chore: bump version to 0.13.2 (#11489)

Signed-off-by: -LAN- <laipz8200@outlook.com>

.devcontainer/Dockerfile

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

.devcontainer/devcontainer.json

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

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

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

.github/pull_request_template.md

@@ -8,16 +8,9 @@ Please include a summary of the change and which issue is fixed. Please also inc
 
 # Screenshots
 
-<table>
-  <tr>
-  <td>Before: </td>
-  <td>After: </td>
-  </tr>
-  <tr>
-  <td>...</td>
-  <td>...</td>
-  </tr>
-</table>
+| Before | After |
+|--------|-------|
+| ...    | ...   |
 
 # Checklist
 

.github/workflows/api-tests.yml

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

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

@@ -48,6 +48,8 @@ jobs:
           cp .env.example .env
 
       - name: Run DB Migration
+        env:
+          DEBUG: true
         run: |
           cd api
           poetry run python -m flask upgrade-db

.github/workflows/vdb-tests.yml

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

CONTRIBUTING.md

@@ -1,6 +1,8 @@
+# CONTRIBUTING
+
 So you're looking to contribute to Dify - that's awesome, we can't wait to see what you do. As a startup with limited headcount and funding, we have grand ambitions to design the most intuitive workflow for building and managing LLM applications. Any help from the community counts, truly.
 
-We need to be nimble and ship fast given where we are, but we also want to make sure that contributors like you get as smooth an experience at contributing as possible. We've assembled this contribution guide for that purpose, aiming at getting you familiarized with the codebase & how we work with contributors, so you could quickly jump to the fun part. 
+We need to be nimble and ship fast given where we are, but we also want to make sure that contributors like you get as smooth an experience at contributing as possible. We've assembled this contribution guide for that purpose, aiming at getting you familiarized with the codebase & how we work with contributors, so you could quickly jump to the fun part.
 
 This guide, like Dify itself, is a constant work in progress. We highly appreciate your understanding if at times it lags behind the actual project, and welcome any feedback for us to improve.
 
@@ -10,14 +12,12 @@ In terms of licensing, please take a minute to read our short [License and Contr
 
 [Find](https://github.com/langgenius/dify/issues?q=is:issue+is:open) an existing issue, or [open](https://github.com/langgenius/dify/issues/new/choose) a new one. We categorize issues into 2 types:
 
-### Feature requests:
+### Feature requests
 
 * If you're opening a new feature request, we'd like you to explain what the proposed feature achieves, and include as much context as possible. [@perzeusss](https://github.com/perzeuss) has made a solid [Feature Request Copilot](https://udify.app/chat/MK2kVSnw1gakVwMX) that helps you draft out your needs. Feel free to give it a try.
 
 * If you want to pick one up from the existing issues, simply drop a comment below it saying so.
 
-  
-
   A team member working in the related direction will be looped in. If all looks good, they will give the go-ahead for you to start coding. We ask that you hold off working on the feature until then, so none of your work goes to waste should we propose changes.
 
   Depending on whichever area the proposed feature falls under, you might talk to different team members. Here's rundown of the areas each our team members are working on at the moment:
@@ -40,7 +40,7 @@ In terms of licensing, please take a minute to read our short [License and Contr
   | Non-core features and minor enhancements                     | Low Priority    |
   | Valuable but not immediate                                   | Future-Feature  |
 
-### Anything else (e.g. bug report, performance optimization, typo correction):
+### Anything else (e.g. bug report, performance optimization, typo correction)
 
 * Start coding right away.
 
@@ -52,7 +52,6 @@ In terms of licensing, please take a minute to read our short [License and Contr
   | Non-critical bugs, performance boosts                        | Medium Priority |
   | Minor fixes (typos, confusing but working UI)                | Low Priority    |
 
-
 ## Installing
 
 Here are the steps to set up Dify for development:
@@ -63,7 +62,7 @@ Here are the steps to set up Dify for development:
 
  Clone the forked repository from your terminal:
 
