1f749890b9803000bad6"},
+    {file = "gevent-24.11.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b24d800328c39456534e3bc3e1684a28747729082684634789c2f5a8febe7671"},
+    {file = "gevent-24.11.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:a5f1701ce0f7832f333dd2faf624484cbac99e60656bfbb72504decd42970f0f"},
+    {file = "gevent-24.11.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:d740206e69dfdfdcd34510c20adcb9777ce2cc18973b3441ab9767cd8948ca8a"},
+    {file = "gevent-24.11.1-cp312-cp312-win_amd64.whl", hash = "sha256:68bee86b6e1c041a187347ef84cf03a792f0b6c7238378bf6ba4118af11feaae"},
+    {file = "gevent-24.11.1-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:d618e118fdb7af1d6c1a96597a5cd6ac84a9f3732b5be8515c6a66e098d498b6"},
+    {file = "gevent-24.11.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2142704c2adce9cd92f6600f371afb2860a446bfd0be5bd86cca5b3e12130766"},
+    {file = "gevent-24.11.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:92e0d7759de2450a501effd99374256b26359e801b2d8bf3eedd3751973e87f5"},
+    {file = "gevent-24.11.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ca845138965c8c56d1550499d6b923eb1a2331acfa9e13b817ad8305dde83d11"},
+    {file = "gevent-24.11.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:356b73d52a227d3313f8f828025b665deada57a43d02b1cf54e5d39028dbcf8d"},
+    {file = "gevent-24.11.1-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:58851f23c4bdb70390f10fc020c973ffcf409eb1664086792c8b1e20f25eef43"},
+    {file = "gevent-24.11.1-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:1ea50009ecb7f1327347c37e9eb6561bdbc7de290769ee1404107b9a9cba7cf1"},
+    {file = "gevent-24.11.1-cp313-cp313-win_amd64.whl", hash = "sha256:ec68e270543ecd532c4c1d70fca020f90aa5486ad49c4f3b8b2e64a66f5c9274"},
+    {file = "gevent-24.11.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d9347690f4e53de2c4af74e62d6fabc940b6d4a6cad555b5a379f61e7d3f2a8e"},
+    {file = "gevent-24.11.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:8619d5c888cb7aebf9aec6703e410620ef5ad48cdc2d813dd606f8aa7ace675f"},
+    {file = "gevent-24.11.1-cp39-cp39-win32.whl", hash = "sha256:c6b775381f805ff5faf250e3a07c0819529571d19bb2a9d474bee8c3f90d66af"},
+    {file = "gevent-24.11.1-cp39-cp39-win_amd64.whl", hash = "sha256:1c3443b0ed23dcb7c36a748d42587168672953d368f2956b17fad36d43b58836"},
+    {file = "gevent-24.11.1-pp310-pypy310_pp73-macosx_11_0_universal2.whl", hash = "sha256:f43f47e702d0c8e1b8b997c00f1601486f9f976f84ab704f8f11536e3fa144c9"},
+    {file = "gevent-24.11.1.tar.gz", hash = "sha256:8bd1419114e9e4a3ed33a5bad766afff9a3cf765cb440a582a1b3a9bc80c1aca"},
 ]
 
 [package.dependencies]
-cffi = {version = ">=1.12.2", markers = "platform_python_implementation == \"CPython\" and sys_platform == \"win32\""}
-greenlet = [
-    {version = ">=2.0.0", markers = "platform_python_implementation == \"CPython\" and python_version < \"3.11\""},
-    {version = ">=3.0rc3", markers = "platform_python_implementation == \"CPython\" and python_version >= \"3.11\""},
-]
+cffi = {version = ">=1.17.1", markers = "platform_python_implementation == \"CPython\" and sys_platform == \"win32\""}
+greenlet = {version = ">=3.1.1", markers = "platform_python_implementation == \"CPython\""}
 "zope.event" = "*"
 "zope.interface" = "*"
 
@@ -3090,8 +3100,8 @@ greenlet = [
 dnspython = ["dnspython (>=1.16.0,<2.0)", "idna"]
 docs = ["furo", "repoze.sphinx.autointerface", "sphinx", "sphinxcontrib-programoutput", "zope.schema"]
 monitor = ["psutil (>=5.7.0)"]
-recommended = ["cffi (>=1.12.2)", "dnspython (>=1.16.0,<2.0)", "idna", "psutil (>=5.7.0)"]
-test = ["cffi (>=1.12.2)", "coverage (>=5.0)", "dnspython (>=1.16.0,<2.0)", "idna", "objgraph", "psutil (>=5.7.0)", "requests", "setuptools"]
+recommended = ["cffi (>=1.17.1)", "dnspython (>=1.16.0,<2.0)", "idna", "psutil (>=5.7.0)"]
+test = ["cffi (>=1.17.1)", "coverage (>=5.0)", "dnspython (>=1.16.0,<2.0)", "idna", "objgraph", "psutil (>=5.7.0)", "requests"]
 
 [[package]]
 name = "gmpy2"
@@ -11041,4 +11051,4 @@ cffi = ["cffi (>=1.11)"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<3.13"
-content-hash = "69a3f471f85dce9e5fb889f739e148a4a6d95aaf94081414503867c7157dba69"
+content-hash = "152b8e11ceffaa482fee6920b7991f52427aa1ffed75614e78ec1065dd5f6898"

api/pyproject.toml

@@ -131,7 +131,7 @@ flask-login = "~0.6.3"
 flask-migrate = "~4.0.5"
 flask-restful = "~0.3.10"
 flask-sqlalchemy = "~3.1.1"
-gevent = "~23.9.1"
+gevent = "~24.11.1"
 gmpy2 = "~2.2.1"
 google-ai-generativelanguage = "0.6.9"
 google-api-core = "2.18.0"
@@ -268,6 +268,7 @@ weaviate-client = "~3.21.0"
 optional = true
 [tool.poetry.group.dev.dependencies]
 coverage = "~7.2.4"
+faker = "~32.1.0"
 pytest = "~8.3.2"
 pytest-benchmark = "~4.0.0"
 pytest-env = "~1.1.3"

