mirror of
https://github.com/langgenius/dify.git
synced 2024-11-16 03:32:23 +08:00
merge main
This commit is contained in:
JzoNg
commit
684896d100
5
.github/workflows/api-tests.yml
vendored
5
.github/workflows/api-tests.yml
vendored
|
|
@ -39,7 +39,7 @@ jobs:
|
|||
api/pyproject.toml
|
||||
api/poetry.lock
|
||||
|
||||
- name: Poetry check
|
||||
- name: Check Poetry lockfile
|
||||
run: |
|
||||
poetry check -C api --lock
|
||||
poetry show -C api
|
||||
|
|
@ -47,6 +47,9 @@ jobs:
|
|||
- name: Install dependencies
|
||||
run: poetry install -C api --with dev
|
||||
|
||||
- name: Check dependencies in pyproject.toml
|
||||
run: poetry run -C api bash dev/pytest/pytest_artifacts.sh
|
||||
|
||||
- name: Run Unit tests
|
||||
run: poetry run -C api bash dev/pytest/pytest_unit_tests.sh
|
||||
|
||||
|
|
|
|||
2
.github/workflows/build-push.yml
vendored
2
.github/workflows/build-push.yml
vendored
|
|
@ -125,7 +125,7 @@ jobs:
|
|||
with:
|
||||
images: ${{ env[matrix.image_name_env] }}
|
||||
tags: |
|
||||
type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/') }}
|
||||
type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/') && !contains(github.ref, '-') }}
|
||||
type=ref,event=branch
|
||||
type=sha,enable=true,priority=100,prefix=,suffix=,format=long
|
||||
type=raw,value=${{ github.ref_name }},enable=${{ startsWith(github.ref, 'refs/tags/') }}
|
||||
|
|
|
|||
10
README.md
10
README.md
|
|
@ -17,7 +17,7 @@
|
|||
alt="chat on Discord"></a>
|
||||
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
|
||||
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
|
||||
alt="follow on Twitter"></a>
|
||||
alt="follow on X(Twitter)"></a>
|
||||
<a href="https://hub.docker.com/u/langgenius" target="_blank">
|
||||
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
|
||||
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
|
||||
|
|
@ -196,10 +196,14 @@ If you'd like to configure a highly-available setup, there are community-contrib
|
|||
|
||||
#### Using Terraform for Deployment
|
||||
|
||||
Deploy Dify to Cloud Platform with a single click using [terraform](https://www.terraform.io/)
|
||||
|
||||
##### Azure Global
|
||||
Deploy Dify to Azure with a single click using [terraform](https://www.terraform.io/).
|
||||
- [Azure Terraform by @nikawang](https://github.com/nikawang/dify-azure-terraform)
|
||||
|
||||
##### Google Cloud
|
||||
- [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
|
||||
|
||||
## Contributing
|
||||
|
||||
For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
|
||||
|
|
@ -219,7 +223,7 @@ At the same time, please consider supporting Dify by sharing it on social media
|
|||
* [Github Discussion](https://github.com/langgenius/dify/discussions). Best for: sharing feedback and asking questions.
|
||||
* [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
|
||||
* [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
|
||||
* [Twitter](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
|
||||
* [X(Twitter)](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
|
||||
|
||||
## Star history
|
||||
|
||||
|
|
|
|||
|
|
@ -17,7 +17,7 @@
|
|||
alt="chat on Discord"></a>
|
||||
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
|
||||
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
|
||||
alt="follow on Twitter"></a>
|
||||
alt="follow on X(Twitter)"></a>
|
||||
<a href="https://hub.docker.com/u/langgenius" target="_blank">
|
||||
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
|
||||
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
|
||||
|
|
@ -179,10 +179,13 @@ docker compose up -d
|
|||
|
||||
#### استخدام Terraform للتوزيع
|
||||
|
||||
انشر Dify إلى منصة السحابة بنقرة واحدة باستخدام [terraform](https://www.terraform.io/)
|
||||
|
||||
##### Azure Global
|
||||
استخدم [terraform](https://www.terraform.io/) لنشر Dify على Azure بنقرة واحدة.
|
||||
- [Azure Terraform بواسطة @nikawang](https://github.com/nikawang/dify-azure-terraform)
|
||||
|
||||
##### Google Cloud
|
||||
- [Google Cloud Terraform بواسطة @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
|
||||
|
||||
## المساهمة
|
||||
|
||||
|
|
|
|||
10
README_CN.md
10
README_CN.md
|
|
@ -17,7 +17,7 @@
|
|||
alt="chat on Discord"></a>
|
||||
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
|
||||
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
|
||||
alt="follow on Twitter"></a>
|
||||
alt="follow on X(Twitter)"></a>
|
||||
<a href="https://hub.docker.com/u/langgenius" target="_blank">
|
||||
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
|
||||
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
|
||||
|
|
@ -202,10 +202,14 @@ docker compose up -d
|
|||
|
||||
#### 使用 Terraform 部署
|
||||
|
||||
使用 [terraform](https://www.terraform.io/) 一键将 Dify 部署到云平台
|
||||
|
||||
##### Azure Global
|
||||
使用 [terraform](https://www.terraform.io/) 一键部署 Dify 到 Azure。
|
||||
- [Azure Terraform by @nikawang](https://github.com/nikawang/dify-azure-terraform)
|
||||
|
||||
##### Google Cloud
|
||||
- [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
|
||||
|
||||
## Star History
|
||||
|
||||
[](https://star-history.com/#langgenius/dify&Date)
|
||||
|
|
@ -232,7 +236,7 @@ docker compose up -d
|
|||
- [GitHub Issues](https://github.com/langgenius/dify/issues)。👉：使用 Dify.AI 时遇到的错误和问题，请参阅[贡献指南](CONTRIBUTING.md)。
|
||||
- [电子邮件支持](mailto:hello@dify.ai?subject=[GitHub]Questions%20About%20Dify)。👉：关于使用 Dify.AI 的问题。
|
||||
- [Discord](https://discord.gg/FngNHpbcY7)。👉：分享您的应用程序并与社区交流。
|
||||
- [Twitter](https://twitter.com/dify_ai)。👉：分享您的应用程序并与社区交流。
|
||||
- [X(Twitter)](https://twitter.com/dify_ai)。👉：分享您的应用程序并与社区交流。
|
||||
- [商业许可](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)。👉：有关商业用途许可 Dify.AI 的商业咨询。
|
||||
- [微信]() 👉：扫描下方二维码，添加微信好友，备注 Dify，我们将邀请您加入 Dify 社区。
|
||||
<img src="./images/wechat.png" alt="wechat" width="100"/>
|
||||
|
|
|
|||
|
|
@ -17,7 +17,7 @@
|
|||
alt="chat en Discord"></a>
|
||||
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
|
||||
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
|
||||
alt="seguir en Twitter"></a>
|
||||
alt="seguir en X(Twitter)"></a>
|
||||
<a href="https://hub.docker.com/u/langgenius" target="_blank">
|
||||
<img alt="Descargas de Docker" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
|
||||
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
|
||||
|
|
@ -204,10 +204,13 @@ Si desea configurar una configuración de alta disponibilidad, la comunidad prop
|
|||
|
||||
#### Uso de Terraform para el despliegue
|
||||
|
||||
Despliega Dify en una plataforma en la nube con un solo clic utilizando [terraform](https://www.terraform.io/)
|
||||
|
||||
##### Azure Global
|
||||
Utiliza [terraform](https://www.terraform.io/) para desplegar Dify en Azure con un solo clic.
|
||||
- [Azure Terraform por @nikawang](https://github.com/nikawang/dify-azure-terraform)
|
||||
|
||||
##### Google Cloud
|
||||
- [Google Cloud Terraform por @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
|
||||
|
||||
## Contribuir
|
||||
|
||||
|
|
@ -228,7 +231,7 @@ Al mismo tiempo, considera apoyar a Dify compartiéndolo en redes sociales y en
|
|||
* [Discusión en GitHub](https://github.com/langgenius/dify/discussions). Lo mejor para: compartir comentarios y hacer preguntas.
|
||||
* [Reporte de problemas en GitHub](https://github.com/langgenius/dify/issues). Lo mejor para: errores que encuentres usando Dify.AI y propuestas de características. Consulta nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
|
||||
* [Discord](https://discord.gg/FngNHpbcY7). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.
|
||||
* [Twitter](https://twitter.com/dify_ai). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.
|
||||
* [X(Twitter)](https://twitter.com/dify_ai). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.
|
||||
|
||||
## Historial de Estrellas
|
||||
|
||||
|
|
|
|||
|
|
@ -17,7 +17,7 @@
|
|||
alt="chat sur Discord"></a>
|
||||
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
|
||||
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
|
||||
alt="suivre sur Twitter"></a>
|
||||
alt="suivre sur X(Twitter)"></a>
|
||||
<a href="https://hub.docker.com/u/langgenius" target="_blank">
|
||||
<img alt="Tirages Docker" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
|
||||
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
|
||||
|
|
@ -202,10 +202,13 @@ Si vous souhaitez configurer une configuration haute disponibilité, la communau
|
|||
|
||||
#### Utilisation de Terraform pour le déploiement
|
||||
|
||||
Déployez Dify sur une plateforme cloud en un clic en utilisant [terraform](https://www.terraform.io/)
|
||||
|
||||
##### Azure Global
|
||||
Utilisez [terraform](https://www.terraform.io/) pour déployer Dify sur Azure en un clic.
|
||||
- [Azure Terraform par @nikawang](https://github.com/nikawang/dify-azure-terraform)
|
||||
|
||||
##### Google Cloud
|
||||
- [Google Cloud Terraform par @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
|
||||
|
||||
## Contribuer
|
||||
|
||||
|
|
@ -226,7 +229,7 @@ Dans le même temps, veuillez envisager de soutenir Dify en le partageant sur le
|
|||
* [Discussion GitHub](https://github.com/langgenius/dify/discussions). Meilleur pour: partager des commentaires et poser des questions.
|
||||
* [Problèmes GitHub](https://github.com/langgenius/dify/issues). Meilleur pour: les bogues que vous rencontrez en utilisant Dify.AI et les propositions de fonctionnalités. Consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
|
||||
* [Discord](https://discord.gg/FngNHpbcY7). Meilleur pour: partager vos applications et passer du temps avec la communauté.
|
||||
* [Twitter](https://twitter.com/dify_ai). Meilleur pour: partager vos applications et passer du temps avec la communauté.
|
||||
* [X(Twitter)](https://twitter.com/dify_ai). Meilleur pour: partager vos applications et passer du temps avec la communauté.
|
||||
|
||||
## Historique des étoiles
|
||||
|
||||
|
|
|
|||
15
README_JA.md
15
README_JA.md
|
|
@ -17,7 +17,7 @@
|
|||
alt="Discordでチャット"></a>
|
||||
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
|
||||
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
|
||||
alt="Twitterでフォロー"></a>
|
||||
alt="X(Twitter)でフォロー"></a>
|
||||
<a href="https://hub.docker.com/u/langgenius" target="_blank">
|
||||
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
|
||||
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
|
||||
|
|
@ -68,7 +68,7 @@ DifyはオープンソースのLLMアプリケーション開発プラットフ
|
|||
プロンプトの作成、モデルパフォーマンスの比較が行え、チャットベースのアプリに音声合成などの機能も追加できます。
|
||||
|
||||
**4. RAGパイプライン**:
|
||||
ドキュメントの取り込みから検索までをカバーする広範なRAG機能ができます。ほかにもPDF、PPT、その他の一般的なドキュメントフォーマットからのテキスト抽出のサーポイントも提供します。
|
||||
ドキュメントの取り込みから検索までをカバーする広範なRAG機能ができます。ほかにもPDF、PPT、その他の一般的なドキュメントフォーマットからのテキスト抽出のサポートも提供します。
|
||||
|
||||
**5. エージェント機能**:
|
||||
LLM Function CallingやReActに基づくエージェントの定義が可能で、AIエージェント用のプリビルトまたはカスタムツールを追加できます。Difyには、Google検索、DALL·E、Stable Diffusion、WolframAlphaなどのAIエージェント用の50以上の組み込みツールが提供します。
|
||||
|
|
@ -201,10 +201,13 @@ docker compose up -d
|
|||
|
||||
#### Terraformを使用したデプロイ
|
||||
|
||||
##### Azure Global
|
||||
[terraform](https://www.terraform.io/) を使用して、AzureにDifyをワンクリックでデプロイします。
|
||||
- [nikawangのAzure Terraform](https://github.com/nikawang/dify-azure-terraform)
|
||||
[terraform](https://www.terraform.io/) を使用して、ワンクリックでDifyをクラウドプラットフォームにデプロイします
|
||||
|
||||
##### Azure Global
|
||||
- [@nikawangによるAzure Terraform](https://github.com/nikawang/dify-azure-terraform)
|
||||
|
||||
##### Google Cloud
|
||||
- [@sotazumによるGoogle Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform)
|
||||
|
||||
## 貢献
|
||||
|
||||
|
|
@ -225,7 +228,7 @@ docker compose up -d
|
|||
* [Github Discussion](https://github.com/langgenius/dify/discussions). 主に: フィードバックの共有や質問。
|
||||
* [GitHub Issues](https://github.com/langgenius/dify/issues). 主に: Dify.AIを使用する際に発生するエラーや問題については、[貢献ガイド](CONTRIBUTING_JA.md)を参照してください
|
||||
* [Discord](https://discord.gg/FngNHpbcY7). 主に: アプリケーションの共有やコミュニティとの交流。
|
||||
* [Twitter](https://twitter.com/dify_ai). 主に: アプリケーションの共有やコミュニティとの交流。
|
||||
* [X(Twitter)](https://twitter.com/dify_ai). 主に: アプリケーションの共有やコミュニティとの交流。
|
||||
|
||||
|
||||
|
||||
|
|
|
|||
13
README_KL.md
13
README_KL.md
|
|
@ -17,7 +17,7 @@
|
|||
alt="chat on Discord"></a>
|
||||
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
|
||||
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
|
||||
alt="follow on Twitter"></a>
|
||||
alt="follow on X(Twitter)"></a>
|
||||
<a href="https://hub.docker.com/u/langgenius" target="_blank">
|
||||
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
|
||||
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
|
||||
|
|
@ -202,10 +202,13 @@ If you'd like to configure a highly-available setup, there are community-contrib
|
|||
|
||||
#### Terraform atorlugu pilersitsineq
|
||||
|
||||
##### Azure Global
|
||||
Atoruk [terraform](https://www.terraform.io/) Dify-mik Azure-mut ataatsikkut ikkussuilluarlugu.
|
||||
- [Azure Terraform atorlugu @nikawang](https://github.com/nikawang/dify-azure-terraform)
|
||||
wa'logh nIqHom neH ghun deployment toy'wI' [terraform](https://www.terraform.io/) lo'laH.
|
||||
|
||||
##### Azure Global
|
||||
- [Azure Terraform mung @nikawang](https://github.com/nikawang/dify-azure-terraform)
|
||||
|
||||
##### Google Cloud
|
||||
- [Google Cloud Terraform qachlot @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
|
||||
|
||||
## Contributing
|
||||
|
||||
|
|
@ -228,7 +231,7 @@ At the same time, please consider supporting Dify by sharing it on social media
|
|||
). Best for: sharing feedback and asking questions.
|
||||
* [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
|
||||
* [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
|
||||
* [Twitter](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
|
||||
* [X(Twitter)](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
|
||||
|
||||
## Star History
|
||||
|
||||
|
|
|
|||
|
|
@ -17,7 +17,7 @@
|
|||
alt="chat on Discord"></a>
|
||||
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
|
||||
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
|
||||
alt="follow on Twitter"></a>
|
||||
alt="follow on X(Twitter)"></a>
|
||||
<a href="https://hub.docker.com/u/langgenius" target="_blank">
|
||||
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
|
||||
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
|
||||
|
|
@ -39,7 +39,6 @@
|
|||
<a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
|
||||
<a href="./README_TR.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
|
||||
<a href="./README_VI.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
|
||||
|
||||
</p>
|
||||
|
||||
|
||||
|
|
@ -195,10 +194,14 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
|
|||
|
||||
#### Terraform을 사용한 배포
|
||||
|
||||
[terraform](https://www.terraform.io/)을 사용하여 단 한 번의 클릭으로 Dify를 클라우드 플랫폼에 배포하십시오
|
||||
|
||||
##### Azure Global
|
||||
[terraform](https://www.terraform.io/)을 사용하여 Azure에 Dify를 원클릭으로 배포하세요.
|
||||
- [nikawang의 Azure Terraform](https://github.com/nikawang/dify-azure-terraform)
|
||||
|
||||
##### Google Cloud
|
||||
- [sotazum의 Google Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform)
|
||||
|
||||
## 기여
|
||||
|
||||
코드에 기여하고 싶은 분들은 [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)를 참조하세요.
|
||||
|
|
|
|||
12
README_TR.md
12
README_TR.md
|
|
@ -17,7 +17,7 @@
|
|||
alt="Discord'da sohbet et"></a>
|
||||
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
|
||||
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
|
||||
alt="Twitter'da takip et"></a>
|
||||
alt="X(Twitter)'da takip et"></a>
|
||||
<a href="https://hub.docker.com/u/langgenius" target="_blank">
|
||||
<img alt="Docker Çekmeleri" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
|
||||
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
|
||||
|
|
@ -200,9 +200,13 @@ Yüksek kullanılabilirliğe sahip bir kurulum yapılandırmak isterseniz, Dify'
|
|||
|
||||
#### Dağıtım için Terraform Kullanımı
|
||||
|
||||
Dify'ı bulut platformuna tek tıklamayla dağıtın [terraform](https://www.terraform.io/) kullanarak
|
||||
|
||||
##### Azure Global
|
||||
[Terraform](https://www.terraform.io/) kullanarak Dify'ı Azure'a tek tıklamayla dağıtın.
|
||||
- [@nikawang tarafından Azure Terraform](https://github.com/nikawang/dify-azure-terraform)
|
||||
- [Azure Terraform tarafından @nikawang](https://github.com/nikawang/dify-azure-terraform)
|
||||
|
||||
##### Google Cloud
|
||||
- [Google Cloud Terraform tarafından @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
|
||||
|
||||
## Katkıda Bulunma
|
||||
|
||||
|
|
@ -222,7 +226,7 @@ Aynı zamanda, lütfen Dify'ı sosyal medyada, etkinliklerde ve konferanslarda p
|
|||
* [Github Tartışmaları](https://github.com/langgenius/dify/discussions). En uygun: geri bildirim paylaşmak ve soru sormak için.
|
||||
* [GitHub Sorunları](https://github.com/langgenius/dify/issues). En uygun: Dify.AI kullanırken karşılaştığınız hatalar ve özellik önerileri için. [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakın.
|
||||
* [Discord](https://discord.gg/FngNHpbcY7). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
|
||||
* [Twitter](https://twitter.com/dify_ai). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
|
||||
* [X(Twitter)](https://twitter.com/dify_ai). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
|
||||
|
||||
## Star history
|
||||
|
||||
|
|
|
|||
10
README_VI.md
10
README_VI.md
|
|
@ -17,7 +17,7 @@
|
|||
alt="chat trên Discord"></a>
|
||||
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
|
||||
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
|
||||
alt="theo dõi trên Twitter"></a>
|
||||
alt="theo dõi trên X(Twitter)"></a>
|
||||
<a href="https://hub.docker.com/u/langgenius" target="_blank">
|
||||
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
|
||||
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
|
||||
|
|
@ -196,10 +196,14 @@ Nếu bạn muốn cấu hình một cài đặt có độ sẵn sàng cao, có
|
|||
|
||||
#### Sử dụng Terraform để Triển khai
|
||||
|
||||
Triển khai Dify lên nền tảng đám mây với một cú nhấp chuột bằng cách sử dụng [terraform](https://www.terraform.io/)
|
||||
|
||||
##### Azure Global
|
||||
Triển khai Dify lên Azure chỉ với một cú nhấp chuột bằng cách sử dụng [terraform](https://www.terraform.io/).