-```
+```shell
 git clone git@github.com:<github_username>/dify.git
 ```
 
@@ -71,11 +70,11 @@ git clone git@github.com:<github_username>/dify.git
 
 Dify requires the following dependencies to build, make sure they're installed on your system:
 
-- [Docker](https://www.docker.com/)
-- [Docker 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.

CONTRIBUTING_CN.md

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

CONTRIBUTING_JA.md

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

CONTRIBUTING_VI.md

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

README.md

@@ -147,6 +147,13 @@ Deploy Dify to Cloud Platform with a single click using [terraform](https://www.
 ##### Google Cloud
 - [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Using AWS CDK for Deployment
+
+Deploy Dify to AWS with [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Contributing
 
 For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 

README_AR.md

@@ -190,6 +190,13 @@ docker compose up -d
 ##### Google Cloud
 - [Google Cloud Terraform بواسطة @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### استخدام AWS CDK للنشر
+
+انشر Dify على AWS باستخدام [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK بواسطة @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## المساهمة
 
 لأولئك الذين يرغبون في المساهمة، انظر إلى [دليل المساهمة](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) لدينا. 
@@ -222,3 +229,10 @@ docker compose up -d
 ## الرخصة
 
 هذا المستودع متاح تحت [رخصة البرنامج الحر Dify](LICENSE)، والتي تعتبر بشكل أساسي Apache 2.0 مع بعض القيود الإضافية.
+## الكشف عن الأمان
+
+لحماية خصوصيتك، يرجى تجنب نشر مشكلات الأمان على GitHub. بدلاً من ذلك، أرسل أسئلتك إلى security@dify.ai وسنقدم لك إجابة أكثر تفصيلاً.
+
+## الرخصة
+
+هذا المستودع متاح تحت [رخصة البرنامج الحر Dify](LICENSE)، والتي تعتبر بشكل أساسي Apache 2.0 مع بعض القيود الإضافية.

README_CN.md

@@ -213,6 +213,13 @@ docker compose up -d
 ##### Google Cloud
 - [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### 使用 AWS CDK 部署
+
+使用 [CDK](https://aws.amazon.com/cdk/) 将 Dify 部署到 AWS
+
+##### AWS 
+- [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)

README_ES.md

@@ -215,6 +215,13 @@ Despliega Dify en una plataforma en la nube con un solo clic utilizando [terrafo
 ##### Google Cloud
 - [Google Cloud Terraform por @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Usando AWS CDK para el Despliegue
+
+Despliegue Dify en AWS usando [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK por @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Contribuir
 
 Para aquellos que deseen contribuir con código, consulten nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
@@ -248,3 +255,10 @@ Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En
 ## Licencia
 
 Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.
+## Divulgación de Seguridad
+
+Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En su lugar, envía tus preguntas a security@dify.ai y te proporcionaremos una respuesta más detallada.
+
+## Licencia
+
+Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.

README_FR.md

@@ -213,6 +213,13 @@ Déployez Dify sur une plateforme cloud en un clic en utilisant [terraform](http
 ##### Google Cloud
 - [Google Cloud Terraform par @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Utilisation d'AWS CDK pour le déploiement
+
+Déployez Dify sur AWS en utilisant [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK par @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Contribuer
 
 Pour ceux qui souhaitent contribuer du code, consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
@@ -246,3 +253,10 @@ Pour protéger votre vie privée, veuillez éviter de publier des problèmes de
 ## Licence
 
 Ce référentiel est disponible sous la [Licence open source Dify](LICENSE), qui est essentiellement l'Apache 2.0 avec quelques restrictions supplémentaires.
+## Divulgation de sécurité
+
+Pour protéger votre vie privée, veuillez éviter de publier des problèmes de sécurité sur GitHub. Au lieu de cela, envoyez vos questions à security@dify.ai et nous vous fournirons une réponse plus détaillée.
+
+## Licence
+
+Ce référentiel est disponible sous la [Licence open source Dify](LICENSE), qui est essentiellement l'Apache 2.0 avec quelques restrictions supplémentaires.

README_JA.md

@@ -212,6 +212,13 @@ docker compose up -d
 ##### Google Cloud
 - [@sotazumによるGoogle Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### AWS CDK を使用したデプロイ
+
+[CDK](https://aws.amazon.com/cdk/) を使用して、DifyをAWSにデプロイします
+
+##### AWS 
+- [@KevinZhaoによるAWS CDK](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## 貢献
 
 コードに貢献したい方は、[Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)を参照してください。

README_KL.md

@@ -213,6 +213,13 @@ wa'logh nIqHom neH ghun deployment toy'wI' [terraform](https://www.terraform.io/
 ##### Google Cloud
 - [Google Cloud Terraform qachlot @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### AWS CDK atorlugh pilersitsineq
+
+wa'logh nIqHom neH ghun deployment toy'wI' [CDK](https://aws.amazon.com/cdk/) lo'laH.
+
+##### AWS 
+- [AWS CDK qachlot @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Contributing
 
 For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 

README_KR.md

@@ -205,6 +205,13 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
 ##### Google Cloud
 - [sotazum의 Google Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### AWS CDK를 사용한 배포
+
+[CDK](https://aws.amazon.com/cdk/)를 사용하여 AWS에 Dify 배포
+
+##### AWS 
+- [KevinZhao의 AWS CDK](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## 기여
 
 코드에 기여하고 싶은 분들은 [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)를 참조하세요.

README_PT.md

@@ -211,6 +211,13 @@ Implante o Dify na Plataforma Cloud com um único clique usando [terraform](http
 ##### Google Cloud
 - [Google Cloud Terraform por @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Usando AWS CDK para Implantação
+
+Implante o Dify na AWS usando [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK por @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Contribuindo
 
 Para aqueles que desejam contribuir com código, veja nosso [Guia de Contribuição](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 

README_SI.md

@@ -145,6 +145,13 @@ namestite Dify v Cloud Platform z enim klikom z uporabo [terraform](https://www.
 ##### Google Cloud
 - [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Uporaba AWS CDK za uvajanje
+
+Uvedite Dify v AWS z uporabo [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Prispevam
 
 Za tiste, ki bi radi prispevali kodo, si oglejte naš vodnik za prispevke . Hkrati vas prosimo, da podprete Dify tako, da ga delite na družbenih medijih ter na dogodkih in konferencah. 

README_TR.md

@@ -211,6 +211,13 @@ Dify'ı bulut platformuna tek tıklamayla dağıtın [terraform](https://www.ter
 ##### Google Cloud
 - [Google Cloud Terraform tarafından @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### AWS CDK ile Dağıtım
+
+[CDK](https://aws.amazon.com/cdk/) kullanarak Dify'ı AWS'ye dağıtın
+
+##### AWS 
+- [AWS CDK tarafından @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Katkıda Bulunma
 
 Kod katkısında bulunmak isteyenler için [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakabilirsiniz.

README_VI.md

@@ -207,6 +207,13 @@ Triển khai Dify lên nền tảng đám mây với một cú nhấp chuột b
 ##### Google Cloud
 - [Google Cloud Terraform bởi @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Sử dụng AWS CDK để Triển khai
+
+Triển khai Dify trên AWS bằng [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK bởi @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Đóng góp
 
 Đối với những người muốn đóng góp mã, xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi. 

api/.env.example

@@ -42,6 +42,11 @@ REDIS_SENTINEL_USERNAME=
 REDIS_SENTINEL_PASSWORD=
 REDIS_SENTINEL_SOCKET_TIMEOUT=0.1
 
+# redis Cluster configuration.
+REDIS_USE_CLUSTERS=false
+REDIS_CLUSTERS=
+REDIS_CLUSTERS_PASSWORD=
+
 # PostgreSQL database configuration
 DB_USERNAME=postgres
 DB_PASSWORD=difyai123456
@@ -234,6 +239,10 @@ ANALYTICDB_ACCOUNT=testaccount
 ANALYTICDB_PASSWORD=testpassword
 ANALYTICDB_NAMESPACE=dify
 ANALYTICDB_NAMESPACE_PASSWORD=difypassword
+ANALYTICDB_HOST=gp-test.aliyuncs.com
+ANALYTICDB_PORT=5432
+ANALYTICDB_MIN_CONNECTION=1
+ANALYTICDB_MAX_CONNECTION=5
 
 # OpenSearch configuration
 OPENSEARCH_HOST=127.0.0.1
@@ -320,6 +329,7 @@ NOTION_INTERNAL_SECRET=you-internal-secret
 ETL_TYPE=dify
 UNSTRUCTURED_API_URL=
 UNSTRUCTURED_API_KEY=
+SCARF_NO_ANALYTICS=true
 
 #ssrf
 SSRF_PROXY_HTTP_URL=
@@ -373,7 +383,7 @@ LOG_DATEFORMAT=%Y-%m-%d %H:%M:%S
 LOG_TZ=UTC
 
 # Indexing configuration
-INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=1000
+INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=4000
 
 # Workflow runtime configuration
 WORKFLOW_MAX_EXECUTION_STEPS=500
@@ -401,4 +411,5 @@ POSITION_PROVIDER_EXCLUDES=
 # Reset password token expiry minutes
 RESET_PASSWORD_TOKEN_EXPIRY_MINUTES=5
 
-CREATE_TIDB_SERVICE_JOB_ENABLED=false
+CREATE_TIDB_SERVICE_JOB_ENABLED=false
+

api/.ruff.toml

@@ -0,0 +1,96 @@
+exclude = [
+    "migrations/*",
+]
+line-length = 120
+
+[format]
+quote-style = "double"
+
+[lint]
+preview = true
+select = [
+    "B", # flake8-bugbear rules
+    "C4", # flake8-comprehensions
+    "E", # pycodestyle E rules
+    "F", # pyflakes rules
+    "FURB", # refurb rules
+    "I", # isort rules
+    "N", # pep8-naming
+    "PT", # flake8-pytest-style rules
+    "PLC0208", # iteration-over-set
+    "PLC2801", # unnecessary-dunder-call
+    "PLC0414", # useless-import-alias
+    "PLE0604", # invalid-all-object
+    "PLE0605", # invalid-all-format
+    "PLR0402", # manual-from-import
+    "PLR1711", # useless-return
+    "PLR1714", # repeated-equality-comparison
+    "RUF013", # implicit-optional
+    "RUF019", # unnecessary-key-check
+    "RUF100", # unused-noqa
+    "RUF101", # redirected-noqa
+    "RUF200", # invalid-pyproject-toml
+    "RUF022", # unsorted-dunder-all
+    "S506", # unsafe-yaml-load
+    "SIM", # flake8-simplify rules
+    "TRY400", # error-instead-of-exception
+    "TRY401", # verbose-log-message
+    "UP", # pyupgrade rules
+    "W191", # tab-indentation
+    "W605", # invalid-escape-sequence
+]
+
+ignore = [
+    "E402", # module-import-not-at-top-of-file
+    "E711", # none-comparison
+    "E712", # true-false-comparison
+    "E721", # type-comparison
+    "E722", # bare-except
+    "E731", # lambda-assignment
+    "F821", # undefined-name
+    "F841", # unused-variable
+    "FURB113", # repeated-append
+    "FURB152", # math-constant
+    "UP007", # non-pep604-annotation
+    "UP032", # f-string
+    "B005", # strip-with-multi-characters
+    "B006", # mutable-argument-default
+    "B007", # unused-loop-control-variable
+    "B026", # star-arg-unpacking-after-keyword-arg
+    "B904", # raise-without-from-inside-except
+    "B905", # zip-without-explicit-strict
+    "N806", # non-lowercase-variable-in-function
+    "N815", # mixed-case-variable-in-class-scope
+    "PT011", # pytest-raises-too-broad
+    "SIM102", # collapsible-if
+    "SIM103", # needless-bool
+    "SIM105", # suppressible-exception
+    "SIM107", # return-in-try-except-finally
+    "SIM108", # if-else-block-instead-of-if-exp
+    "SIM113", # eumerate-for-loop
+    "SIM117", # multiple-with-statements
+    "SIM210", # if-expr-with-true-false
+    "SIM300", # yoda-conditions,
+]
+
+[lint.per-file-ignores]
+"__init__.py" = [
+    "F401", # unused-import
+    "F811", # redefined-while-unused
+]
+"configs/*" = [
+    "N802", # invalid-function-name
+]
+"libs/gmpy2_pkcs10aep_cipher.py" = [
+    "N803", # invalid-argument-name
+]
+"tests/*" = [
+    "F811", # redefined-while-unused
+    "F401", # unused-import
+]
+
+[lint.pyflakes]
+extend-generics = [
+    "_pytest.monkeypatch",
+    "tests.integration_tests",
+]

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
 
@@ -55,7 +55,7 @@ RUN apt-get update \
     && echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
     && apt-get update \
     # For Security
-    && apt-get install -y --no-install-recommends expat=2.6.4-1 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-7 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
+    && apt-get install -y --no-install-recommends expat=2.6.4-1 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-8 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
     # install a chinese font to support the use of tools like matplotlib
     && apt-get install -y fonts-noto-cjk \
     && apt-get autoremove -y \

api/README.md

@@ -18,12 +18,17 @@
    ```
 
 2. Copy `.env.example` to `.env`
+
+   ```cli
+   cp .env.example .env 
+   ```
 3. Generate a `SECRET_KEY` in the `.env` file.
 
+   bash for Linux
    ```bash for Linux
    sed -i "/^SECRET_KEY=/c\SECRET_KEY=$(openssl rand -base64 42)" .env
    ```
-
+   bash for Mac
    ```bash for Mac
    secret_key=$(openssl rand -base64 42)
    sed -i '' "/^SECRET_KEY=/c\\
@@ -37,18 +42,10 @@
 5. Install dependencies
 
    ```bash
-   poetry env use 3.10
+   poetry env use 3.12
    poetry install
    ```
 
-   In case of contributors missing to update dependencies for `pyproject.toml`, you can perform the following shell instead.
-
-   ```bash
-   poetry shell                                               # activate current environment
-   poetry add $(cat requirements.txt)           # install dependencies of production and update pyproject.toml
-   poetry add $(cat requirements-dev.txt) --group dev    # install dependencies of development and update pyproject.toml
-   ```
-
 6. Run migrate
 
    Before the first launch, migrate the database to the latest version.
@@ -84,5 +81,3 @@
    ```bash
    poetry run -C api bash dev/pytest/pytest_all_tests.sh
    ```
-
-

api/app.py

@@ -1,111 +1,13 @@
-import os
-import sys
-
-from configs import dify_config
-
-if not dify_config.DEBUG:
-    from gevent import monkey
-
-    monkey.patch_all()
-
-    import grpc.experimental.gevent
-
-    grpc.experimental.gevent.init_gevent()
-
-import json
-import threading
-import time
-import warnings
-
-from flask import Response
-
 from app_factory import create_app
+from libs import threadings_utils, version_utils
 
-# DO NOT REMOVE BELOW
-from events import event_handlers  # noqa: F401
-from extensions.ext_database import db
-
-# TODO: Find a way to avoid importing models here
-from models import account, dataset, model, source, task, tool, tools, web  # noqa: F401
-
-# DO NOT REMOVE ABOVE
-
-if sys.version_info[:2] == (3, 10):
-    print("Warning: Python 3.10 will not be supported in the next version.")
-
-
-warnings.simplefilter("ignore", ResourceWarning)
-
-os.environ["TZ"] = "UTC"
-# windows platform not support tzset
-if hasattr(time, "tzset"):
-    time.tzset()
-
+# preparation before creating app
+version_utils.check_supported_python_version()
+threadings_utils.apply_gevent_threading_patch()
 
 # create app
 app = create_app()
 celery = app.extensions["celery"]
 
-if dify_config.TESTING:
-    print("App is running in TESTING mode")
-
-
-@app.after_request
-def after_request(response):
-    """Add Version headers to the response."""
-    response.headers.add("X-Version", dify_config.CURRENT_VERSION)
-    response.headers.add("X-Env", dify_config.DEPLOY_ENV)
-    return response
-
-
-@app.route("/health")
-def health():
-    return Response(
-        json.dumps({"pid": os.getpid(), "status": "ok", "version": dify_config.CURRENT_VERSION}),
-        status=200,
-        content_type="application/json",
-    )
-
-
-@app.route("/threads")
-def threads():
-    num_threads = threading.active_count()
-    threads = threading.enumerate()
-
-    thread_list = []
-    for thread in threads:
-        thread_name = thread.name
-        thread_id = thread.ident
-        is_alive = thread.is_alive()
-
-        thread_list.append(
-            {
-                "name": thread_name,
-                "id": thread_id,
-                "is_alive": is_alive,
-            }
-        )
-
-    return {
-        "pid": os.getpid(),
-        "thread_num": num_threads,
-        "threads": thread_list,
-    }
-
-
-@app.route("/db-pool-stat")
-def pool_stat():
-    engine = db.engine
-    return {
-        "pid": os.getpid(),
-        "pool_size": engine.pool.size(),
-        "checked_in_connections": engine.pool.checkedin(),
-        "checked_out_connections": engine.pool.checkedout(),
-        "overflow_connections": engine.pool.overflow(),
-        "connection_timeout": engine.pool.timeout(),
-        "recycle_time": db.engine.pool._recycle,
-    }
-
-
 if __name__ == "__main__":
     app.run(host="0.0.0.0", port=5001)

api/app_factory.py

@@ -1,54 +1,15 @@
+import logging
 import os
+import time
 
 from configs import dify_config
-
-if not dify_config.DEBUG:
-    from gevent import monkey
-
-    monkey.patch_all()
-
-    import grpc.experimental.gevent
-
-    grpc.experimental.gevent.init_gevent()
-
-import json
-
-from flask import Flask, Response, request
-from flask_cors import CORS
-from werkzeug.exceptions import Unauthorized
-
-import contexts
-from commands import register_commands
-from configs import dify_config
-from extensions import (
-    ext_celery,
-    ext_code_based_extension,
-    ext_compress,
-    ext_database,
-    ext_hosting_provider,
-    ext_logging,
-    ext_login,
-    ext_mail,
-    ext_migrate,
-    ext_proxy_fix,
-    ext_redis,
-    ext_sentry,
-    ext_storage,
-)
-from extensions.ext_database import db
-from extensions.ext_login import login_manager
-from libs.passport import PassportService
-from services.account_service import AccountService
-
-
-class DifyApp(Flask):
-    pass
+from dify_app import DifyApp
 
 
 # ----------------------------
 # Application Factory Function
 # ----------------------------
-def create_flask_app_with_configs() -> Flask:
+def create_flask_app_with_configs() -> DifyApp:
     """
     create a raw flask app
     with configs loaded from .env file
@@ -68,111 +29,72 @@ def create_flask_app_with_configs() -> Flask:
     return dify_app
 
 
-def create_app() -> Flask:
+def create_app() -> DifyApp:
+    start_time = time.perf_counter()
     app = create_flask_app_with_configs()
-    app.secret_key = dify_config.SECRET_KEY
     initialize_extensions(app)
-    register_blueprints(app)
-    register_commands(app)
-
+    end_time = time.perf_counter()
+    if dify_config.DEBUG:
+        logging.info(f"Finished create_app ({round((end_time - start_time) * 1000, 2)} ms)")
     return app
 
 
-def initialize_extensions(app):
-    # Since the application instance is now created, pass it to each Flask
-    # extension instance to bind it to the Flask application instance (app)
-    ext_logging.init_app(app)
-    ext_compress.init_app(app)
-    ext_code_based_extension.init()
-    ext_database.init_app(app)
-    ext_migrate.init(app, db)
-    ext_redis.init_app(app)
-    ext_storage.init_app(app)
-    ext_celery.init_app(app)
-    ext_login.init_app(app)
-    ext_mail.init_app(app)
-    ext_hosting_provider.init_app(app)
-    ext_sentry.init_app(app)
-    ext_proxy_fix.init_app(app)
-
-
-# Flask-Login configuration
-@login_manager.request_loader
-def load_user_from_request(request_from_flask_login):
-    """Load user based on the request."""
-    if request.blueprint not in {"console", "inner_api"}:
-        return None
-    # Check if the user_id contains a dot, indicating the old format
-    auth_header = request.headers.get("Authorization", "")
-    if not auth_header:
-        auth_token = request.args.get("_token")
-        if not auth_token:
-            raise Unauthorized("Invalid Authorization token.")
-    else:
-        if " " not in auth_header:
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
-        auth_scheme, auth_token = auth_header.split(None, 1)
-        auth_scheme = auth_scheme.lower()
-        if auth_scheme != "bearer":
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
-
-    decoded = PassportService().verify(auth_token)
-    user_id = decoded.get("user_id")
-
-    logged_in_account = AccountService.load_logged_in_account(account_id=user_id)
-    if logged_in_account:
-        contexts.tenant_id.set(logged_in_account.current_tenant_id)
-    return logged_in_account
-
-
-@login_manager.unauthorized_handler
-def unauthorized_handler():
-    """Handle unauthorized requests."""
-    return Response(
-        json.dumps({"code": "unauthorized", "message": "Unauthorized."}),
-        status=401,
-        content_type="application/json",
+def initialize_extensions(app: DifyApp):
+    from extensions import (
+        ext_app_metrics,
+        ext_blueprints,
+        ext_celery,
+        ext_code_based_extension,
+        ext_commands,
+        ext_compress,
+        ext_database,
+        ext_hosting_provider,
+        ext_import_modules,
+        ext_logging,
+        ext_login,
+        ext_mail,
+        ext_migrate,
+        ext_proxy_fix,
+        ext_redis,
+        ext_sentry,
+        ext_set_secretkey,
+        ext_storage,
+        ext_timezone,
+        ext_warnings,
     )
 
+    extensions = [
+        ext_timezone,
+        ext_logging,
+        ext_warnings,
+        ext_import_modules,
+        ext_set_secretkey,
+        ext_compress,
+        ext_code_based_extension,
+        ext_database,
+        ext_app_metrics,
+        ext_migrate,
+        ext_redis,
+        ext_storage,
+        ext_celery,
+        ext_login,
+        ext_mail,
+        ext_hosting_provider,
+        ext_sentry,
+        ext_proxy_fix,
+        ext_blueprints,
+        ext_commands,
+    ]
+    for ext in extensions:
+        short_name = ext.__name__.split(".")[-1]
+        is_enabled = ext.is_enabled() if hasattr(ext, "is_enabled") else True
+        if not is_enabled:
+            if dify_config.DEBUG:
+                logging.info(f"Skipped {short_name}")
+            continue
 
-# register blueprint routers
-def register_blueprints(app):
-    from controllers.console import bp as console_app_bp
-    from controllers.files import bp as files_bp
-    from controllers.inner_api import bp as inner_api_bp
-    from controllers.service_api import bp as service_api_bp
-    from controllers.web import bp as web_bp
-
-    CORS(
-        service_api_bp,
-        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-    )
-    app.register_blueprint(service_api_bp)
-
-    CORS(
-        web_bp,
-        resources={r"/*": {"origins": dify_config.WEB_API_CORS_ALLOW_ORIGINS}},
-        supports_credentials=True,
-        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-        expose_headers=["X-Version", "X-Env"],
-    )
-
-    app.register_blueprint(web_bp)
-
-    CORS(
-        console_app_bp,
-        resources={r"/*": {"origins": dify_config.CONSOLE_CORS_ALLOW_ORIGINS}},
-        supports_credentials=True,
-        allow_headers=["Content-Type", "Authorization"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-        expose_headers=["X-Version", "X-Env"],
-    )
-
-    app.register_blueprint(console_app_bp)
-
-    CORS(files_bp, allow_headers=["Content-Type"], methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"])
-    app.register_blueprint(files_bp)
-
-    app.register_blueprint(inner_api_bp)
+        start_time = time.perf_counter()
+        ext.init_app(app)
+        end_time = time.perf_counter()
+        if dify_config.DEBUG:
+            logging.info(f"Loaded {short_name} ({round((end_time - start_time) * 1000, 2)} ms)")

api/commands.py

@@ -259,7 +259,7 @@ def migrate_knowledge_vector_database():
     skipped_count = 0
     total_count = 0
     vector_type = dify_config.VECTOR_STORE
-    upper_colletion_vector_types = {
+    upper_collection_vector_types = {
         VectorType.MILVUS,
         VectorType.PGVECTOR,
         VectorType.RELYT,
@@ -267,7 +267,7 @@ def migrate_knowledge_vector_database():
         VectorType.ORACLE,
         VectorType.ELASTICSEARCH,
     }
-    lower_colletion_vector_types = {
+    lower_collection_vector_types = {
         VectorType.ANALYTICDB,
         VectorType.CHROMA,
         VectorType.MYSCALE,
@@ -307,7 +307,7 @@ def migrate_knowledge_vector_database():
                         continue
                 collection_name = ""
                 dataset_id = dataset.id
-                if vector_type in upper_colletion_vector_types:
+                if vector_type in upper_collection_vector_types:
                     collection_name = Dataset.gen_collection_name_by_id(dataset_id)
                 elif vector_type == VectorType.QDRANT:
                     if dataset.collection_binding_id:
@@ -323,7 +323,7 @@ def migrate_knowledge_vector_database():
                     else:
                         collection_name = Dataset.gen_collection_name_by_id(dataset_id)
 
-                elif vector_type in lower_colletion_vector_types:
+                elif vector_type in lower_collection_vector_types:
                     collection_name = Dataset.gen_collection_name_by_id(dataset_id).lower()
                 else:
                     raise ValueError(f"Vector store {vector_type} is not supported.")
@@ -640,15 +640,3 @@ where sites.id is null limit 1000"""
                 break
 
     click.echo(click.style("Fix for missing app-related sites completed successfully!", fg="green"))
-
-
-def register_commands(app):
-    app.cli.add_command(reset_password)
-    app.cli.add_command(reset_email)
-    app.cli.add_command(reset_encrypt_key_pair)
-    app.cli.add_command(vdb_migrate)
-    app.cli.add_command(convert_to_agent_apps)
-    app.cli.add_command(add_qdrant_doc_id_index)
-    app.cli.add_command(create_tenant)
-    app.cli.add_command(upgrade_db)
-    app.cli.add_command(fix_app_site_missing)

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/configs/deploy/__init__.py

@@ -17,11 +17,6 @@ class DeploymentConfig(BaseSettings):
         default=False,
     )
 
-    TESTING: bool = Field(
-        description="Enable testing mode for running automated tests",
-        default=False,
-    )
-
     EDITION: str = Field(
         description="Deployment edition of the application (e.g., 'SELF_HOSTED', 'CLOUD')",
         default="SELF_HOSTED",

api/configs/feature/__init__.py

@@ -585,6 +585,11 @@ class RagEtlConfig(BaseSettings):
         default=None,
     )
 
+    SCARF_NO_ANALYTICS: Optional[str] = Field(
+        description="This is about whether to disable Scarf analytics in Unstructured library.",
+        default="false",
+    )
+
 
 class DataSetConfig(BaseSettings):
     """
@@ -640,7 +645,7 @@ class IndexingConfig(BaseSettings):
 
     INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH: PositiveInt = Field(
         description="Maximum token length for text segmentation during indexing",
-        default=1000,
+        default=4000,
     )
 
 

api/configs/middleware/cache/redis_config.py

@@ -68,3 +68,18 @@ class RedisConfig(BaseSettings):
         description="Socket timeout in seconds for Redis Sentinel connections",
         default=0.1,
     )
+
+    REDIS_USE_CLUSTERS: bool = Field(
+        description="Enable Redis Clusters mode for high availability",
+        default=False,
+    )
+
+    REDIS_CLUSTERS: Optional[str] = Field(
+        description="Comma-separated list of Redis Clusters nodes (host:port)",
+        default=None,
+    )
+
+    REDIS_CLUSTERS_PASSWORD: Optional[str] = Field(
+        description="Password for Redis Clusters authentication (if required)",
+        default=None,
+    )

api/configs/middleware/vdb/analyticdb_config.py

@@ -1,6 +1,6 @@
 from typing import Optional
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, PositiveInt
 
 
 class AnalyticdbConfig(BaseModel):
@@ -40,3 +40,11 @@ class AnalyticdbConfig(BaseModel):
         description="The password for accessing the specified namespace within the AnalyticDB instance"
         " (if namespace feature is enabled).",
     )
+    ANALYTICDB_HOST: Optional[str] = Field(
+        default=None, description="The host of the AnalyticDB instance you want to connect to."
+    )
+    ANALYTICDB_PORT: PositiveInt = Field(
+        default=5432, description="The port of the AnalyticDB instance you want to connect to."
+    )
+    ANALYTICDB_MIN_CONNECTION: PositiveInt = Field(default=1, description="Min connection of the AnalyticDB database.")
+    ANALYTICDB_MAX_CONNECTION: PositiveInt = Field(default=5, description="Max connection of the AnalyticDB database.")

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="0.11.2",
+        default="0.13.2",
     )
 
     COMMIT_SHA: str = Field(

api/constants/languages.py

@@ -18,6 +18,7 @@ language_timezone_mapping = {
     "tr-TR": "Europe/Istanbul",
     "fa-IR": "Asia/Tehran",
     "sl-SI": "Europe/Ljubljana",
+    "th-TH": "Asia/Bangkok",
 }
 
 languages = list(language_timezone_mapping.keys())

api/controllers/console/__init__.py

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

api/controllers/console/app/app.py

@@ -1,7 +1,10 @@
 import uuid
+from typing import cast
 
 from flask_login import current_user
 from flask_restful import Resource, inputs, marshal, marshal_with, reqparse
+from sqlalchemy import select
+from sqlalchemy.orm import Session
 from werkzeug.exceptions import BadRequest, Forbidden, abort
 
 from controllers.console import api
@@ -13,13 +16,15 @@ from controllers.console.wraps import (
     setup_required,
 )
 from core.ops.ops_trace_manager import OpsTraceManager
+from extensions.ext_database import db
 from fields.app_fields import (
     app_detail_fields,
     app_detail_fields_with_site,
     app_pagination_fields,
 )
 from libs.login import login_required
-from services.app_dsl_service import AppDslService
+from models import Account, App
+from services.app_dsl_service import AppDslService, ImportMode
 from services.app_service import AppService
 
 ALLOW_CREATE_APP_MODES = ["chat", "agent-chat", "advanced-chat", "workflow", "completion"]
@@ -92,61 +97,6 @@ class AppListApi(Resource):
         return app, 201
 
 
-class AppImportApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    @marshal_with(app_detail_fields_with_site)
-    @cloud_edition_billing_resource_check("apps")
-    def post(self):
-        """Import app"""
-        # The role of the current user in the ta table must be admin, owner, or editor
-        if not current_user.is_editor:
-            raise Forbidden()
-
-        parser = reqparse.RequestParser()
-        parser.add_argument("data", type=str, required=True, nullable=False, location="json")
-        parser.add_argument("name", type=str, location="json")
-        parser.add_argument("description", type=str, location="json")
-        parser.add_argument("icon_type", type=str, location="json")
-        parser.add_argument("icon", type=str, location="json")
-        parser.add_argument("icon_background", type=str, location="json")
-        args = parser.parse_args()
-
-        app = AppDslService.import_and_create_new_app(
-            tenant_id=current_user.current_tenant_id, data=args["data"], args=args, account=current_user
-        )
-
-        return app, 201
-
-
-class AppImportFromUrlApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    @marshal_with(app_detail_fields_with_site)
-    @cloud_edition_billing_resource_check("apps")
-    def post(self):
-        """Import app from url"""
-        # The role of the current user in the ta table must be admin, owner, or editor
-        if not current_user.is_editor:
-            raise Forbidden()
-
-        parser = reqparse.RequestParser()
-        parser.add_argument("url", type=str, required=True, nullable=False, location="json")
-        parser.add_argument("name", type=str, location="json")
-        parser.add_argument("description", type=str, location="json")
-        parser.add_argument("icon", type=str, location="json")
-        parser.add_argument("icon_background", type=str, location="json")
-        args = parser.parse_args()
-
-        app = AppDslService.import_and_create_new_app_from_url(
-            tenant_id=current_user.current_tenant_id, url=args["url"], args=args, account=current_user
-        )
-
-        return app, 201
-
-
 class AppApi(Resource):
     @setup_required
     @login_required
@@ -224,10 +174,24 @@ class AppCopyApi(Resource):
         parser.add_argument("icon_background", type=str, location="json")
         args = parser.parse_args()
 
-        data = AppDslService.export_dsl(app_model=app_model, include_secret=True)
-        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/conversation.py

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

api/controllers/console/app/site.py

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

api/controllers/console/app/workflow.py

@@ -20,7 +20,6 @@ from libs.helper import TimestampField, uuid_value
 from libs.login import current_user, login_required
 from models import App
 from models.model import AppMode
-from services.app_dsl_service import AppDslService
 from services.app_generate_service import AppGenerateService
 from services.errors.app import WorkflowHashNotEqualError
 from services.workflow_service import WorkflowService
@@ -101,11 +100,11 @@ class DraftWorkflowApi(Resource):
         try:
             environment_variables_list = args.get("environment_variables") or []
             environment_variables = [
-                variable_factory.build_variable_from_mapping(obj) for obj in environment_variables_list
+                variable_factory.build_environment_variable_from_mapping(obj) for obj in environment_variables_list
             ]