api/services/app_dsl_service.py

@@ -0,0 +1,485 @@
+import logging
+import uuid
+from enum import Enum
+from typing import Optional
+from uuid import uuid4
+
+import yaml
+from packaging import version
+from pydantic import BaseModel
+from sqlalchemy import select
+from sqlalchemy.orm import Session
+
+from core.helper import ssrf_proxy
+from events.app_event import app_model_config_was_updated, app_was_created
+from extensions.ext_redis import redis_client
+from factories import variable_factory
+from models import Account, App, AppMode
+from models.model import AppModelConfig
+from services.workflow_service import WorkflowService
+
+logger = logging.getLogger(__name__)
+
+IMPORT_INFO_REDIS_KEY_PREFIX = "app_import_info:"
+IMPORT_INFO_REDIS_EXPIRY = 180  # 3 minutes
+CURRENT_DSL_VERSION = "0.1.3"
+
+
+class ImportMode(str, Enum):
+    YAML_CONTENT = "yaml-content"
+    YAML_URL = "yaml-url"
+
+
+class ImportStatus(str, Enum):
+    COMPLETED = "completed"
+    COMPLETED_WITH_WARNINGS = "completed-with-warnings"
+    PENDING = "pending"
+    FAILED = "failed"
+
+
+class Import(BaseModel):
+    id: str
+    status: ImportStatus
+    app_id: Optional[str] = None
+    current_dsl_version: str = CURRENT_DSL_VERSION
+    imported_dsl_version: str = ""
+    error: str = ""
+
+
+def _check_version_compatibility(imported_version: str) -> ImportStatus:
+    """Determine import status based on version comparison"""
+    try:
+        current_ver = version.parse(CURRENT_DSL_VERSION)
+        imported_ver = version.parse(imported_version)
+    except version.InvalidVersion:
+        return ImportStatus.FAILED
+
+    # Compare major version and minor version
+    if current_ver.major != imported_ver.major or current_ver.minor != imported_ver.minor:
+        return ImportStatus.PENDING
+
+    if current_ver.micro != imported_ver.micro:
+        return ImportStatus.COMPLETED_WITH_WARNINGS
+
+    return ImportStatus.COMPLETED
+
+
+class PendingData(BaseModel):
+    import_mode: str
+    yaml_content: str
+    name: str | None
+    description: str | None
+    icon_type: str | None
+    icon: str | None
+    icon_background: str | None
+    app_id: str | None
+
+
+class AppDslService:
+    def __init__(self, session: Session):
+        self._session = session
+
+    def import_app(
+        self,
+        *,
+        account: Account,
+        import_mode: str,
+        yaml_content: Optional[str] = None,
+        yaml_url: Optional[str] = None,
+        name: Optional[str] = None,
+        description: Optional[str] = None,
+        icon_type: Optional[str] = None,
+        icon: Optional[str] = None,
+        icon_background: Optional[str] = None,
+        app_id: Optional[str] = None,
+    ) -> Import:
+        """Import an app from YAML content or URL."""
+        import_id = str(uuid.uuid4())
+
+        # Validate import mode
+        try:
+            mode = ImportMode(import_mode)
+        except ValueError:
+            raise ValueError(f"Invalid import_mode: {import_mode}")
+
+        # Get YAML content
+        content = ""
+        if mode == ImportMode.YAML_URL:
+            if not yaml_url:
+                return Import(
+                    id=import_id,
+                    status=ImportStatus.FAILED,
+                    error="yaml_url is required when import_mode is yaml-url",
+                )
+            try:
+                max_size = 10 * 1024 * 1024  # 10MB
+                response = ssrf_proxy.get(yaml_url.strip(), follow_redirects=True, timeout=(10, 10))
+                response.raise_for_status()
+                content = response.content
+
+                if len(content) > max_size:
+                    return Import(
+                        id=import_id,
+                        status=ImportStatus.FAILED,
+                        error="File size exceeds the limit of 10MB",
+                    )
+
+                if not content:
+                    return Import(
+                        id=import_id,
+                        status=ImportStatus.FAILED,
+                        error="Empty content from url",
+                    )
+
+                try:
+                    content = content.decode("utf-8")
+                except UnicodeDecodeError as e:
+                    return Import(
+                        id=import_id,
+                        status=ImportStatus.FAILED,
+                        error=f"Error decoding content: {e}",
+                    )
+            except Exception as e:
+                return Import(
+                    id=import_id,
+                    status=ImportStatus.FAILED,
+                    error=f"Error fetching YAML from URL: {str(e)}",
+                )
+        elif mode == ImportMode.YAML_CONTENT:
+            if not yaml_content:
+                return Import(
+                    id=import_id,
+                    status=ImportStatus.FAILED,
+                    error="yaml_content is required when import_mode is yaml-content",
+                )
+            content = yaml_content
+
+        # Process YAML content
+        try:
+            # Parse YAML to validate format
+            data = yaml.safe_load(content)
+            if not isinstance(data, dict):
+                return Import(
+                    id=import_id,
+                    status=ImportStatus.FAILED,
+                    error="Invalid YAML format: content must be a mapping",
+                )
+
+            # Validate and fix DSL version
+            if not data.get("version"):
+                data["version"] = "0.1.0"
+            if not data.get("kind") or data.get("kind") != "app":
+                data["kind"] = "app"
+
+            imported_version = data.get("version", "0.1.0")
+            status = _check_version_compatibility(imported_version)
+
+            # Extract app data
+            app_data = data.get("app")
+            if not app_data:
+                return Import(
+                    id=import_id,
+                    status=ImportStatus.FAILED,
+                    error="Missing app data in YAML content",
+                )
+
+            # If app_id is provided, check if it exists
+            app = None
+            if app_id:
+                stmt = select(App).where(App.id == app_id, App.tenant_id == account.current_tenant_id)
+                app = self._session.scalar(stmt)
+
+                if not app:
+                    return Import(
+                        id=import_id,
+                        status=ImportStatus.FAILED,
+                        error="App not found",
+                    )
+
+                if app.mode not in [AppMode.WORKFLOW.value, AppMode.ADVANCED_CHAT.value]:
+                    return Import(
+                        id=import_id,
+                        status=ImportStatus.FAILED,
+                        error="Only workflow or advanced chat apps can be overwritten",
+                    )
+
+            # If major version mismatch, store import info in Redis
+            if status == ImportStatus.PENDING:
+                panding_data = PendingData(
+                    import_mode=import_mode,
+                    yaml_content=content,
+                    name=name,
+                    description=description,
+                    icon_type=icon_type,
+                    icon=icon,
+                    icon_background=icon_background,
+                    app_id=app_id,
+                )
+                redis_client.setex(
+                    f"{IMPORT_INFO_REDIS_KEY_PREFIX}{import_id}",
+                    IMPORT_INFO_REDIS_EXPIRY,
+                    panding_data.model_dump_json(),
+                )
+
+                return Import(
+                    id=import_id,
+                    status=status,
+                    app_id=app_id,
+                    imported_dsl_version=imported_version,
+                )
+
+            # Create or update app
+            app = self._create_or_update_app(
+                app=app,
+                data=data,
+                account=account,
+                name=name,
+                description=description,
+                icon_type=icon_type,
+                icon=icon,
+                icon_background=icon_background,
+            )
+
+            return Import(
+                id=import_id,
+                status=status,
+                app_id=app.id,
+                imported_dsl_version=imported_version,
+            )
+
+        except yaml.YAMLError as e:
+            return Import(
+                id=import_id,
+                status=ImportStatus.FAILED,
+                error=f"Invalid YAML format: {str(e)}",
+            )
+
+        except Exception as e:
+            logger.exception("Failed to import app")
+            return Import(
+                id=import_id,
+                status=ImportStatus.FAILED,
+                error=str(e),
+            )
+
+    def confirm_import(self, *, import_id: str, account: Account) -> Import:
+        """
+        Confirm an import that requires confirmation
+        """
+        redis_key = f"{IMPORT_INFO_REDIS_KEY_PREFIX}{import_id}"
+        pending_data = redis_client.get(redis_key)
+
+        if not pending_data:
+            return Import(
+                id=import_id,
+                status=ImportStatus.FAILED,
+                error="Import information expired or does not exist",
+            )
+
+        try:
+            if not isinstance(pending_data, str | bytes):
+                return Import(
+                    id=import_id,
+                    status=ImportStatus.FAILED,
+                    error="Invalid import information",
+                )
+            pending_data = PendingData.model_validate_json(pending_data)
+            data = yaml.safe_load(pending_data.yaml_content)
+
+            app = None
+            if pending_data.app_id:
+                stmt = select(App).where(App.id == pending_data.app_id, App.tenant_id == account.current_tenant_id)
+                app = self._session.scalar(stmt)
+
+            # Create or update app
+            app = self._create_or_update_app(
+                app=app,
+                data=data,
+                account=account,
+                name=pending_data.name,
+                description=pending_data.description,
+                icon_type=pending_data.icon_type,
+                icon=pending_data.icon,
+                icon_background=pending_data.icon_background,
+            )
+
+            # Delete import info from Redis
+            redis_client.delete(redis_key)
+
+            return Import(
+                id=import_id,
+                status=ImportStatus.COMPLETED,
+                app_id=app.id,
+                current_dsl_version=CURRENT_DSL_VERSION,
+                imported_dsl_version=data.get("version", "0.1.0"),
+            )
+
+        except Exception as e:
+            logger.exception("Error confirming import")
+            return Import(
+                id=import_id,
+                status=ImportStatus.FAILED,
+                error=str(e),
+            )
+
+    def _create_or_update_app(
+        self,
+        *,
+        app: Optional[App],
+        data: dict,
+        account: Account,
+        name: Optional[str] = None,
+        description: Optional[str] = None,
+        icon_type: Optional[str] = None,
+        icon: Optional[str] = None,
+        icon_background: Optional[str] = None,
+    ) -> App:
+        """Create a new app or update an existing one."""
+        app_data = data.get("app", {})
+        app_mode = AppMode(app_data["mode"])
+
+        # Set icon type
+        icon_type_value = icon_type or app_data.get("icon_type")
+        if icon_type_value in ["emoji", "link"]:
+            icon_type = icon_type_value
+        else:
+            icon_type = "emoji"
+        icon = icon or str(app_data.get("icon", ""))
+
+        if app:
+            # Update existing app
+            app.name = name or app_data.get("name", app.name)
+            app.description = description or app_data.get("description", app.description)
+            app.icon_type = icon_type
+            app.icon = icon
+            app.icon_background = icon_background or app_data.get("icon_background", app.icon_background)
+            app.updated_by = account.id
+        else:
+            # Create new app
+            app = App()
+            app.id = str(uuid4())
+            app.tenant_id = account.current_tenant_id
+            app.mode = app_mode.value
+            app.name = name or app_data.get("name", "")
+            app.description = description or app_data.get("description", "")
+            app.icon_type = icon_type
+            app.icon = icon
+            app.icon_background = icon_background or app_data.get("icon_background", "#FFFFFF")
+            app.enable_site = True
+            app.enable_api = True
+            app.use_icon_as_answer_icon = app_data.get("use_icon_as_answer_icon", False)
+            app.created_by = account.id
+            app.updated_by = account.id
+
+            self._session.add(app)
+            self._session.commit()
+            app_was_created.send(app, account=account)
+
+        # Initialize app based on mode
+        if app_mode in {AppMode.ADVANCED_CHAT, AppMode.WORKFLOW}:
+            workflow_data = data.get("workflow")
+            if not workflow_data or not isinstance(workflow_data, dict):
+                raise ValueError("Missing workflow data for workflow/advanced chat app")
+
+            environment_variables_list = workflow_data.get("environment_variables", [])
+            environment_variables = [
+                variable_factory.build_variable_from_mapping(obj) for obj in environment_variables_list
+            ]
+            conversation_variables_list = workflow_data.get("conversation_variables", [])
+            conversation_variables = [
+                variable_factory.build_variable_from_mapping(obj) for obj in conversation_variables_list
+            ]
+
+            workflow_service = WorkflowService()
+            current_draft_workflow = workflow_service.get_draft_workflow(app_model=app)
+            if current_draft_workflow:
+                unique_hash = current_draft_workflow.unique_hash
+            else:
+                unique_hash = None
+            workflow_service.sync_draft_workflow(
+                app_model=app,
+                graph=workflow_data.get("graph", {}),
+                features=workflow_data.get("features", {}),
+                unique_hash=unique_hash,
+                account=account,
+                environment_variables=environment_variables,
+                conversation_variables=conversation_variables,
+            )
+        elif app_mode in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.COMPLETION}:
+            # Initialize model config
+            model_config = data.get("model_config")
+            if not model_config or not isinstance(model_config, dict):
+                raise ValueError("Missing model_config for chat/agent-chat/completion app")
+            # Initialize or update model config
+            if not app.app_model_config:
+                app_model_config = AppModelConfig().from_model_config_dict(model_config)
+                app_model_config.id = str(uuid4())
+                app_model_config.app_id = app.id
+                app_model_config.created_by = account.id
+                app_model_config.updated_by = account.id
+
+                app.app_model_config_id = app_model_config.id
+
+                self._session.add(app_model_config)
+                app_model_config_was_updated.send(app, app_model_config=app_model_config)
+        else:
+            raise ValueError("Invalid app mode")
+        return app
+
+    @classmethod
+    def export_dsl(cls, app_model: App, include_secret: bool = False) -> str:
+        """
+        Export app
+        :param app_model: App instance
+        :return:
+        """
+        app_mode = AppMode.value_of(app_model.mode)
+
+        export_data = {
+            "version": CURRENT_DSL_VERSION,
+            "kind": "app",
+            "app": {
+                "name": app_model.name,
+                "mode": app_model.mode,
+                "icon": "🤖" if app_model.icon_type == "image" else app_model.icon,
+                "icon_background": "#FFEAD5" if app_model.icon_type == "image" else app_model.icon_background,
+                "description": app_model.description,
+                "use_icon_as_answer_icon": app_model.use_icon_as_answer_icon,
+            },
+        }
+
+        if app_mode in {AppMode.ADVANCED_CHAT, AppMode.WORKFLOW}:
+            cls._append_workflow_export_data(
+                export_data=export_data, app_model=app_model, include_secret=include_secret
+            )
+        else:
+            cls._append_model_config_export_data(export_data, app_model)
+
+        return yaml.dump(export_data, allow_unicode=True)
+
+    @classmethod
+    def _append_workflow_export_data(cls, *, export_data: dict, app_model: App, include_secret: bool) -> None:
+        """
+        Append workflow export data
+        :param export_data: export data
+        :param app_model: App instance
+        """
+        workflow_service = WorkflowService()
+        workflow = workflow_service.get_draft_workflow(app_model)
+        if not workflow:
+            raise ValueError("Missing draft workflow configuration, please check.")
+
+        export_data["workflow"] = workflow.to_dict(include_secret=include_secret)
+
+    @classmethod
+    def _append_model_config_export_data(cls, export_data: dict, app_model: App) -> None:
+        """
+        Append model config export data
+        :param export_data: export data
+        :param app_model: App instance
+        """
+        app_model_config = app_model.app_model_config
+        if not app_model_config:
+            raise ValueError("Missing app configuration, please check.")
+
+        export_data["model_config"] = app_model_config.to_dict()

api/services/app_dsl_service/__init__.py

@@ -1,3 +0,0 @@
-from .service import AppDslService
-
-__all__ = ["AppDslService"]

api/services/app_dsl_service/exc.py

@@ -1,34 +0,0 @@
-class DSLVersionNotSupportedError(ValueError):
-    """Raised when the imported DSL version is not supported by the current Dify version."""
-
-
-class InvalidYAMLFormatError(ValueError):
-    """Raised when the provided YAML format is invalid."""
-
-
-class MissingAppDataError(ValueError):
-    """Raised when the app data is missing in the provided DSL."""
-
-
-class InvalidAppModeError(ValueError):
-    """Raised when the app mode is invalid."""
-
-
-class MissingWorkflowDataError(ValueError):
-    """Raised when the workflow data is missing in the provided DSL."""
-
-
-class MissingModelConfigError(ValueError):
-    """Raised when the model config data is missing in the provided DSL."""
-
-
-class FileSizeLimitExceededError(ValueError):
-    """Raised when the file size exceeds the allowed limit."""
-
-
-class EmptyContentError(ValueError):
-    """Raised when the content fetched from the URL is empty."""
-
-
-class ContentDecodingError(ValueError):
-    """Raised when there is an error decoding the content."""