|
||||
- [Azure Terraform bởi @nikawang](https://github.com/nikawang/dify-azure-terraform)
|
||||
|
||||
##### Google Cloud
|
||||
- [Google Cloud Terraform bởi @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
|
||||
|
||||
## 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.
|
||||
|
|
@ -219,7 +223,7 @@ Triển khai Dify lên Azure chỉ với một cú nhấp chuột bằng cách s
|
|||
* [Thảo luận GitHub](https://github.com/langgenius/dify/discussions). Tốt nhất cho: chia sẻ phản hồi và đặt câu hỏi.
|
||||
* [Vấn đề GitHub](https://github.com/langgenius/dify/issues). Tốt nhất cho: lỗi bạn gặp phải khi sử dụng Dify.AI và đề xuất tính năng. Xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi.
|
||||
* [Discord](https://discord.gg/FngNHpbcY7). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng.
|
||||
* [Twitter](https://twitter.com/dify_ai). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng.
|
||||
* [X(Twitter)](https://twitter.com/dify_ai). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng.
|
||||
|
||||
## Lịch sử Yêu thích
|
||||
|
||||
|
|
|
|||
|
|
@ -20,6 +20,9 @@ FILES_URL=http://127.0.0.1:5001
|
|||
# The time in seconds after the signature is rejected
|
||||
FILES_ACCESS_TIMEOUT=300
|
||||
|
||||
# Access token expiration time in minutes
|
||||
ACCESS_TOKEN_EXPIRE_MINUTES=60
|
||||
|
||||
# celery configuration
|
||||
CELERY_BROKER_URL=redis://:difyai123456@localhost:6379/1
|
||||
|
||||
|
|
@ -39,7 +42,7 @@ DB_DATABASE=dify
|
|||
|
||||
# Storage configuration
|
||||
# use for store upload files, private keys...
|
||||
# storage type: local, s3, azure-blob, google-storage, tencent-cos, huawei-obs, volcengine-tos
|
||||
# storage type: local, s3, azure-blob, google-storage, tencent-cos, huawei-obs, volcengine-tos, baidu-obs, supabase
|
||||
STORAGE_TYPE=local
|
||||
STORAGE_LOCAL_PATH=storage
|
||||
S3_USE_AWS_MANAGED_IAM=false
|
||||
|
|
@ -79,6 +82,12 @@ HUAWEI_OBS_SECRET_KEY=your-secret-key
|
|||
HUAWEI_OBS_ACCESS_KEY=your-access-key
|
||||
HUAWEI_OBS_SERVER=your-server-url
|
||||
|
||||
# Baidu OBS Storage Configuration
|
||||
BAIDU_OBS_BUCKET_NAME=your-bucket-name
|
||||
BAIDU_OBS_SECRET_KEY=your-secret-key
|
||||
BAIDU_OBS_ACCESS_KEY=your-access-key
|
||||
BAIDU_OBS_ENDPOINT=your-server-url
|
||||
|
||||
# OCI Storage configuration
|
||||
OCI_ENDPOINT=your-endpoint
|
||||
OCI_BUCKET_NAME=your-bucket-name
|
||||
|
|
@ -93,11 +102,16 @@ VOLCENGINE_TOS_ACCESS_KEY=your-access-key
|
|||
VOLCENGINE_TOS_SECRET_KEY=your-secret-key
|
||||
VOLCENGINE_TOS_REGION=your-region
|
||||
|
||||
# Supabase Storage Configuration
|
||||
SUPABASE_BUCKET_NAME=your-bucket-name
|
||||
SUPABASE_API_KEY=your-access-key
|
||||
SUPABASE_URL=your-server-url
|
||||
|
||||
# CORS configuration
|
||||
WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
|
||||
CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
|
||||
|
||||
# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector
|
||||
# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, vikingdb
|
||||
VECTOR_STORE=weaviate
|
||||
|
||||
# Weaviate configuration
|
||||
|
|
@ -162,6 +176,8 @@ PGVECTOR_PORT=5433
|
|||
PGVECTOR_USER=postgres
|
||||
PGVECTOR_PASSWORD=postgres
|
||||
PGVECTOR_DATABASE=postgres
|
||||
PGVECTOR_MIN_CONNECTION=1
|
||||
PGVECTOR_MAX_CONNECTION=5
|
||||
|
||||
# Tidb Vector configuration
|
||||
TIDB_VECTOR_HOST=xxx.eu-central-1.xxx.aws.tidbcloud.com
|
||||
|
|
@ -195,6 +211,24 @@ OPENSEARCH_USER=admin
|
|||
OPENSEARCH_PASSWORD=admin
|
||||
OPENSEARCH_SECURE=true
|
||||
|
||||
# Baidu configuration
|
||||
BAIDU_VECTOR_DB_ENDPOINT=http://127.0.0.1:5287
|
||||
BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS=30000
|
||||
BAIDU_VECTOR_DB_ACCOUNT=root
|
||||
BAIDU_VECTOR_DB_API_KEY=dify
|
||||
BAIDU_VECTOR_DB_DATABASE=dify
|
||||
BAIDU_VECTOR_DB_SHARD=1
|
||||
BAIDU_VECTOR_DB_REPLICAS=3
|
||||
|
||||
# ViKingDB configuration
|
||||
VIKINGDB_ACCESS_KEY=your-ak
|
||||
VIKINGDB_SECRET_KEY=your-sk
|
||||
VIKINGDB_REGION=cn-shanghai
|
||||
VIKINGDB_HOST=api-vikingdb.xxx.volces.com
|
||||
VIKINGDB_SCHEMA=http
|
||||
VIKINGDB_CONNECTION_TIMEOUT=30
|
||||
VIKINGDB_SOCKET_TIMEOUT=30
|
||||
|
||||
# Upload configuration
|
||||
UPLOAD_FILE_SIZE_LIMIT=15
|
||||
UPLOAD_FILE_BATCH_LIMIT=5
|
||||
|
|
@ -263,6 +297,9 @@ HTTP_REQUEST_MAX_WRITE_TIMEOUT=600
|
|||
HTTP_REQUEST_NODE_MAX_BINARY_SIZE=10485760
|
||||
HTTP_REQUEST_NODE_MAX_TEXT_SIZE=1048576
|
||||
|
||||
# Respect X-* headers to redirect clients
|
||||
RESPECT_XFORWARD_HEADERS_ENABLED=false
|
||||
|
||||
# Log file path
|
||||
LOG_FILE=
|
||||
|
||||
|
|
|
|||
14
api/app.py
14
api/app.py
|
|
@ -26,7 +26,7 @@ from commands import register_commands
|
|||
from configs import dify_config
|
||||
|
||||
# DO NOT REMOVE BELOW
|
||||
from events import event_handlers
|
||||
from events import event_handlers # noqa: F401
|
||||
from extensions import (
|
||||
ext_celery,
|
||||
ext_code_based_extension,
|
||||
|
|
@ -36,6 +36,7 @@ from extensions import (
|
|||
ext_login,
|
||||
ext_mail,
|
||||
ext_migrate,
|
||||
ext_proxy_fix,
|
||||
ext_redis,
|
||||
ext_sentry,
|
||||
ext_storage,
|
||||
|
|
@ -45,7 +46,7 @@ from extensions.ext_login import login_manager
|
|||
from libs.passport import PassportService
|
||||
|
||||
# TODO: Find a way to avoid importing models here
|
||||
from models import account, dataset, model, source, task, tool, tools, web
|
||||
from models import account, dataset, model, source, task, tool, tools, web # noqa: F401
|
||||
from services.account_service import AccountService
|
||||
|
||||
# DO NOT REMOVE ABOVE
|
||||
|
|
@ -156,6 +157,7 @@ def initialize_extensions(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
|
||||
|
|
@ -181,10 +183,10 @@ def load_user_from_request(request_from_flask_login):
|
|||
decoded = PassportService().verify(auth_token)
|
||||
user_id = decoded.get("user_id")
|
||||
|
||||
account = AccountService.load_logged_in_account(account_id=user_id, token=auth_token)
|
||||
if account:
|
||||
contexts.tenant_id.set(account.current_tenant_id)
|
||||
return account
|
||||
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
|
||||
|
|
|
|||
|
|
@ -347,6 +347,14 @@ def migrate_knowledge_vector_database():
|
|||
index_name = Dataset.gen_collection_name_by_id(dataset_id)
|
||||
index_struct_dict = {"type": "elasticsearch", "vector_store": {"class_prefix": index_name}}
|
||||
dataset.index_struct = json.dumps(index_struct_dict)
|
||||
elif vector_type == VectorType.BAIDU:
|
||||
dataset_id = dataset.id
|
||||
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
|
||||
index_struct_dict = {
|
||||
"type": VectorType.BAIDU,
|
||||
"vector_store": {"class_prefix": collection_name},
|
||||
}
|
||||
dataset.index_struct = json.dumps(index_struct_dict)
|
||||
else:
|
||||
raise ValueError(f"Vector store {vector_type} is not supported.")
|
||||
|
||||
|
|
|
|||
|
|
@ -247,6 +247,12 @@ class HttpConfig(BaseSettings):
|
|||
default=None,
|
||||
)
|
||||
|
||||
RESPECT_XFORWARD_HEADERS_ENABLED: bool = Field(
|
||||
description="Enable or disable the X-Forwarded-For Proxy Fix middleware from Werkzeug"
|
||||
" to respect X-* headers to redirect clients",
|
||||
default=False,
|
||||
)
|
||||
|
||||
|
||||
class InnerAPIConfig(BaseSettings):
|
||||
"""
|
||||
|
|
@ -354,9 +360,9 @@ class WorkflowConfig(BaseSettings):
|
|||
)
|
||||
|
||||
|
||||
class OAuthConfig(BaseSettings):
|
||||
class AuthConfig(BaseSettings):
|
||||
"""
|
||||
Configuration for OAuth authentication
|
||||
Configuration for authentication and OAuth
|
||||
"""
|
||||
|
||||
OAUTH_REDIRECT_PATH: str = Field(
|
||||
|
|
@ -365,7 +371,7 @@ class OAuthConfig(BaseSettings):
|
|||
)
|
||||
|
||||
GITHUB_CLIENT_ID: Optional[str] = Field(
|
||||
description="GitHub OAuth client secret",
|
||||
description="GitHub OAuth client ID",
|
||||
default=None,
|
||||
)
|
||||
|
||||
|
|
@ -384,6 +390,11 @@ class OAuthConfig(BaseSettings):
|
|||
default=None,
|
||||
)
|
||||
|
||||
ACCESS_TOKEN_EXPIRE_MINUTES: PositiveInt = Field(
|
||||
description="Expiration time for access tokens in minutes",
|
||||
default=60,
|
||||
)
|
||||
|
||||
|
||||
class ModerationConfig(BaseSettings):
|
||||
"""
|
||||
|
|
@ -601,6 +612,7 @@ class PositionConfig(BaseSettings):
|
|||
class FeatureConfig(
|
||||
# place the configs in alphabet order
|
||||
AppExecutionConfig,
|
||||
AuthConfig, # Changed from OAuthConfig to AuthConfig
|
||||
BillingConfig,
|
||||
CodeExecutionSandboxConfig,
|
||||
DataSetConfig,
|
||||
|
|
@ -615,14 +627,13 @@ class FeatureConfig(
|
|||
MailConfig,
|
||||
ModelLoadBalanceConfig,
|
||||
ModerationConfig,
|
||||
OAuthConfig,
|
||||
PositionConfig,
|
||||
RagEtlConfig,
|
||||
SecurityConfig,
|
||||
ToolConfig,
|
||||
UpdateConfig,
|
||||
WorkflowConfig,
|
||||
WorkspaceConfig,
|
||||
PositionConfig,
|
||||
# hosted services config
|
||||
HostedServiceConfig,
|
||||
CeleryBeatConfig,
|
||||
|
|
|
|||
|
|
@ -8,9 +8,11 @@ from configs.middleware.cache.redis_config import RedisConfig
|
|||
from configs.middleware.storage.aliyun_oss_storage_config import AliyunOSSStorageConfig
|
||||
from configs.middleware.storage.amazon_s3_storage_config import S3StorageConfig
|
||||
from configs.middleware.storage.azure_blob_storage_config import AzureBlobStorageConfig
|
||||
from configs.middleware.storage.baidu_obs_storage_config import BaiduOBSStorageConfig
|
||||
from configs.middleware.storage.google_cloud_storage_config import GoogleCloudStorageConfig
|
||||
from configs.middleware.storage.huawei_obs_storage_config import HuaweiCloudOBSStorageConfig
|
||||
from configs.middleware.storage.oci_storage_config import OCIStorageConfig
|
||||
from configs.middleware.storage.supabase_storage_config import SupabaseStorageConfig
|
||||
from configs.middleware.storage.tencent_cos_storage_config import TencentCloudCOSStorageConfig
|
||||
from configs.middleware.storage.volcengine_tos_storage_config import VolcengineTOSStorageConfig
|
||||
from configs.middleware.vdb.analyticdb_config import AnalyticdbConfig
|
||||
|
|
@ -26,6 +28,7 @@ from configs.middleware.vdb.qdrant_config import QdrantConfig
|
|||
from configs.middleware.vdb.relyt_config import RelytConfig
|
||||
from configs.middleware.vdb.tencent_vector_config import TencentVectorDBConfig
|
||||
from configs.middleware.vdb.tidb_vector_config import TiDBVectorConfig
|
||||
from configs.middleware.vdb.vikingdb_config import VikingDBConfig
|
||||
from configs.middleware.vdb.weaviate_config import WeaviateConfig
|
||||
|
||||
|
||||
|
|
@ -190,6 +193,22 @@ class CeleryConfig(DatabaseConfig):
|
|||
return self.CELERY_BROKER_URL.startswith("rediss://") if self.CELERY_BROKER_URL else False
|
||||
|
||||
|
||||
class InternalTestConfig(BaseSettings):
|
||||
"""
|
||||
Configuration settings for Internal Test
|
||||
"""
|
||||
|
||||
AWS_SECRET_ACCESS_KEY: Optional[str] = Field(
|
||||
description="Internal test AWS secret access key",
|
||||
default=None,
|
||||
)
|
||||
|
||||
AWS_ACCESS_KEY_ID: Optional[str] = Field(
|
||||
description="Internal test AWS access key ID",
|
||||
default=None,
|
||||
)
|
||||
|
||||
|
||||
class MiddlewareConfig(
|
||||
# place the configs in alphabet order
|
||||
CeleryConfig,
|
||||
|
|
@ -200,12 +219,14 @@ class MiddlewareConfig(
|
|||
StorageConfig,
|
||||
AliyunOSSStorageConfig,
|
||||
AzureBlobStorageConfig,
|
||||
BaiduOBSStorageConfig,
|
||||
GoogleCloudStorageConfig,
|
||||
TencentCloudCOSStorageConfig,
|
||||
HuaweiCloudOBSStorageConfig,
|
||||
VolcengineTOSStorageConfig,
|
||||
S3StorageConfig,
|
||||
OCIStorageConfig,
|
||||
S3StorageConfig,
|
||||
SupabaseStorageConfig,
|
||||
TencentCloudCOSStorageConfig,
|
||||
VolcengineTOSStorageConfig,
|
||||
# configs of vdb and vdb providers
|
||||
VectorStoreConfig,
|
||||
AnalyticdbConfig,
|
||||
|
|
@ -222,5 +243,7 @@ class MiddlewareConfig(
|
|||
TiDBVectorConfig,
|
||||
WeaviateConfig,
|
||||
ElasticsearchConfig,
|
||||
InternalTestConfig,
|
||||
VikingDBConfig,
|
||||
):
|
||||
pass
|
||||
|
|
|
|||
29
api/configs/middleware/storage/baidu_obs_storage_config.py
Normal file
29
api/configs/middleware/storage/baidu_obs_storage_config.py
Normal file
|
|
@ -0,0 +1,29 @@
|
|||
from typing import Optional
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class BaiduOBSStorageConfig(BaseModel):
|
||||
"""
|
||||
Configuration settings for Baidu Object Storage Service (OBS)
|
||||
"""
|
||||
|
||||
BAIDU_OBS_BUCKET_NAME: Optional[str] = Field(
|
||||
description="Name of the Baidu OBS bucket to store and retrieve objects (e.g., 'my-obs-bucket')",
|
||||
default=None,
|
||||
)
|
||||
|
||||
BAIDU_OBS_ACCESS_KEY: Optional[str] = Field(
|
||||
description="Access Key ID for authenticating with Baidu OBS",
|
||||
default=None,
|
||||
)
|
||||
|
||||
BAIDU_OBS_SECRET_KEY: Optional[str] = Field(
|
||||
description="Secret Access Key for authenticating with Baidu OBS",
|
||||
default=None,
|
||||
)
|
||||
|
||||
BAIDU_OBS_ENDPOINT: Optional[str] = Field(
|
||||
description="URL of the Baidu OSS endpoint for your chosen region (e.g., 'https://.bj.bcebos.com')",
|
||||
default=None,
|
||||
)
|
||||
24
api/configs/middleware/storage/supabase_storage_config.py
Normal file
24
api/configs/middleware/storage/supabase_storage_config.py
Normal file
|
|
@ -0,0 +1,24 @@
|
|||
from typing import Optional
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class SupabaseStorageConfig(BaseModel):
|
||||
"""
|
||||
Configuration settings for Supabase Object Storage Service
|
||||
"""
|
||||
|
||||
SUPABASE_BUCKET_NAME: Optional[str] = Field(
|
||||
description="Name of the Supabase bucket to store and retrieve objects (e.g., 'dify-bucket')",
|
||||
default=None,
|
||||
)
|
||||
|
||||
SUPABASE_API_KEY: Optional[str] = Field(
|
||||
description="API KEY for authenticating with Supabase",
|
||||
default=None,
|
||||
)
|
||||
|
||||
SUPABASE_URL: Optional[str] = Field(
|
||||
description="URL of the Supabase",
|
||||
default=None,
|
||||
)
|
||||
45
api/configs/middleware/vdb/baidu_vector_config.py
Normal file
45
api/configs/middleware/vdb/baidu_vector_config.py
Normal file
|
|
@ -0,0 +1,45 @@
|
|||
from typing import Optional
|
||||
|
||||
from pydantic import Field, NonNegativeInt, PositiveInt
|
||||
from pydantic_settings import BaseSettings
|
||||
|
||||
|
||||
class BaiduVectorDBConfig(BaseSettings):
|
||||
"""
|
||||
Configuration settings for Baidu Vector Database
|
||||
"""
|
||||
|
||||
BAIDU_VECTOR_DB_ENDPOINT: Optional[str] = Field(
|
||||
description="URL of the Baidu Vector Database service (e.g., 'http://vdb.bj.baidubce.com')",
|
||||
default=None,
|
||||
)
|
||||
|
||||
BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS: PositiveInt = Field(
|
||||
description="Timeout in milliseconds for Baidu Vector Database operations (default is 30000 milliseconds)",
|
||||
default=30000,
|
||||
)
|
||||
|
||||
BAIDU_VECTOR_DB_ACCOUNT: Optional[str] = Field(
|
||||
description="Account for authenticating with the Baidu Vector Database",
|
||||
default=None,
|
||||
)
|
||||
|
||||
BAIDU_VECTOR_DB_API_KEY: Optional[str] = Field(
|
||||
description="API key for authenticating with the Baidu Vector Database service",
|
||||
default=None,
|
||||
)
|
||||
|
||||
BAIDU_VECTOR_DB_DATABASE: Optional[str] = Field(
|
||||
description="Name of the specific Baidu Vector Database to connect to",
|
||||
default=None,
|
||||
)
|
||||
|
||||
BAIDU_VECTOR_DB_SHARD: PositiveInt = Field(
|
||||
description="Number of shards for the Baidu Vector Database (default is 1)",
|
||||
default=1,
|
||||
)
|
||||
|
||||
BAIDU_VECTOR_DB_REPLICAS: NonNegativeInt = Field(
|
||||
description="Number of replicas for the Baidu Vector Database (default is 3)",
|
||||
default=3,
|
||||
)
|
||||
|
|
@ -33,3 +33,13 @@ class PGVectorConfig(BaseSettings):
|
|||
description="Name of the PostgreSQL database to connect to",
|
||||
default=None,
|
||||
)
|
||||
|
||||
PGVECTOR_MIN_CONNECTION: PositiveInt = Field(
|
||||
description="Min connection of the PostgreSQL database",
|
||||
default=1,
|
||||
)
|
||||
|
||||
PGVECTOR_MAX_CONNECTION: PositiveInt = Field(
|
||||
description="Max connection of the PostgreSQL database",
|
||||
default=5,
|
||||
)
|
||||
|
|
|
|||
37
api/configs/middleware/vdb/vikingdb_config.py
Normal file
37
api/configs/middleware/vdb/vikingdb_config.py
Normal file
|
|
@ -0,0 +1,37 @@
|
|||
from typing import Optional
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class VikingDBConfig(BaseModel):
|
||||
"""
|
||||
Configuration for connecting to Volcengine VikingDB.