             conversation_variables_list = args.get("conversation_variables") or []
             conversation_variables = [
-                variable_factory.build_variable_from_mapping(obj) for obj in conversation_variables_list
+                variable_factory.build_conversation_variable_from_mapping(obj) for obj in conversation_variables_list
             ]
             workflow = workflow_service.sync_draft_workflow(
                 app_model=app_model,
@@ -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
@@ -408,7 +382,7 @@ class DefaultBlockConfigApi(Resource):
         filters = None
         if args.get("q"):
             try:
-                filters = json.loads(args.get("q"))
+                filters = json.loads(args.get("q", ""))
             except json.JSONDecodeError:
                 raise ValueError("Invalid filters")
 
@@ -453,7 +427,6 @@ class ConvertToWorkflowApi(Resource):
 
 
 api.add_resource(DraftWorkflowApi, "/apps/<uuid:app_id>/workflows/draft")
-api.add_resource(DraftWorkflowImportApi, "/apps/<uuid:app_id>/workflows/draft/import")
 api.add_resource(AdvancedChatDraftWorkflowRunApi, "/apps/<uuid:app_id>/advanced-chat/workflows/draft/run")
 api.add_resource(DraftWorkflowRunApi, "/apps/<uuid:app_id>/workflows/draft/run")
 api.add_resource(WorkflowTaskStopApi, "/apps/<uuid:app_id>/workflow-runs/tasks/<string:task_id>/stop")

api/controllers/console/auth/activate.py

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

api/controllers/console/auth/data_source_oauth.py

@@ -34,7 +34,6 @@ class OAuthDataSource(Resource):
         OAUTH_DATASOURCE_PROVIDERS = get_oauth_providers()
         with current_app.app_context():
             oauth_provider = OAUTH_DATASOURCE_PROVIDERS.get(provider)
-            print(vars(oauth_provider))
         if not oauth_provider:
             return {"error": "Invalid provider"}, 400
         if dify_config.NOTION_INTEGRATION_TYPE == "internal":

api/controllers/console/auth/oauth.py

@@ -1,5 +1,5 @@
 import logging
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from typing import Optional
 
 import requests
@@ -52,7 +52,6 @@ class OAuthLogin(Resource):
         OAUTH_PROVIDERS = get_oauth_providers()
         with current_app.app_context():
             oauth_provider = OAUTH_PROVIDERS.get(provider)
-            print(vars(oauth_provider))
         if not oauth_provider:
             return {"error": "Invalid provider"}, 400
 
@@ -106,7 +105,7 @@ class OAuthCallback(Resource):
 
         if account.status == AccountStatus.PENDING.value:
             account.status = AccountStatus.ACTIVE.value
-            account.initialized_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            account.initialized_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
         try:

api/controllers/console/datasets/data_source.py

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

api/controllers/console/datasets/datasets_document.py

@@ -1,6 +1,6 @@
 import logging
 from argparse import ArgumentTypeError
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 
 from flask import request
 from flask_login import current_user
@@ -106,6 +106,7 @@ class GetProcessRuleApi(Resource):
         # get default rules
         mode = DocumentService.DEFAULT_RULES["mode"]
         rules = DocumentService.DEFAULT_RULES["rules"]
+        limits = DocumentService.DEFAULT_RULES["limits"]
         if document_id:
             # get the latest process rule
             document = Document.query.get_or_404(document_id)
@@ -132,7 +133,7 @@ class GetProcessRuleApi(Resource):
                 mode = dataset_process_rule.mode
                 rules = dataset_process_rule.rules_dict
 
-        return {"mode": mode, "rules": rules}
+        return {"mode": mode, "rules": rules, "limits": limits}
 
 
 class DatasetDocumentListApi(Resource):
@@ -665,7 +666,7 @@ class DocumentProcessingApi(DocumentResource):
                 raise InvalidActionError("Document not in indexing state.")
 
             document.paused_by = current_user.id
-            document.paused_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.paused_at = datetime.now(UTC).replace(tzinfo=None)
             document.is_paused = True
             db.session.commit()
 
@@ -745,7 +746,7 @@ class DocumentMetadataApi(DocumentResource):
                     document.doc_metadata[key] = value
 
         document.doc_type = doc_type
-        document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        document.updated_at = datetime.now(UTC).replace(tzinfo=None)
         db.session.commit()
 
         return {"result": "success", "message": "Document metadata updated."}, 200
@@ -787,7 +788,7 @@ class DocumentStatusApi(DocumentResource):
             document.enabled = True
             document.disabled_at = None
             document.disabled_by = None
-            document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.updated_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
             # Set cache to prevent indexing the same document multiple times
@@ -804,9 +805,9 @@ class DocumentStatusApi(DocumentResource):
                 raise InvalidActionError("Document already disabled.")
 
             document.enabled = False
-            document.disabled_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.disabled_at = datetime.now(UTC).replace(tzinfo=None)
             document.disabled_by = current_user.id
-            document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.updated_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
             # Set cache to prevent indexing the same document multiple times
@@ -821,9 +822,9 @@ class DocumentStatusApi(DocumentResource):
                 raise InvalidActionError("Document already archived.")
 
             document.archived = True
-            document.archived_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.archived_at = datetime.now(UTC).replace(tzinfo=None)
             document.archived_by = current_user.id
-            document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.updated_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
             if document.enabled:
@@ -840,7 +841,7 @@ class DocumentStatusApi(DocumentResource):
             document.archived = False
             document.archived_at = None
             document.archived_by = None
-            document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            document.updated_at = datetime.now(UTC).replace(tzinfo=None)
             db.session.commit()
 
             # Set cache to prevent indexing the same document multiple times

api/controllers/console/datasets/datasets_segments.py

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

api/controllers/console/explore/completion.py

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

api/controllers/console/explore/installed_app.py

@@ -1,5 +1,6 @@
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 
+from flask import request
 from flask_login import current_user
 from flask_restful import Resource, inputs, marshal_with, reqparse
 from sqlalchemy import and_
@@ -20,8 +21,17 @@ class InstalledAppsListApi(Resource):
     @account_initialization_required
     @marshal_with(installed_app_list_fields)
     def get(self):
+        app_id = request.args.get("app_id", default=None, type=str)
         current_tenant_id = current_user.current_tenant_id
-        installed_apps = db.session.query(InstalledApp).filter(InstalledApp.tenant_id == current_tenant_id).all()
+
+        if app_id:
+            installed_apps = (
+                db.session.query(InstalledApp)
+                .filter(and_(InstalledApp.tenant_id == current_tenant_id, InstalledApp.app_id == app_id))
+                .all()
+            )
+        else:
+            installed_apps = db.session.query(InstalledApp).filter(InstalledApp.tenant_id == current_tenant_id).all()
 
         current_user.role = TenantService.get_user_role(current_user, current_user.current_tenant)
         installed_apps = [
@@ -81,7 +91,7 @@ class InstalledAppsListApi(Resource):
                 tenant_id=current_tenant_id,
                 app_owner_tenant_id=app.tenant_id,
                 is_pinned=False,
-                last_used_at=datetime.now(timezone.utc).replace(tzinfo=None),
+                last_used_at=datetime.now(UTC).replace(tzinfo=None),
             )
             db.session.add(new_installed_app)
             db.session.commit()

api/controllers/console/remote_files.py

@@ -45,7 +45,7 @@ class RemoteFileUploadApi(Resource):
 
         resp = ssrf_proxy.head(url=url)
         if resp.status_code != httpx.codes.OK:
-            resp = ssrf_proxy.get(url=url, timeout=3)
+            resp = ssrf_proxy.get(url=url, timeout=3, follow_redirects=True)
         resp.raise_for_status()
 
         file_info = helpers.guess_file_info_from_response(resp)

api/controllers/console/workspace/account.py

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

api/controllers/console/workspace/members.py

@@ -1,3 +1,5 @@
+from urllib import parse
+
 from flask_login import current_user
 from flask_restful import Resource, abort, marshal_with, reqparse
 
@@ -57,11 +59,12 @@ class MemberInviteEmailApi(Resource):
                 token = RegisterService.invite_new_member(
                     inviter.current_tenant, invitee_email, interface_language, role=invitee_role, inviter=inviter
                 )
+                encoded_invitee_email = parse.quote(invitee_email)
                 invitation_results.append(
                     {
                         "status": "success",
                         "email": invitee_email,
-                        "url": f"{console_web_url}/activate?email={invitee_email}&token={token}",
+                        "url": f"{console_web_url}/activate?email={encoded_invitee_email}&token={token}",
                     }
                 )
             except AccountAlreadyInTenantError:

api/controllers/console/workspace/tool_providers.py

@@ -368,6 +368,7 @@ class ToolWorkflowProviderCreateApi(Resource):
             description=args["description"],
             parameters=args["parameters"],
             privacy_policy=args["privacy_policy"],
+            labels=args["labels"],
         )
 
 

api/controllers/service_api/app/app.py

@@ -48,7 +48,8 @@ class AppInfoApi(Resource):
     @validate_app_token
     def get(self, app_model: App):
         """Get app information"""
-        return {"name": app_model.name, "description": app_model.description}
+        tags = [tag.name for tag in app_model.tags]
+        return {"name": app_model.name, "description": app_model.description, "tags": tags}
 
 
 api.add_resource(AppParameterApi, "/parameters")

api/controllers/service_api/wraps.py

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

api/core/agent/base_agent_runner.py

@@ -2,7 +2,7 @@ import json
 import logging
 import uuid
 from collections.abc import Mapping, Sequence
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from typing import Optional, Union, cast
 
 from core.agent.entities import AgentEntity, AgentToolEntity
@@ -114,16 +114,9 @@ class BaseAgentRunner(AppRunner):
         # check if model supports stream tool call
         llm_model = cast(LargeLanguageModel, model_instance.model_type_instance)
         model_schema = llm_model.get_model_schema(model_instance.model, model_instance.credentials)
-        if model_schema and ModelFeature.STREAM_TOOL_CALL in (model_schema.features or []):
-            self.stream_tool_call = True
-        else:
-            self.stream_tool_call = False
-
-        # check if model supports vision
-        if model_schema and ModelFeature.VISION in (model_schema.features or []):
-            self.files = application_generate_entity.files
-        else:
-            self.files = []
+        features = model_schema.features if model_schema and model_schema.features else []
+        self.stream_tool_call = ModelFeature.STREAM_TOOL_CALL in features
+        self.files = application_generate_entity.files if ModelFeature.VISION in features else []
         self.query = None
         self._current_thoughts: list[PromptMessage] = []
 
@@ -250,7 +243,7 @@ class BaseAgentRunner(AppRunner):
         update prompt message tool
         """
         # try to get tool runtime parameters
-        tool_runtime_parameters = tool.get_runtime_parameters() or []
+        tool_runtime_parameters = tool.get_runtime_parameters()
 
         for parameter in tool_runtime_parameters:
             if parameter.form != ToolParameter.ToolParameterForm.LLM:
@@ -419,7 +412,7 @@ class BaseAgentRunner(AppRunner):
             .first()
         )
 
-        db_variables.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        db_variables.updated_at = datetime.now(UTC).replace(tzinfo=None)
         db_variables.variables_str = json.dumps(jsonable_encoder(tool_variables.pool))
         db.session.commit()
         db.session.close()

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

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

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

@@ -11,7 +11,7 @@ from core.provider_manager import ProviderManager
 
 class ModelConfigConverter:
     @classmethod
-    def convert(cls, app_config: EasyUIBasedAppConfig, skip_check: bool = False) -> ModelConfigWithCredentialsEntity:
+    def convert(cls, app_config: EasyUIBasedAppConfig) -> ModelConfigWithCredentialsEntity:
         """
         Convert app model config dict to entity.
         :param app_config: app config
@@ -38,27 +38,23 @@ class ModelConfigConverter:
         )
 
         if model_credentials is None:
-            if not skip_check:
-                raise ProviderTokenNotInitError(f"Model {model_name} credentials is not initialized.")
-            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/app_config/easy_ui_based_app/model_config/manager.py

@@ -1,3 +1,6 @@
+from collections.abc import Mapping
+from typing import Any
+
 from core.app.app_config.entities import ModelConfigEntity
 from core.model_runtime.entities.model_entities import ModelPropertyKey, ModelType
 from core.model_runtime.model_providers import model_provider_factory
@@ -36,7 +39,7 @@ class ModelConfigManager:
         )
 
     @classmethod
-    def validate_and_set_defaults(cls, tenant_id: str, config: dict) -> tuple[dict, list[str]]:
+    def validate_and_set_defaults(cls, tenant_id: str, config: Mapping[str, Any]) -> tuple[dict, list[str]]:
         """
         Validate and set defaults for model config
 

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

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

api/core/app/app_config/entities.py

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

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

@@ -16,9 +16,7 @@ class FileUploadConfigManager:
         file_upload_dict = config.get("file_upload")
         if file_upload_dict:
             if file_upload_dict.get("enabled"):
-                transform_methods = file_upload_dict.get("allowed_file_upload_methods") or file_upload_dict.get(
-                    "allowed_upload_methods", []
-                )
+                transform_methods = file_upload_dict.get("allowed_file_upload_methods", [])
                 data = {
                     "image_config": {
                         "number_limits": file_upload_dict["number_limits"],

api/core/app/apps/README.md

@@ -2,7 +2,7 @@
 
 Due to the presence of tasks in App Runner that require long execution times, such as LLM generation and external requests, Flask-Sqlalchemy's strategy for database connection pooling is to allocate one connection (transaction) per request. This approach keeps a connection occupied even during non-DB tasks, leading to the inability to acquire new connections during high concurrency requests due to multiple long-running tasks.
 
-Therefore, the database operations in App Runner and Task Pipeline must ensure connections are closed immediately after use, and it's better to pass IDs rather than Model objects to avoid deattach errors.
+Therefore, the database operations in App Runner and Task Pipeline must ensure connections are closed immediately after use, and it's better to pass IDs rather than Model objects to avoid detach errors.
 
 Examples:
 

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

@@ -2,8 +2,8 @@ import contextvars
 import logging
 import threading
 import uuid
-from collections.abc import Generator
-from typing import Any, Literal, Optional, Union, overload
+from collections.abc import Generator, Mapping
+from typing import Any, Optional, Union
 
 from flask import Flask, current_app
 from pydantic import ValidationError
@@ -23,6 +23,7 @@ from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity,