api/services/app_dsl_service/service.py

@@ -1,484 +0,0 @@
-import logging
-from collections.abc import Mapping
-from typing import Any
-
-import yaml
-from packaging import version
-
-from core.helper import ssrf_proxy
-from events.app_event import app_model_config_was_updated, app_was_created
-from extensions.ext_database import db
-from factories import variable_factory
-from models.account import Account
-from models.model import App, AppMode, AppModelConfig
-from models.workflow import Workflow
-from services.workflow_service import WorkflowService
-
-from .exc import (
-    ContentDecodingError,
-    EmptyContentError,
-    FileSizeLimitExceededError,
-    InvalidAppModeError,
-    InvalidYAMLFormatError,
-    MissingAppDataError,
-    MissingModelConfigError,
-    MissingWorkflowDataError,
-)
-
-logger = logging.getLogger(__name__)
-
-current_dsl_version = "0.1.3"
-
-
-class AppDslService:
-    @classmethod
-    def import_and_create_new_app_from_url(cls, tenant_id: str, url: str, args: dict, account: Account) -> App:
-        """
-        Import app dsl from url and create new app
-        :param tenant_id: tenant id
-        :param url: import url
-        :param args: request args
-        :param account: Account instance
-        """
-        max_size = 10 * 1024 * 1024  # 10MB
-        response = ssrf_proxy.get(url.strip(), follow_redirects=True, timeout=(10, 10))
-        response.raise_for_status()
-        content = response.content
-
-        if len(content) > max_size:
-            raise FileSizeLimitExceededError("File size exceeds the limit of 10MB")
-
-        if not content:
-            raise EmptyContentError("Empty content from url")
-
-        try:
-            data = content.decode("utf-8")
-        except UnicodeDecodeError as e:
-            raise ContentDecodingError(f"Error decoding content: {e}")
-
-        return cls.import_and_create_new_app(tenant_id, data, args, account)
-
-    @classmethod
-    def import_and_create_new_app(cls, tenant_id: str, data: str, args: dict, account: Account) -> App:
-        """
-        Import app dsl and create new app
-        :param tenant_id: tenant id
-        :param data: import data
-        :param args: request args
-        :param account: Account instance
-        """
-        try:
-            import_data = yaml.safe_load(data)
-        except yaml.YAMLError:
-            raise InvalidYAMLFormatError("Invalid YAML format in data argument.")
-
-        # check or repair dsl version
-        import_data = _check_or_fix_dsl(import_data)
-
-        app_data = import_data.get("app")
-        if not app_data:
-            raise MissingAppDataError("Missing app in data argument")
-
-        # get app basic info
-        name = args.get("name") or app_data.get("name")
-        description = args.get("description") or app_data.get("description", "")
-        icon_type = args.get("icon_type") or app_data.get("icon_type")
-        icon = args.get("icon") or app_data.get("icon")
-        icon_background = args.get("icon_background") or app_data.get("icon_background")
-        use_icon_as_answer_icon = app_data.get("use_icon_as_answer_icon", False)
-
-        # import dsl and create app
-        app_mode = AppMode.value_of(app_data.get("mode"))
-
-        if app_mode in {AppMode.ADVANCED_CHAT, AppMode.WORKFLOW}:
-            workflow_data = import_data.get("workflow")
-            if not workflow_data or not isinstance(workflow_data, dict):
-                raise MissingWorkflowDataError(
-                    "Missing workflow in data argument when app mode is advanced-chat or workflow"
-                )
-
-            app = cls._import_and_create_new_workflow_based_app(
-                tenant_id=tenant_id,
-                app_mode=app_mode,
-                workflow_data=workflow_data,
-                account=account,
-                name=name,
-                description=description,
-                icon_type=icon_type,
-                icon=icon,
-                icon_background=icon_background,
-                use_icon_as_answer_icon=use_icon_as_answer_icon,
-            )
-        elif app_mode in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.COMPLETION}:
-            model_config = import_data.get("model_config")
-            if not model_config or not isinstance(model_config, dict):
-                raise MissingModelConfigError(
-                    "Missing model_config in data argument when app mode is chat, agent-chat or completion"
-                )
-
-            app = cls._import_and_create_new_model_config_based_app(
-                tenant_id=tenant_id,
-                app_mode=app_mode,
-                model_config_data=model_config,
-                account=account,
-                name=name,
-                description=description,
-                icon_type=icon_type,
-                icon=icon,
-                icon_background=icon_background,
-                use_icon_as_answer_icon=use_icon_as_answer_icon,
-            )
-        else:
-            raise InvalidAppModeError("Invalid app mode")
-
-        return app
-
-    @classmethod
-    def import_and_overwrite_workflow(cls, app_model: App, data: str, account: Account) -> Workflow:
-        """
-        Import app dsl and overwrite workflow
-        :param app_model: App instance
-        :param data: import data
-        :param account: Account instance
-        """
-        try:
-            import_data = yaml.safe_load(data)
-        except yaml.YAMLError:
-            raise InvalidYAMLFormatError("Invalid YAML format in data argument.")
-
-        # check or repair dsl version
-        import_data = _check_or_fix_dsl(import_data)
-
-        app_data = import_data.get("app")
-        if not app_data:
-            raise MissingAppDataError("Missing app in data argument")
-
-        # import dsl and overwrite app
-        app_mode = AppMode.value_of(app_data.get("mode"))
-        if app_mode not in {AppMode.ADVANCED_CHAT, AppMode.WORKFLOW}:
-            raise InvalidAppModeError("Only support import workflow in advanced-chat or workflow app.")
-
-        if app_data.get("mode") != app_model.mode:
-            raise ValueError(f"App mode {app_data.get('mode')} is not matched with current app mode {app_mode.value}")
-
-        workflow_data = import_data.get("workflow")
-        if not workflow_data or not isinstance(workflow_data, dict):
-            raise MissingWorkflowDataError(
-                "Missing workflow in data argument when app mode is advanced-chat or workflow"
-            )
-
-        return cls._import_and_overwrite_workflow_based_app(
-            app_model=app_model,
-            workflow_data=workflow_data,
-            account=account,
-        )
-
-    @classmethod
-    def export_dsl(cls, app_model: App, include_secret: bool = False) -> str:
-        """
-        Export app
-        :param app_model: App instance
-        :return:
-        """
-        app_mode = AppMode.value_of(app_model.mode)
-
-        export_data = {
-            "version": current_dsl_version,
-            "kind": "app",
-            "app": {
-                "name": app_model.name,
-                "mode": app_model.mode,
-                "icon": "🤖" if app_model.icon_type == "image" else app_model.icon,
-                "icon_background": "#FFEAD5" if app_model.icon_type == "image" else app_model.icon_background,
-                "description": app_model.description,
-                "use_icon_as_answer_icon": app_model.use_icon_as_answer_icon,
-            },
-        }
-
-        if app_mode in {AppMode.ADVANCED_CHAT, AppMode.WORKFLOW}:
-            cls._append_workflow_export_data(
-                export_data=export_data, app_model=app_model, include_secret=include_secret
-            )
-        else:
-            cls._append_model_config_export_data(export_data, app_model)
-
-        return yaml.dump(export_data, allow_unicode=True)
-
-    @classmethod
-    def _import_and_create_new_workflow_based_app(
-        cls,
-        tenant_id: str,
-        app_mode: AppMode,
-        workflow_data: Mapping[str, Any],
-        account: Account,
-        name: str,
-        description: str,
-        icon_type: str,
-        icon: str,
-        icon_background: str,
-        use_icon_as_answer_icon: bool,
-    ) -> App:
-        """
-        Import app dsl and create new workflow based app
-
-        :param tenant_id: tenant id
-        :param app_mode: app mode
-        :param workflow_data: workflow data
-        :param account: Account instance
-        :param name: app name
-        :param description: app description
-        :param icon_type: app icon type, "emoji" or "image"
-        :param icon: app icon
-        :param icon_background: app icon background
-        :param use_icon_as_answer_icon: use app icon as answer icon
-        """
-        if not workflow_data:
-            raise MissingWorkflowDataError(
-                "Missing workflow in data argument when app mode is advanced-chat or workflow"
-            )
-
-        app = cls._create_app(
-            tenant_id=tenant_id,
-            app_mode=app_mode,
-            account=account,
-            name=name,
-            description=description,
-            icon_type=icon_type,
-            icon=icon,
-            icon_background=icon_background,
-            use_icon_as_answer_icon=use_icon_as_answer_icon,
-        )
-
-        # init draft workflow
-        environment_variables_list = workflow_data.get("environment_variables") or []
-        environment_variables = [
-            variable_factory.build_variable_from_mapping(obj) for obj in environment_variables_list
-        ]
-        conversation_variables_list = workflow_data.get("conversation_variables") or []
-        conversation_variables = [
-            variable_factory.build_variable_from_mapping(obj) for obj in conversation_variables_list
-        ]
-        workflow_service = WorkflowService()
-        draft_workflow = workflow_service.sync_draft_workflow(
-            app_model=app,
-            graph=workflow_data.get("graph", {}),
-            features=workflow_data.get("features", {}),
-            unique_hash=None,
-            account=account,
-            environment_variables=environment_variables,
-            conversation_variables=conversation_variables,
-        )
-        workflow_service.publish_workflow(app_model=app, account=account, draft_workflow=draft_workflow)
-
-        return app
-
-    @classmethod
-    def _import_and_overwrite_workflow_based_app(
-        cls, app_model: App, workflow_data: Mapping[str, Any], account: Account
-    ) -> Workflow:
-        """
-        Import app dsl and overwrite workflow based app
-
-        :param app_model: App instance
-        :param workflow_data: workflow data
-        :param account: Account instance
-        """
-        if not workflow_data:
-            raise MissingWorkflowDataError(
-                "Missing workflow in data argument when app mode is advanced-chat or workflow"
-            )
-
-        # fetch draft workflow by app_model
-        workflow_service = WorkflowService()
-        current_draft_workflow = workflow_service.get_draft_workflow(app_model=app_model)
-        if current_draft_workflow:
-            unique_hash = current_draft_workflow.unique_hash
-        else:
-            unique_hash = None
-
-        # sync draft workflow
-        environment_variables_list = workflow_data.get("environment_variables") or []
-        environment_variables = [
-            variable_factory.build_variable_from_mapping(obj) for obj in environment_variables_list
-        ]
-        conversation_variables_list = workflow_data.get("conversation_variables") or []
-        conversation_variables = [
-            variable_factory.build_variable_from_mapping(obj) for obj in conversation_variables_list
-        ]
-        draft_workflow = workflow_service.sync_draft_workflow(
-            app_model=app_model,
-            graph=workflow_data.get("graph", {}),
-            features=workflow_data.get("features", {}),
-            unique_hash=unique_hash,
-            account=account,
-            environment_variables=environment_variables,
-            conversation_variables=conversation_variables,
-        )
-
-        return draft_workflow
-
-    @classmethod
-    def _import_and_create_new_model_config_based_app(
-        cls,
-        tenant_id: str,
-        app_mode: AppMode,
-        model_config_data: Mapping[str, Any],
-        account: Account,
-        name: str,
-        description: str,
-        icon_type: str,
-        icon: str,
-        icon_background: str,
-        use_icon_as_answer_icon: bool,
-    ) -> App:
-        """
-        Import app dsl and create new model config based app
-
-        :param tenant_id: tenant id
-        :param app_mode: app mode
-        :param model_config_data: model config data
-        :param account: Account instance
-        :param name: app name
-        :param description: app description
-        :param icon: app icon
-        :param icon_background: app icon background
-        """
-        if not model_config_data:
-            raise MissingModelConfigError(
-                "Missing model_config in data argument when app mode is chat, agent-chat or completion"
-            )
-
-        app = cls._create_app(
-            tenant_id=tenant_id,
-            app_mode=app_mode,
-            account=account,
-            name=name,
-            description=description,
-            icon_type=icon_type,
-            icon=icon,
-            icon_background=icon_background,
-            use_icon_as_answer_icon=use_icon_as_answer_icon,
-        )
-
-        app_model_config = AppModelConfig()
-        app_model_config = app_model_config.from_model_config_dict(model_config_data)
-        app_model_config.app_id = app.id
-        app_model_config.created_by = account.id
-        app_model_config.updated_by = account.id
-
-        db.session.add(app_model_config)
-        db.session.commit()
-
-        app.app_model_config_id = app_model_config.id
-
-        app_model_config_was_updated.send(app, app_model_config=app_model_config)
-
-        return app
-
-    @classmethod
-    def _create_app(
-        cls,
-        tenant_id: str,
-        app_mode: AppMode,
-        account: Account,
-        name: str,
-        description: str,
-        icon_type: str,
-        icon: str,
-        icon_background: str,
-        use_icon_as_answer_icon: bool,
-    ) -> App:
-        """
-        Create new app
-
-        :param tenant_id: tenant id
-        :param app_mode: app mode
-        :param account: Account instance
-        :param name: app name
-        :param description: app description
-        :param icon_type: app icon type, "emoji" or "image"
-        :param icon: app icon
-        :param icon_background: app icon background
-        :param use_icon_as_answer_icon: use app icon as answer icon
-        """
-        app = App(
-            tenant_id=tenant_id,
-            mode=app_mode.value,
-            name=name,
-            description=description,
-            icon_type=icon_type,
-            icon=icon,
-            icon_background=icon_background,
-            enable_site=True,
-            enable_api=True,
-            use_icon_as_answer_icon=use_icon_as_answer_icon,
-            created_by=account.id,
-            updated_by=account.id,
-        )
-
-        db.session.add(app)
-        db.session.commit()
-
-        app_was_created.send(app, account=account)
-
-        return app
-
-    @classmethod
-    def _append_workflow_export_data(cls, *, export_data: dict, app_model: App, include_secret: bool) -> None:
-        """
-        Append workflow export data
-        :param export_data: export data
-        :param app_model: App instance
-        """
-        workflow_service = WorkflowService()
-        workflow = workflow_service.get_draft_workflow(app_model)
-        if not workflow:
-            raise ValueError("Missing draft workflow configuration, please check.")
-
-        export_data["workflow"] = workflow.to_dict(include_secret=include_secret)
-
-    @classmethod
-    def _append_model_config_export_data(cls, export_data: dict, app_model: App) -> None:
-        """
-        Append model config export data
-        :param export_data: export data
-        :param app_model: App instance
-        """
-        app_model_config = app_model.app_model_config
-        if not app_model_config:
-            raise ValueError("Missing app configuration, please check.")
-
-        export_data["model_config"] = app_model_config.to_dict()
-
-
-def _check_or_fix_dsl(import_data: dict[str, Any]) -> Mapping[str, Any]:
-    """
-    Check or fix dsl
-
-    :param import_data: import data
-    :raises DSLVersionNotSupportedError: if the imported DSL version is newer than the current version
-    """
-    if not import_data.get("version"):
-        import_data["version"] = "0.1.0"
-
-    if not import_data.get("kind") or import_data.get("kind") != "app":
-        import_data["kind"] = "app"
-
-    imported_version = import_data.get("version")
-    if imported_version != current_dsl_version:
-        if imported_version and version.parse(imported_version) > version.parse(current_dsl_version):
-            errmsg = (
-                f"The imported DSL version {imported_version} is newer than "
-                f"the current supported version {current_dsl_version}. "
-                f"Please upgrade your Dify instance to import this configuration."
-            )
-            logger.warning(errmsg)
-            # raise DSLVersionNotSupportedError(errmsg)
-        else:
-            logger.warning(
-                f"DSL version {imported_version} is older than "
-                f"the current version {current_dsl_version}. "
-                f"This may cause compatibility issues."
-            )
-
-    return import_data