|
||||
Refer to the following documentation for details on obtaining credentials:
|
||||
https://www.volcengine.com/docs/6291/65568
|
||||
"""
|
||||
|
||||
VIKINGDB_ACCESS_KEY: Optional[str] = Field(
|
||||
default=None, description="The Access Key provided by Volcengine VikingDB for API authentication."
|
||||
)
|
||||
VIKINGDB_SECRET_KEY: Optional[str] = Field(
|
||||
default=None, description="The Secret Key provided by Volcengine VikingDB for API authentication."
|
||||
)
|
||||
VIKINGDB_REGION: Optional[str] = Field(
|
||||
default="cn-shanghai",
|
||||
description="The region of the Volcengine VikingDB service.(e.g., 'cn-shanghai', 'cn-beijing').",
|
||||
)
|
||||
VIKINGDB_HOST: Optional[str] = Field(
|
||||
default="api-vikingdb.mlp.cn-shanghai.volces.com",
|
||||
description="The host of the Volcengine VikingDB service.(e.g., 'api-vikingdb.volces.com', \
|
||||
'api-vikingdb.mlp.cn-shanghai.volces.com')",
|
||||
)
|
||||
VIKINGDB_SCHEME: Optional[str] = Field(
|
||||
default="http",
|
||||
description="The scheme of the Volcengine VikingDB service.(e.g., 'http', 'https').",
|
||||
)
|
||||
VIKINGDB_CONNECTION_TIMEOUT: Optional[int] = Field(
|
||||
default=30, description="The connection timeout of the Volcengine VikingDB service."
|
||||
)
|
||||
VIKINGDB_SOCKET_TIMEOUT: Optional[int] = Field(
|
||||
default=30, description="The socket timeout of the Volcengine VikingDB service."
|
||||
)
|
||||
|
|
@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
|
|||
|
||||
CURRENT_VERSION: str = Field(
|
||||
description="Dify version",
|
||||
default="0.8.3",
|
||||
default="0.9.1",
|
||||
)
|
||||
|
||||
COMMIT_SHA: str = Field(
|
||||
|
|
|
|||
|
|
@ -37,7 +37,16 @@ from .auth import activate, data_source_bearer_auth, data_source_oauth, forgot_p
|
|||
from .billing import billing
|
||||
|
||||
# Import datasets controllers
|
||||
from .datasets import data_source, datasets, datasets_document, datasets_segments, file, hit_testing, website
|
||||
from .datasets import (
|
||||
data_source,
|
||||
datasets,
|
||||
datasets_document,
|
||||
datasets_segments,
|
||||
external,
|
||||
file,
|
||||
hit_testing,
|
||||
website,
|
||||
)
|
||||
|
||||
# Import explore controllers
|
||||
from .explore import (
|
||||
|
|
|
|||
|
|
@ -188,6 +188,7 @@ class ChatConversationApi(Resource):
|
|||
subquery.c.from_end_user_session_id.ilike(keyword_filter),
|
||||
),
|
||||
)
|
||||
.group_by(Conversation.id)
|
||||
)
|
||||
|
||||
account = current_user
|
||||
|
|
|
|||
|
|
@ -7,7 +7,7 @@ from flask_restful import Resource, reqparse
|
|||
import services
|
||||
from controllers.console import api
|
||||
from controllers.console.setup import setup_required
|
||||
from libs.helper import email, get_remote_ip
|
||||
from libs.helper import email, extract_remote_ip
|
||||
from libs.password import valid_password
|
||||
from models.account import Account
|
||||
from services.account_service import AccountService, TenantService
|
||||
|
|
@ -40,17 +40,16 @@ class LoginApi(Resource):
|
|||
"data": "workspace not found, please contact system admin to invite you to join in a workspace",
|
||||
}
|
||||
|
||||
token = AccountService.login(account, ip_address=get_remote_ip(request))
|
||||
token_pair = AccountService.login(account=account, ip_address=extract_remote_ip(request))
|
||||
|
||||
return {"result": "success", "data": token}
|
||||
return {"result": "success", "data": token_pair.model_dump()}
|
||||
|
||||
|
||||
class LogoutApi(Resource):
|
||||
@setup_required
|
||||
def get(self):
|
||||
account = cast(Account, flask_login.current_user)
|
||||
token = request.headers.get("Authorization", "").split(" ")[1]
|
||||
AccountService.logout(account=account, token=token)
|
||||
AccountService.logout(account=account)
|
||||
flask_login.logout_user()
|
||||
return {"result": "success"}
|
||||
|
||||
|
|
@ -106,5 +105,19 @@ class ResetPasswordApi(Resource):
|
|||
return {"result": "success"}
|
||||
|
||||
|
||||
class RefreshTokenApi(Resource):
|
||||
def post(self):
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument("refresh_token", type=str, required=True, location="json")
|
||||
args = parser.parse_args()
|
||||
|
||||
try:
|
||||
new_token_pair = AccountService.refresh_token(args["refresh_token"])
|
||||
return {"result": "success", "data": new_token_pair.model_dump()}
|
||||
except Exception as e:
|
||||
return {"result": "fail", "data": str(e)}, 401
|
||||
|
||||
|
||||
api.add_resource(LoginApi, "/login")
|
||||
api.add_resource(LogoutApi, "/logout")
|
||||
api.add_resource(RefreshTokenApi, "/refresh-token")
|
||||
|
|
|
|||
|
|
@ -9,7 +9,7 @@ from flask_restful import Resource
|
|||
from configs import dify_config
|
||||
from constants.languages import languages
|
||||
from extensions.ext_database import db
|
||||
from libs.helper import get_remote_ip
|
||||
from libs.helper import extract_remote_ip
|
||||
from libs.oauth import GitHubOAuth, GoogleOAuth, OAuthUserInfo
|
||||
from models.account import Account, AccountStatus
|
||||
from services.account_service import AccountService, RegisterService, TenantService
|
||||
|
|
@ -81,9 +81,14 @@ class OAuthCallback(Resource):
|
|||
|
||||
TenantService.create_owner_tenant_if_not_exist(account)
|
||||
|
||||
token = AccountService.login(account, ip_address=get_remote_ip(request))
|
||||
token_pair = AccountService.login(
|
||||
account=account,
|
||||
ip_address=extract_remote_ip(request),
|
||||
)
|
||||
|
||||
return redirect(f"{dify_config.CONSOLE_WEB_URL}?console_token={token}")
|
||||
return redirect(
|
||||
f"{dify_config.CONSOLE_WEB_URL}?access_token={token_pair.access_token}&refresh_token={token_pair.refresh_token}"
|
||||
)
|
||||
|
||||
|
||||
def _get_account_by_openid_or_email(provider: str, user_info: OAuthUserInfo) -> Optional[Account]:
|
||||
|
|
|
|||
|
|
@ -49,7 +49,7 @@ class DatasetListApi(Resource):
|
|||
page = request.args.get("page", default=1, type=int)
|
||||
limit = request.args.get("limit", default=20, type=int)
|
||||
ids = request.args.getlist("ids")
|
||||
provider = request.args.get("provider", default="vendor")
|
||||
# provider = request.args.get("provider", default="vendor")
|
||||
search = request.args.get("keyword", default=None, type=str)
|
||||
tag_ids = request.args.getlist("tag_ids")
|
||||
|
||||
|
|
@ -57,7 +57,7 @@ class DatasetListApi(Resource):
|
|||
datasets, total = DatasetService.get_datasets_by_ids(ids, current_user.current_tenant_id)
|
||||
else:
|
||||
datasets, total = DatasetService.get_datasets(
|
||||
page, limit, provider, current_user.current_tenant_id, current_user, search, tag_ids
|
||||
page, limit, current_user.current_tenant_id, current_user, search, tag_ids
|
||||
)
|
||||
|
||||
# check embedding setting
|
||||
|
|
@ -110,6 +110,26 @@ class DatasetListApi(Resource):
|
|||
nullable=True,
|
||||
help="Invalid indexing technique.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"external_knowledge_api_id",
|
||||
type=str,
|
||||
nullable=True,
|
||||
required=False,
|
||||
)
|
||||
parser.add_argument(
|
||||
"provider",
|
||||
type=str,
|
||||
nullable=True,
|
||||
choices=Dataset.PROVIDER_LIST,
|
||||
required=False,
|
||||
default="vendor",
|
||||
)
|
||||
parser.add_argument(
|
||||
"external_knowledge_id",
|
||||
type=str,
|
||||
nullable=True,
|
||||
required=False,
|
||||
)
|
||||
args = parser.parse_args()
|
||||
|
||||
# The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
|
||||
|
|
@ -123,6 +143,9 @@ class DatasetListApi(Resource):
|
|||
indexing_technique=args["indexing_technique"],
|
||||
account=current_user,
|
||||
permission=DatasetPermissionEnum.ONLY_ME,
|
||||
provider=args["provider"],
|
||||
external_knowledge_api_id=args["external_knowledge_api_id"],
|
||||
external_knowledge_id=args["external_knowledge_id"],
|
||||
)
|
||||
except services.errors.dataset.DatasetNameDuplicateError:
|
||||
raise DatasetNameDuplicateError()
|
||||
|
|
@ -211,6 +234,33 @@ class DatasetApi(Resource):
|
|||
)
|
||||
parser.add_argument("retrieval_model", type=dict, location="json", help="Invalid retrieval model.")
|
||||
parser.add_argument("partial_member_list", type=list, location="json", help="Invalid parent user list.")
|
||||
|
||||
parser.add_argument(
|
||||
"external_retrieval_model",
|
||||
type=dict,
|
||||
required=False,
|
||||
nullable=True,
|
||||
location="json",
|
||||
help="Invalid external retrieval model.",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"external_knowledge_id",
|
||||
type=str,
|
||||
required=False,
|
||||
nullable=True,
|
||||
location="json",
|
||||
help="Invalid external knowledge id.",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"external_knowledge_api_id",
|
||||
type=str,
|
||||
required=False,
|
||||
nullable=True,
|
||||
location="json",
|
||||
help="Invalid external knowledge api id.",
|
||||
)
|
||||
args = parser.parse_args()
|
||||
data = request.get_json()
|
||||
|
||||
|
|
@ -563,10 +613,12 @@ class DatasetRetrievalSettingApi(Resource):
|
|||
case (
|
||||
VectorType.MILVUS
|
||||
| VectorType.RELYT
|
||||
| VectorType.PGVECTOR
|
||||
| VectorType.TIDB_VECTOR
|
||||
| VectorType.CHROMA
|
||||
| VectorType.TENCENT
|
||||
| VectorType.PGVECTO_RS
|
||||
| VectorType.BAIDU
|
||||
| VectorType.VIKINGDB
|
||||
):
|
||||
return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
|
||||
case (
|
||||
|
|
@ -577,6 +629,7 @@ class DatasetRetrievalSettingApi(Resource):
|
|||
| VectorType.MYSCALE
|
||||
| VectorType.ORACLE
|
||||
| VectorType.ELASTICSEARCH
|
||||
| VectorType.PGVECTOR
|
||||
):
|
||||
return {
|
||||
"retrieval_method": [
|
||||
|
|
@ -602,6 +655,8 @@ class DatasetRetrievalSettingMockApi(Resource):
|
|||
| VectorType.CHROMA
|
||||
| VectorType.TENCENT
|
||||
| VectorType.PGVECTO_RS
|
||||
| VectorType.BAIDU
|
||||
| VectorType.VIKINGDB
|
||||
):
|
||||
return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
|
||||
case (
|
||||
|
|
|
|||
263
api/controllers/console/datasets/external.py
Normal file
263
api/controllers/console/datasets/external.py
Normal file
|
|
@ -0,0 +1,263 @@
|
|||
from flask import request
|
||||
from flask_login import current_user
|
||||
from flask_restful import Resource, marshal, reqparse
|
||||
from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
|
||||
|
||||
import services
|
||||
from controllers.console import api
|
||||
from controllers.console.datasets.error import DatasetNameDuplicateError
|
||||
from controllers.console.setup import setup_required
|
||||
from controllers.console.wraps import account_initialization_required
|
||||
from fields.dataset_fields import dataset_detail_fields
|
||||
from libs.login import login_required
|
||||
from services.dataset_service import DatasetService
|
||||
from services.external_knowledge_service import ExternalDatasetService
|
||||
from services.hit_testing_service import HitTestingService
|
||||
from services.knowledge_service import ExternalDatasetTestService
|
||||
|
||||
|
||||
def _validate_name(name):
|
||||
if not name or len(name) < 1 or len(name) > 100:
|
||||
raise ValueError("Name must be between 1 to 100 characters.")
|
||||
return name
|
||||
|
||||
|
||||
def _validate_description_length(description):
|
||||
if description and len(description) > 400:
|
||||
raise ValueError("Description cannot exceed 400 characters.")
|
||||
return description
|
||||
|
||||
|
||||
class ExternalApiTemplateListApi(Resource):
|
||||
@setup_required
|
||||
@login_required
|
||||
@account_initialization_required
|
||||
def get(self):
|
||||
page = request.args.get("page", default=1, type=int)
|
||||
limit = request.args.get("limit", default=20, type=int)
|
||||
search = request.args.get("keyword", default=None, type=str)
|
||||
|
||||
external_knowledge_apis, total = ExternalDatasetService.get_external_knowledge_apis(
|
||||
page, limit, current_user.current_tenant_id, search
|
||||
)
|
||||
response = {
|
||||
"data": [item.to_dict() for item in external_knowledge_apis],
|
||||
"has_more": len(external_knowledge_apis) == limit,
|
||||
"limit": limit,
|
||||
"total": total,
|
||||
"page": page,
|
||||
}
|
||||
return response, 200
|
||||
|
||||
@setup_required
|
||||
@login_required
|
||||
@account_initialization_required
|
||||
def post(self):
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument(
|
||||
"name",
|
||||
nullable=False,
|
||||
required=True,
|
||||
help="Name is required. Name must be between 1 to 100 characters.",
|
||||
type=_validate_name,
|
||||
)
|
||||
parser.add_argument(
|
||||
"settings",
|
||||
type=dict,
|
||||
location="json",
|
||||
nullable=False,
|
||||
required=True,
|
||||
)
|
||||
args = parser.parse_args()
|
||||
|
||||
ExternalDatasetService.validate_api_list(args["settings"])
|
||||
|
||||
# The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
|
||||
if not current_user.is_dataset_editor:
|
||||
raise Forbidden()
|
||||
|
||||
try:
|
||||
external_knowledge_api = ExternalDatasetService.create_external_knowledge_api(
|
||||
tenant_id=current_user.current_tenant_id, user_id=current_user.id, args=args
|
||||
)
|
||||
except services.errors.dataset.DatasetNameDuplicateError:
|
||||
raise DatasetNameDuplicateError()
|
||||
|
||||
return external_knowledge_api.to_dict(), 201
|
||||
|
||||
|
||||
class ExternalApiTemplateApi(Resource):
|
||||
@setup_required
|
||||
@login_required
|
||||
@account_initialization_required
|
||||
def get(self, external_knowledge_api_id):
|
||||
external_knowledge_api_id = str(external_knowledge_api_id)
|
||||
external_knowledge_api = ExternalDatasetService.get_external_knowledge_api(external_knowledge_api_id)
|
||||
if external_knowledge_api is None:
|
||||
raise NotFound("API template not found.")
|
||||
|
||||
return external_knowledge_api.to_dict(), 200
|
||||
|
||||
@setup_required
|
||||
@login_required
|
||||
@account_initialization_required
|
||||
def patch(self, external_knowledge_api_id):
|
||||
external_knowledge_api_id = str(external_knowledge_api_id)
|
||||
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument(
|
||||
"name",
|
||||
nullable=False,
|
||||
required=True,
|
||||
help="type is required. Name must be between 1 to 100 characters.",
|
||||
type=_validate_name,
|
||||
)
|
||||
parser.add_argument(
|
||||
"settings",
|
||||
type=dict,
|
||||
location="json",
|
||||
nullable=False,
|
||||
required=True,
|
||||
)
|
||||
args = parser.parse_args()
|
||||
ExternalDatasetService.validate_api_list(args["settings"])
|
||||
|
||||
external_knowledge_api = ExternalDatasetService.update_external_knowledge_api(
|
||||
tenant_id=current_user.current_tenant_id,
|
||||
user_id=current_user.id,
|
||||
external_knowledge_api_id=external_knowledge_api_id,
|
||||
args=args,
|
||||
)
|
||||
|
||||
return external_knowledge_api.to_dict(), 200
|
||||
|
||||
@setup_required
|
||||
@login_required
|
||||
@account_initialization_required
|
||||
def delete(self, external_knowledge_api_id):
|
||||
external_knowledge_api_id = str(external_knowledge_api_id)
|
||||
|
||||
# The role of the current user in the ta table must be admin, owner, or editor
|
||||
if not current_user.is_editor or current_user.is_dataset_operator:
|
||||
raise Forbidden()
|
||||
|
||||
ExternalDatasetService.delete_external_knowledge_api(current_user.current_tenant_id, external_knowledge_api_id)
|
||||
return {"result": "success"}, 200
|
||||
|
||||
|
||||
class ExternalApiUseCheckApi(Resource):
|
||||
@setup_required
|
||||
@login_required
|
||||
@account_initialization_required
|
||||
def get(self, external_knowledge_api_id):
|
||||
external_knowledge_api_id = str(external_knowledge_api_id)
|
||||
|
||||
external_knowledge_api_is_using, count = ExternalDatasetService.external_knowledge_api_use_check(
|
||||
external_knowledge_api_id
|
||||
)
|
||||
return {"is_using": external_knowledge_api_is_using, "count": count}, 200
|
||||
|
||||
|
||||
class ExternalDatasetCreateApi(Resource):
|
||||
@setup_required
|
||||
@login_required
|
||||
@account_initialization_required
|
||||
def post(self):
|
||||
# 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("external_knowledge_api_id", type=str, required=True, nullable=False, location="json")
|
||||
parser.add_argument("external_knowledge_id", type=str, required=True, nullable=False, location="json")
|
||||
parser.add_argument(
|
||||
"name",
|
||||
nullable=False,
|
||||
required=True,
|
||||
help="name is required. Name must be between 1 to 100 characters.",
|
||||
type=_validate_name,
|
||||
)
|
||||
parser.add_argument("description", type=str, required=False, nullable=True, location="json")
|
||||
parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
# The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
|
||||
if not current_user.is_dataset_editor:
|
||||
raise Forbidden()
|
||||
|
||||
try:
|
||||
dataset = ExternalDatasetService.create_external_dataset(
|
||||
tenant_id=current_user.current_tenant_id,
|
||||
user_id=current_user.id,
|
||||
args=args,
|
||||
)
|
||||
except services.errors.dataset.DatasetNameDuplicateError:
|
||||
raise DatasetNameDuplicateError()
|
||||
|
||||
return marshal(dataset, dataset_detail_fields), 201
|
||||
|
||||
|
||||
class ExternalKnowledgeHitTestingApi(Resource):
|
||||
@setup_required
|
||||
@login_required
|
||||
@account_initialization_required
|
||||
def post(self, dataset_id):
|
||||
dataset_id_str = str(dataset_id)
|
||||
dataset = DatasetService.get_dataset(dataset_id_str)
|
||||
if dataset is None:
|
||||
raise NotFound("Dataset not found.")