 from core.app.entities.task_entities import ChatbotAppBlockingResponse, ChatbotAppStreamResponse
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.ops.ops_trace_manager import TraceQueueManager
+from core.prompt.utils.get_thread_messages_length import get_thread_messages_length
 from extensions.ext_database import db
 from factories import file_factory
 from models.account import Account
@@ -33,37 +34,17 @@ logger = logging.getLogger(__name__)
 
 
 class AdvancedChatAppGenerator(MessageBasedAppGenerator):
-    @overload
-    def generate(
-        self,
-        app_model: App,
-        workflow: Workflow,
-        user: Union[Account, EndUser],
-        args: dict,
-        invoke_from: InvokeFrom,
-        stream: Literal[True] = True,
-    ) -> Generator[str, None, None]: ...
-
-    @overload
-    def generate(
-        self,
-        app_model: App,
-        workflow: Workflow,
-        user: Union[Account, EndUser],
-        args: dict,
-        invoke_from: InvokeFrom,
-        stream: Literal[False] = False,
-    ) -> dict: ...
+    _dialogue_count: int
 
     def generate(
         self,
         app_model: App,
         workflow: Workflow,
         user: Union[Account, EndUser],
-        args: dict,
+        args: Mapping[str, Any],
         invoke_from: InvokeFrom,
-        stream: bool = True,
-    ) -> dict[str, Any] | Generator[str, Any, None]:
+        streaming: bool = True,
+    ) -> Mapping[str, Any] | Generator[str, None, None]:
         """
         Generate App response.
 
@@ -127,12 +108,14 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             conversation_id=conversation.id if conversation else None,
             inputs=conversation.inputs
             if conversation
-            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            else self._prepare_user_inputs(
+                user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
+            ),
             query=query,
             files=file_objs,
             parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
             user_id=user.id,
-            stream=stream,
+            stream=streaming,
             invoke_from=invoke_from,
             extras=extras,
             trace_manager=trace_manager,
@@ -146,12 +129,12 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             invoke_from=invoke_from,
             application_generate_entity=application_generate_entity,
             conversation=conversation,
-            stream=stream,
+            stream=streaming,
         )
 
     def single_iteration_generate(
-        self, app_model: App, workflow: Workflow, node_id: str, user: Account, args: dict, stream: bool = True
-    ) -> dict[str, Any] | Generator[str, Any, None]:
+        self, app_model: App, workflow: Workflow, node_id: str, user: Account, args: dict, streaming: bool = True
+    ) -> Mapping[str, Any] | Generator[str, None, None]:
         """
         Generate App response.
 
@@ -180,7 +163,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             query="",
             files=[],
             user_id=user.id,
-            stream=stream,
+            stream=streaming,
             invoke_from=InvokeFrom.DEBUGGER,
             extras={"auto_generate_conversation_name": False},
             single_iteration_run=AdvancedChatAppGenerateEntity.SingleIterationRunEntity(
@@ -195,7 +178,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             invoke_from=InvokeFrom.DEBUGGER,
             application_generate_entity=application_generate_entity,
             conversation=None,
-            stream=stream,
+            stream=streaming,
         )
 
     def _generate(
@@ -207,7 +190,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
         application_generate_entity: AdvancedChatAppGenerateEntity,
         conversation: Optional[Conversation] = None,
         stream: bool = True,
-    ) -> dict[str, Any] | Generator[str, Any, None]:
+    ) -> Mapping[str, Any] | Generator[str, None, None]:
         """
         Generate App response.
 
@@ -231,6 +214,9 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             db.session.commit()
             db.session.refresh(conversation)
 
+        # get conversation dialogue count
+        self._dialogue_count = get_thread_messages_length(conversation.id)
+
         # init queue manager
         queue_manager = MessageBasedAppQueueManager(
             task_id=application_generate_entity.task_id,
@@ -301,6 +287,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
                     queue_manager=queue_manager,
                     conversation=conversation,
                     message=message,
+                    dialogue_count=self._dialogue_count,
                 )
 
                 runner.run()
@@ -354,6 +341,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             message=message,
             user=user,
             stream=stream,
+            dialogue_count=self._dialogue_count,
         )
 
         try:

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

@@ -39,12 +39,14 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
         queue_manager: AppQueueManager,
         conversation: Conversation,
         message: Message,
+        dialogue_count: int,
     ) -> None:
         super().__init__(queue_manager)
 
         self.application_generate_entity = application_generate_entity
         self.conversation = conversation
         self.message = message
+        self._dialogue_count = dialogue_count
 
     def run(self) -> None:
         app_config = self.application_generate_entity.app_config
@@ -122,19 +124,13 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
 
                 session.commit()
 
-            # Increment dialogue count.
-            self.conversation.dialogue_count += 1
-
-            conversation_dialogue_count = self.conversation.dialogue_count
-            db.session.commit()
-
             # Create a variable pool.
             system_inputs = {
                 SystemVariableKey.QUERY: query,
                 SystemVariableKey.FILES: files,
                 SystemVariableKey.CONVERSATION_ID: self.conversation.id,
                 SystemVariableKey.USER_ID: user_id,
-                SystemVariableKey.DIALOGUE_COUNT: conversation_dialogue_count,
+                SystemVariableKey.DIALOGUE_COUNT: self._dialogue_count,
                 SystemVariableKey.APP_ID: app_config.app_id,
                 SystemVariableKey.WORKFLOW_ID: app_config.workflow_id,
                 SystemVariableKey.WORKFLOW_RUN_ID: self.application_generate_entity.workflow_run_id,

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

@@ -88,6 +88,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
         message: Message,
         user: Union[Account, EndUser],
         stream: bool,
+        dialogue_count: int,
     ) -> None:
         """
         Initialize AdvancedChatAppGenerateTaskPipeline.
@@ -98,6 +99,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
         :param message: message
         :param user: user
         :param stream: stream
+        :param dialogue_count: dialogue count
         """
         super().__init__(application_generate_entity, queue_manager, user, stream)
 
@@ -114,7 +116,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
             SystemVariableKey.FILES: application_generate_entity.files,
             SystemVariableKey.CONVERSATION_ID: conversation.id,
             SystemVariableKey.USER_ID: user_id,
-            SystemVariableKey.DIALOGUE_COUNT: conversation.dialogue_count,
+            SystemVariableKey.DIALOGUE_COUNT: dialogue_count,
             SystemVariableKey.APP_ID: application_generate_entity.app_config.app_id,
             SystemVariableKey.WORKFLOW_ID: workflow.id,
             SystemVariableKey.WORKFLOW_RUN_ID: application_generate_entity.workflow_run_id,
@@ -125,6 +127,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
 
         self._conversation_name_generate_thread = None
         self._recorded_files: list[Mapping[str, Any]] = []
+        self.total_tokens: int = 0
 
     def process(self):
         """
@@ -358,6 +361,8 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
                 if not workflow_run:
                     raise Exception("Workflow run not initialized.")
 
+                # FIXME for issue #11221 quick fix maybe have a better solution
+                self.total_tokens += event.metadata.get("total_tokens", 0) if event.metadata else 0
                 yield self._workflow_iteration_completed_to_stream_response(
                     task_id=self._application_generate_entity.task_id, workflow_run=workflow_run, event=event
                 )
@@ -371,7 +376,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
                 workflow_run = self._handle_workflow_run_success(
                     workflow_run=workflow_run,
                     start_at=graph_runtime_state.start_at,
-                    total_tokens=graph_runtime_state.total_tokens,
+                    total_tokens=graph_runtime_state.total_tokens or self.total_tokens,
                     total_steps=graph_runtime_state.node_run_steps,
                     outputs=event.outputs,
                     conversation_id=self._conversation.id,

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

@@ -1,5 +1,6 @@
 import uuid
-from typing import Optional
+from collections.abc import Mapping
+from typing import Any, Optional
 
 from core.agent.entities import AgentEntity
 from core.app.app_config.base_app_config_manager import BaseAppConfigManager
@@ -85,7 +86,7 @@ class AgentChatAppConfigManager(BaseAppConfigManager):
         return app_config
 
     @classmethod
-    def config_validate(cls, tenant_id: str, config: dict) -> dict:
+    def config_validate(cls, tenant_id: str, config: Mapping[str, Any]) -> dict:
         """
         Validate for agent chat app model config
 

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

@@ -1,8 +1,8 @@
 import logging
 import threading
 import uuid
-from collections.abc import Generator
-from typing import Any, Literal, Union, overload
+from collections.abc import Generator, Mapping
+from typing import Any, Union
 
 from flask import Flask, current_app
 from pydantic import ValidationError
@@ -28,34 +28,15 @@ logger = logging.getLogger(__name__)
 
 
 class AgentChatAppGenerator(MessageBasedAppGenerator):
-    @overload
     def generate(
         self,
+        *,
         app_model: App,
         user: Union[Account, EndUser],
-        args: dict,
+        args: Mapping[str, Any],
         invoke_from: InvokeFrom,
-        stream: Literal[True] = True,
-    ) -> Generator[dict, None, None]: ...
-
-    @overload
-    def generate(
-        self,
-        app_model: App,
-        user: Union[Account, EndUser],
-        args: dict,
-        invoke_from: InvokeFrom,
-        stream: Literal[False] = False,
-    ) -> dict: ...
-
-    def generate(
-        self,
-        app_model: App,
-        user: Union[Account, EndUser],
-        args: Any,
-        invoke_from: InvokeFrom,
-        stream: bool = True,
-    ) -> Union[dict, Generator[dict, None, None]]:
+        streaming: bool = True,
+    ) -> Mapping[str, Any] | Generator[str, None, None]:
         """
         Generate App response.
 
@@ -65,7 +46,7 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
         :param invoke_from: invoke from source
         :param stream: is stream
         """
-        if not stream:
+        if not streaming:
             raise ValueError("Agent Chat App does not support blocking mode")
 
         if not args.get("query"):
@@ -96,7 +77,8 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
 
             # validate config
             override_model_config_dict = AgentChatAppConfigManager.config_validate(
-                tenant_id=app_model.tenant_id, config=args.get("model_config")
+                tenant_id=app_model.tenant_id,
+                config=args["model_config"],
             )
 
             # always enable retriever resource in debugger mode
@@ -134,12 +116,14 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
             conversation_id=conversation.id if conversation else None,
             inputs=conversation.inputs
             if conversation
-            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            else self._prepare_user_inputs(
+                user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
+            ),
             query=query,
             files=file_objs,
             parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
             user_id=user.id,
-            stream=stream,
+            stream=streaming,
             invoke_from=invoke_from,
             extras=extras,
             call_depth=0,
@@ -180,7 +164,7 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
             conversation=conversation,
             message=message,
             user=user,
-            stream=stream,
+            stream=streaming,
         )
 
         return AgentChatAppGenerateResponseConverter.convert(response=response, invoke_from=invoke_from)

api/core/app/apps/base_app_generate_response_converter.py

@@ -1,6 +1,6 @@
 import logging
 from abc import ABC, abstractmethod
-from collections.abc import Generator
+from collections.abc import Generator, Mapping
 from typing import Any, Union
 
 from core.app.entities.app_invoke_entities import InvokeFrom
@@ -14,8 +14,10 @@ class AppGenerateResponseConverter(ABC):
 
     @classmethod
     def convert(
-        cls, response: Union[AppBlockingResponse, Generator[AppStreamResponse, Any, None]], invoke_from: InvokeFrom
-    ) -> dict[str, Any] | Generator[str, Any, None]:
+        cls,
+        response: Union[AppBlockingResponse, Generator[AppStreamResponse, Any, None]],
+        invoke_from: InvokeFrom,
+    ) -> Mapping[str, Any] | Generator[str, None, None]:
         if invoke_from in {InvokeFrom.DEBUGGER, InvokeFrom.SERVICE_API}:
             if isinstance(response, AppBlockingResponse):
                 return cls.convert_blocking_full_response(response)
@@ -80,7 +82,7 @@ class AppGenerateResponseConverter(ABC):
             for resource in metadata["retriever_resources"]:
                 updated_resources.append(
                     {
-                        "segment_id": resource["segment_id"],
+                        "segment_id": resource.get("segment_id", ""),
                         "position": resource["position"],
                         "document_name": resource["document_name"],
                         "score": resource["score"],

api/core/app/apps/base_app_generator.py

@@ -1,4 +1,4 @@
-from collections.abc import Mapping
+from collections.abc import Mapping, Sequence
 from typing import TYPE_CHECKING, Any, Optional
 
 from core.app.app_config.entities import VariableEntityType
@@ -6,7 +6,7 @@ from core.file import File, FileUploadConfig
 from factories import file_factory
 
 if TYPE_CHECKING:
-    from core.app.app_config.entities import AppConfig, VariableEntity
+    from core.app.app_config.entities import VariableEntity
 
 
 class BaseAppGenerator:
@@ -14,27 +14,27 @@ class BaseAppGenerator:
         self,
         *,
         user_inputs: Optional[Mapping[str, Any]],
-        app_config: "AppConfig",
+        variables: Sequence["VariableEntity"],
+        tenant_id: str,
     ) -> Mapping[str, Any]:
         user_inputs = user_inputs or {}
         # Filter input variables from form configuration, handle required fields, default values, and option values
-        variables = app_config.variables
         user_inputs = {
             var.variable: self._validate_inputs(value=user_inputs.get(var.variable), variable_entity=var)
             for var in variables
         }
         user_inputs = {k: self._sanitize_value(v) for k, v in user_inputs.items()}
         # Convert files in inputs to File
-        entity_dictionary = {item.variable: item for item in app_config.variables}
+        entity_dictionary = {item.variable: item for item in variables}
         # Convert single file to File
         files_inputs = {
             k: file_factory.build_from_mapping(
                 mapping=v,
-                tenant_id=app_config.tenant_id,
+                tenant_id=tenant_id,
                 config=FileUploadConfig(
                     allowed_file_types=entity_dictionary[k].allowed_file_types,
-                    allowed_extensions=entity_dictionary[k].allowed_file_extensions,
-                    allowed_upload_methods=entity_dictionary[k].allowed_file_upload_methods,
+                    allowed_file_extensions=entity_dictionary[k].allowed_file_extensions,
+                    allowed_file_upload_methods=entity_dictionary[k].allowed_file_upload_methods,