api/services/app_service.py

@@ -155,7 +155,7 @@ class AppService:
         """
         # get original app model config
         if app.mode == AppMode.AGENT_CHAT.value or app.is_agent:
-            model_config: AppModelConfig = app.app_model_config
+            model_config = app.app_model_config
             agent_mode = model_config.agent_mode_dict
             # decrypt agent tool parameters if it's secret-input
             for tool in agent_mode.get("tools") or []:

api/tests/integration_tests/model_runtime/azure_ai_studio/test_llm.py

@@ -11,7 +11,6 @@ from core.model_runtime.entities.message_entities import (
 )
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from core.model_runtime.model_providers.azure_ai_studio.llm.llm import AzureAIStudioLargeLanguageModel
-from tests.integration_tests.model_runtime.__mock.azure_ai_studio import setup_azure_ai_studio_mock
 
 
 @pytest.mark.parametrize("setup_azure_ai_studio_mock", [["chat"]], indirect=True)

api/tests/integration_tests/model_runtime/azure_ai_studio/test_rerank.py

@@ -4,29 +4,21 @@ import pytest
 
 from core.model_runtime.entities.rerank_entities import RerankResult
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
-from core.model_runtime.model_providers.azure_ai_studio.rerank.rerank import AzureAIStudioRerankModel
+from core.model_runtime.model_providers.azure_ai_studio.rerank.rerank import AzureRerankModel
 
 
 def test_validate_credentials():
-    model = AzureAIStudioRerankModel()
+    model = AzureRerankModel()
 
     with pytest.raises(CredentialsValidateFailedError):
         model.validate_credentials(
             model="azure-ai-studio-rerank-v1",
             credentials={"api_key": "invalid_key", "api_base": os.getenv("AZURE_AI_STUDIO_API_BASE")},
-            query="What is the capital of the United States?",
-            docs=[
-                "Carson City is the capital city of the American state of Nevada. At the 2010 United States "
-                "Census, Carson City had a population of 55,274.",
-                "The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean that "
-                "are a political division controlled by the United States. Its capital is Saipan.",
-            ],
-            score_threshold=0.8,
         )
 
 
 def test_invoke_model():
-    model = AzureAIStudioRerankModel()
+    model = AzureRerankModel()
 
     result = model.invoke(
         model="azure-ai-studio-rerank-v1",

api/tests/unit_tests/core/workflow/nodes/llm/test_node.py

@@ -1,125 +1,431 @@
+from collections.abc import Sequence
+from typing import Optional
+
 import pytest
 
-from core.app.entities.app_invoke_entities import InvokeFrom
+from configs import dify_config
+from core.app.entities.app_invoke_entities import InvokeFrom, ModelConfigWithCredentialsEntity
+from core.entities.provider_configuration import ProviderConfiguration, ProviderModelBundle
+from core.entities.provider_entities import CustomConfiguration, SystemConfiguration
 from core.file import File, FileTransferMethod, FileType
-from core.model_runtime.entities.message_entities import ImagePromptMessageContent
+from core.model_runtime.entities.common_entities import I18nObject
+from core.model_runtime.entities.message_entities import (
+    AssistantPromptMessage,
+    ImagePromptMessageContent,
+    PromptMessage,
+    PromptMessageRole,
+    SystemPromptMessage,
+    TextPromptMessageContent,
+    UserPromptMessage,
+)
+from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelFeature, ModelType, ProviderModel
+from core.model_runtime.entities.provider_entities import ConfigurateMethod, ProviderEntity
+from core.model_runtime.model_providers.model_provider_factory import ModelProviderFactory
+from core.prompt.entities.advanced_prompt_entities import MemoryConfig
 from core.variables import ArrayAnySegment, ArrayFileSegment, NoneSegment
 from core.workflow.entities.variable_pool import VariablePool
 from core.workflow.graph_engine import Graph, GraphInitParams, GraphRuntimeState
 from core.workflow.nodes.answer import AnswerStreamGenerateRoute
 from core.workflow.nodes.end import EndStreamParam
-from core.workflow.nodes.llm.entities import ContextConfig, LLMNodeData, ModelConfig, VisionConfig, VisionConfigOptions
+from core.workflow.nodes.llm.entities import (
+    ContextConfig,
+    LLMNodeChatModelMessage,
+    LLMNodeData,
+    ModelConfig,
+    VisionConfig,
+    VisionConfigOptions,
+)
 from core.workflow.nodes.llm.node import LLMNode
 from models.enums import UserFrom
+from models.provider import ProviderType
 from models.workflow import WorkflowType
+from tests.unit_tests.core.workflow.nodes.llm.test_scenarios import LLMNodeTestScenario
 
 
-class TestLLMNode:
-    @pytest.fixture
-    def llm_node(self):
-        data = LLMNodeData(
-            title="Test LLM",
-            model=ModelConfig(provider="openai", name="gpt-3.5-turbo", mode="chat", completion_params={}),
-            prompt_template=[],
-            memory=None,
-            context=ContextConfig(enabled=False),
-            vision=VisionConfig(
-                enabled=True,
-                configs=VisionConfigOptions(
-                    variable_selector=["sys", "files"],
-                    detail=ImagePromptMessageContent.DETAIL.HIGH,
-                ),
-            ),
-        )
-        variable_pool = VariablePool(
-            system_variables={},
-            user_inputs={},
-        )
-        node = LLMNode(
-            id="1",
-            config={
-                "id": "1",
-                "data": data.model_dump(),
-            },
-            graph_init_params=GraphInitParams(
-                tenant_id="1",
-                app_id="1",
-                workflow_type=WorkflowType.WORKFLOW,
-                workflow_id="1",
-                graph_config={},
-                user_id="1",
-                user_from=UserFrom.ACCOUNT,
-                invoke_from=InvokeFrom.SERVICE_API,
-                call_depth=0,
-            ),
-            graph=Graph(
-                root_node_id="1",
-                answer_stream_generate_routes=AnswerStreamGenerateRoute(
-                    answer_dependencies={},
-                    answer_generate_route={},
-                ),
-                end_stream_param=EndStreamParam(
-                    end_dependencies={},
-                    end_stream_variable_selector_mapping={},
-                ),
-            ),
-            graph_runtime_state=GraphRuntimeState(
-                variable_pool=variable_pool,
-                start_at=0,
-            ),
-        )
-        return node
+class MockTokenBufferMemory:
+    def __init__(self, history_messages=None):
+        self.history_messages = history_messages or []
 