|
||||
|
||||
try:
|
||||
DatasetService.check_dataset_permission(dataset, current_user)
|
||||
except services.errors.account.NoPermissionError as e:
|
||||
raise Forbidden(str(e))
|
||||
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument("query", type=str, location="json")
|
||||
parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
|
||||
args = parser.parse_args()
|
||||
|
||||
HitTestingService.hit_testing_args_check(args)
|
||||
|
||||
try:
|
||||
response = HitTestingService.external_retrieve(
|
||||
dataset=dataset,
|
||||
query=args["query"],
|
||||
account=current_user,
|
||||
external_retrieval_model=args["external_retrieval_model"],
|
||||
)
|
||||
|
||||
return response
|
||||
except Exception as e:
|
||||
raise InternalServerError(str(e))
|
||||
|
||||
|
||||
class BedrockRetrievalApi(Resource):
|
||||
# this api is only for internal testing
|
||||
def post(self):
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument("retrieval_setting", nullable=False, required=True, type=dict, location="json")
|
||||
parser.add_argument(
|
||||
"query",
|
||||
nullable=False,
|
||||
required=True,
|
||||
type=str,
|
||||
)
|
||||
parser.add_argument("knowledge_id", nullable=False, required=True, type=str)
|
||||
args = parser.parse_args()
|
||||
|
||||
# Call the knowledge retrieval service
|
||||
result = ExternalDatasetTestService.knowledge_retrieval(
|
||||
args["retrieval_setting"], args["query"], args["knowledge_id"]
|
||||
)
|
||||
return result, 200
|
||||
|
||||
|
||||
api.add_resource(ExternalKnowledgeHitTestingApi, "/datasets/<uuid:dataset_id>/external-hit-testing")
|
||||
api.add_resource(ExternalDatasetCreateApi, "/datasets/external")
|
||||
api.add_resource(ExternalApiTemplateListApi, "/datasets/external-knowledge-api")
|
||||
api.add_resource(ExternalApiTemplateApi, "/datasets/external-knowledge-api/<uuid:external_knowledge_api_id>")
|
||||
api.add_resource(ExternalApiUseCheckApi, "/datasets/external-knowledge-api/<uuid:external_knowledge_api_id>/use-check")
|
||||
# this api is only for internal test
|
||||
api.add_resource(BedrockRetrievalApi, "/test/retrieval")
|
||||
|
|
@ -47,6 +47,7 @@ class HitTestingApi(Resource):
|
|||
parser = reqparse.RequestParser()
|
||||
parser.add_argument("query", type=str, location="json")
|
||||
parser.add_argument("retrieval_model", type=dict, required=False, location="json")
|
||||
parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
|
||||
args = parser.parse_args()
|
||||
|
||||
HitTestingService.hit_testing_args_check(args)
|
||||
|
|
@ -57,6 +58,7 @@ class HitTestingApi(Resource):
|
|||
query=args["query"],
|
||||
account=current_user,
|
||||
retrieval_model=args["retrieval_model"],
|
||||
external_retrieval_model=args["external_retrieval_model"],
|
||||
limit=10,
|
||||
)
|
||||
|
||||
|
|
|
|||
|
|
@ -14,7 +14,9 @@ class WebsiteCrawlApi(Resource):
|
|||
@account_initialization_required
|
||||
def post(self):
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument("provider", type=str, choices=["firecrawl"], required=True, nullable=True, location="json")
|
||||
parser.add_argument(
|
||||
"provider", type=str, choices=["firecrawl", "jinareader"], required=True, nullable=True, location="json"
|
||||
)
|
||||
parser.add_argument("url", type=str, required=True, nullable=True, location="json")
|
||||
parser.add_argument("options", type=dict, required=True, nullable=True, location="json")
|
||||
args = parser.parse_args()
|
||||
|
|
@ -33,7 +35,7 @@ class WebsiteCrawlStatusApi(Resource):
|
|||
@account_initialization_required
|
||||
def get(self, job_id: str):
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument("provider", type=str, choices=["firecrawl"], required=True, location="args")
|
||||
parser.add_argument("provider", type=str, choices=["firecrawl", "jinareader"], required=True, location="args")
|
||||
args = parser.parse_args()
|
||||
# get crawl status
|
||||
try:
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@ from flask import request
|
|||
from flask_restful import Resource, reqparse
|
||||
|
||||
from configs import dify_config
|
||||
from libs.helper import StrLen, email, get_remote_ip
|
||||
from libs.helper import StrLen, email, extract_remote_ip
|
||||
from libs.password import valid_password
|
||||
from models.model import DifySetup
|
||||
from services.account_service import RegisterService, TenantService
|
||||
|
|
@ -46,7 +46,7 @@ class SetupApi(Resource):
|
|||
|
||||
# setup
|
||||
RegisterService.setup(
|
||||
email=args["email"], name=args["name"], password=args["password"], ip_address=get_remote_ip(request)
|
||||
email=args["email"], name=args["name"], password=args["password"], ip_address=extract_remote_ip(request)
|
||||
)
|
||||
|
||||
return {"result": "success"}, 201
|
||||
|
|
|
|||
|
|
@ -38,11 +38,52 @@ class VersionApi(Resource):
|
|||
return result
|
||||
|
||||
content = json.loads(response.content)
|
||||
result["version"] = content["version"]
|
||||
result["release_date"] = content["releaseDate"]
|
||||
result["release_notes"] = content["releaseNotes"]
|
||||
result["can_auto_update"] = content["canAutoUpdate"]
|
||||
if _has_new_version(latest_version=content["version"], current_version=f"{args.get('current_version')}"):
|
||||
result["version"] = content["version"]
|
||||
result["release_date"] = content["releaseDate"]
|
||||
result["release_notes"] = content["releaseNotes"]
|
||||
result["can_auto_update"] = content["canAutoUpdate"]
|
||||
return result
|
||||
|
||||
|
||||
def _has_new_version(*, latest_version: str, current_version: str) -> bool:
|
||||
def parse_version(version: str) -> tuple:
|
||||
# Split version into parts and pre-release suffix if any
|
||||
parts = version.split("-")
|
||||
version_parts = parts[0].split(".")
|
||||
pre_release = parts[1] if len(parts) > 1 else None
|
||||
|
||||
# Validate version format
|
||||
if len(version_parts) != 3:
|
||||
raise ValueError(f"Invalid version format: {version}")
|
||||
|
||||
try:
|
||||
# Convert version parts to integers
|
||||
major, minor, patch = map(int, version_parts)
|
||||
return (major, minor, patch, pre_release)
|
||||
except ValueError:
|
||||
raise ValueError(f"Invalid version format: {version}")
|
||||
|
||||
latest = parse_version(latest_version)
|
||||
current = parse_version(current_version)
|
||||
|
||||
# Compare major, minor, and patch versions
|
||||
for latest_part, current_part in zip(latest[:3], current[:3]):
|
||||
if latest_part > current_part:
|
||||
return True
|
||||
elif latest_part < current_part:
|
||||
return False
|
||||
|
||||
# If versions are equal, check pre-release suffixes
|
||||
if latest[3] is None and current[3] is not None:
|
||||
return True
|
||||
elif latest[3] is not None and current[3] is None:
|
||||
return False
|
||||
elif latest[3] is not None and current[3] is not None:
|
||||
# Simple string comparison for pre-release versions
|
||||
return latest[3] > current[3]
|
||||
|
||||
return False
|
||||
|
||||
|
||||
api.add_resource(VersionApi, "/version")
|
||||
|
|
|
|||
|
|
@ -126,13 +126,12 @@ class ModelProviderIconApi(Resource):
|
|||
Get model provider icon
|
||||
"""
|
||||
|
||||
@setup_required
|
||||
@login_required
|
||||
@account_initialization_required
|
||||
def get(self, provider: str, icon_type: str, lang: str):
|
||||
model_provider_service = ModelProviderService()
|
||||
icon, mimetype = model_provider_service.get_model_provider_icon(
|
||||
provider=provider, icon_type=icon_type, lang=lang
|
||||
provider=provider,
|
||||
icon_type=icon_type,
|
||||
lang=lang,
|
||||
)
|
||||
|
||||
return send_file(io.BytesIO(icon), mimetype=mimetype)
|
||||
|
|
|
|||
|
|
@ -72,8 +72,9 @@ class DefaultModelApi(Resource):
|
|||
provider=model_setting["provider"],
|
||||
model=model_setting["model"],
|
||||
)
|
||||
except Exception:
|
||||
logging.warning(f"{model_setting['model_type']} save error")
|
||||
except Exception as ex:
|
||||
logging.exception(f"{model_setting['model_type']} save error: {ex}")
|
||||
raise ex
|
||||
|
||||
return {"result": "success"}
|
||||
|
||||
|
|
|
|||
7
api/controllers/files/error.py
Normal file
7
api/controllers/files/error.py
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
from libs.exception import BaseHTTPException
|
||||
|
||||
|
||||
class UnsupportedFileTypeError(BaseHTTPException):
|
||||
error_code = "unsupported_file_type"
|
||||
description = "File type not allowed."
|
||||
code = 415
|
||||
|
|
@ -4,7 +4,7 @@ from werkzeug.exceptions import NotFound
|
|||
|
||||
import services
|
||||
from controllers.files import api
|
||||
from libs.exception import BaseHTTPException
|
||||
from controllers.files.error import UnsupportedFileTypeError
|
||||
from services.account_service import TenantService
|
||||
from services.file_service import FileService
|
||||
|
||||
|
|
@ -50,9 +50,3 @@ class WorkspaceWebappLogoApi(Resource):
|
|||
|
||||
api.add_resource(ImagePreviewApi, "/files/<uuid:file_id>/image-preview")
|
||||
api.add_resource(WorkspaceWebappLogoApi, "/files/workspaces/<uuid:workspace_id>/webapp-logo")
|
||||
|
||||
|
||||
class UnsupportedFileTypeError(BaseHTTPException):
|
||||
error_code = "unsupported_file_type"
|
||||
description = "File type not allowed."
|
||||
code = 415
|
||||
|
|
|
|||
|
|
@ -3,8 +3,8 @@ from flask_restful import Resource, reqparse
|
|||
from werkzeug.exceptions import Forbidden, NotFound
|
||||
|
||||
from controllers.files import api
|
||||
from controllers.files.error import UnsupportedFileTypeError
|
||||
from core.tools.tool_file_manager import ToolFileManager
|
||||
from libs.exception import BaseHTTPException
|
||||
|
||||
|
||||
class ToolFilePreviewApi(Resource):
|
||||
|
|
@ -43,9 +43,3 @@ class ToolFilePreviewApi(Resource):
|
|||
|
||||
|
||||
api.add_resource(ToolFilePreviewApi, "/files/tools/<uuid:file_id>.<string:extension>")
|
||||
|
||||
|
||||
class UnsupportedFileTypeError(BaseHTTPException):
|
||||
error_code = "unsupported_file_type"
|
||||
description = "File type not allowed."
|
||||
code = 415
|
||||
|
|
|
|||
|
|
@ -4,6 +4,7 @@ from flask_restful import Resource, reqparse
|
|||
from werkzeug.exceptions import InternalServerError, NotFound
|
||||
|
||||
import services
|
||||
from constants import UUID_NIL
|
||||
from controllers.service_api import api
|
||||
from controllers.service_api.app.error import (
|
||||
AppUnavailableError,
|
||||
|
|
@ -107,6 +108,7 @@ class ChatApi(Resource):
|
|||
parser.add_argument("conversation_id", type=uuid_value, location="json")
|
||||
parser.add_argument("retriever_from", type=str, required=False, default="dev", location="json")
|
||||
parser.add_argument("auto_generate_name", type=bool, required=False, default=True, location="json")
|
||||
parser.add_argument("parent_message_id", type=uuid_value, required=False, default=UUID_NIL, location="json")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
|
|
|
|||
|
|
@ -28,11 +28,11 @@ class DatasetListApi(DatasetApiResource):
|
|||
|
||||
page = request.args.get("page", default=1, type=int)
|
||||
limit = request.args.get("limit", default=20, type=int)
|
||||
provider = request.args.get("provider", default="vendor")
|
||||
# provider = request.args.get("provider", default="vendor")
|
||||
search = request.args.get("keyword", default=None, type=str)
|
||||
tag_ids = request.args.getlist("tag_ids")
|
||||
|
||||
datasets, total = DatasetService.get_datasets(page, limit, provider, tenant_id, current_user, search, tag_ids)
|
||||
datasets, total = DatasetService.get_datasets(page, limit, tenant_id, current_user, search, tag_ids)
|
||||
# check embedding setting
|
||||
provider_manager = ProviderManager()
|
||||
configurations = provider_manager.get_configurations(tenant_id=current_user.current_tenant_id)
|
||||
|
|
@ -82,6 +82,26 @@ class DatasetListApi(DatasetApiResource):
|
|||
required=False,
|
||||
nullable=False,
|
||||
)
|
||||
parser.add_argument(
|
||||
"external_knowledge_api_id",
|
||||
type=str,
|
||||
nullable=True,
|
||||
required=False,
|
||||
default="_validate_name",
|
||||
)
|
||||
parser.add_argument(
|
||||
"provider",
|
||||
type=str,
|
||||
nullable=True,
|
||||
required=False,
|
||||
default="vendor",
|
||||
)
|
||||
parser.add_argument(
|
||||
"external_knowledge_id",
|
||||
type=str,
|
||||
nullable=True,
|
||||
required=False,
|
||||
)
|
||||
args = parser.parse_args()
|
||||
|
||||
try:
|
||||
|
|
@ -91,6 +111,9 @@ class DatasetListApi(DatasetApiResource):
|
|||
indexing_technique=args["indexing_technique"],
|
||||
account=current_user,
|
||||
permission=args["permission"],
|
||||
provider=args["provider"],
|
||||
external_knowledge_api_id=args["external_knowledge_api_id"],
|
||||
external_knowledge_id=args["external_knowledge_id"],
|
||||
)
|
||||
except services.errors.dataset.DatasetNameDuplicateError:
|
||||
raise DatasetNameDuplicateError()
|
||||
|
|
|
|||
|
|
@ -369,7 +369,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):
|
|||
return message
|
||||
|
||||
def _organize_historic_prompt_messages(
|
||||
self, current_session_messages: list[PromptMessage] = None
|
||||
self, current_session_messages: Optional[list[PromptMessage]] = None
|
||||
) -> list[PromptMessage]:
|
||||
"""
|
||||
organize historic prompt messages
|
||||
|
|
|
|||
|
|
@ -27,7 +27,7 @@ class CotChatAgentRunner(CotAgentRunner):
|
|||
|
||||
return SystemPromptMessage(content=system_prompt)
|
||||
|
||||
def _organize_user_query(self, query, prompt_messages: list[PromptMessage] = None) -> list[PromptMessage]:
|
||||
def _organize_user_query(self, query, prompt_messages: list[PromptMessage]) -> list[PromptMessage]:
|
||||
"""
|
||||
Organize user query
|
||||
"""
|
||||
|
|
|
|||
|
|
@ -1,4 +1,5 @@
|
|||
import json
|
||||
from typing import Optional
|
||||
|
||||
from core.agent.cot_agent_runner import CotAgentRunner
|
||||
from core.model_runtime.entities.message_entities import AssistantPromptMessage, PromptMessage, UserPromptMessage
|
||||
|
|
@ -21,7 +22,7 @@ class CotCompletionAgentRunner(CotAgentRunner):
|
|||
|
||||
return system_prompt
|
||||
|
||||
def _organize_historic_prompt(self, current_session_messages: list[PromptMessage] = None) -> str:
|
||||
def _organize_historic_prompt(self, current_session_messages: Optional[list[PromptMessage]] = None) -> str:
|
||||
"""
|
||||
Organize historic prompt
|
||||
"""
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ import json
|
|||
import logging
|
||||
from collections.abc import Generator
|
||||
from copy import deepcopy
|
||||
from typing import Any, Union
|
||||
from typing import Any, Optional, Union
|
||||
|
||||
from core.agent.base_agent_runner import BaseAgentRunner
|
||||
from core.app.apps.base_app_queue_manager import PublishFrom
|
||||
|
|
@ -370,7 +370,7 @@ class FunctionCallAgentRunner(BaseAgentRunner):
|
|||
return tool_calls
|
||||
|
||||
def _init_system_message(
|
||||
self, prompt_template: str, prompt_messages: list[PromptMessage] = None
|
||||
self, prompt_template: str, prompt_messages: Optional[list[PromptMessage]] = None
|
||||
) -> list[PromptMessage]:
|
||||
"""
|
||||
Initialize system message
|
||||
|
|
@ -385,7 +385,7 @@ class FunctionCallAgentRunner(BaseAgentRunner):
|
|||
|
||||
return prompt_messages
|
||||
|
||||
def _organize_user_query(self, query, prompt_messages: list[PromptMessage] = None) -> list[PromptMessage]:
|
||||
def _organize_user_query(self, query, prompt_messages: list[PromptMessage]) -> list[PromptMessage]:
|
||||
"""
|
||||
Organize user query
|
||||
"""
|
||||
|
|
|
|||
|
|
@ -14,7 +14,7 @@ class CotAgentOutputParser:
|
|||
) -> Generator[Union[str, AgentScratchpadUnit.Action], None, None]:
|
||||
def parse_action(json_str):
|
||||
try:
|
||||
action = json.loads(json_str)
|
||||
action = json.loads(json_str, strict=False)
|
||||
action_name = None
|
||||
action_input = None
|
||||
|
||||
|
|
|
|||
|
|
@ -113,6 +113,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
|||
# always enable retriever resource in debugger mode
|
||||
app_config.additional_features.show_retrieve_source = True
|
||||
|
||||
workflow_run_id = str(uuid.uuid4())
|
||||
# init application generate entity
|
||||
application_generate_entity = AdvancedChatAppGenerateEntity(
|
||||
task_id=str(uuid.uuid4()),
|
||||
|
|
@ -127,6 +128,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
|||
invoke_from=invoke_from,
|
||||
extras=extras,
|
||||
trace_manager=trace_manager,
|
||||
workflow_run_id=workflow_run_id,
|
||||
)
|
||||
contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
|
||||
|
||||
|
|
|
|||
|
|
@ -149,6 +149,9 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
|
|||
SystemVariableKey.CONVERSATION_ID: self.conversation.id,
|
||||