                 ),
             )
             for k, v in user_inputs.items()
@@ -44,11 +44,11 @@ class BaseAppGenerator:
         file_list_inputs = {
             k: file_factory.build_from_mappings(
                 mappings=v,
-                tenant_id=app_config.tenant_id,
+                tenant_id=tenant_id,
                 config=FileUploadConfig(
                     allowed_file_types=entity_dictionary[k].allowed_file_types,
-                    allowed_extensions=entity_dictionary[k].allowed_file_extensions,
-                    allowed_upload_methods=entity_dictionary[k].allowed_file_upload_methods,
+                    allowed_file_extensions=entity_dictionary[k].allowed_file_extensions,
+                    allowed_file_upload_methods=entity_dictionary[k].allowed_file_upload_methods,
                 ),
             )
             for k, v in user_inputs.items()

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

@@ -55,7 +55,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
         user: Union[Account, EndUser],
         args: Any,
         invoke_from: InvokeFrom,
-        stream: bool = True,
+        streaming: bool = True,
     ) -> Union[dict, Generator[str, None, None]]:
         """
         Generate App response.
@@ -132,7 +132,9 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             conversation_id=conversation.id if conversation else None,
             inputs=conversation.inputs
             if conversation
-            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            else self._prepare_user_inputs(
+                user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
+            ),
             query=query,
             files=file_objs,
             parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
@@ -140,7 +142,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             invoke_from=invoke_from,
             extras=extras,
             trace_manager=trace_manager,
-            stream=stream,
+            stream=streaming,
         )
 
         # init generate records
@@ -177,7 +179,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             conversation=conversation,
             message=message,
             user=user,
-            stream=stream,
+            stream=streaming,
         )
 
         return ChatAppGenerateResponseConverter.convert(response=response, invoke_from=invoke_from)

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

@@ -50,7 +50,7 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
     ) -> dict: ...
 
     def generate(
-        self, app_model: App, user: Union[Account, EndUser], args: Any, invoke_from: InvokeFrom, stream: bool = True
+        self, app_model: App, user: Union[Account, EndUser], args: Any, invoke_from: InvokeFrom, streaming: bool = True
     ) -> Union[dict, Generator[str, None, None]]:
         """
         Generate App response.
@@ -113,11 +113,13 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
             app_config=app_config,
             model_conf=ModelConfigConverter.convert(app_config),
             file_upload_config=file_extra_config,
-            inputs=self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            inputs=self._prepare_user_inputs(
+                user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
+            ),
             query=query,
             files=file_objs,
             user_id=user.id,
-            stream=stream,
+            stream=streaming,
             invoke_from=invoke_from,
             extras=extras,
             trace_manager=trace_manager,
@@ -156,7 +158,7 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
             conversation=conversation,
             message=message,
             user=user,
-            stream=stream,
+            stream=streaming,
         )
 
         return CompletionAppGenerateResponseConverter.convert(response=response, invoke_from=invoke_from)

api/core/app/apps/message_based_app_generator.py

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

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

@@ -3,7 +3,7 @@ import logging
 import threading
 import uuid
 from collections.abc import Generator, Mapping, Sequence
-from typing import Any, Literal, Optional, Union, overload
+from typing import Any, Optional, Union
 
 from flask import Flask, current_app
 from pydantic import ValidationError
@@ -30,43 +30,18 @@ logger = logging.getLogger(__name__)
 
 
 class WorkflowAppGenerator(BaseAppGenerator):
-    @overload
     def generate(
         self,
+        *,
         app_model: App,
         workflow: Workflow,
-        user: Union[Account, EndUser],
-        args: dict,
-        invoke_from: InvokeFrom,
-        stream: Literal[True] = True,
-        call_depth: int = 0,
-        workflow_thread_pool_id: Optional[str] = None,
-    ) -> Generator[str, None, None]: ...
-
-    @overload
-    def generate(
-        self,
-        app_model: App,
-        workflow: Workflow,
-        user: Union[Account, EndUser],
-        args: dict,
-        invoke_from: InvokeFrom,
-        stream: Literal[False] = False,
-        call_depth: int = 0,
-        workflow_thread_pool_id: Optional[str] = None,
-    ) -> dict: ...
-
-    def generate(
-        self,
-        app_model: App,
-        workflow: Workflow,
-        user: Union[Account, EndUser],
+        user: Account | EndUser,
         args: Mapping[str, Any],
         invoke_from: InvokeFrom,
-        stream: bool = True,
+        streaming: bool = True,
         call_depth: int = 0,
         workflow_thread_pool_id: Optional[str] = None,
-    ):
+    ) -> Mapping[str, Any] | Generator[str, None, None]:
         files: Sequence[Mapping[str, Any]] = args.get("files") or []
 
         # parse files
@@ -96,10 +71,12 @@ class WorkflowAppGenerator(BaseAppGenerator):
             task_id=str(uuid.uuid4()),
             app_config=app_config,
             file_upload_config=file_extra_config,
-            inputs=self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            inputs=self._prepare_user_inputs(
+                user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
+            ),
             files=system_files,
             user_id=user.id,
-            stream=stream,
+            stream=streaming,
             invoke_from=invoke_from,
             call_depth=call_depth,
             trace_manager=trace_manager,
@@ -113,7 +90,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
             user=user,
             application_generate_entity=application_generate_entity,
             invoke_from=invoke_from,
-            stream=stream,
+            streaming=streaming,
             workflow_thread_pool_id=workflow_thread_pool_id,
         )
 
@@ -125,20 +102,9 @@ class WorkflowAppGenerator(BaseAppGenerator):
         user: Union[Account, EndUser],
         application_generate_entity: WorkflowAppGenerateEntity,
         invoke_from: InvokeFrom,
-        stream: bool = True,
+        streaming: bool = True,
         workflow_thread_pool_id: Optional[str] = None,
-    ) -> dict[str, Any] | Generator[str, None, None]:
-        """
-        Generate App response.
-
-        :param app_model: App
-        :param workflow: Workflow
-        :param user: account or end user
-        :param application_generate_entity: application generate entity
-        :param invoke_from: invoke from source
-        :param stream: is stream
-        :param workflow_thread_pool_id: workflow thread pool id
-        """
+    ) -> Mapping[str, Any] | Generator[str, None, None]:
         # init queue manager
         queue_manager = WorkflowAppQueueManager(
             task_id=application_generate_entity.task_id,
@@ -167,14 +133,20 @@ class WorkflowAppGenerator(BaseAppGenerator):
             workflow=workflow,
             queue_manager=queue_manager,
             user=user,
-            stream=stream,
+            stream=streaming,
         )
 
         return WorkflowAppGenerateResponseConverter.convert(response=response, invoke_from=invoke_from)
 
     def single_iteration_generate(
-        self, app_model: App, workflow: Workflow, node_id: str, user: Account, args: dict, stream: bool = True
-    ) -> dict[str, Any] | Generator[str, Any, None]:
+        self,
+        app_model: App,
+        workflow: Workflow,
+        node_id: str,
+        user: Account,
+        args: Mapping[str, Any],
+        streaming: bool = True,
+    ) -> Mapping[str, Any] | Generator[str, None, None]:
         """
         Generate App response.
 
@@ -201,7 +173,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
             inputs={},
             files=[],
             user_id=user.id,
-            stream=stream,
+            stream=streaming,
             invoke_from=InvokeFrom.DEBUGGER,
             extras={"auto_generate_conversation_name": False},
             single_iteration_run=WorkflowAppGenerateEntity.SingleIterationRunEntity(
@@ -216,7 +188,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
             user=user,
             invoke_from=InvokeFrom.DEBUGGER,
             application_generate_entity=application_generate_entity,
-            stream=stream,
+            streaming=streaming,
         )
 
     def _generate_worker(

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

@@ -106,6 +106,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
 
         self._task_state = WorkflowTaskState()
         self._wip_workflow_node_executions = {}
+        self.total_tokens: int = 0
 
     def process(self) -> Union[WorkflowAppBlockingResponse, Generator[WorkflowAppStreamResponse, None, None]]:
         """
@@ -319,6 +320,8 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
                 if not workflow_run:
                     raise Exception("Workflow run not initialized.")
 
+                # FIXME for issue #11221 quick fix maybe have a better solution
+                self.total_tokens += event.metadata.get("total_tokens", 0) if event.metadata else 0
                 yield self._workflow_iteration_completed_to_stream_response(
                     task_id=self._application_generate_entity.task_id, workflow_run=workflow_run, event=event
                 )
@@ -332,7 +335,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
                 workflow_run = self._handle_workflow_run_success(
                     workflow_run=workflow_run,
                     start_at=graph_runtime_state.start_at,
-                    total_tokens=graph_runtime_state.total_tokens,
+                    total_tokens=graph_runtime_state.total_tokens or self.total_tokens,
                     total_steps=graph_runtime_state.node_run_steps,
                     outputs=event.outputs,
                     conversation_id=None,

api/core/app/apps/workflow_app_runner.py

@@ -43,8 +43,7 @@ from core.workflow.graph_engine.entities.event import (
 )
 from core.workflow.graph_engine.entities.graph import Graph
 from core.workflow.nodes import NodeType
-from core.workflow.nodes.iteration import IterationNodeData
-from core.workflow.nodes.node_mapping import node_type_classes_mapping
+from core.workflow.nodes.node_mapping import NODE_TYPE_CLASSES_MAPPING
 from core.workflow.workflow_entry import WorkflowEntry
 from extensions.ext_database import db
 from models.model import App
@@ -139,7 +138,8 @@ class WorkflowBasedAppRunner(AppRunner):
 
         # Get node class
         node_type = NodeType(iteration_node_config.get("data", {}).get("type"))
-        node_cls = node_type_classes_mapping[node_type]
+        node_version = iteration_node_config.get("data", {}).get("version", "1")
+        node_cls = NODE_TYPE_CLASSES_MAPPING[node_type][node_version]
 
         # init variable pool
         variable_pool = VariablePool(
@@ -160,8 +160,6 @@ class WorkflowBasedAppRunner(AppRunner):
             user_inputs=user_inputs,
             variable_pool=variable_pool,
             tenant_id=workflow.tenant_id,
-            node_type=node_type,
-            node_data=IterationNodeData(**iteration_node_config.get("data", {})),
         )
 
         return graph, variable_pool

api/core/app/entities/queue_entities.py

@@ -1,8 +1,8 @@
 from datetime import datetime
-from enum import Enum
+from enum import Enum, StrEnum
 from typing import Any, Optional
 
-from pydantic import BaseModel, field_validator
+from pydantic import BaseModel
 
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk
 from core.workflow.entities.node_entities import NodeRunMetadataKey
@@ -11,7 +11,7 @@ from core.workflow.nodes import NodeType
 from core.workflow.nodes.base import BaseNodeData
 
 
-class QueueEvent(str, Enum):
+class QueueEvent(StrEnum):
     """
     QueueEvent enum
     """
@@ -113,18 +113,6 @@ class QueueIterationNextEvent(AppQueueEvent):
     output: Optional[Any] = None  # output for the current iteration
     duration: Optional[float] = None
 
-    @field_validator("output", mode="before")
-    @classmethod
-    def set_output(cls, v):
-        """
-        Set output
-        """
-        if v is None:
-            return None
-        if isinstance(v, int | float | str | bool | dict | list):
-            return v
-        raise ValueError("output must be a valid type")
-
 
 class QueueIterationCompletedEvent(AppQueueEvent):
     """

api/core/app/features/rate_limiting/rate_limit.py

@@ -1,9 +1,9 @@
 import logging
 import time
 import uuid
-from collections.abc import Generator
+from collections.abc import Generator, Mapping
 from datetime import timedelta
-from typing import Optional, Union
+from typing import Any, Optional, Union
 
 from core.errors.error import AppInvokeQuotaExceededError
 from extensions.ext_redis import redis_client
@@ -88,20 +88,17 @@ class RateLimit:
     def gen_request_key() -> str:
         return str(uuid.uuid4())
 
-    def generate(self, generator: Union[Generator, callable, dict], request_id: str):
-        if isinstance(generator, dict):
+    def generate(self, generator: Union[Generator[str, None, None], Mapping[str, Any]], request_id: str):
+        if isinstance(generator, Mapping):
             return generator
         else:
-            return RateLimitGenerator(self, generator, request_id)
+            return RateLimitGenerator(rate_limit=self, generator=generator, request_id=request_id)
 
 
 class RateLimitGenerator:
-    def __init__(self, rate_limit: RateLimit, generator: Union[Generator, callable], request_id: str):
+    def __init__(self, rate_limit: RateLimit, generator: Generator[str, None, None], request_id: str):
         self.rate_limit = rate_limit
-        if callable(generator):
-            self.generator = generator()
-        else:
-            self.generator = generator
+        self.generator = generator
         self.request_id = request_id
         self.closed = False
 

api/core/app/task_pipeline/workflow_cycle_manage.py

@@ -1,8 +1,9 @@
 import json
 import time
 from collections.abc import Mapping, Sequence
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from typing import Any, Optional, Union, cast
+from uuid import uuid4
 
 from sqlalchemy.orm import Session
 
@@ -80,38 +81,38 @@ class WorkflowCycleManage:
 
             inputs[f"sys.{key.value}"] = value
 
-        inputs = WorkflowEntry.handle_special_values(inputs)
-
         triggered_from = (
             WorkflowRunTriggeredFrom.DEBUGGING
             if self._application_generate_entity.invoke_from == InvokeFrom.DEBUGGER
             else WorkflowRunTriggeredFrom.APP_RUN
         )
 
-        # init workflow run
-        workflow_run = WorkflowRun()
-        workflow_run_id = self._workflow_system_variables[SystemVariableKey.WORKFLOW_RUN_ID]
-        if workflow_run_id:
-            workflow_run.id = workflow_run_id
-        workflow_run.tenant_id = self._workflow.tenant_id
-        workflow_run.app_id = self._workflow.app_id
-        workflow_run.sequence_number = new_sequence_number
-        workflow_run.workflow_id = self._workflow.id
-        workflow_run.type = self._workflow.type
-        workflow_run.triggered_from = triggered_from.value
-        workflow_run.version = self._workflow.version
-        workflow_run.graph = self._workflow.graph
-        workflow_run.inputs = json.dumps(inputs)
-        workflow_run.status = WorkflowRunStatus.RUNNING.value
-        workflow_run.created_by_role = (
-            CreatedByRole.ACCOUNT.value if isinstance(self._user, Account) else CreatedByRole.END_USER.value
-        )
-        workflow_run.created_by = self._user.id
+        # handle special values
+        inputs = WorkflowEntry.handle_special_values(inputs)
 
-        db.session.add(workflow_run)
-        db.session.commit()
-        db.session.refresh(workflow_run)
-        db.session.close()
+        # init workflow run