-    def test_fetch_files_with_file_segment(self, llm_node):
-        file = File(
+    def get_history_prompt_messages(
+        self, max_token_limit: int = 2000, message_limit: Optional[int] = None
+    ) -> Sequence[PromptMessage]:
+        if message_limit is not None:
+            return self.history_messages[-message_limit * 2 :]
+        return self.history_messages
+
+
+@pytest.fixture
+def llm_node():
+    data = LLMNodeData(
+        title="Test LLM",
+        model=ModelConfig(provider="openai", name="gpt-3.5-turbo", mode="chat", completion_params={}),
+        prompt_template=[],
+        memory=None,
+        context=ContextConfig(enabled=False),
+        vision=VisionConfig(
+            enabled=True,
+            configs=VisionConfigOptions(
+                variable_selector=["sys", "files"],
+                detail=ImagePromptMessageContent.DETAIL.HIGH,
+            ),
+        ),
+    )
+    variable_pool = VariablePool(
+        system_variables={},
+        user_inputs={},
+    )
+    node = LLMNode(
+        id="1",
+        config={
+            "id": "1",
+            "data": data.model_dump(),
+        },
+        graph_init_params=GraphInitParams(
+            tenant_id="1",
+            app_id="1",
+            workflow_type=WorkflowType.WORKFLOW,
+            workflow_id="1",
+            graph_config={},
+            user_id="1",
+            user_from=UserFrom.ACCOUNT,
+            invoke_from=InvokeFrom.SERVICE_API,
+            call_depth=0,
+        ),
+        graph=Graph(
+            root_node_id="1",
+            answer_stream_generate_routes=AnswerStreamGenerateRoute(
+                answer_dependencies={},
+                answer_generate_route={},
+            ),
+            end_stream_param=EndStreamParam(
+                end_dependencies={},
+                end_stream_variable_selector_mapping={},
+            ),
+        ),
+        graph_runtime_state=GraphRuntimeState(
+            variable_pool=variable_pool,
+            start_at=0,
+        ),
+    )
+    return node
+
+
+@pytest.fixture
+def model_config():
+    # Create actual provider and model type instances
+    model_provider_factory = ModelProviderFactory()
+    provider_instance = model_provider_factory.get_provider_instance("openai")
+    model_type_instance = provider_instance.get_model_instance(ModelType.LLM)
+
+    # Create a ProviderModelBundle
+    provider_model_bundle = ProviderModelBundle(
+        configuration=ProviderConfiguration(
+            tenant_id="1",
+            provider=provider_instance.get_provider_schema(),
+            preferred_provider_type=ProviderType.CUSTOM,
+            using_provider_type=ProviderType.CUSTOM,
+            system_configuration=SystemConfiguration(enabled=False),
+            custom_configuration=CustomConfiguration(provider=None),
+            model_settings=[],
+        ),
+        provider_instance=provider_instance,
+        model_type_instance=model_type_instance,
+    )
+
+    # Create and return a ModelConfigWithCredentialsEntity
+    return ModelConfigWithCredentialsEntity(
+        provider="openai",
+        model="gpt-3.5-turbo",
+        model_schema=AIModelEntity(
+            model="gpt-3.5-turbo",
+            label=I18nObject(en_US="GPT-3.5 Turbo"),
+            model_type=ModelType.LLM,
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_properties={},
+        ),
+        mode="chat",
+        credentials={},
+        parameters={},
+        provider_model_bundle=provider_model_bundle,
+    )
+
+
+def test_fetch_files_with_file_segment(llm_node):
+    file = File(
+        id="1",
+        tenant_id="test",
+        type=FileType.IMAGE,
+        filename="test.jpg",
+        transfer_method=FileTransferMethod.LOCAL_FILE,
+        related_id="1",
+    )
+    llm_node.graph_runtime_state.variable_pool.add(["sys", "files"], file)
+
+    result = llm_node._fetch_files(selector=["sys", "files"])
+    assert result == [file]
+
+
+def test_fetch_files_with_array_file_segment(llm_node):
+    files = [
+        File(
             id="1",
             tenant_id="test",
             type=FileType.IMAGE,
-            filename="test.jpg",
+            filename="test1.jpg",
             transfer_method=FileTransferMethod.LOCAL_FILE,
             related_id="1",
+        ),
+        File(
+            id="2",
+            tenant_id="test",
+            type=FileType.IMAGE,
+            filename="test2.jpg",
+            transfer_method=FileTransferMethod.LOCAL_FILE,
+            related_id="2",
+        ),
+    ]
+    llm_node.graph_runtime_state.variable_pool.add(["sys", "files"], ArrayFileSegment(value=files))
+
+    result = llm_node._fetch_files(selector=["sys", "files"])
+    assert result == files
+
+
+def test_fetch_files_with_none_segment(llm_node):
+    llm_node.graph_runtime_state.variable_pool.add(["sys", "files"], NoneSegment())
+
+    result = llm_node._fetch_files(selector=["sys", "files"])
+    assert result == []
+
+
+def test_fetch_files_with_array_any_segment(llm_node):
+    llm_node.graph_runtime_state.variable_pool.add(["sys", "files"], ArrayAnySegment(value=[]))
+
+    result = llm_node._fetch_files(selector=["sys", "files"])
+    assert result == []
+
+
+def test_fetch_files_with_non_existent_variable(llm_node):
+    result = llm_node._fetch_files(selector=["sys", "files"])
+    assert result == []
+
+
+def test_fetch_prompt_messages__vison_disabled(faker, llm_node, model_config):
+    prompt_template = []
+    llm_node.node_data.prompt_template = prompt_template
+
+    fake_vision_detail = faker.random_element(
+        [ImagePromptMessageContent.DETAIL.HIGH, ImagePromptMessageContent.DETAIL.LOW]
+    )
+    fake_remote_url = faker.url()
+    files = [
+        File(
+            id="1",
+            tenant_id="test",
+            type=FileType.IMAGE,
+            filename="test1.jpg",
+            transfer_method=FileTransferMethod.REMOTE_URL,
+            remote_url=fake_remote_url,
         )
-        llm_node.graph_runtime_state.variable_pool.add(["sys", "files"], file)
+    ]
 
-        result = llm_node._fetch_files(selector=["sys", "files"])
-        assert result == [file]
+    fake_query = faker.sentence()
 
-    def test_fetch_files_with_array_file_segment(self, llm_node):
-        files = [
-            File(
-                id="1",
-                tenant_id="test",
-                type=FileType.IMAGE,
-                filename="test1.jpg",
-                transfer_method=FileTransferMethod.LOCAL_FILE,
-                related_id="1",
-            ),
-            File(
-                id="2",
-                tenant_id="test",
-                type=FileType.IMAGE,
-                filename="test2.jpg",
-                transfer_method=FileTransferMethod.LOCAL_FILE,
-                related_id="2",
-            ),
-        ]
-        llm_node.graph_runtime_state.variable_pool.add(["sys", "files"], ArrayFileSegment(value=files))
+    prompt_messages, _ = llm_node._fetch_prompt_messages(
+        user_query=fake_query,
+        user_files=files,
+        context=None,
+        memory=None,
+        model_config=model_config,
+        prompt_template=prompt_template,
+        memory_config=None,
+        vision_enabled=False,
+        vision_detail=fake_vision_detail,
+        variable_pool=llm_node.graph_runtime_state.variable_pool,
+        jinja2_variables=[],
+    )
 
-        result = llm_node._fetch_files(selector=["sys", "files"])
-        assert result == files
+    assert prompt_messages == [UserPromptMessage(content=fake_query)]
 
-    def test_fetch_files_with_none_segment(self, llm_node):
-        llm_node.graph_runtime_state.variable_pool.add(["sys", "files"], NoneSegment())
 
-        result = llm_node._fetch_files(selector=["sys", "files"])
-        assert result == []
+def test_fetch_prompt_messages__basic(faker, llm_node, model_config):
+    # Setup dify config
+    dify_config.MULTIMODAL_SEND_IMAGE_FORMAT = "url"
+    dify_config.MULTIMODAL_SEND_VIDEO_FORMAT = "url"
 
-    def test_fetch_files_with_array_any_segment(self, llm_node):
-        llm_node.graph_runtime_state.variable_pool.add(["sys", "files"], ArrayAnySegment(value=[]))
+    # Generate fake values for prompt template
+    fake_assistant_prompt = faker.sentence()
+    fake_query = faker.sentence()
+    fake_context = faker.sentence()
+    fake_window_size = faker.random_int(min=1, max=3)
+    fake_vision_detail = faker.random_element(
+        [ImagePromptMessageContent.DETAIL.HIGH, ImagePromptMessageContent.DETAIL.LOW]
+    )
+    fake_remote_url = faker.url()
 
-        result = llm_node._fetch_files(selector=["sys", "files"])
-        assert result == []
+    # Setup mock memory with history messages
+    mock_history = [
+        UserPromptMessage(content=faker.sentence()),
+        AssistantPromptMessage(content=faker.sentence()),
+        UserPromptMessage(content=faker.sentence()),
+        AssistantPromptMessage(content=faker.sentence()),
+        UserPromptMessage(content=faker.sentence()),
+        AssistantPromptMessage(content=faker.sentence()),
+    ]
 
-    def test_fetch_files_with_non_existent_variable(self, llm_node):
-        result = llm_node._fetch_files(selector=["sys", "files"])
-        assert result == []
+    # Setup memory configuration
+    memory_config = MemoryConfig(
+        role_prefix=MemoryConfig.RolePrefix(user="Human", assistant="Assistant"),
+        window=MemoryConfig.WindowConfig(enabled=True, size=fake_window_size),
+        query_prompt_template=None,
+    )
+
+    memory = MockTokenBufferMemory(history_messages=mock_history)
+
+    # Test scenarios covering different file input combinations
+    test_scenarios = [
+        LLMNodeTestScenario(
+            description="No files",
+            user_query=fake_query,
+            user_files=[],
+            features=[],
+            vision_enabled=False,
+            vision_detail=None,
+            window_size=fake_window_size,
+            prompt_template=[
+                LLMNodeChatModelMessage(
+                    text=fake_context,
+                    role=PromptMessageRole.SYSTEM,
+                    edition_type="basic",
+                ),
+                LLMNodeChatModelMessage(
+                    text="{#context#}",
+                    role=PromptMessageRole.USER,
+                    edition_type="basic",
+                ),
+                LLMNodeChatModelMessage(
+                    text=fake_assistant_prompt,
+                    role=PromptMessageRole.ASSISTANT,
+                    edition_type="basic",
+                ),
+            ],
+            expected_messages=[
+                SystemPromptMessage(content=fake_context),
+                UserPromptMessage(content=fake_context),
+                AssistantPromptMessage(content=fake_assistant_prompt),
+            ]
+            + mock_history[fake_window_size * -2 :]
+            + [
+                UserPromptMessage(content=fake_query),
+            ],
+        ),
+        LLMNodeTestScenario(
+            description="User files",
+            user_query=fake_query,
+            user_files=[
+                File(
+                    tenant_id="test",
+                    type=FileType.IMAGE,
+                    filename="test1.jpg",
+                    transfer_method=FileTransferMethod.REMOTE_URL,
+                    remote_url=fake_remote_url,
+                )
+            ],
+            vision_enabled=True,
+            vision_detail=fake_vision_detail,
+            features=[ModelFeature.VISION],
+            window_size=fake_window_size,
+            prompt_template=[
+                LLMNodeChatModelMessage(
+                    text=fake_context,
+                    role=PromptMessageRole.SYSTEM,
+                    edition_type="basic",
+                ),
+                LLMNodeChatModelMessage(
+                    text="{#context#}",
+                    role=PromptMessageRole.USER,
+                    edition_type="basic",
+                ),
+                LLMNodeChatModelMessage(
+                    text=fake_assistant_prompt,
+                    role=PromptMessageRole.ASSISTANT,
+                    edition_type="basic",
+                ),
+            ],
+            expected_messages=[
+                SystemPromptMessage(content=fake_context),
+                UserPromptMessage(content=fake_context),
+                AssistantPromptMessage(content=fake_assistant_prompt),
+            ]
+            + mock_history[fake_window_size * -2 :]
+            + [
+                UserPromptMessage(
+                    content=[
+                        TextPromptMessageContent(data=fake_query),
+                        ImagePromptMessageContent(data=fake_remote_url, detail=fake_vision_detail),
+                    ]
+                ),
+            ],
+        ),
+        LLMNodeTestScenario(
+            description="Prompt template with variable selector of File",
+            user_query=fake_query,
+            user_files=[],
+            vision_enabled=False,
+            vision_detail=fake_vision_detail,
+            features=[ModelFeature.VISION],
+            window_size=fake_window_size,
+            prompt_template=[
+                LLMNodeChatModelMessage(
+                    text="{{#input.image#}}",
+                    role=PromptMessageRole.USER,
+                    edition_type="basic",
+                ),
+            ],
+            expected_messages=[
+                UserPromptMessage(
+                    content=[
+                        ImagePromptMessageContent(data=fake_remote_url, detail=fake_vision_detail),
+                    ]
+                ),
+            ]
+            + mock_history[fake_window_size * -2 :]
+            + [UserPromptMessage(content=fake_query)],
+            file_variables={
+                "input.image": File(
+                    tenant_id="test",
+                    type=FileType.IMAGE,
+                    filename="test1.jpg",
+                    transfer_method=FileTransferMethod.REMOTE_URL,
+                    remote_url=fake_remote_url,
+                )
+            },
+        ),
+    ]
+
+    for scenario in test_scenarios:
+        model_config.model_schema.features = scenario.features
+
+        for k, v in scenario.file_variables.items():
+            selector = k.split(".")
+            llm_node.graph_runtime_state.variable_pool.add(selector, v)
+
+        # Call the method under test
+        prompt_messages, _ = llm_node._fetch_prompt_messages(
+            user_query=scenario.user_query,
+            user_files=scenario.user_files,
+            context=fake_context,
+            memory=memory,
+            model_config=model_config,
+            prompt_template=scenario.prompt_template,
+            memory_config=memory_config,
+            vision_enabled=scenario.vision_enabled,
+            vision_detail=scenario.vision_detail,
+            variable_pool=llm_node.graph_runtime_state.variable_pool,
+            jinja2_variables=[],
+        )
+
+        # Verify the result
+        assert len(prompt_messages) == len(scenario.expected_messages), f"Scenario failed: {scenario.description}"
+        assert (
+            prompt_messages == scenario.expected_messages
+        ), f"Message content mismatch in scenario: {scenario.description}"