SystemVariableKey.USER_ID: user_id,
|
||||
SystemVariableKey.DIALOGUE_COUNT: conversation_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,
|
||||
}
|
||||
|
||||
# init variable pool
|
||||
|
|
|
|||
|
|
@ -45,6 +45,7 @@ from core.app.entities.task_entities import (
|
|||
from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline
|
||||
from core.app.task_pipeline.message_cycle_manage import MessageCycleManage
|
||||
from core.app.task_pipeline.workflow_cycle_manage import WorkflowCycleManage
|
||||
from core.model_runtime.entities.llm_entities import LLMUsage
|
||||
from core.model_runtime.utils.encoders import jsonable_encoder
|
||||
from core.ops.ops_trace_manager import TraceQueueManager
|
||||
from core.workflow.enums import SystemVariableKey
|
||||
|
|
@ -55,6 +56,7 @@ from models.account import Account
|
|||
from models.model import Conversation, EndUser, Message
|
||||
from models.workflow import (
|
||||
Workflow,
|
||||
WorkflowNodeExecution,
|
||||
WorkflowRunStatus,
|
||||
)
|
||||
|
||||
|
|
@ -71,6 +73,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
|
|||
_workflow: Workflow
|
||||
_user: Union[Account, EndUser]
|
||||
_workflow_system_variables: dict[SystemVariableKey, Any]
|
||||
_wip_workflow_node_executions: dict[str, WorkflowNodeExecution]
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
|
|
@ -107,9 +110,14 @@ 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.APP_ID: application_generate_entity.app_config.app_id,
|
||||
SystemVariableKey.WORKFLOW_ID: workflow.id,
|
||||
SystemVariableKey.WORKFLOW_RUN_ID: application_generate_entity.workflow_run_id,
|
||||
}
|
||||
|
||||
self._task_state = WorkflowTaskState()
|
||||
self._wip_workflow_node_executions = {}
|
||||
|
||||
self._conversation_name_generate_thread = None
|
||||
|
||||
|
|
@ -231,7 +239,8 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
|
|||
except Exception as e:
|
||||
logger.error(e)
|
||||
break
|
||||
yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
|
||||
if tts_publisher:
|
||||
yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
|
||||
|
||||
def _process_stream_response(
|
||||
self,
|
||||
|
|
@ -504,6 +513,10 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
|
|||
self._message.total_price = usage.total_price
|
||||
self._message.currency = usage.currency
|
||||
|
||||
self._task_state.metadata["usage"] = jsonable_encoder(usage)
|
||||
else:
|
||||
self._task_state.metadata["usage"] = jsonable_encoder(LLMUsage.empty_usage())
|
||||
|
||||
db.session.commit()
|
||||
|
||||
message_was_created.send(
|
||||
|
|
|
|||
|
|
@ -99,6 +99,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
|
|||
user_id = user.id if isinstance(user, Account) else user.session_id
|
||||
trace_manager = TraceQueueManager(app_model.id, user_id)
|
||||
|
||||
workflow_run_id = str(uuid.uuid4())
|
||||
# init application generate entity
|
||||
application_generate_entity = WorkflowAppGenerateEntity(
|
||||
task_id=str(uuid.uuid4()),
|
||||
|
|
@ -110,6 +111,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
|
|||
invoke_from=invoke_from,
|
||||
call_depth=call_depth,
|
||||
trace_manager=trace_manager,
|
||||
workflow_run_id=workflow_run_id,
|
||||
)
|
||||
contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
|
||||
|
||||
|
|
|
|||
|
|
@ -90,6 +90,9 @@ class WorkflowAppRunner(WorkflowBasedAppRunner):
|
|||
system_inputs = {
|
||||
SystemVariableKey.FILES: files,
|
||||
SystemVariableKey.USER_ID: user_id,
|
||||
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,
|
||||
}
|
||||
|
||||
variable_pool = VariablePool(
|
||||
|
|
|
|||
|
|
@ -52,6 +52,7 @@ from models.workflow import (
|
|||
Workflow,
|
||||
WorkflowAppLog,
|
||||
WorkflowAppLogCreatedFrom,
|
||||
WorkflowNodeExecution,
|
||||
WorkflowRun,
|
||||
WorkflowRunStatus,
|
||||
)
|
||||
|
|
@ -69,6 +70,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
|
|||
_task_state: WorkflowTaskState
|
||||
_application_generate_entity: WorkflowAppGenerateEntity
|
||||
_workflow_system_variables: dict[SystemVariableKey, Any]
|
||||
_wip_workflow_node_executions: dict[str, WorkflowNodeExecution]
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
|
|
@ -97,9 +99,13 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
|
|||
self._workflow_system_variables = {
|
||||
SystemVariableKey.FILES: application_generate_entity.files,
|
||||
SystemVariableKey.USER_ID: user_id,
|
||||
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,
|
||||
}
|
||||
|
||||
self._task_state = WorkflowTaskState()
|
||||
self._wip_workflow_node_executions = {}
|
||||
|
||||
def process(self) -> Union[WorkflowAppBlockingResponse, Generator[WorkflowAppStreamResponse, None, None]]:
|
||||
"""
|
||||
|
|
@ -212,7 +218,8 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
|
|||
except Exception as e:
|
||||
logger.error(e)
|
||||
break
|
||||
yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
|
||||
if tts_publisher:
|
||||
yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
|
||||
|
||||
def _process_stream_response(
|
||||
self,
|
||||
|
|
|
|||
|
|
@ -152,6 +152,7 @@ class AdvancedChatAppGenerateEntity(AppGenerateEntity):
|
|||
|
||||
conversation_id: Optional[str] = None
|
||||
parent_message_id: Optional[str] = None
|
||||
workflow_run_id: Optional[str] = None
|
||||
query: str
|
||||
|
||||
class SingleIterationRunEntity(BaseModel):
|
||||
|
|
@ -172,6 +173,7 @@ class WorkflowAppGenerateEntity(AppGenerateEntity):
|
|||
|
||||
# app config
|
||||
app_config: WorkflowUIBasedAppConfig
|
||||
workflow_run_id: Optional[str] = None
|
||||
|
||||
class SingleIterationRunEntity(BaseModel):
|
||||
"""
|
||||
|
|
|
|||
|
|
@ -1,2 +1,2 @@
|
|||
class VariableError(Exception):
|
||||
class VariableError(ValueError):
|
||||
pass
|
||||
|
|
|
|||
|
|
@ -248,7 +248,8 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
|
|||
else:
|
||||
start_listener_time = time.time()
|
||||
yield MessageAudioStreamResponse(audio=audio.audio, task_id=task_id)
|
||||
yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
|
||||
if publisher:
|
||||
yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
|
||||
|
||||
def _process_stream_response(
|
||||
self, publisher: AppGeneratorTTSPublisher, trace_manager: Optional[TraceQueueManager] = None
|
||||
|
|
|
|||
|
|
@ -1,8 +1,10 @@
|
|||
import logging
|
||||
from threading import Thread
|
||||
from typing import Optional, Union
|
||||
|
||||
from flask import Flask, current_app
|
||||
|
||||
from configs import dify_config
|
||||
from core.app.entities.app_invoke_entities import (
|
||||
AdvancedChatAppGenerateEntity,
|
||||
AgentChatAppGenerateEntity,
|
||||
|
|
@ -82,7 +84,9 @@ class MessageCycleManage:
|
|||
try:
|
||||
name = LLMGenerator.generate_conversation_name(app_model.tenant_id, query)
|
||||
conversation.name = name
|
||||
except:
|
||||
except Exception as e:
|
||||
if dify_config.DEBUG:
|
||||
logging.exception(f"generate conversation name failed: {e}")
|
||||
pass
|
||||
|
||||
db.session.merge(conversation)
|
||||
|
|
|
|||
|
|
@ -57,6 +57,7 @@ class WorkflowCycleManage:
|
|||
_user: Union[Account, EndUser]
|
||||
_task_state: WorkflowTaskState
|
||||
_workflow_system_variables: dict[SystemVariableKey, Any]
|
||||
_wip_workflow_node_executions: dict[str, WorkflowNodeExecution]
|
||||
|
||||
def _handle_workflow_run_start(self) -> WorkflowRun:
|
||||
max_sequence = (
|
||||
|
|
@ -85,6 +86,9 @@ class WorkflowCycleManage:
|
|||
|
||||
# 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
|
||||
|
|
@ -248,6 +252,8 @@ class WorkflowCycleManage:
|
|||
db.session.refresh(workflow_node_execution)
|
||||
db.session.close()
|
||||
|
||||
self._wip_workflow_node_executions[workflow_node_execution.node_execution_id] = workflow_node_execution
|
||||
|
||||
return workflow_node_execution
|
||||
|
||||
def _handle_workflow_node_execution_success(self, event: QueueNodeSucceededEvent) -> WorkflowNodeExecution:
|
||||
|
|
@ -260,20 +266,36 @@ class WorkflowCycleManage:
|
|||
|
||||
inputs = WorkflowEntry.handle_special_values(event.inputs)
|
||||
outputs = WorkflowEntry.handle_special_values(event.outputs)
|
||||
execution_metadata = (
|
||||
json.dumps(jsonable_encoder(event.execution_metadata)) if event.execution_metadata else None
|
||||
)
|
||||
finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
|
||||
elapsed_time = (finished_at - event.start_at).total_seconds()
|
||||
|
||||
db.session.query(WorkflowNodeExecution).filter(WorkflowNodeExecution.id == workflow_node_execution.id).update(
|
||||
{
|
||||
WorkflowNodeExecution.status: WorkflowNodeExecutionStatus.SUCCEEDED.value,
|
||||
WorkflowNodeExecution.inputs: json.dumps(inputs) if inputs else None,
|
||||
WorkflowNodeExecution.process_data: json.dumps(event.process_data) if event.process_data else None,
|
||||
WorkflowNodeExecution.outputs: json.dumps(outputs) if outputs else None,
|
||||
WorkflowNodeExecution.execution_metadata: execution_metadata,
|
||||
WorkflowNodeExecution.finished_at: finished_at,
|
||||
WorkflowNodeExecution.elapsed_time: elapsed_time,
|
||||
}
|
||||
)
|
||||
|
||||
db.session.commit()
|
||||
db.session.close()
|
||||
|
||||
workflow_node_execution.status = WorkflowNodeExecutionStatus.SUCCEEDED.value
|
||||
workflow_node_execution.inputs = json.dumps(inputs) if inputs else None
|
||||
workflow_node_execution.process_data = json.dumps(event.process_data) if event.process_data else None
|
||||
workflow_node_execution.outputs = json.dumps(outputs) if outputs else None
|
||||
workflow_node_execution.execution_metadata = (
|
||||
json.dumps(jsonable_encoder(event.execution_metadata)) if event.execution_metadata else None
|
||||
)
|
||||
workflow_node_execution.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
|
||||
workflow_node_execution.elapsed_time = (workflow_node_execution.finished_at - event.start_at).total_seconds()
|
||||
workflow_node_execution.execution_metadata = execution_metadata
|
||||
workflow_node_execution.finished_at = finished_at
|
||||
workflow_node_execution.elapsed_time = elapsed_time
|
||||
|
||||
db.session.commit()
|
||||
db.session.refresh(workflow_node_execution)
|
||||
db.session.close()
|
||||
self._wip_workflow_node_executions.pop(workflow_node_execution.node_execution_id)
|
||||
|
||||
return workflow_node_execution
|
||||
|
||||
|
|
@ -287,18 +309,33 @@ class WorkflowCycleManage:
|
|||
|
||||
inputs = WorkflowEntry.handle_special_values(event.inputs)
|
||||
outputs = WorkflowEntry.handle_special_values(event.outputs)
|
||||
finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
|
||||
elapsed_time = (finished_at - event.start_at).total_seconds()
|
||||
|
||||
db.session.query(WorkflowNodeExecution).filter(WorkflowNodeExecution.id == workflow_node_execution.id).update(
|
||||
{
|
||||
WorkflowNodeExecution.status: WorkflowNodeExecutionStatus.FAILED.value,
|
||||
WorkflowNodeExecution.error: event.error,
|
||||
WorkflowNodeExecution.inputs: json.dumps(inputs) if inputs else None,
|
||||
WorkflowNodeExecution.process_data: json.dumps(event.process_data) if event.process_data else None,
|
||||
WorkflowNodeExecution.outputs: json.dumps(outputs) if outputs else None,
|
||||
WorkflowNodeExecution.finished_at: finished_at,
|
||||
WorkflowNodeExecution.elapsed_time: elapsed_time,
|
||||
}
|
||||
)
|
||||
|
||||
db.session.commit()
|
||||
db.session.close()
|
||||
|
||||
workflow_node_execution.status = WorkflowNodeExecutionStatus.FAILED.value
|
||||
workflow_node_execution.error = event.error
|
||||
workflow_node_execution.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
|
||||
workflow_node_execution.inputs = json.dumps(inputs) if inputs else None
|
||||
workflow_node_execution.process_data = json.dumps(event.process_data) if event.process_data else None
|
||||
workflow_node_execution.outputs = json.dumps(outputs) if outputs else None
|
||||
workflow_node_execution.elapsed_time = (workflow_node_execution.finished_at - event.start_at).total_seconds()
|
||||
workflow_node_execution.finished_at = finished_at
|
||||
workflow_node_execution.elapsed_time = elapsed_time
|
||||
|
||||
db.session.commit()
|
||||
db.session.refresh(workflow_node_execution)
|
||||
db.session.close()
|
||||
self._wip_workflow_node_executions.pop(workflow_node_execution.node_execution_id)
|
||||
|
||||
return workflow_node_execution
|
||||
|
||||
|
|
@ -675,17 +712,7 @@ class WorkflowCycleManage:
|
|||
:param node_execution_id: workflow node execution id
|
||||
:return:
|
||||
"""
|
||||
workflow_node_execution = (
|
||||
db.session.query(WorkflowNodeExecution)
|
||||
.filter(
|
||||
WorkflowNodeExecution.tenant_id == self._application_generate_entity.app_config.tenant_id,
|
||||
WorkflowNodeExecution.app_id == self._application_generate_entity.app_config.app_id,
|
||||
WorkflowNodeExecution.workflow_id == self._workflow.id,
|
||||
WorkflowNodeExecution.triggered_from == WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN.value,
|
||||
WorkflowNodeExecution.node_execution_id == node_execution_id,
|
||||
)
|
||||
.first()
|
||||
)
|
||||
workflow_node_execution = self._wip_workflow_node_executions.get(node_execution_id)
|
||||
|
||||
if not workflow_node_execution:
|
||||
raise Exception(f"Workflow node execution not found: {node_execution_id}")
|
||||
|
|
|
|||
|
|
@ -1,9 +1,9 @@
|
|||
import os
|
||||
from collections.abc import Mapping, Sequence
|
||||
from typing import Any, Optional, TextIO, Union
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from configs import dify_config
|
||||
from core.ops.entities.trace_entity import TraceTaskName
|
||||
from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
|
||||
from core.tools.entities.tool_entities import ToolInvokeMessage
|
||||
|
|
@ -50,7 +50,8 @@ class DifyAgentCallbackHandler(BaseModel):
|
|||
tool_inputs: Mapping[str, Any],
|
||||
) -> None:
|
||||
"""Do nothing."""
|
||||
print_text("\n[on_tool_start] ToolCall:" + tool_name + "\n" + str(tool_inputs) + "\n", color=self.color)
|
||||
if dify_config.DEBUG:
|
||||
print_text("\n[on_tool_start] ToolCall:" + tool_name + "\n" + str(tool_inputs) + "\n", color=self.color)
|
||||
|
||||
def on_tool_end(
|
||||
self,
|
||||
|
|
@ -62,11 +63,12 @@ class DifyAgentCallbackHandler(BaseModel):
|
|||
trace_manager: Optional[TraceQueueManager] = None,
|
||||
) -> None:
|
||||
"""If not the final action, print out observation."""
|
||||
print_text("\n[on_tool_end]\n", color=self.color)
|
||||
print_text("Tool: " + tool_name + "\n", color=self.color)
|
||||
print_text("Inputs: " + str(tool_inputs) + "\n", color=self.color)
|
||||
print_text("Outputs: " + str(tool_outputs)[:1000] + "\n", color=self.color)
|
||||
print_text("\n")
|
||||
if dify_config.DEBUG:
|
||||
print_text("\n[on_tool_end]\n", color=self.color)
|
||||
print_text("Tool: " + tool_name + "\n", color=self.color)
|
||||
print_text("Inputs: " + str(tool_inputs) + "\n", color=self.color)
|
||||
print_text("Outputs: " + str(tool_outputs)[:1000] + "\n", color=self.color)
|
||||
print_text("\n")
|
||||
|
||||
if trace_manager:
|
||||
trace_manager.add_trace_task(
|
||||
|
|
@ -82,30 +84,33 @@ class DifyAgentCallbackHandler(BaseModel):
|
|||
|
||||
def on_tool_error(self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any) -> None:
|
||||
"""Do nothing."""
|
||||
print_text("\n[on_tool_error] Error: " + str(error) + "\n", color="red")
|
||||
if dify_config.DEBUG:
|
||||
print_text("\n[on_tool_error] Error: " + str(error) + "\n", color="red")
|
||||
|
||||
def on_agent_start(self, thought: str) -> None:
|
||||
"""Run on agent start."""
|
||||
if thought:
|
||||
print_text(
|
||||
"\n[on_agent_start] \nCurrent Loop: " + str(self.current_loop) + "\nThought: " + thought + "\n",
|
||||
color=self.color,
|
||||
)
|
||||
else:
|
||||
print_text("\n[on_agent_start] \nCurrent Loop: " + str(self.current_loop) + "\n", color=self.color)
|
||||
if dify_config.DEBUG:
|
||||
if thought:
|
||||
print_text(
|
||||
"\n[on_agent_start] \nCurrent Loop: " + str(self.current_loop) + "\nThought: " + thought + "\n",
|
||||
color=self.color,
|
||||
)
|
||||
else:
|
||||
print_text("\n[on_agent_start] \nCurrent Loop: " + str(self.current_loop) + "\n", color=self.color)
|
||||
|
||||
def on_agent_finish(self, color: Optional[str] = None, **kwargs: Any) -> None:
|
||||
"""Run on agent end."""
|
||||
print_text("\n[on_agent_finish]\n Loop: " + str(self.current_loop) + "\n", color=self.color)
|
||||
if dify_config.DEBUG:
|
||||
print_text("\n[on_agent_finish]\n Loop: " + str(self.current_loop) + "\n", color=self.color)
|
||||
|
||||
self.current_loop += 1
|
||||
|
||||
@property
|
||||
def ignore_agent(self) -> bool:
|
||||
"""Whether to ignore agent callbacks."""