+        with Session(db.engine, expire_on_commit=False) as session:
+            workflow_run = WorkflowRun()
+            system_id = self._workflow_system_variables[SystemVariableKey.WORKFLOW_RUN_ID]
+            workflow_run.id = system_id or str(uuid4())
+            workflow_run.tenant_id = self._workflow.tenant_id
+            workflow_run.app_id = self._workflow.app_id
+            workflow_run.sequence_number = new_sequence_number
+            workflow_run.workflow_id = self._workflow.id
+            workflow_run.type = self._workflow.type
+            workflow_run.triggered_from = triggered_from.value
+            workflow_run.version = self._workflow.version
+            workflow_run.graph = self._workflow.graph
+            workflow_run.inputs = json.dumps(inputs)
+            workflow_run.status = WorkflowRunStatus.RUNNING
+            workflow_run.created_by_role = (
+                CreatedByRole.ACCOUNT if isinstance(self._user, Account) else CreatedByRole.END_USER
+            )
+            workflow_run.created_by = self._user.id
+            workflow_run.created_at = datetime.now(UTC).replace(tzinfo=None)
+
+            session.add(workflow_run)
+            session.commit()
 
         return workflow_run
 
@@ -144,7 +145,7 @@ class WorkflowCycleManage:
         workflow_run.elapsed_time = time.perf_counter() - start_at
         workflow_run.total_tokens = total_tokens
         workflow_run.total_steps = total_steps
-        workflow_run.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        workflow_run.finished_at = datetime.now(UTC).replace(tzinfo=None)
 
         db.session.commit()
         db.session.refresh(workflow_run)
@@ -191,7 +192,7 @@ class WorkflowCycleManage:
         workflow_run.elapsed_time = time.perf_counter() - start_at
         workflow_run.total_tokens = total_tokens
         workflow_run.total_steps = total_steps
-        workflow_run.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        workflow_run.finished_at = datetime.now(UTC).replace(tzinfo=None)
 
         db.session.commit()
 
@@ -211,15 +212,18 @@ class WorkflowCycleManage:
         for workflow_node_execution in running_workflow_node_executions:
             workflow_node_execution.status = WorkflowNodeExecutionStatus.FAILED.value
             workflow_node_execution.error = error
-            workflow_node_execution.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            workflow_node_execution.finished_at = datetime.now(UTC).replace(tzinfo=None)
             workflow_node_execution.elapsed_time = (
                 workflow_node_execution.finished_at - workflow_node_execution.created_at
             ).total_seconds()
             db.session.commit()
 
-        db.session.refresh(workflow_run)
         db.session.close()
 
+        with Session(db.engine, expire_on_commit=False) as session:
+            session.add(workflow_run)
+            session.refresh(workflow_run)
+
         if trace_manager:
             trace_manager.add_trace_task(
                 TraceTask(
@@ -259,7 +263,7 @@ class WorkflowCycleManage:
                     NodeRunMetadataKey.ITERATION_ID: event.in_iteration_id,
                 }
             )
-            workflow_node_execution.created_at = datetime.now(timezone.utc).replace(tzinfo=None)
+            workflow_node_execution.created_at = datetime.now(UTC).replace(tzinfo=None)
 
             session.add(workflow_node_execution)
             session.commit()
@@ -282,7 +286,7 @@ class WorkflowCycleManage:
         execution_metadata = (
             json.dumps(jsonable_encoder(event.execution_metadata)) if event.execution_metadata else None
         )
-        finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        finished_at = datetime.now(UTC).replace(tzinfo=None)
         elapsed_time = (finished_at - event.start_at).total_seconds()
 
         db.session.query(WorkflowNodeExecution).filter(WorkflowNodeExecution.id == workflow_node_execution.id).update(
@@ -326,7 +330,7 @@ class WorkflowCycleManage:
         inputs = WorkflowEntry.handle_special_values(event.inputs)
         process_data = WorkflowEntry.handle_special_values(event.process_data)
         outputs = WorkflowEntry.handle_special_values(event.outputs)
-        finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        finished_at = datetime.now(UTC).replace(tzinfo=None)
         elapsed_time = (finished_at - event.start_at).total_seconds()
         execution_metadata = (
             json.dumps(jsonable_encoder(event.execution_metadata)) if event.execution_metadata else None
@@ -336,7 +340,7 @@ class WorkflowCycleManage:
                 WorkflowNodeExecution.status: WorkflowNodeExecutionStatus.FAILED.value,
                 WorkflowNodeExecution.error: event.error,
                 WorkflowNodeExecution.inputs: json.dumps(inputs) if inputs else None,
-                WorkflowNodeExecution.process_data: json.dumps(event.process_data) if event.process_data else None,
+                WorkflowNodeExecution.process_data: json.dumps(process_data) if process_data else None,
                 WorkflowNodeExecution.outputs: json.dumps(outputs) if outputs else None,
                 WorkflowNodeExecution.finished_at: finished_at,
                 WorkflowNodeExecution.elapsed_time: elapsed_time,
@@ -381,7 +385,7 @@ class WorkflowCycleManage:
                 id=workflow_run.id,
                 workflow_id=workflow_run.workflow_id,
                 sequence_number=workflow_run.sequence_number,
-                inputs=workflow_run.inputs_dict or {},
+                inputs=workflow_run.inputs_dict,
                 created_at=int(workflow_run.created_at.timestamp()),
             ),
         )
@@ -428,7 +432,7 @@ class WorkflowCycleManage:
                 created_by=created_by,
                 created_at=int(workflow_run.created_at.timestamp()),
                 finished_at=int(workflow_run.finished_at.timestamp()),
-                files=self._fetch_files_from_node_outputs(workflow_run.outputs_dict or {}),
+                files=self._fetch_files_from_node_outputs(workflow_run.outputs_dict),
             ),
         )
 
@@ -654,7 +658,7 @@ class WorkflowCycleManage:
                 if event.error is None
                 else WorkflowNodeExecutionStatus.FAILED,
                 error=None,
-                elapsed_time=(datetime.now(timezone.utc).replace(tzinfo=None) - event.start_at).total_seconds(),
+                elapsed_time=(datetime.now(UTC).replace(tzinfo=None) - event.start_at).total_seconds(),
                 total_tokens=event.metadata.get("total_tokens", 0) if event.metadata else 0,
                 execution_metadata=event.metadata,
                 finished_at=int(time.time()),

api/core/entities/provider_configuration.py

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

api/core/file/__init__.py

@@ -7,13 +7,13 @@ from .models import (
 )
 
 __all__ = [
+    "FILE_MODEL_IDENTITY",
+    "ArrayFileAttribute",
+    "File",
+    "FileAttribute",
+    "FileBelongsTo",
+    "FileTransferMethod",
     "FileType",
     "FileUploadConfig",
-    "FileTransferMethod",
-    "FileBelongsTo",
-    "File",
     "ImageConfig",
-    "FileAttribute",
-    "ArrayFileAttribute",
-    "FILE_MODEL_IDENTITY",
 ]

api/core/file/enums.py

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

api/core/file/file_manager.py

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

api/core/file/models.py

@@ -28,8 +28,8 @@ class FileUploadConfig(BaseModel):
 
     image_config: Optional[ImageConfig] = None
     allowed_file_types: Sequence[FileType] = Field(default_factory=list)
-    allowed_extensions: Sequence[str] = Field(default_factory=list)
-    allowed_upload_methods: Sequence[FileTransferMethod] = Field(default_factory=list)
+    allowed_file_extensions: Sequence[str] = Field(default_factory=list)
+    allowed_file_upload_methods: Sequence[FileTransferMethod] = Field(default_factory=list)
     number_limits: int = 0
 
 

api/core/helper/code_executor/code_executor.py

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

api/core/helper/ssrf_proxy.py

@@ -39,6 +39,7 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
         )
 
     retries = 0
+    stream = kwargs.pop("stream", False)
     while retries <= max_retries:
         try:
             if dify_config.SSRF_PROXY_ALL_URL:

api/core/indexing_runner.py

@@ -29,6 +29,8 @@ from core.rag.splitter.fixed_text_splitter import (
     FixedRecursiveCharacterTextSplitter,
 )
 from core.rag.splitter.text_splitter import TextSplitter
+from core.tools.utils.text_processing_utils import remove_leading_symbols
+from core.tools.utils.web_reader_tool import get_image_upload_file_ids
 from extensions.ext_database import db
 from extensions.ext_redis import redis_client
 from extensions.ext_storage import storage
@@ -84,7 +86,7 @@ class IndexingRunner:
             except ProviderTokenNotInitError as e:
                 dataset_document.indexing_status = "error"
                 dataset_document.error = str(e.description)
-                dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+                dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
                 db.session.commit()
             except ObjectDeletedError:
                 logging.warning("Document deleted, document id: {}".format(dataset_document.id))
@@ -92,7 +94,7 @@ class IndexingRunner:
                 logging.exception("consume document failed")
                 dataset_document.indexing_status = "error"
                 dataset_document.error = str(e)
-                dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+                dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
                 db.session.commit()
 
     def run_in_splitting_status(self, dataset_document: DatasetDocument):
@@ -140,13 +142,13 @@ class IndexingRunner:
         except ProviderTokenNotInitError as e:
             dataset_document.indexing_status = "error"
             dataset_document.error = str(e.description)
-            dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         except Exception as e:
             logging.exception("consume document failed")
             dataset_document.indexing_status = "error"
             dataset_document.error = str(e)
-            dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
 
     def run_in_indexing_status(self, dataset_document: DatasetDocument):
@@ -198,13 +200,13 @@ class IndexingRunner:
         except ProviderTokenNotInitError as e:
             dataset_document.indexing_status = "error"
             dataset_document.error = str(e.description)
-            dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
         except Exception as e:
             logging.exception("consume document failed")
             dataset_document.indexing_status = "error"
             dataset_document.error = str(e)
-            dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+            dataset_document.stopped_at = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
             db.session.commit()
 
     def indexing_estimate(
@@ -278,6 +280,19 @@ class IndexingRunner:
                 if len(preview_texts) < 5:
                     preview_texts.append(document.page_content)
 
+                # delete image files and related db records
+                image_upload_file_ids = get_image_upload_file_ids(document.page_content)
+                for upload_file_id in image_upload_file_ids:
+                    image_file = db.session.query(UploadFile).filter(UploadFile.id == upload_file_id).first()
+                    try:
+                        storage.delete(image_file.key)
+                    except Exception:
+                        logging.exception(
+                            "Delete image_files failed while indexing_estimate, \
+                                          image_upload_file_is: {}".format(upload_file_id)
+                        )
+                    db.session.delete(image_file)
+
         if doc_form and doc_form == "qa_model":
             if len(preview_texts) > 0:
                 # qa model document
@@ -357,7 +372,7 @@ class IndexingRunner:
             after_indexing_status="splitting",
             extra_update_params={
                 DatasetDocument.word_count: sum(len(text_doc.page_content) for text_doc in text_docs),
-                DatasetDocument.parsing_completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                DatasetDocument.parsing_completed_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
             },
         )
 
@@ -449,7 +464,7 @@ class IndexingRunner:
         doc_store.add_documents(documents)
 
         # update document status to indexing
-        cur_time = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+        cur_time = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
         self._update_document_index_status(
             document_id=dataset_document.id,
             after_indexing_status="indexing",
@@ -464,7 +479,7 @@ class IndexingRunner:
             dataset_document_id=dataset_document.id,
             update_params={
                 DocumentSegment.status: "indexing",
-                DocumentSegment.indexing_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                DocumentSegment.indexing_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
             },
         )
 
@@ -500,11 +515,7 @@ class IndexingRunner:
                     document_node.metadata["doc_hash"] = hash
                     # delete Splitter character
                     page_content = document_node.page_content
-                    if page_content.startswith(".") or page_content.startswith("。"):
-                        page_content = page_content[1:]
-                    else:
-                        page_content = page_content
-                    document_node.page_content = page_content
+                    document_node.page_content = remove_leading_symbols(page_content)
 
                     if document_node.page_content:
                         split_documents.append(document_node)
@@ -669,7 +680,7 @@ class IndexingRunner:
             after_indexing_status="completed",
             extra_update_params={
                 DatasetDocument.tokens: tokens,
-                DatasetDocument.completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                DatasetDocument.completed_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
                 DatasetDocument.indexing_latency: indexing_end_at - indexing_start_at,
                 DatasetDocument.error: None,
             },
@@ -694,7 +705,7 @@ class IndexingRunner:
                     {
                         DocumentSegment.status: "completed",
                         DocumentSegment.enabled: True,
-                        DocumentSegment.completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                        DocumentSegment.completed_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
                     }
                 )
 
@@ -727,7 +738,7 @@ class IndexingRunner:
                 {
                     DocumentSegment.status: "completed",
                     DocumentSegment.enabled: True,
-                    DocumentSegment.completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                    DocumentSegment.completed_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
                 }
             )
 
@@ -838,7 +849,7 @@ class IndexingRunner:
         doc_store.add_documents(documents)
 
         # update document status to indexing
-        cur_time = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+        cur_time = datetime.datetime.now(datetime.UTC).replace(tzinfo=None)
         self._update_document_index_status(
             document_id=dataset_document.id,
             after_indexing_status="indexing",
@@ -853,7 +864,7 @@ class IndexingRunner:
             dataset_document_id=dataset_document.id,
             update_params={
                 DocumentSegment.status: "indexing",
-                DocumentSegment.indexing_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+                DocumentSegment.indexing_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
             },
         )
         pass

api/core/llm_generator/output_parser/suggested_questions_after_answer.py

@@ -15,6 +15,5 @@ class SuggestedQuestionsAfterAnswerOutputParser:
             json_obj = json.loads(action_match.group(0).strip())
         else:
             json_obj = []
-            print(f"Could not parse LLM output: {text}")
 
         return json_obj

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/docs/zh_Hans/interfaces.md

@@ -91,7 +91,7 @@ class XinferenceProvider(Provider):
       """
   ```
 