api/tests/unit_tests/core/workflow/nodes/llm/test_scenarios.py

@@ -0,0 +1,25 @@
+from collections.abc import Mapping, Sequence
+
+from pydantic import BaseModel, Field
+
+from core.file import File
+from core.model_runtime.entities.message_entities import PromptMessage
+from core.model_runtime.entities.model_entities import ModelFeature
+from core.workflow.nodes.llm.entities import LLMNodeChatModelMessage
+
+
+class LLMNodeTestScenario(BaseModel):
+    """Test scenario for LLM node testing."""
+
+    description: str = Field(..., description="Description of the test scenario")
+    user_query: str = Field(..., description="User query input")
+    user_files: Sequence[File] = Field(default_factory=list, description="List of user files")
+    vision_enabled: bool = Field(default=False, description="Whether vision is enabled")
+    vision_detail: str | None = Field(None, description="Vision detail level if vision is enabled")
+    features: Sequence[ModelFeature] = Field(default_factory=list, description="List of model features")
+    window_size: int = Field(..., description="Window size for memory")
+    prompt_template: Sequence[LLMNodeChatModelMessage] = Field(..., description="Template for prompt messages")
+    file_variables: Mapping[str, File | Sequence[File]] = Field(
+        default_factory=dict, description="List of file variables"
+    )
+    expected_messages: Sequence[PromptMessage] = Field(..., description="Expected messages after processing")

api/tests/unit_tests/services/app_dsl_service/test_app_dsl_service.py

@@ -1,47 +0,0 @@
-import pytest
-from packaging import version
-
-from services.app_dsl_service import AppDslService
-from services.app_dsl_service.exc import DSLVersionNotSupportedError
-from services.app_dsl_service.service import _check_or_fix_dsl, current_dsl_version
-
-
-class TestAppDSLService:
-    @pytest.mark.skip(reason="Test skipped")
-    def test_check_or_fix_dsl_missing_version(self):
-        import_data = {}
-        result = _check_or_fix_dsl(import_data)
-        assert result["version"] == "0.1.0"
-        assert result["kind"] == "app"
-
-    @pytest.mark.skip(reason="Test skipped")
-    def test_check_or_fix_dsl_missing_kind(self):
-        import_data = {"version": "0.1.0"}
-        result = _check_or_fix_dsl(import_data)
-        assert result["kind"] == "app"
-
-    @pytest.mark.skip(reason="Test skipped")
-    def test_check_or_fix_dsl_older_version(self):
-        import_data = {"version": "0.0.9", "kind": "app"}
-        result = _check_or_fix_dsl(import_data)
-        assert result["version"] == "0.0.9"
-
-    @pytest.mark.skip(reason="Test skipped")
-    def test_check_or_fix_dsl_current_version(self):
-        import_data = {"version": current_dsl_version, "kind": "app"}
-        result = _check_or_fix_dsl(import_data)
-        assert result["version"] == current_dsl_version
-
-    @pytest.mark.skip(reason="Test skipped")
-    def test_check_or_fix_dsl_newer_version(self):
-        current_version = version.parse(current_dsl_version)
-        newer_version = f"{current_version.major}.{current_version.minor + 1}.0"
-        import_data = {"version": newer_version, "kind": "app"}
-        with pytest.raises(DSLVersionNotSupportedError):
-            _check_or_fix_dsl(import_data)
-
-    @pytest.mark.skip(reason="Test skipped")
-    def test_check_or_fix_dsl_invalid_kind(self):
-        import_data = {"version": current_dsl_version, "kind": "invalid"}
-        result = _check_or_fix_dsl(import_data)
-        assert result["kind"] == "app"

docker/.env.example

@@ -574,9 +574,11 @@ UPLOAD_FILE_BATCH_LIMIT=5
 # `Unstructured` Unstructured.io file extraction scheme
 ETL_TYPE=dify
 
-# Unstructured API path, needs to be configured when ETL_TYPE is Unstructured.
+# Unstructured API path and API key, needs to be configured when ETL_TYPE is Unstructured
+# Or using Unstructured for document extractor node for pptx.
 # For example: http://unstructured:8000/general/v0/general
 UNSTRUCTURED_API_URL=
+UNSTRUCTURED_API_KEY=
 
 # ------------------------------
 # Model Configuration

docker/docker-compose.yaml

@@ -222,6 +222,7 @@ x-shared-env: &shared-api-worker-env
   UPLOAD_FILE_BATCH_LIMIT: ${UPLOAD_FILE_BATCH_LIMIT:-5}
   ETL_TYPE: ${ETL_TYPE:-dify}
   UNSTRUCTURED_API_URL: ${UNSTRUCTURED_API_URL:-}
+  UNSTRUCTURED_API_KEY: ${UNSTRUCTURED_API_KEY:-}
   PROMPT_GENERATION_MAX_TOKENS: ${PROMPT_GENERATION_MAX_TOKENS:-512}
   CODE_GENERATION_MAX_TOKENS: ${CODE_GENERATION_MAX_TOKENS:-1024}
   MULTIMODAL_SEND_IMAGE_FORMAT: ${MULTIMODAL_SEND_IMAGE_FORMAT:-base64}
@@ -290,7 +291,7 @@ x-shared-env: &shared-api-worker-env
 services:
   # API service
   api:
-    image: langgenius/dify-api:0.11.2
+    image: langgenius/dify-api:latest
     restart: always
     environment:
       # Use the shared environment variables.
@@ -310,7 +311,7 @@ services:
   # worker service
   # The Celery worker for processing the queue.
   worker:
-    image: langgenius/dify-api:0.11.2
+    image: langgenius/dify-api:latest
     restart: always
     environment:
       # Use the shared environment variables.
@@ -329,7 +330,7 @@ services:
 
   # Frontend web application.
   web:
-    image: langgenius/dify-web:0.11.2
+    image: langgenius/dify-web:latest
     restart: always
     environment:
       CONSOLE_API_URL: ${CONSOLE_API_URL:-}

web/app/components/app/configuration/config-vision/index.tsx

@@ -12,34 +12,46 @@ import ConfigContext from '@/context/debug-configuration'
 // import { Resolution } from '@/types/app'
 import { useFeatures, useFeaturesStore } from '@/app/components/base/features/hooks'
 import Switch from '@/app/components/base/switch'
-import type { FileUpload } from '@/app/components/base/features/types'
+import { SupportUploadFileTypes } from '@/app/components/workflow/types'
 
 const ConfigVision: FC = () => {
   const { t } = useTranslation()
-  const { isShowVisionConfig } = useContext(ConfigContext)
+  const { isShowVisionConfig, isAllowVideoUpload } = useContext(ConfigContext)
   const file = useFeatures(s => s.features.file)
   const featuresStore = useFeaturesStore()
 
-  const handleChange = useCallback((data: FileUpload) => {
+  const isImageEnabled = file?.allowed_file_types?.includes(SupportUploadFileTypes.image) ?? false
+
+  const handleChange = useCallback((value: boolean) => {
     const {
       features,
       setFeatures,
     } = featuresStore!.getState()
 
     const newFeatures = produce(features, (draft) => {
-      draft.file = {
-        ...draft.file,
-        enabled: data.enabled,
-        image: {
-          enabled: data.enabled,
-          detail: data.image?.detail,
-          transfer_methods: data.image?.transfer_methods,
-          number_limits: data.image?.number_limits,
-        },
+      if (value) {
+        draft.file!.allowed_file_types = Array.from(new Set([
+          ...(draft.file?.allowed_file_types || []),
+          SupportUploadFileTypes.image,
+          ...(isAllowVideoUpload ? [SupportUploadFileTypes.video] : []),
+        ]))
+      }
+      else {
+        draft.file!.allowed_file_types = draft.file!.allowed_file_types?.filter(
+          type => type !== SupportUploadFileTypes.image && (isAllowVideoUpload ? type !== SupportUploadFileTypes.video : true),
+        )
+      }
+
+      if (draft.file) {
+        draft.file.enabled = (draft.file.allowed_file_types?.length ?? 0) > 0
+        draft.file.image = {
+          ...(draft.file.image || {}),
+          enabled: value,
+        }
       }
     })
     setFeatures(newFeatures)
-  }, [featuresStore])
+  }, [featuresStore, isAllowVideoUpload])
 
   if (!isShowVisionConfig)
     return null
@@ -89,11 +101,8 @@ const ConfigVision: FC = () => {
         <ParamConfig />
         <div className='ml-1 mr-3 w-[1px] h-3.5 bg-divider-subtle'></div>
         <Switch
-          defaultValue={file?.enabled}
-          onChange={value => handleChange({
-            ...(file || {}),
-            enabled: value,
-          })}
+          defaultValue={isImageEnabled}
+          onChange={handleChange}
           size='md'
         />
       </div>

web/app/components/app/configuration/config/config-document.tsx

@@ -0,0 +1,78 @@
+'use client'
+import type { FC } from 'react'
+import React, { useCallback } from 'react'
+import { useTranslation } from 'react-i18next'
+import produce from 'immer'
+import { useContext } from 'use-context-selector'
+
+import { Document } from '@/app/components/base/icons/src/vender/features'
+import Tooltip from '@/app/components/base/tooltip'
+import ConfigContext from '@/context/debug-configuration'
+import { SupportUploadFileTypes } from '@/app/components/workflow/types'
+import { useFeatures, useFeaturesStore } from '@/app/components/base/features/hooks'
+import Switch from '@/app/components/base/switch'
+
+const ConfigDocument: FC = () => {
+  const { t } = useTranslation()
+  const file = useFeatures(s => s.features.file)
+  const featuresStore = useFeaturesStore()
+  const { isShowDocumentConfig } = useContext(ConfigContext)
+
+  const isDocumentEnabled = file?.allowed_file_types?.includes(SupportUploadFileTypes.document) ?? false
+
+  const handleChange = useCallback((value: boolean) => {
+    const {
+      features,
+      setFeatures,
+    } = featuresStore!.getState()
+
+    const newFeatures = produce(features, (draft) => {
+      if (value) {
+        draft.file!.allowed_file_types = Array.from(new Set([
+          ...(draft.file?.allowed_file_types || []),
+          SupportUploadFileTypes.document,
+        ]))
+      }
+      else {
+        draft.file!.allowed_file_types = draft.file!.allowed_file_types?.filter(
+          type => type !== SupportUploadFileTypes.document,
+        )
+      }
+      if (draft.file)
+        draft.file.enabled = (draft.file.allowed_file_types?.length ?? 0) > 0
+    })
+    setFeatures(newFeatures)
+  }, [featuresStore])
+
+  if (!isShowDocumentConfig)
+    return null
+
+  return (
+    <div className='mt-2 flex items-center gap-2 p-2 rounded-xl border-t-[0.5px] border-l-[0.5px] bg-background-section-burn'>
+      <div className='shrink-0 p-1'>
+        <div className='p-1 rounded-lg border-[0.5px] border-divider-subtle shadow-xs bg-util-colors-indigo-indigo-600'>
+          <Document className='w-4 h-4 text-text-primary-on-surface' />
+        </div>
+      </div>
+      <div className='grow flex items-center'>
+        <div className='mr-1 text-text-secondary system-sm-semibold'>{t('appDebug.feature.documentUpload.title')}</div>
+        <Tooltip
+          popupContent={
+            <div className='w-[180px]' >
+              {t('appDebug.feature.documentUpload.description')}
+            </div>
+          }
+        />
+      </div>
+      <div className='shrink-0 flex items-center'>
+        <div className='ml-1 mr-3 w-[1px] h-3.5 bg-divider-subtle'></div>
+        <Switch
+          defaultValue={isDocumentEnabled}
+          onChange={handleChange}
+          size='md'
+        />
+      </div>
+    </div>
+  )
+}
+export default React.memo(ConfigDocument)