|
||||
return not os.environ.get("DEBUG") or os.environ.get("DEBUG").lower() != "true"
|
||||
return not dify_config.DEBUG
|
||||
|
||||
@property
|
||||
def ignore_chat_model(self) -> bool:
|
||||
"""Whether to ignore chat model callbacks."""
|
||||
return not os.environ.get("DEBUG") or os.environ.get("DEBUG").lower() != "true"
|
||||
return not dify_config.DEBUG
|
||||
|
|
|
|||
|
|
@ -44,7 +44,6 @@ class DatasetIndexToolCallbackHandler:
|
|||
DocumentSegment.index_node_id == document.metadata["doc_id"]
|
||||
)
|
||||
|
||||
# if 'dataset_id' in document.metadata:
|
||||
if "dataset_id" in document.metadata:
|
||||
query = query.filter(DocumentSegment.dataset_id == document.metadata["dataset_id"])
|
||||
|
||||
|
|
@ -59,7 +58,7 @@ class DatasetIndexToolCallbackHandler:
|
|||
for item in resource:
|
||||
dataset_retriever_resource = DatasetRetrieverResource(
|
||||
message_id=self._message_id,
|
||||
position=item.get("position"),
|
||||
position=item.get("position") or 0,
|
||||
dataset_id=item.get("dataset_id"),
|
||||
dataset_name=item.get("dataset_name"),
|
||||
document_id=item.get("document_id"),
|
||||
|
|
|
|||
|
|
@ -5,6 +5,7 @@ from typing import Optional, cast
|
|||
import numpy as np
|
||||
from sqlalchemy.exc import IntegrityError
|
||||
|
||||
from configs import dify_config
|
||||
from core.embedding.embedding_constant import EmbeddingInputType
|
||||
from core.model_manager import ModelInstance
|
||||
from core.model_runtime.entities.model_entities import ModelPropertyKey
|
||||
|
|
@ -110,6 +111,8 @@ class CacheEmbedding(Embeddings):
|
|||
embedding_results = embedding_result.embeddings[0]
|
||||
embedding_results = (embedding_results / np.linalg.norm(embedding_results)).tolist()
|
||||
except Exception as ex:
|
||||
if dify_config.DEBUG:
|
||||
logging.exception(f"Failed to embed query text: {ex}")
|
||||
raise ex
|
||||
|
||||
try:
|
||||
|
|
@ -122,6 +125,8 @@ class CacheEmbedding(Embeddings):
|
|||
encoded_str = encoded_vector.decode("utf-8")
|
||||
redis_client.setex(embedding_cache_key, 600, encoded_str)
|
||||
except Exception as ex:
|
||||
logging.exception("Failed to add embedding to redis %s", ex)
|
||||
if dify_config.DEBUG:
|
||||
logging.exception("Failed to add embedding to redis %s", ex)
|
||||
raise ex
|
||||
|
||||
return embedding_results
|
||||
|
|
|
|||
|
|
@ -119,7 +119,7 @@ class ProviderConfiguration(BaseModel):
|
|||
credentials = model_configuration.credentials
|
||||
break
|
||||
|
||||
if self.custom_configuration.provider:
|
||||
if not credentials and self.custom_configuration.provider:
|
||||
credentials = self.custom_configuration.provider.credentials
|
||||
|
||||
return credentials
|
||||
|
|
|
|||
|
|
@ -198,16 +198,34 @@ class MessageFileParser:
|
|||
if "amazonaws.com" not in parsed_url.netloc:
|
||||
return False
|
||||
query_params = parse_qs(parsed_url.query)
|
||||
required_params = ["Signature", "Expires"]
|
||||
for param in required_params:
|
||||
if param not in query_params:
|
||||
|
||||
def check_presign_v2(query_params):
|
||||
required_params = ["Signature", "Expires"]
|
||||
for param in required_params:
|
||||
if param not in query_params:
|
||||
return False
|
||||
if not query_params["Expires"][0].isdigit():
|
||||
return False
|
||||
if not query_params["Expires"][0].isdigit():
|
||||
return False
|
||||
signature = query_params["Signature"][0]
|
||||
if not re.match(r"^[A-Za-z0-9+/]+={0,2}$", signature):
|
||||
return False
|
||||
return True
|
||||
signature = query_params["Signature"][0]
|
||||
if not re.match(r"^[A-Za-z0-9+/]+={0,2}$", signature):
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
def check_presign_v4(query_params):
|
||||
required_params = ["X-Amz-Signature", "X-Amz-Expires"]
|
||||
for param in required_params:
|
||||
if param not in query_params:
|
||||
return False
|
||||
if not query_params["X-Amz-Expires"][0].isdigit():
|
||||
return False
|
||||
signature = query_params["X-Amz-Signature"][0]
|
||||
if not re.match(r"^[A-Za-z0-9+/]+={0,2}$", signature):
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
return check_presign_v4(query_params) or check_presign_v2(query_params)
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
|
|
|||
|
|
@ -211,9 +211,9 @@ class IndexingRunner:
|
|||
tenant_id: str,
|
||||
extract_settings: list[ExtractSetting],
|
||||
tmp_processing_rule: dict,
|
||||
doc_form: str = None,
|
||||
doc_form: Optional[str] = None,
|
||||
doc_language: str = "English",
|
||||
dataset_id: str = None,
|
||||
dataset_id: Optional[str] = None,
|
||||
indexing_technique: str = "economy",
|
||||
) -> dict:
|
||||
"""
|
||||
|
|
|
|||
|
|
@ -58,7 +58,11 @@ class TokenBufferMemory:
|
|||
# instead of all messages from the conversation, we only need to extract messages
|
||||
# that belong to the thread of last message
|
||||
thread_messages = extract_thread_messages(messages)
|
||||
thread_messages.pop(0)
|
||||
|
||||
# for newly created message, its answer is temporarily empty, we don't need to add it to memory
|
||||
if thread_messages and not thread_messages[0].answer:
|
||||
thread_messages.pop(0)
|
||||
|
||||
messages = list(reversed(thread_messages))
|
||||
|
||||
message_file_parser = MessageFileParser(tenant_id=app_record.tenant_id, app_id=app_record.id)
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
from abc import ABC, abstractmethod
|
||||
from typing import Optional
|
||||
|
||||
from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk
|
||||
|
|
@ -13,7 +14,7 @@ _TEXT_COLOR_MAPPING = {
|
|||
}
|
||||
|
||||
|
||||
class Callback:
|
||||
class Callback(ABC):
|
||||
"""
|
||||
Base class for callbacks.
|
||||
Only for LLM.
|
||||
|
|
@ -21,6 +22,7 @@ class Callback:
|
|||
|
||||
raise_error: bool = False
|
||||
|
||||
@abstractmethod
|
||||
def on_before_invoke(
|
||||
self,
|
||||
llm_instance: AIModel,
|
||||
|
|
@ -48,6 +50,7 @@ class Callback:
|
|||
"""
|
||||
raise NotImplementedError()
|
||||
|
||||
@abstractmethod
|
||||
def on_new_chunk(
|
||||
self,
|
||||
llm_instance: AIModel,
|
||||
|
|
@ -77,6 +80,7 @@ class Callback:
|
|||
"""
|
||||
raise NotImplementedError()
|
||||
|
||||
@abstractmethod
|
||||
def on_after_invoke(
|
||||
self,
|
||||
llm_instance: AIModel,
|
||||
|
|
@ -106,6 +110,7 @@ class Callback:
|
|||
"""
|
||||
raise NotImplementedError()
|
||||
|
||||
@abstractmethod
|
||||
def on_invoke_error(
|
||||
self,
|
||||
llm_instance: AIModel,
|
||||
|
|
|
|||
|
|
@ -0,0 +1,310 @@
|
|||
## Custom Integration of Pre-defined Models
|
||||
|
||||
### Introduction
|
||||
|
||||
After completing the vendors integration, the next step is to connect the vendor's models. To illustrate the entire connection process, we will use Xinference as an example to demonstrate a complete vendor integration.
|
||||
|
||||
It is important to note that for custom models, each model connection requires a complete vendor credential.
|
||||
|
||||
Unlike pre-defined models, a custom vendor integration always includes the following two parameters, which do not need to be defined in the vendor YAML file.
|
||||
|
||||
|
||||
|
||||
As mentioned earlier, vendors do not need to implement validate_provider_credential. The runtime will automatically call the corresponding model layer's validate_credentials to validate the credentials based on the model type and name selected by the user.
|
||||
|
||||
### Writing the Vendor YAML
|
||||
|
||||
First, we need to identify the types of models supported by the vendor we are integrating.
|
||||
|
||||
Currently supported model types are as follows:
|
||||
|
||||
- `llm` Text Generation Models
|
||||
|
||||
- `text_embedding` Text Embedding Models
|
||||
|
||||
- `rerank` Rerank Models
|
||||
|
||||
- `speech2text` Speech-to-Text
|
||||
|
||||
- `tts` Text-to-Speech
|
||||
|
||||
- `moderation` Moderation
|
||||
|
||||
Xinference supports LLM, Text Embedding, and Rerank. So we will start by writing xinference.yaml.
|
||||
|
||||
```yaml
|
||||
provider: xinference #Define the vendor identifier
|
||||
label: # Vendor display name, supports both en_US (English) and zh_Hans (Simplified Chinese). If zh_Hans is not set, it will use en_US by default.
|
||||
en_US: Xorbits Inference
|
||||
icon_small: # Small icon, refer to other vendors' icons stored in the _assets directory within the vendor implementation directory; follows the same language policy as the label
|
||||
en_US: icon_s_en.svg
|
||||
icon_large: # Large icon
|
||||
en_US: icon_l_en.svg
|
||||
help: # Help information
|
||||
title:
|
||||
en_US: How to deploy Xinference
|
||||
zh_Hans: 如何部署 Xinference
|
||||
url:
|
||||
en_US: https://github.com/xorbitsai/inference
|
||||
supported_model_types: # Supported model types. Xinference supports LLM, Text Embedding, and Rerank
|
||||
- llm
|
||||
- text-embedding
|
||||
- rerank
|
||||
configurate_methods: # Since Xinference is a locally deployed vendor with no predefined models, users need to deploy whatever models they need according to Xinference documentation. Thus, it only supports custom models.
|
||||
- customizable-model
|
||||
provider_credential_schema:
|
||||
credential_form_schemas:
|
||||
```
|
||||
|
||||
|
||||
Then, we need to determine what credentials are required to define a model in Xinference.
|
||||
|
||||
- Since it supports three different types of models, we need to specify the model_type to denote the model type. Here is how we can define it:
|
||||
|
||||
```yaml
|
||||
provider_credential_schema:
|
||||
credential_form_schemas:
|
||||
- variable: model_type
|
||||
type: select
|
||||
label:
|
||||
en_US: Model type
|
||||
zh_Hans: 模型类型
|
||||
required: true
|
||||
options:
|
||||
- value: text-generation
|
||||
label:
|
||||
en_US: Language Model
|
||||
zh_Hans: 语言模型
|
||||
- value: embeddings
|
||||
label:
|
||||
en_US: Text Embedding
|
||||
- value: reranking
|
||||
label:
|
||||
en_US: Rerank
|
||||
```
|
||||
|
||||
- Next, each model has its own model_name, so we need to define that here:
|
||||
|
||||
```yaml
|
||||
- variable: model_name
|
||||
type: text-input
|
||||
label:
|
||||
en_US: Model name
|
||||
zh_Hans: 模型名称
|
||||
required: true
|
||||
placeholder:
|
||||
zh_Hans: 填写模型名称
|
||||
en_US: Input model name
|
||||
```
|
||||
|
||||
- Specify the Xinference local deployment address:
|
||||
|
||||
```yaml
|
||||
- variable: server_url
|
||||
label:
|
||||
zh_Hans: 服务器URL
|
||||
en_US: Server url
|
||||
type: text-input
|
||||
required: true
|
||||
placeholder:
|
||||
zh_Hans: 在此输入Xinference的服务器地址，如 https://example.com/xxx
|
||||
en_US: Enter the url of your Xinference, for example https://example.com/xxx
|
||||
```
|
||||
|
||||
- Each model has a unique model_uid, so we also need to define that here:
|
||||
|
||||
```yaml
|
||||
- variable: model_uid
|
||||
label:
|
||||
zh_Hans: 模型UID
|
||||
en_US: Model uid
|
||||
type: text-input
|
||||
required: true
|
||||
placeholder:
|
||||
zh_Hans: 在此输入您的Model UID
|
||||
en_US: Enter the model uid
|
||||
```
|
||||
|
||||
Now, we have completed the basic definition of the vendor.
|
||||
|
||||
### Writing the Model Code
|
||||
|
||||
Next, let's take the `llm` type as an example and write `xinference.llm.llm.py`.
|
||||
|
||||
In `llm.py`, create a Xinference LLM class, we name it `XinferenceAILargeLanguageModel` (this can be arbitrary), inheriting from the `__base.large_language_model.LargeLanguageModel` base class, and implement the following methods:
|
||||
|
||||
- LLM Invocation
|
||||
|
||||
Implement the core method for LLM invocation, supporting both stream and synchronous responses.
|
||||
|
||||
```python
|
||||
def _invoke(self, model: str, credentials: dict,
|
||||
prompt_messages: list[PromptMessage], model_parameters: dict,
|
||||
tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
|
||||
stream: bool = True, user: Optional[str] = None) \
|
||||
-> Union[LLMResult, Generator]:
|
||||
"""
|
||||
Invoke large language model
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:param prompt_messages: prompt messages
|
||||
:param model_parameters: model parameters
|
||||
:param tools: tools for tool usage
|
||||
:param stop: stop words
|
||||
:param stream: is the response a stream
|
||||
:param user: unique user id
|
||||
:return: full response or stream response chunk generator result
|
||||
"""
|
||||
```
|
||||
|
||||
When implementing, ensure to use two functions to return data separately for synchronous and stream responses. This is important because Python treats functions containing the `yield` keyword as generator functions, mandating them to return `Generator` types. Here’s an example (note that the example uses simplified parameters; in real implementation, use the parameter list as defined above):
|
||||
|
||||
```python
|
||||
def _invoke(self, stream: bool, **kwargs) \
|
||||
-> Union[LLMResult, Generator]:
|
||||
if stream:
|
||||
return self._handle_stream_response(**kwargs)
|
||||
return self._handle_sync_response(**kwargs)
|
||||
|
||||
def _handle_stream_response(self, **kwargs) -> Generator:
|
||||
for chunk in response:
|
||||
yield chunk
|
||||
def _handle_sync_response(self, **kwargs) -> LLMResult:
|
||||
return LLMResult(**response)
|
||||
```
|
||||
|
||||
- Pre-compute Input Tokens
|
||||
|
||||
If the model does not provide an interface for pre-computing tokens, you can return 0 directly.
|
||||
|
||||
```python
|
||||
def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],tools: Optional[list[PromptMessageTool]] = None) -> int:
|
||||
"""
|
||||
Get number of tokens for given prompt messages
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:param prompt_messages: prompt messages
|
||||
:param tools: tools for tool usage
|
||||
:return: token count
|
||||
"""
|
||||
```
|
||||
|
||||
|
||||
Sometimes, you might not want to return 0 directly. In such cases, you can use `self._get_num_tokens_by_gpt2(text: str)` to get pre-computed tokens. This method is provided by the `AIModel` base class, and it uses GPT2's Tokenizer for calculation. However, it should be noted that this is only a substitute and may not be fully accurate.
|
||||
|
||||
- Model Credentials Validation
|
||||
|
||||
Similar to vendor credentials validation, this method validates individual model credentials.
|
||||
|
||||
```python
|
||||
def validate_credentials(self, model: str, credentials: dict) -> None:
|
||||
"""
|
||||
Validate model credentials
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:return: None
|
||||
"""
|
||||
```
|
||||
|
||||
- Model Parameter Schema
|
||||
|
||||
Unlike custom types, since the YAML file does not define which parameters a model supports, we need to dynamically generate the model parameter schema.
|
||||
|
||||
For instance, Xinference supports `max_tokens`, `temperature`, and `top_p` parameters.
|
||||
|
||||
However, some vendors may support different parameters for different models. For example, the `OpenLLM` vendor supports `top_k`, but not all models provided by this vendor support `top_k`. Let's say model A supports `top_k` but model B does not. In such cases, we need to dynamically generate the model parameter schema, as illustrated below:
|
||||
|
||||
```python
|
||||
def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity | None:
|
||||
"""
|
||||
used to define customizable model schema
|
||||
"""
|
||||
rules = [
|
||||
ParameterRule(
|
||||
name='temperature', type=ParameterType.FLOAT,
|
||||
use_template='temperature',
|
||||
label=I18nObject(
|
||||
zh_Hans='温度', en_US='Temperature'
|
||||
)
|
||||
),
|
||||
ParameterRule(
|
||||
name='top_p', type=ParameterType.FLOAT,
|
||||
use_template='top_p',
|
||||
label=I18nObject(
|
||||
zh_Hans='Top P', en_US='Top P'
|
||||
)
|
||||
),
|
||||
ParameterRule(
|
||||
name='max_tokens', type=ParameterType.INT,
|
||||
use_template='max_tokens',
|
||||
min=1,
|
||||
default=512,
|
||||
label=I18nObject(
|
||||
zh_Hans='最大生成长度', en_US='Max Tokens'
|
||||
)
|
||||
)
|
||||
]
|
||||
|
||||
# if model is A, add top_k to rules
|
||||
if model == 'A':
|
||||
rules.append(
|
||||
ParameterRule(
|
||||
name='top_k', type=ParameterType.INT,
|
||||
use_template='top_k',
|
||||
min=1,
|
||||
default=50,
|
||||
label=I18nObject(
|
||||
zh_Hans='Top K', en_US='Top K'
|
||||
)
|
||||
)
|
||||
)
|
||||
|
||||
"""
|
||||
some NOT IMPORTANT code here
|
||||
"""
|
||||
|
||||
entity = AIModelEntity(
|
||||
model=model,
|
||||
label=I18nObject(
|
||||
en_US=model
|
||||
),
|
||||
fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
|
||||
model_type=model_type,
|
||||
model_properties={
|
||||
ModelPropertyKey.MODE: ModelType.LLM,
|
||||
},
|
||||
parameter_rules=rules
|
||||
)
|
||||
|
||||
return entity
|
||||
```
|
||||
|
||||
- Exception Error Mapping
|
||||
|
||||
When a model invocation error occurs, it should be mapped to the runtime's specified `InvokeError` type, enabling Dify to handle different errors appropriately.
|
||||
|
||||
Runtime Errors:
|
||||
|
||||
- `InvokeConnectionError` Connection error during invocation
|
||||
- `InvokeServerUnavailableError` Service provider unavailable
|
||||
- `InvokeRateLimitError` Rate limit reached
|
||||
- `InvokeAuthorizationError` Authorization failure
|
||||
- `InvokeBadRequestError` Invalid request parameters
|
||||
|
||||
```python
|
||||
@property
|
||||
def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
|
||||
"""
|
||||
Map model invoke error to unified error
|
||||
The key is the error type thrown to the caller
|
||||
The value is the error type thrown by the model,
|
||||
which needs to be converted into a unified error type for the caller.
|
||||
|
||||
:return: Invoke error mapping
|
||||
"""
|
||||
```
|
||||
|
||||
For interface method details, see: [Interfaces](./interfaces.md). For specific implementations, refer to: [llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py).