-  也可以直接抛出对应Erros，并做如下定义，这样在之后的调用中可以直接抛出`InvokeConnectionError`等异常。
+  也可以直接抛出对应 Errors，并做如下定义，这样在之后的调用中可以直接抛出`InvokeConnectionError`等异常。
   
     ```python
     @property

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,
@@ -17,24 +18,25 @@ from .message_entities import (
 from .model_entities import ModelPropertyKey
 
 __all__ = [
-    "ImagePromptMessageContent",
-    "VideoPromptMessageContent",
-    "PromptMessage",
-    "PromptMessageRole",
-    "LLMUsage",
-    "ModelPropertyKey",
     "AssistantPromptMessage",
-    "PromptMessage",
-    "PromptMessageContent",
-    "PromptMessageRole",
-    "SystemPromptMessage",
-    "TextPromptMessageContent",
-    "UserPromptMessage",
-    "PromptMessageTool",
-    "ToolPromptMessage",
-    "PromptMessageContentType",
+    "AudioPromptMessageContent",
+    "DocumentPromptMessageContent",
+    "ImagePromptMessageContent",
     "LLMResult",
     "LLMResultChunk",
     "LLMResultChunkDelta",
-    "AudioPromptMessageContent",
+    "LLMUsage",
+    "ModelPropertyKey",
+    "PromptMessage",
+    "PromptMessage",
+    "PromptMessageContent",
+    "PromptMessageContentType",
+    "PromptMessageRole",
+    "PromptMessageRole",
+    "PromptMessageTool",
+    "SystemPromptMessage",
+    "TextPromptMessageContent",
+    "ToolPromptMessage",
+    "UserPromptMessage",
+    "VideoPromptMessageContent",
 ]

api/core/model_runtime/entities/message_entities.py

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

api/core/model_runtime/entities/model_entities.py

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

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

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

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

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

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

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