web/app/components/app/configuration/config/index.tsx

@@ -7,6 +7,7 @@ import { useFormattingChangedDispatcher } from '../debug/hooks'
 import DatasetConfig from '../dataset-config'
 import HistoryPanel from '../config-prompt/conversation-history/history-panel'
 import ConfigVision from '../config-vision'
+import ConfigDocument from './config-document'
 import AgentTools from './agent/agent-tools'
 import ConfigContext from '@/context/debug-configuration'
 import ConfigPrompt from '@/app/components/app/configuration/config-prompt'
@@ -82,6 +83,8 @@ const Config: FC = () => {
 
         <ConfigVision />
 
+        <ConfigDocument />
+
         {/* Chat History */}
         {isAdvancedMode && isChatApp && modelModeType === ModelModeType.completion && (
           <HistoryPanel

web/app/components/app/configuration/index.tsx

@@ -451,7 +451,8 @@ const Configuration: FC = () => {
   }
 
   const isShowVisionConfig = !!currModel?.features?.includes(ModelFeatureEnum.vision)
-
+  const isShowDocumentConfig = !!currModel?.features?.includes(ModelFeatureEnum.document)
+  const isAllowVideoUpload = !!currModel?.features?.includes(ModelFeatureEnum.video)
   // *** web app features ***
   const featuresData: FeaturesData = useMemo(() => {
     return {
@@ -472,7 +473,7 @@ const Configuration: FC = () => {
           transfer_methods: modelConfig.file_upload?.image?.transfer_methods || ['local_file', 'remote_url'],
         },
         enabled: !!(modelConfig.file_upload?.enabled || modelConfig.file_upload?.image?.enabled),
-        allowed_file_types: modelConfig.file_upload?.allowed_file_types || [SupportUploadFileTypes.image, SupportUploadFileTypes.video],
+        allowed_file_types: modelConfig.file_upload?.allowed_file_types || [],
         allowed_file_extensions: modelConfig.file_upload?.allowed_file_extensions || [...FILE_EXTS[SupportUploadFileTypes.image], ...FILE_EXTS[SupportUploadFileTypes.video]].map(ext => `.${ext}`),
         allowed_file_upload_methods: modelConfig.file_upload?.allowed_file_upload_methods || modelConfig.file_upload?.image?.transfer_methods || ['local_file', 'remote_url'],
         number_limits: modelConfig.file_upload?.number_limits || modelConfig.file_upload?.image?.number_limits || 3,
@@ -861,6 +862,8 @@ const Configuration: FC = () => {
       isShowVisionConfig,
       visionConfig,
       setVisionConfig: handleSetVisionConfig,
+      isAllowVideoUpload,
+      isShowDocumentConfig,
       rerankSettingModalOpen,
       setRerankSettingModalOpen,
     }}

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

@@ -12,9 +12,13 @@ import Input from '@/app/components/base/input'
 import Modal from '@/app/components/base/modal'
 import { ToastContext } from '@/app/components/base/toast'
 import {
-  importApp,
-  importAppFromUrl,
+  importDSL,
+  importDSLConfirm,
 } from '@/service/apps'
+import {
+  DSLImportMode,
+  DSLImportStatus,
+} from '@/models/app'
 import { useAppContext } from '@/context/app-context'
 import { useProviderContext } from '@/context/provider-context'
 import AppsFull from '@/app/components/billing/apps-full-in-dialog'
@@ -43,6 +47,9 @@ const CreateFromDSLModal = ({ show, onSuccess, onClose, activeTab = CreateFromDS
   const [fileContent, setFileContent] = useState<string>()
   const [currentTab, setCurrentTab] = useState(activeTab)
   const [dslUrlValue, setDslUrlValue] = useState(dslUrl)
+  const [showErrorModal, setShowErrorModal] = useState(false)
+  const [versions, setVersions] = useState<{ importedVersion: string; systemVersion: string }>()
+  const [importId, setImportId] = useState<string>()
 
   const readFile = (file: File) => {
     const reader = new FileReader()
@@ -66,6 +73,7 @@ const CreateFromDSLModal = ({ show, onSuccess, onClose, activeTab = CreateFromDS
   const isAppsFull = (enableBilling && plan.usage.buildApps >= plan.total.buildApps)
 
   const isCreatingRef = useRef(false)
+
   const onCreate: MouseEventHandler = async () => {
     if (currentTab === CreateFromDSLModalTab.FROM_FILE && !currentFile)
       return
@@ -75,25 +83,54 @@ const CreateFromDSLModal = ({ show, onSuccess, onClose, activeTab = CreateFromDS
       return
     isCreatingRef.current = true
     try {
-      let app
+      let response
 
       if (currentTab === CreateFromDSLModalTab.FROM_FILE) {
-        app = await importApp({
-          data: fileContent || '',
+        response = await importDSL({
+          mode: DSLImportMode.YAML_CONTENT,
+          yaml_content: fileContent || '',
         })
       }
       if (currentTab === CreateFromDSLModalTab.FROM_URL) {
-        app = await importAppFromUrl({
-          url: dslUrlValue || '',
+        response = await importDSL({
+          mode: DSLImportMode.YAML_URL,
+          yaml_url: dslUrlValue || '',
         })
       }
-      if (onSuccess)
-        onSuccess()
-      if (onClose)
-        onClose()
-      notify({ type: 'success', message: t('app.newApp.appCreated') })
-      localStorage.setItem(NEED_REFRESH_APP_LIST_KEY, '1')
-      getRedirection(isCurrentWorkspaceEditor, app, push)
+
+      if (!response)
+        return
+
+      const { id, status, app_id, imported_dsl_version, current_dsl_version } = response
+      if (status === DSLImportStatus.COMPLETED || status === DSLImportStatus.COMPLETED_WITH_WARNINGS) {
+        if (onSuccess)
+          onSuccess()
+        if (onClose)
+          onClose()
+
+        notify({
+          type: status === DSLImportStatus.COMPLETED ? 'success' : 'warning',
+          message: t(status === DSLImportStatus.COMPLETED ? 'app.newApp.appCreated' : 'app.newApp.caution'),
+          children: status === DSLImportStatus.COMPLETED_WITH_WARNINGS && t('app.newApp.appCreateDSLWarning'),
+        })
+        localStorage.setItem(NEED_REFRESH_APP_LIST_KEY, '1')
+        getRedirection(isCurrentWorkspaceEditor, { id: app_id }, push)
+      }
+      else if (status === DSLImportStatus.PENDING) {
+        setVersions({
+          importedVersion: imported_dsl_version ?? '',
+          systemVersion: current_dsl_version ?? '',
+        })
+        if (onClose)
+          onClose()
+        setTimeout(() => {
+          setShowErrorModal(true)
+        }, 300)
+        setImportId(id)
+      }
+      else {
+        notify({ type: 'error', message: t('app.newApp.appCreateFailed') })
+      }
     }
     catch (e) {
       notify({ type: 'error', message: t('app.newApp.appCreateFailed') })
@@ -101,6 +138,38 @@ const CreateFromDSLModal = ({ show, onSuccess, onClose, activeTab = CreateFromDS
     isCreatingRef.current = false
   }
 
+  const onDSLConfirm: MouseEventHandler = async () => {
+    try {
+      if (!importId)
+        return
+      const response = await importDSLConfirm({
+        import_id: importId,
+      })
+
+      const { status, app_id } = response
+
+      if (status === DSLImportStatus.COMPLETED) {
+        if (onSuccess)
+          onSuccess()
+        if (onClose)
+          onClose()
+
+        notify({
+          type: 'success',
+          message: t('app.newApp.appCreated'),
+        })
+        localStorage.setItem(NEED_REFRESH_APP_LIST_KEY, '1')
+        getRedirection(isCurrentWorkspaceEditor, { id: app_id }, push)
+      }
+      else if (status === DSLImportStatus.FAILED) {
+        notify({ type: 'error', message: t('app.newApp.appCreateFailed') })
+      }
+    }
+    catch (e) {
+      notify({ type: 'error', message: t('app.newApp.appCreateFailed') })
+    }
+  }
+
   const tabs = [
     {
       key: CreateFromDSLModalTab.FROM_FILE,
@@ -123,74 +192,96 @@ const CreateFromDSLModal = ({ show, onSuccess, onClose, activeTab = CreateFromDS
   }, [isAppsFull, currentTab, currentFile, dslUrlValue])
 