|
||||
BIN
api/core/model_runtime/docs/en_US/images/index/image-1.png
Normal file
BIN
api/core/model_runtime/docs/en_US/images/index/image-1.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 230 KiB |
BIN
api/core/model_runtime/docs/en_US/images/index/image-2.png
Normal file
BIN
api/core/model_runtime/docs/en_US/images/index/image-2.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 205 KiB |
BIN
api/core/model_runtime/docs/en_US/images/index/image-3.png
Normal file
BIN
api/core/model_runtime/docs/en_US/images/index/image-3.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 44 KiB |
BIN
api/core/model_runtime/docs/en_US/images/index/image.png
Normal file
BIN
api/core/model_runtime/docs/en_US/images/index/image.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 262 KiB |
173
api/core/model_runtime/docs/en_US/predefined_model_scale_out.md
Normal file
173
api/core/model_runtime/docs/en_US/predefined_model_scale_out.md
Normal file
|
|
@ -0,0 +1,173 @@
|
|||
## Predefined Model Integration
|
||||
|
||||
After completing the vendor integration, the next step is to integrate the models from the vendor.
|
||||
|
||||
First, we need to determine the type of model to be integrated and create the corresponding model type `module` under the respective vendor's directory.
|
||||
|
||||
Currently supported model types are:
|
||||
|
||||
- `llm` Text Generation Model
|
||||
- `text_embedding` Text Embedding Model
|
||||
- `rerank` Rerank Model
|
||||
- `speech2text` Speech-to-Text
|
||||
- `tts` Text-to-Speech
|
||||
- `moderation` Moderation
|
||||
|
||||
Continuing with `Anthropic` as an example, `Anthropic` only supports LLM, so create a `module` named `llm` under `model_providers.anthropic`.
|
||||
|
||||
For predefined models, we first need to create a YAML file named after the model under the `llm` `module`, such as `claude-2.1.yaml`.
|
||||
|
||||
### Prepare Model YAML
|
||||
|
||||
```yaml
|
||||
model: claude-2.1 # Model identifier
|
||||
# Display name of the model, which can be set to en_US English or zh_Hans Chinese. If zh_Hans is not set, it will default to en_US.
|
||||
# This can also be omitted, in which case the model identifier will be used as the label
|
||||
label:
|
||||
en_US: claude-2.1
|
||||
model_type: llm # Model type, claude-2.1 is an LLM
|
||||
features: # Supported features, agent-thought supports Agent reasoning, vision supports image understanding
|
||||
- agent-thought
|
||||
model_properties: # Model properties
|
||||
mode: chat # LLM mode, complete for text completion models, chat for conversation models
|
||||
context_size: 200000 # Maximum context size
|
||||
parameter_rules: # Parameter rules for the model call; only LLM requires this
|
||||
- name: temperature # Parameter variable name
|
||||
# Five default configuration templates are provided: temperature/top_p/max_tokens/presence_penalty/frequency_penalty
|
||||
# The template variable name can be set directly in use_template, which will use the default configuration in entities.defaults.PARAMETER_RULE_TEMPLATE
|
||||
# Additional configuration parameters will override the default configuration if set
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label: # Display name of the parameter
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int # Parameter type, supports float/int/string/boolean
|
||||
help: # Help information, describing the parameter's function
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false # Whether the parameter is mandatory; can be omitted
|
||||
- name: max_tokens_to_sample
|
||||
use_template: max_tokens
|
||||
default: 4096 # Default value of the parameter
|
||||
min: 1 # Minimum value of the parameter, applicable to float/int only
|
||||
max: 4096 # Maximum value of the parameter, applicable to float/int only
|
||||
pricing: # Pricing information
|
||||
input: '8.00' # Input unit price, i.e., prompt price
|
||||
output: '24.00' # Output unit price, i.e., response content price
|
||||
unit: '0.000001' # Price unit, meaning the above prices are per 100K
|
||||
currency: USD # Price currency
|
||||
```
|
||||
|
||||
It is recommended to prepare all model configurations before starting the implementation of the model code.
|
||||
|
||||
You can also refer to the YAML configuration information under the corresponding model type directories of other vendors in the `model_providers` directory. For the complete YAML rules, refer to: [Schema](schema.md#aimodelentity).
|
||||
|
||||
### Implement the Model Call Code
|
||||
|
||||
Next, create a Python file named `llm.py` under the `llm` `module` to write the implementation code.
|
||||
|
||||
Create an Anthropic LLM class named `AnthropicLargeLanguageModel` (or any other name), inheriting from the `__base.large_language_model.LargeLanguageModel` base class, and implement the following methods:
|
||||
|
||||
- LLM Call
|
||||
|
||||
Implement the core method for calling the LLM, supporting both streaming and synchronous responses.
|
||||
|
||||
```python
|
||||
def _invoke(self, model: str, credentials: dict,
|
||||
prompt_messages: list[PromptMessage], model_parameters: dict,
|
||||
tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
|
||||
stream: bool = True, user: Optional[str] = None) \
|
||||
-> Union[LLMResult, Generator]:
|
||||
"""
|
||||
Invoke large language model
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:param prompt_messages: prompt messages
|
||||
:param model_parameters: model parameters
|
||||
:param tools: tools for tool calling
|
||||
:param stop: stop words
|
||||
:param stream: is stream response
|
||||
:param user: unique user id
|
||||
:return: full response or stream response chunk generator result
|
||||
"""
|
||||
```
|
||||
|
||||
Ensure to use two functions for returning data, one for synchronous returns and the other for streaming returns, because Python identifies functions containing the `yield` keyword as generator functions, fixing the return type to `Generator`. Thus, synchronous and streaming returns need to be implemented separately, as shown below (note that the example uses simplified parameters, for actual implementation follow the above parameter list):
|
||||
|
||||
```python
|
||||
def _invoke(self, stream: bool, **kwargs) \
|
||||
-> Union[LLMResult, Generator]:
|
||||
if stream:
|
||||
return self._handle_stream_response(**kwargs)
|
||||
return self._handle_sync_response(**kwargs)
|
||||
|
||||
def _handle_stream_response(self, **kwargs) -> Generator:
|
||||
for chunk in response:
|
||||
yield chunk
|
||||
def _handle_sync_response(self, **kwargs) -> LLMResult:
|
||||
return LLMResult(**response)
|
||||
```
|
||||
|
||||
- Pre-compute Input Tokens
|
||||
|
||||
If the model does not provide an interface to precompute tokens, return 0 directly.
|
||||
|
||||
```python
|
||||
def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
|
||||
tools: Optional[list[PromptMessageTool]] = None) -> int:
|
||||
"""
|
||||
Get number of tokens for given prompt messages
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:param prompt_messages: prompt messages
|
||||
:param tools: tools for tool calling
|
||||
:return:
|
||||
"""
|
||||
```
|
||||
|
||||
- Validate Model Credentials
|
||||
|
||||
Similar to vendor credential validation, but specific to a single model.
|
||||
|
||||
```python
|
||||
def validate_credentials(self, model: str, credentials: dict) -> None:
|
||||
"""
|
||||
Validate model credentials
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:return:
|
||||
"""
|
||||
```
|
||||
|
||||
- Map Invoke Errors
|
||||
|
||||
When a model call fails, map it to a specific `InvokeError` type as required by Runtime, allowing Dify to handle different errors accordingly.
|
||||
|
||||
Runtime Errors:
|
||||
|
||||
- `InvokeConnectionError` Connection error
|
||||
|
||||
- `InvokeServerUnavailableError` Service provider unavailable
|
||||
- `InvokeRateLimitError` Rate limit reached
|
||||
- `InvokeAuthorizationError` Authorization failed
|
||||
- `InvokeBadRequestError` Parameter error
|
||||
|
||||
```python
|
||||
@property
|
||||
def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
|
||||
"""
|
||||
Map model invoke error to unified error
|
||||
The key is the error type thrown to the caller
|
||||
The value is the error type thrown by the model,
|
||||
which needs to be converted into a unified error type for the caller.
|
||||
|
||||
:return: Invoke error mapping
|
||||
"""
|
||||
```
|
||||
|
||||
For interface method explanations, see: [Interfaces](./interfaces.md). For detailed implementation, refer to: [llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py).
|
||||
|
|
@ -58,7 +58,7 @@ provider_credential_schema: # Provider credential rules, as Anthropic only supp
|
|||
en_US: Enter your API URL
|
||||
```
|
||||
|
||||
You can also refer to the YAML configuration information under other provider directories in `model_providers`. The complete YAML rules are available at: [Schema](schema.md#Provider).
|
||||
You can also refer to the YAML configuration information under other provider directories in `model_providers`. The complete YAML rules are available at: [Schema](schema.md#provider).
|
||||
|
||||
### Implementing Provider Code
|
||||
|
||||
|
|
|
|||
|
|
@ -117,7 +117,7 @@ model_credential_schema:
|
|||
en_US: Enter your API Base
|
||||
```
|
||||
|
||||
也可以参考 `model_providers` 目录下其他供应商目录下的 YAML 配置信息，完整的 YAML 规则见：[Schema](schema.md#Provider)。
|
||||
也可以参考 `model_providers` 目录下其他供应商目录下的 YAML 配置信息，完整的 YAML 规则见：[Schema](schema.md#provider)。
|
||||
|
||||
#### 实现供应商代码
|
||||
|
||||
|
|
|
|||
|
|
@ -94,7 +94,7 @@ class LargeLanguageModel(AIModel):
|
|||
)
|
||||
|
||||
try:
|
||||
if "response_format" in model_parameters:
|
||||
if "response_format" in model_parameters and model_parameters["response_format"] in {"JSON", "XML"}:
|
||||
result = self._code_block_mode_wrapper(
|
||||
model=model,
|
||||
credentials=credentials,
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
import logging
|
||||
import re
|
||||
from abc import abstractmethod
|
||||
from typing import Optional
|
||||
from typing import Any, Optional
|
||||
|
||||
from pydantic import ConfigDict
|
||||
|
||||
|
|
@ -88,7 +88,7 @@ class TTSModel(AIModel):
|
|||
else:
|
||||
return [{"name": d["name"], "value": d["mode"]} for d in voices]
|
||||
|
||||
def _get_model_default_voice(self, model: str, credentials: dict) -> any:
|
||||
def _get_model_default_voice(self, model: str, credentials: dict) -> Any:
|
||||
"""
|
||||
Get voice for given tts model
|
||||
|
||||
|
|
|
|||
|
|
@ -40,3 +40,4 @@
|
|||
- fireworks
|
||||
- mixedbread
|
||||
- nomic
|
||||
- voyage
|
||||
|
|
|
|||
|
|
@ -169,7 +169,7 @@ class AnthropicLargeLanguageModel(LargeLanguageModel):
|
|||
stop: Optional[list[str]] = None,
|
||||
stream: bool = True,
|
||||
user: Optional[str] = None,
|
||||
callbacks: list[Callback] = None,
|
||||
callbacks: Optional[list[Callback]] = None,
|
||||
) -> Union[LLMResult, Generator]:
|
||||
"""
|
||||
Code block mode wrapper for invoking large language model
|
||||
|
|
|
|||
|
|
@ -1081,8 +1081,81 @@ LLM_BASE_MODELS = [
|
|||
),
|
||||
),
|
||||
),
|
||||
AzureBaseModel(
|
||||
base_model_name="o1-preview",
|
||||
entity=AIModelEntity(
|
||||
model="fake-deployment-name",
|
||||
label=I18nObject(
|
||||
en_US="fake-deployment-name-label",
|
||||
),
|
||||
model_type=ModelType.LLM,
|
||||
features=[
|
||||
ModelFeature.AGENT_THOUGHT,
|
||||
],
|
||||
fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
|
||||
model_properties={
|
||||
ModelPropertyKey.MODE: LLMMode.CHAT.value,
|
||||
ModelPropertyKey.CONTEXT_SIZE: 128000,
|
||||
},
|
||||
parameter_rules=[
|
||||
ParameterRule(
|
||||
name="response_format",
|
||||
label=I18nObject(zh_Hans="回复格式", en_US="response_format"),
|
||||
type="string",
|
||||
help=I18nObject(
|
||||
zh_Hans="指定模型必须输出的格式", en_US="specifying the format that the model must output"
|
||||
),
|
||||
required=False,
|
||||
options=["text", "json_object"],
|
||||
),
|
||||
_get_max_tokens(default=512, min_val=1, max_val=32768),
|
||||
],
|
||||
pricing=PriceConfig(
|
||||
input=15.00,
|
||||
output=60.00,
|
||||
unit=0.000001,
|
||||
currency="USD",
|
||||
),
|
||||
),
|
||||
),
|
||||
AzureBaseModel(
|
||||
base_model_name="o1-mini",
|
||||
entity=AIModelEntity(
|
||||
model="fake-deployment-name",
|
||||
label=I18nObject(
|
||||
en_US="fake-deployment-name-label",
|
||||
),
|
||||
model_type=ModelType.LLM,
|
||||
features=[
|
||||
ModelFeature.AGENT_THOUGHT,
|
||||
],
|
||||
fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
|
||||
model_properties={
|
||||
ModelPropertyKey.MODE: LLMMode.CHAT.value,
|
||||
ModelPropertyKey.CONTEXT_SIZE: 128000,
|
||||
},
|
||||
parameter_rules=[
|
||||
ParameterRule(
|
||||
name="response_format",
|
||||
label=I18nObject(zh_Hans="回复格式", en_US="response_format"),
|
||||
type="string",
|
||||
help=I18nObject(
|
||||
zh_Hans="指定模型必须输出的格式", en_US="specifying the format that the model must output"
|
||||
),
|
||||
required=False,
|
||||
options=["text", "json_object"],
|
||||
),
|
||||
_get_max_tokens(default=512, min_val=1, max_val=65536),
|
||||
],
|
||||
pricing=PriceConfig(
|
||||
input=3.00,
|
||||
output=12.00,
|
||||
unit=0.000001,
|
||||
currency="USD",
|
||||
),
|
||||
),
|
||||
),
|
||||
]
|
||||
|
||||
EMBEDDING_BASE_MODELS = [
|
||||
AzureBaseModel(
|
||||
base_model_name="text-embedding-ada-002",
|
||||
|
|
|
|||
|
|
@ -53,6 +53,9 @@ model_credential_schema:
|
|||
type: select
|
||||
required: true
|
||||
options:
|
||||
- label:
|
||||
en_US: 2024-09-01-preview
|
||||
value: 2024-09-01-preview
|
||||
- label:
|
||||
en_US: 2024-08-01-preview
|
||||
value: 2024-08-01-preview
|
||||
|
|
@ -120,6 +123,18 @@ model_credential_schema:
|
|||
show_on:
|
||||
- variable: __model_type
|
||||
value: llm
|
||||
- label:
|
||||
en_US: o1-mini
|
||||
value: o1-mini
|
||||
show_on:
|
||||
- variable: __model_type
|
||||
value: llm
|
||||
- label:
|
||||
en_US: o1-preview
|
||||
value: o1-preview
|
||||
show_on:
|
||||
- variable: __model_type
|
||||
value: llm
|
||||
- label:
|
||||
en_US: gpt-4o-mini
|
||||
value: gpt-4o-mini
|
||||
|
|
|
|||
|
|
@ -312,10 +312,24 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
|
|||
if user:
|
||||
extra_model_kwargs["user"] = user
|
||||
|
||||
# clear illegal prompt messages
|
||||
prompt_messages = self._clear_illegal_prompt_messages(model, prompt_messages)
|
||||
|
||||
block_as_stream = False
|
||||
if model.startswith("o1"):
|
||||
if stream:
|
||||
block_as_stream = True
|
||||
stream = False
|
||||
|
||||
if "stream_options" in extra_model_kwargs:
|
||||
del extra_model_kwargs["stream_options"]
|
||||
|
||||
if "stop" in extra_model_kwargs:
|
||||
del extra_model_kwargs["stop"]
|
||||
|
||||
# chat model
|
||||
messages = [self._convert_prompt_message_to_dict(m) for m in prompt_messages]
|
||||
response = client.chat.completions.create(
|
||||
messages=messages,
|
||||
messages=[self._convert_prompt_message_to_dict(m) for m in prompt_messages],
|
||||
model=model,
|
||||
stream=stream,
|
||||
**model_parameters,
|
||||
|
|
@ -325,7 +339,91 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
|
|||
if stream:
|
||||
return self._handle_chat_generate_stream_response(model, credentials, response, prompt_messages, tools)
|
||||
|
||||
return self._handle_chat_generate_response(model, credentials, response, prompt_messages, tools)
|
||||
block_result = self._handle_chat_generate_response(model, credentials, response, prompt_messages, tools)
|
||||
|
||||
if block_as_stream:
|
||||
return self._handle_chat_block_as_stream_response(block_result, prompt_messages, stop)
|
||||
|
||||
return block_result
|
||||
|
||||
def _handle_chat_block_as_stream_response(
|
||||
self,
|
||||
block_result: LLMResult,
|
||||
prompt_messages: list[PromptMessage],
|
||||
stop: Optional[list[str]] = None,
|
||||
) -> Generator[LLMResultChunk, None, None]:
|
||||
"""
|
||||
Handle llm chat response
|
||||
|
||||
:param model: model name
|
||||
:param credentials: credentials
|
||||
:param response: response
|
||||
:param prompt_messages: prompt messages
|
||||
:param tools: tools for tool calling
|
||||
:param stop: stop words
|
||||
:return: llm response chunk generator
|
||||
"""
|
||||
text = block_result.message.content
|
||||
text = cast(str, text)
|
||||
|
||||
if stop:
|
||||
text = self.enforce_stop_tokens(text, stop)
|
||||
|
||||
yield LLMResultChunk(
|
||||
model=block_result.model,
|
||||
prompt_messages=prompt_messages,
|
||||
system_fingerprint=block_result.system_fingerprint,
|
||||
delta=LLMResultChunkDelta(
|
||||
index=0,
|
||||
message=AssistantPromptMessage(content=text),
|
||||
finish_reason="stop",
|
||||
usage=block_result.usage,
|
||||
),
|
||||
)
|
||||
|
||||
def _clear_illegal_prompt_messages(self, model: str, prompt_messages: list[PromptMessage]) -> list[PromptMessage]:
|
||||
"""
|
||||
Clear illegal prompt messages for OpenAI API
|
||||
|
||||
:param model: model name
|
||||
:param prompt_messages: prompt messages
|
||||
:return: cleaned prompt messages
|
||||
"""
|
||||
checklist = ["gpt-4-turbo", "gpt-4-turbo-2024-04-09"]
|
||||
|
||||
if model in checklist:
|
||||
# count how many user messages are there
|
||||
user_message_count = len([m for m in prompt_messages if isinstance(m, UserPromptMessage)])