   return (
-    <Modal
-      className='p-0 w-[520px] rounded-2xl border-[0.5px] border-components-panel-border bg-components-panel-bg shadow-xl'
-      isShow={show}
-      onClose={() => { }}
-    >
-      <div className='flex items-center justify-between pt-6 pl-6 pr-5 pb-3 text-text-primary title-2xl-semi-bold'>
-        {t('app.importFromDSL')}
-        <div
-          className='flex items-center w-8 h-8 cursor-pointer'
-          onClick={() => onClose()}
-        >
-          <RiCloseLine className='w-5 h-5 text-text-tertiary' />
+    <>
+      <Modal
+        className='p-0 w-[520px] rounded-2xl border-[0.5px] border-components-panel-border bg-components-panel-bg shadow-xl'
+        isShow={show}
+        onClose={() => { }}
+      >
+        <div className='flex items-center justify-between pt-6 pl-6 pr-5 pb-3 text-text-primary title-2xl-semi-bold'>
+          {t('app.importFromDSL')}
+          <div
+            className='flex items-center w-8 h-8 cursor-pointer'
+            onClick={() => onClose()}
+          >
+            <RiCloseLine className='w-5 h-5 text-text-tertiary' />
+          </div>
         </div>
-      </div>
-      <div className='flex items-center px-6 h-9 space-x-6 system-md-semibold text-text-tertiary border-b border-divider-subtle'>
-        {
-          tabs.map(tab => (
-            <div
-              key={tab.key}
-              className={cn(
-                'relative flex items-center h-full cursor-pointer',
-                currentTab === tab.key && 'text-text-primary',
-              )}
-              onClick={() => setCurrentTab(tab.key)}
-            >
-              {tab.label}
-              {
-                currentTab === tab.key && (
-                  <div className='absolute bottom-0 w-full h-[2px] bg-util-colors-blue-brand-blue-brand-600'></div>
-                )
-              }
-            </div>
-          ))
-        }
-      </div>
-      <div className='px-6 py-4'>
-        {
-          currentTab === CreateFromDSLModalTab.FROM_FILE && (
-            <Uploader
-              className='mt-0'
-              file={currentFile}
-              updateFile={handleFile}
-            />
-          )
-        }
-        {
-          currentTab === CreateFromDSLModalTab.FROM_URL && (
-            <div>
-              <div className='mb-1 system-md-semibold leading6'>DSL URL</div>
-              <Input
-                placeholder={t('app.importFromDSLUrlPlaceholder') || ''}
-                value={dslUrlValue}
-                onChange={e => setDslUrlValue(e.target.value)}
+        <div className='flex items-center px-6 h-9 space-x-6 system-md-semibold text-text-tertiary border-b border-divider-subtle'>
+          {
+            tabs.map(tab => (
+              <div
+                key={tab.key}
+                className={cn(
+                  'relative flex items-center h-full cursor-pointer',
+                  currentTab === tab.key && 'text-text-primary',
+                )}
+                onClick={() => setCurrentTab(tab.key)}
+              >
+                {tab.label}
+                {
+                  currentTab === tab.key && (
+                    <div className='absolute bottom-0 w-full h-[2px] bg-util-colors-blue-brand-blue-brand-600'></div>
+                  )
+                }
+              </div>
+            ))
+          }
+        </div>
+        <div className='px-6 py-4'>
+          {
+            currentTab === CreateFromDSLModalTab.FROM_FILE && (
+              <Uploader
+                className='mt-0'
+                file={currentFile}
+                updateFile={handleFile}
               />
-            </div>
-          )
-        }
-      </div>
-      {isAppsFull && (
-        <div className='px-6'>
-          <AppsFull className='mt-0' loc='app-create-dsl' />
+            )
+          }
+          {
+            currentTab === CreateFromDSLModalTab.FROM_URL && (
+              <div>
+                <div className='mb-1 system-md-semibold leading6'>DSL URL</div>
+                <Input
+                  placeholder={t('app.importFromDSLUrlPlaceholder') || ''}
+                  value={dslUrlValue}
+                  onChange={e => setDslUrlValue(e.target.value)}
+                />
+              </div>
+            )
+          }
         </div>
-      )}
-      <div className='flex justify-end px-6 py-5'>
-        <Button className='mr-2' onClick={onClose}>{t('app.newApp.Cancel')}</Button>
-        <Button disabled={buttonDisabled} variant="primary" onClick={onCreate}>{t('app.newApp.Create')}</Button>
-      </div>
-    </Modal>
+        {isAppsFull && (
+          <div className='px-6'>
+            <AppsFull className='mt-0' loc='app-create-dsl' />
+          </div>
+        )}
+        <div className='flex justify-end px-6 py-5'>
+          <Button className='mr-2' onClick={onClose}>{t('app.newApp.Cancel')}</Button>
+          <Button disabled={buttonDisabled} variant="primary" onClick={onCreate}>{t('app.newApp.Create')}</Button>
+        </div>
+      </Modal>
+      <Modal
+        isShow={showErrorModal}
+        onClose={() => setShowErrorModal(false)}
+        className='w-[480px]'
+      >
+        <div className='flex pb-4 flex-col items-start gap-2 self-stretch'>
+          <div className='text-text-primary title-2xl-semi-bold'>{t('app.newApp.appCreateDSLErrorTitle')}</div>
+          <div className='flex flex-grow flex-col text-text-secondary system-md-regular'>
+            <div>{t('app.newApp.appCreateDSLErrorPart1')}</div>
+            <div>{t('app.newApp.appCreateDSLErrorPart2')}</div>
+            <br />
+            <div>{t('app.newApp.appCreateDSLErrorPart3')}<span className='system-md-medium'>{versions?.importedVersion}</span></div>
+            <div>{t('app.newApp.appCreateDSLErrorPart4')}<span className='system-md-medium'>{versions?.systemVersion}</span></div>
+          </div>
+        </div>
+        <div className='flex pt-6 justify-end items-start gap-2 self-stretch'>
+          <Button variant='secondary' onClick={() => setShowErrorModal(false)}>{t('app.newApp.Cancel')}</Button>
+          <Button variant='primary' destructive onClick={onDSLConfirm}>{t('app.newApp.Confirm')}</Button>
+        </div>
+      </Modal>
+    </>
   )
 }
 

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

@@ -6,6 +6,7 @@ import {
 } from '@remixicon/react'
 import { useTranslation } from 'react-i18next'
 import { useContext } from 'use-context-selector'
+import { formatFileSize } from '@/utils/format'
 import cn from '@/utils/classnames'
 import { Yaml as YamlIcon } from '@/app/components/base/icons/src/public/files'
 import { ToastContext } from '@/app/components/base/toast'
@@ -58,8 +59,13 @@ const Uploader: FC<Props> = ({
     updateFile(files[0])
   }
   const selectHandle = () => {
-    if (fileUploader.current)
+    const originalFile = file
+    if (fileUploader.current) {
+      fileUploader.current.value = ''
       fileUploader.current.click()
+      // If no file is selected, restore the original file
+      fileUploader.current.oncancel = () => updateFile(originalFile)
+    }
   }
   const removeFile = () => {
     if (fileUploader.current)
@@ -96,7 +102,7 @@ const Uploader: FC<Props> = ({
       />
       <div ref={dropRef}>
         {!file && (
-          <div className={cn('flex items-center h-20 rounded-xl bg-gray-50 border border-dashed border-gray-200 text-sm font-normal', dragging && 'bg-[#F5F8FF] border border-[#B2CCFF]')}>
+          <div className={cn('flex items-center h-12 rounded-xl bg-gray-50 border border-dashed border-gray-200 text-sm font-normal', dragging && 'bg-[#F5F8FF] border border-[#B2CCFF]')}>
             <div className='w-full flex items-center justify-center space-x-2'>
               <UploadCloud01 className='w-6 h-6 mr-2' />
               <div className='text-gray-500'>
@@ -108,17 +114,23 @@ const Uploader: FC<Props> = ({
           </div>
         )}
         {file && (
-          <div className={cn('flex items-center h-20 px-6 rounded-xl bg-gray-50 border border-gray-200 text-sm font-normal group', 'hover:bg-[#F5F8FF] hover:border-[#B2CCFF]')}>
-            <YamlIcon className="shrink-0" />
-            <div className='flex ml-2 w-0 grow'>
-              <span className='max-w-[calc(100%_-_30px)] text-ellipsis whitespace-nowrap overflow-hidden text-gray-800'>{file.name.replace(/(.yaml|.yml)$/, '')}</span>
-              <span className='shrink-0 text-gray-500'>.yml</span>
+          <div className={cn('flex items-center rounded-lg bg-components-panel-on-panel-item-bg border-[0.5px] border-components-panel-border shadow-xs group', 'hover:bg-[#F5F8FF] hover:border-[#B2CCFF]')}>
+            <div className='flex p-3 justify-center items-center'>
+              <YamlIcon className="w-6 h-6 shrink-0" />
+            </div>
+            <div className='flex py-1 pr-2 grow flex-col items-start gap-0.5'>
+              <span className='max-w-[calc(100%_-_30px)] text-ellipsis whitespace-nowrap overflow-hidden text-text-secondary font-inter text-[12px] font-medium leading-4'>{file.name}</span>
+              <div className='flex h-3 items-center gap-1 self-stretch text-text-tertiary font-inter text-[10px] font-medium leading-3 uppercase'>
+                <span>YAML</span>
+                <span className='text-text-quaternary'>·</span>
+                <span>{formatFileSize(file.size)}</span>
+              </div>
             </div>
             <div className='hidden group-hover:flex items-center'>
               <Button onClick={selectHandle}>{t('datasetCreation.stepOne.uploader.change')}</Button>
               <div className='mx-2 w-px h-4 bg-gray-200' />
               <div className='p-2 cursor-pointer' onClick={removeFile}>
-                <RiDeleteBinLine className='w-4 h-4 text-gray-500' />
+                <RiDeleteBinLine className='w-4 h-4 text-text-tertiary' />
               </div>
             </div>
           </div>

web/app/components/base/chat/chat/chat-input-area/index.tsx

@@ -102,21 +102,21 @@ const ChatInputArea = ({
       setCurrentIndex(historyRef.current.length)
       handleSend()
     }
-    else if (e.key === 'ArrowUp' && !e.shiftKey && !e.nativeEvent.isComposing) {
-      // When the up key is pressed, output the previous element
+    else if (e.key === 'ArrowUp' && !e.shiftKey && !e.nativeEvent.isComposing && e.metaKey) {
+      // When the cmd + up key is pressed, output the previous element
       if (currentIndex > 0) {
         setCurrentIndex(currentIndex - 1)
         setQuery(historyRef.current[currentIndex - 1])
       }
     }
-    else if (e.key === 'ArrowDown' && !e.shiftKey && !e.nativeEvent.isComposing) {
-      // When the down key is pressed, output the next element
+    else if (e.key === 'ArrowDown' && !e.shiftKey && !e.nativeEvent.isComposing && e.metaKey) {
+      // When the cmd + down key is pressed, output the next element
       if (currentIndex < historyRef.current.length - 1) {
         setCurrentIndex(currentIndex + 1)
         setQuery(historyRef.current[currentIndex + 1])
       }
       else if (currentIndex === historyRef.current.length - 1) {
-        // If it is the last element, clear the input box
+      // If it is the last element, clear the input box
         setCurrentIndex(historyRef.current.length)
         setQuery('')
       }

web/app/components/base/divider/index.tsx

@@ -1,17 +1,31 @@
 import type { CSSProperties, FC } from 'react'
 import React from 'react'
-import s from './style.module.css'
+import { type VariantProps, cva } from 'class-variance-authority'
+import classNames from '@/utils/classnames'
 
-type Props = {
-  type?: 'horizontal' | 'vertical'
-  // orientation?: 'left' | 'right' | 'center'
+const dividerVariants = cva(
+  'bg-divider-regular',
+  {
+    variants: {
+      type: {
+        horizontal: 'w-full h-[0.5px] my-2',
+        vertical: 'w-[1px] h-full mx-2',
+      },
+    },
+    defaultVariants: {
+      type: 'horizontal',
+    },
+  },
+)
+
+type DividerProps = {
   className?: string
   style?: CSSProperties
-}
+} & VariantProps<typeof dividerVariants>
 
-const Divider: FC<Props> = ({ type = 'horizontal', className = '', style }) => {
+const Divider: FC<DividerProps> = ({ type, className = '', style }) => {
   return (
-    <div className={`${s.divider} ${s[type]} ${className}`} style={style}></div>
+    <div className={classNames(dividerVariants({ type }), className)} style={style}></div>
   )
 }
 

web/app/components/base/divider/style.module.css

@@ -1,9 +0,0 @@
-.divider {
-  @apply bg-gray-200;
-}
-.horizontal {
-  @apply w-full h-[0.5px] my-2;
-}
-.vertical {
-  @apply w-[1px] h-full mx-2;
-}

web/app/components/base/icons/assets/vender/features/document.svg

@@ -0,0 +1,3 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor">
+<path d="M20 22H4C3.44772 22 3 21.5523 3 21V3C3 2.44772 3.44772 2 4 2H20C20.5523 2 21 2.44772 21 3V21C21 21.5523 20.5523 22 20 22ZM7 6V10H11V6H7ZM7 12V14H17V12H7ZM7 16V18H17V16H7ZM13 7V9H17V7H13Z"></path>
+</svg>