|
||||
if user_message_count > 1:
|
||||
for prompt_message in prompt_messages:
|
||||
if isinstance(prompt_message, UserPromptMessage):
|
||||
if isinstance(prompt_message.content, list):
|
||||
prompt_message.content = "\n".join(
|
||||
[
|
||||
item.data
|
||||
if item.type == PromptMessageContentType.TEXT
|
||||
else "[IMAGE]"
|
||||
if item.type == PromptMessageContentType.IMAGE
|
||||
else ""
|
||||
for item in prompt_message.content
|
||||
]
|
||||
)
|
||||
|
||||
if model.startswith("o1"):
|
||||
system_message_count = len([m for m in prompt_messages if isinstance(m, SystemPromptMessage)])
|
||||
if system_message_count > 0:
|
||||
new_prompt_messages = []
|
||||
for prompt_message in prompt_messages:
|
||||
if isinstance(prompt_message, SystemPromptMessage):
|
||||
prompt_message = UserPromptMessage(
|
||||
content=prompt_message.content,
|
||||
name=prompt_message.name,
|
||||
)
|
||||
|
||||
new_prompt_messages.append(prompt_message)
|
||||
prompt_messages = new_prompt_messages
|
||||
|
||||
return prompt_messages
|
||||
|
||||
def _handle_chat_generate_response(
|
||||
self,
|
||||
|
|
@ -560,7 +658,7 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
|
|||
tokens_per_message = 4
|
||||
# if there's a name, the role is omitted
|
||||
tokens_per_name = -1
|
||||
elif model.startswith("gpt-35-turbo") or model.startswith("gpt-4"):
|
||||
elif model.startswith("gpt-35-turbo") or model.startswith("gpt-4") or model.startswith("o1"):
|
||||
tokens_per_message = 3
|
||||
tokens_per_name = 1
|
||||
else:
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
import concurrent.futures
|
||||
import copy
|
||||
from typing import Optional
|
||||
from typing import Any, Optional
|
||||
|
||||
from openai import AzureOpenAI
|
||||
|
||||
|
|
@ -19,7 +19,7 @@ class AzureOpenAIText2SpeechModel(_CommonAzureOpenAI, TTSModel):
|
|||
|
||||
def _invoke(
|
||||
self, model: str, tenant_id: str, credentials: dict, content_text: str, voice: str, user: Optional[str] = None
|
||||
) -> any:
|
||||
) -> Any:
|
||||
"""
|
||||
_invoke text2speech model
|
||||
|
||||
|
|
@ -56,7 +56,7 @@ class AzureOpenAIText2SpeechModel(_CommonAzureOpenAI, TTSModel):
|
|||
except Exception as ex:
|
||||
raise CredentialsValidateFailedError(str(ex))
|
||||
|
||||
def _tts_invoke_streaming(self, model: str, credentials: dict, content_text: str, voice: str) -> any:
|
||||
def _tts_invoke_streaming(self, model: str, credentials: dict, content_text: str, voice: str) -> Any:
|
||||
"""
|
||||
_tts_invoke_streaming text2speech model
|
||||
:param model: model name
|
||||
|
|
|
|||
|
|
@ -50,34 +50,62 @@ provider_credential_schema:
|
|||
label:
|
||||
en_US: US East (N. Virginia)
|
||||
zh_Hans: 美国东部 (弗吉尼亚北部)
|
||||
- value: us-east-2
|
||||
label:
|
||||
en_US: US East (Ohio)
|
||||
zh_Hans: 美国东部 (弗吉尼亚北部)
|
||||
- value: us-west-2
|
||||
label:
|
||||
en_US: US West (Oregon)
|
||||
zh_Hans: 美国西部 (俄勒冈州)
|
||||
- value: ap-south-1
|
||||
label:
|
||||
en_US: Asia Pacific (Mumbai)
|
||||
zh_Hans: 亚太地区（孟买）
|
||||
- value: ap-southeast-1
|
||||
label:
|
||||
en_US: Asia Pacific (Singapore)
|
||||
zh_Hans: 亚太地区 (新加坡)
|
||||
- value: ap-northeast-1
|
||||
label:
|
||||
en_US: Asia Pacific (Tokyo)
|
||||
zh_Hans: 亚太地区 (东京)
|
||||
- value: eu-central-1
|
||||
label:
|
||||
en_US: Europe (Frankfurt)
|
||||
zh_Hans: 欧洲 (法兰克福)
|
||||
- value: eu-west-2
|
||||
label:
|
||||
en_US: Eu west London (London)
|
||||
zh_Hans: 欧洲西部 (伦敦)
|
||||
- value: us-gov-west-1
|
||||
label:
|
||||
en_US: AWS GovCloud (US-West)
|
||||
zh_Hans: AWS GovCloud (US-West)
|
||||
- value: ap-southeast-2
|
||||
label:
|
||||
en_US: Asia Pacific (Sydney)
|
||||
zh_Hans: 亚太地区 (悉尼)
|
||||
- value: ap-northeast-1
|
||||
label:
|
||||
en_US: Asia Pacific (Tokyo)
|
||||
zh_Hans: 亚太地区 (东京)
|
||||
- value: ap-northeast-2
|
||||
label:
|
||||
en_US: Asia Pacific (Seoul)
|
||||
zh_Hans: 亚太地区（首尔）
|
||||
- value: ca-central-1
|
||||
label:
|
||||
en_US: Canada (Central)
|
||||
zh_Hans: 加拿大（中部）
|
||||
- value: eu-central-1
|
||||
label:
|
||||
en_US: Europe (Frankfurt)
|
||||
zh_Hans: 欧洲 (法兰克福)
|
||||
- value: eu-west-1
|
||||
label:
|
||||
en_US: Europe (Ireland)
|
||||
zh_Hans: 欧洲（爱尔兰）
|
||||
- value: eu-west-2
|
||||
label:
|
||||
en_US: Europe (London)
|
||||
zh_Hans: 欧洲西部 (伦敦)
|
||||
- value: eu-west-3
|
||||
label:
|
||||
en_US: Europe (Paris)
|
||||
zh_Hans: 欧洲（巴黎）
|
||||
- value: sa-east-1
|
||||
label:
|
||||
en_US: South America (São Paulo)
|
||||
zh_Hans: 南美洲（圣保罗）
|
||||
- value: us-gov-west-1
|
||||
label:
|
||||
en_US: AWS GovCloud (US-West)
|
||||
zh_Hans: AWS GovCloud (US-West)
|
||||
- variable: model_for_validation
|
||||
required: false
|
||||
label:
|
||||
|
|
|
|||
|
|
@ -6,6 +6,8 @@
|
|||
- anthropic.claude-v2:1
|
||||
- anthropic.claude-3-sonnet-v1:0
|
||||
- anthropic.claude-3-haiku-v1:0
|
||||
- ai21.jamba-1-5-large-v1:0
|
||||
- ai21.jamba-1-5-mini-v1:0
|
||||
- cohere.command-light-text-v14
|
||||
- cohere.command-text-v14
|
||||
- cohere.command-r-plus-v1.0
|
||||
|
|
@ -15,6 +17,10 @@
|
|||
- meta.llama3-1-405b-instruct-v1:0
|
||||
- meta.llama3-8b-instruct-v1:0
|
||||
- meta.llama3-70b-instruct-v1:0
|
||||
- us.meta.llama3-2-1b-instruct-v1:0
|
||||
- us.meta.llama3-2-3b-instruct-v1:0
|
||||
- us.meta.llama3-2-11b-instruct-v1:0
|
||||
- us.meta.llama3-2-90b-instruct-v1:0
|
||||
- meta.llama2-13b-chat-v1
|
||||
- meta.llama2-70b-chat-v1
|
||||
- mistral.mistral-large-2407-v1:0
|
||||
|
|
|
|||
|
|
@ -0,0 +1,26 @@
|
|||
model: ai21.jamba-1-5-large-v1:0
|
||||
label:
|
||||
en_US: Jamba 1.5 Large
|
||||
model_type: llm
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 256000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 2.0
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_gen_len
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 4096
|
||||
min: 1
|
||||
max: 4096
|
||||
pricing:
|
||||
input: '0.002'
|
||||
output: '0.008'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
|
|
@ -0,0 +1,26 @@
|
|||
model: ai21.jamba-1-5-mini-v1:0
|
||||
label:
|
||||
en_US: Jamba 1.5 Mini
|
||||
model_type: llm
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 256000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 2.0
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_gen_len
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 4096
|
||||
min: 1
|
||||
max: 4096
|
||||
pricing:
|
||||
input: '0.0002'
|
||||
output: '0.0004'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
|
|
@ -63,6 +63,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
|
|||
{"prefix": "us.anthropic.claude-3", "support_system_prompts": True, "support_tool_use": True},
|
||||
{"prefix": "eu.anthropic.claude-3", "support_system_prompts": True, "support_tool_use": True},
|
||||
{"prefix": "anthropic.claude-3", "support_system_prompts": True, "support_tool_use": True},
|
||||
{"prefix": "us.meta.llama3-2", "support_system_prompts": True, "support_tool_use": True},
|
||||
{"prefix": "meta.llama", "support_system_prompts": True, "support_tool_use": False},
|
||||
{"prefix": "mistral.mistral-7b-instruct", "support_system_prompts": False, "support_tool_use": False},
|
||||
{"prefix": "mistral.mixtral-8x7b-instruct", "support_system_prompts": False, "support_tool_use": False},
|
||||
|
|
@ -70,6 +71,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
|
|||
{"prefix": "mistral.mistral-small", "support_system_prompts": True, "support_tool_use": True},
|
||||
{"prefix": "cohere.command-r", "support_system_prompts": True, "support_tool_use": True},
|
||||
{"prefix": "amazon.titan", "support_system_prompts": False, "support_tool_use": False},
|
||||
{"prefix": "ai21.jamba-1-5", "support_system_prompts": True, "support_tool_use": False},
|
||||
]
|
||||
|
||||
@staticmethod
|
||||
|
|
@ -90,7 +92,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
|
|||
stop: Optional[list[str]] = None,
|
||||
stream: bool = True,
|
||||
user: Optional[str] = None,
|
||||
callbacks: list[Callback] = None,
|
||||
callbacks: Optional[list[Callback]] = None,
|
||||
) -> Union[LLMResult, Generator]:
|
||||
"""
|
||||
Code block mode wrapper for invoking large language model
|
||||
|
|
|
|||
|
|
@ -0,0 +1,29 @@
|
|||
model: us.meta.llama3-2-11b-instruct-v1:0
|
||||
label:
|
||||
en_US: US Meta Llama 3.2 11B Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- vision
|
||||
- tool-call
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 0.5
|
||||
min: 0.0
|
||||
max: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_gen_len
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 512
|
||||
min: 1
|
||||
max: 2048
|
||||
pricing:
|
||||
input: '0.00035'
|
||||
output: '0.00035'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
|
|
@ -0,0 +1,26 @@
|
|||
model: us.meta.llama3-2-1b-instruct-v1:0
|
||||
label:
|
||||
en_US: US Meta Llama 3.2 1B Instruct
|
||||
model_type: llm
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 0.5
|
||||
min: 0.0
|
||||
max: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_gen_len
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 512
|
||||
min: 1
|
||||
max: 2048
|
||||
pricing:
|
||||
input: '0.0001'
|
||||
output: '0.0001'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
|
|
@ -0,0 +1,26 @@
|
|||
model: us.meta.llama3-2-3b-instruct-v1:0
|
||||
label:
|
||||
en_US: US Meta Llama 3.2 3B Instruct
|
||||
model_type: llm
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 0.5
|
||||
min: 0.0
|
||||
max: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_gen_len
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 512
|
||||
min: 1
|
||||
max: 2048
|
||||
pricing:
|
||||
input: '0.00015'
|
||||
output: '0.00015'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
|
|
@ -0,0 +1,31 @@
|
|||
model: us.meta.llama3-2-90b-instruct-v1:0
|
||||
label:
|
||||
en_US: US Meta Llama 3.2 90B Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- tool-call
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 0.5
|
||||
min: 0.0
|
||||
max: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
default: 0.9
|
||||
min: 0
|
||||
max: 1
|
||||
- name: max_gen_len
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 512
|
||||
min: 1
|
||||
max: 2048
|
||||
pricing:
|
||||
input: '0.002'
|
||||
output: '0.002'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
|
|
@ -511,7 +511,7 @@ class FireworksLargeLanguageModel(_CommonFireworks, LargeLanguageModel):
|
|||
model: str,
|
||||
messages: list[PromptMessage],
|
||||
tools: Optional[list[PromptMessageTool]] = None,
|
||||
credentials: dict = None,
|
||||
credentials: Optional[dict] = None,
|
||||
) -> int:
|
||||
"""
|
||||
Approximate num tokens with GPT2 tokenizer.
|
||||
|
|
|
|||
|
|
@ -1,4 +1,4 @@
|
|||
from typing import Optional
|
||||
from typing import Any, Optional
|
||||
|
||||
import httpx
|
||||
|
||||
|
|
@ -46,7 +46,7 @@ class FishAudioText2SpeechModel(TTSModel):
|
|||
content_text: str,
|
||||
voice: str,
|
||||
user: Optional[str] = None,
|
||||
) -> any:
|
||||
) -> Any:
|
||||
"""
|
||||
Invoke text2speech model
|
||||
|
||||
|
|
@ -87,7 +87,7 @@ class FishAudioText2SpeechModel(TTSModel):
|
|||
except Exception as ex:
|
||||
raise CredentialsValidateFailedError(str(ex))
|
||||
|
||||
def _tts_invoke_streaming(self, model: str, credentials: dict, content_text: str, voice: str) -> any:
|
||||
def _tts_invoke_streaming(self, model: str, credentials: dict, content_text: str, voice: str) -> Any:
|
||||
"""
|
||||
Invoke streaming text2speech model
|
||||
:param model: model name
|
||||
|
|
@ -112,7 +112,7 @@ class FishAudioText2SpeechModel(TTSModel):
|
|||
except Exception as ex:
|
||||
raise InvokeBadRequestError(str(ex))
|
||||
|
||||
def _tts_invoke_streaming_sentence(self, credentials: dict, content_text: str, voice: Optional[str] = None) -> any:
|
||||
def _tts_invoke_streaming_sentence(self, credentials: dict, content_text: str, voice: Optional[str] = None) -> Any:
|
||||
"""
|
||||
Invoke streaming text2speech model
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,15 @@
|
|||
- gemini-1.5-pro
|
||||
- gemini-1.5-pro-latest
|
||||
- gemini-1.5-pro-001
|
||||
- gemini-1.5-pro-002
|
||||
- gemini-1.5-pro-exp-0801
|
||||
- gemini-1.5-pro-exp-0827
|
||||
- gemini-1.5-flash
|
||||
- gemini-1.5-flash-latest
|
||||
- gemini-1.5-flash-001
|
||||
- gemini-1.5-flash-002
|
||||
- gemini-1.5-flash-exp-0827
|
||||
- gemini-1.5-flash-8b-exp-0827
|
||||
- gemini-1.5-flash-8b-exp-0924
|
||||
- gemini-pro
|
||||
- gemini-pro-vision
|
||||
|
|
@ -5,3 +5,4 @@
|
|||
- llama3-8b-8192
|
||||
- mixtral-8x7b-32768
|
||||
- llama2-70b-4096
|
||||
- llama-guard-3-8b
|
||||
|
|
|
|||
|
|
@ -0,0 +1,25 @@
|
|||
model: llama-guard-3-8b
|
||||
label:
|
||||
zh_Hans: Llama-Guard-3-8B
|
||||
en_US: Llama-Guard-3-8B
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 8192
|
||||
pricing:
|
||||
input: '0.20'
|
||||
output: '0.20'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
|
|
@ -61,11 +61,19 @@ class JinaRerankModel(RerankModel):
|
|||
|
||||
rerank_documents = []
|
||||
for result in results["results"]:
|
||||
index = result["index"]
|
||||
if "document" in result:
|
||||
text = result["document"]["text"]
|
||||
else:
|
||||
# llama.cpp rerank maynot return original documents
|
||||
text = docs[index]
|
||||
|
||||
rerank_document = RerankDocument(
|
||||
index=result["index"],
|
||||
text=result["document"]["text"],
|
||||
index=index,
|
||||
text=text,
|
||||
score=result["relevance_score"],
|
||||
)
|
||||
|
||||
if score_threshold is None or result["relevance_score"] >= score_threshold:
|
||||
rerank_documents.append(rerank_document)
|
||||
|
||||
|
|
|
|||
|
|
@ -70,11 +70,19 @@ class LocalaiRerankModel(RerankModel):
|
|||
|
||||
rerank_documents = []
|
||||
for result in results["results"]:
|
||||
index = result["index"]
|
||||
if "document" in result:
|
||||
text = result["document"]["text"]
|
||||
else:
|
||||
# llama.cpp rerank maynot return original documents
|
||||
text = docs[index]
|
||||
|
||||
rerank_document = RerankDocument(
|
||||
index=result["index"],
|
||||
text=result["document"]["text"],
|
||||
index=index,
|
||||
text=text,
|
||||
score=result["relevance_score"],
|
||||
)
|
||||
|
||||
if score_threshold is None or result["relevance_score"] >= score_threshold:
|
||||
rerank_documents.append(rerank_document)
|
||||
|
||||
|
|
|
|||
|
|
@ -111,7 +111,7 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
|
|||
stop: Optional[list[str]] = None,
|
||||
stream: bool = True,
|
||||
user: Optional[str] = None,
|
||||
callbacks: list[Callback] = None,
|
||||
callbacks: Optional[list[Callback]] = None,
|
||||
) -> Union[LLMResult, Generator]:
|
||||
"""
|
||||
Code block mode wrapper for invoking large language model
|
||||
|
|
|
|||
|
|
@ -2,6 +2,8 @@ from typing import IO, Optional
|
|||
|
||||
from openai import OpenAI
|
||||
|
||||
from core.model_runtime.entities.common_entities import I18nObject
|
||||
from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelType
|
||||
from core.model_runtime.errors.validate import CredentialsValidateFailedError
|
||||
from core.model_runtime.model_providers.__base.speech2text_model import Speech2TextModel
|
||||
from core.model_runtime.model_providers.openai._common import _CommonOpenAI
|
||||
|
|
@ -58,3 +60,18 @@ class OpenAISpeech2TextModel(_CommonOpenAI, Speech2TextModel):
|
|||
response = client.audio.transcriptions.create(model=model, file=file)
|
||||
|
||||
return response.text
|
||||
|
||||
def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity | None:
|
||||
"""
|
||||
used to define customizable model schema
|
||||
"""
|
||||
entity = AIModelEntity(
|
||||
model=model,
|
||||
label=I18nObject(en_US=model),
|
||||
fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
|
||||
model_type=ModelType.SPEECH2TEXT,
|
||||
model_properties={},
|
||||
parameter_rules=[],
|
||||
)
|
||||
|
||||
return entity
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
import concurrent.futures
|
||||
from typing import Optional
|
||||
from typing import Any, Optional
|
||||
|
||||
from openai import OpenAI
|
||||
|
||||
|
|
@ -16,7 +16,7 @@ class OpenAIText2SpeechModel(_CommonOpenAI, TTSModel):
|
|||
|
||||
def _invoke(
|
||||
self, model: str, tenant_id: str, credentials: dict, content_text: str, voice: str, user: Optional[str] = None
|
||||
) -> any:
|
||||
) -> Any:
|
||||
"""
|
||||
_invoke text2speech model
|
||||
|
||||
|
|
@ -55,7 +55,7 @@ class OpenAIText2SpeechModel(_CommonOpenAI, TTSModel):
|
|||
except Exception as ex:
|
||||
raise CredentialsValidateFailedError(str(ex))
|
||||
|
||||
def _tts_invoke_streaming(self, model: str, credentials: dict, content_text: str, voice: str) -> any:
|
||||
def _tts_invoke_streaming(self, model: str, credentials: dict, content_text: str, voice: str) -> Any:
|
||||
"""
|
||||
_tts_invoke_streaming text2speech model
|
||||
|
||||
|
|
|
|||
|
|
@ -688,7 +688,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
|
|||
model: str,
|
||||
messages: list[PromptMessage],
|
||||
tools: Optional[list[PromptMessageTool]] = None,
|
||||
credentials: dict = None,
|
||||
credentials: Optional[dict] = None,
|
||||
) -> int:
|
||||
"""
|
||||
Approximate num tokens with GPT2 tokenizer.
|
||||
|
|
|
|||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue
Block a user