mirror of
https://github.com/langgenius/dify.git
synced 2024-11-16 19:59:50 +08:00
Merge branch 'main' into feat/add-tidb-on-qdrant-type
# Conflicts: # api/controllers/console/datasets/datasets.py # api/core/rag/datasource/vdb/vector_type.py
This commit is contained in:
jyong
commit
09e7f814e7
4
.github/workflows/api-tests.yml
vendored
4
.github/workflows/api-tests.yml
vendored
|
|
@ -21,6 +21,7 @@ jobs:
|
|||
python-version:
|
||||
- "3.10"
|
||||
- "3.11"
|
||||
- "3.12"
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
|
|
@ -75,7 +76,7 @@ jobs:
|
|||
- name: Run Workflow
|
||||
run: poetry run -C api bash dev/pytest/pytest_workflow.sh
|
||||
|
||||
- name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale)
|
||||
- name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch)
|
||||
uses: hoverkraft-tech/compose-action@v2.0.0
|
||||
with:
|
||||
compose-file: |
|
||||
|
|
@ -89,5 +90,6 @@ jobs:
|
|||
pgvecto-rs
|
||||
pgvector
|
||||
chroma
|
||||
elasticsearch
|
||||
- name: Test Vector Stores
|
||||
run: poetry run -C api bash dev/pytest/pytest_vdb.sh
|
||||
|
|
|
|||
3
.github/workflows/expose_service_ports.sh
vendored
3
.github/workflows/expose_service_ports.sh
vendored
|
|
@ -6,5 +6,6 @@ yq eval '.services.chroma.ports += ["8000:8000"]' -i docker/docker-compose.yaml
|
|||
yq eval '.services["milvus-standalone"].ports += ["19530:19530"]' -i docker/docker-compose.yaml
|
||||
yq eval '.services.pgvector.ports += ["5433:5432"]' -i docker/docker-compose.yaml
|
||||
yq eval '.services["pgvecto-rs"].ports += ["5431:5432"]' -i docker/docker-compose.yaml
|
||||
yq eval '.services["elasticsearch"].ports += ["9200:9200"]' -i docker/docker-compose.yaml
|
||||
|
||||
echo "Ports exposed for sandbox, weaviate, qdrant, chroma, milvus, pgvector, pgvecto-rs."
|
||||
echo "Ports exposed for sandbox, weaviate, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch"
|
||||
1
.gitignore
vendored
1
.gitignore
vendored
|
|
@ -155,6 +155,7 @@ docker-legacy/volumes/milvus/*
|
|||
docker-legacy/volumes/chroma/*
|
||||
|
||||
docker/volumes/app/storage/*
|
||||
docker/volumes/certbot/*
|
||||
docker/volumes/db/data/*
|
||||
docker/volumes/redis/data/*
|
||||
docker/volumes/weaviate/*
|
||||
|
|
|
|||
25
README.md
25
README.md
|
|
@ -4,7 +4,7 @@
|
|||
<a href="https://cloud.dify.ai">Dify Cloud</a> ·
|
||||
<a href="https://docs.dify.ai/getting-started/install-self-hosted">Self-hosting</a> ·
|
||||
<a href="https://docs.dify.ai">Documentation</a> ·
|
||||
<a href="https://cal.com/guchenhe/60-min-meeting">Enterprise inquiry</a>
|
||||
<a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Enterprise inquiry</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
|
|
@ -37,6 +37,8 @@
|
|||
<a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
|
||||
<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>
|
||||
|
||||
|
||||
|
|
@ -64,7 +66,7 @@ Dify is an open-source LLM app development platform. Its intuitive interface com
|
|||
Extensive RAG capabilities that cover everything from document ingestion to retrieval, with out-of-box support for text extraction from PDFs, PPTs, and other common document formats.
|
||||
|
||||
**5. Agent capabilities**:
|
||||
You can define agents based on LLM Function Calling or ReAct, and add pre-built or custom tools for the agent. Dify provides 50+ built-in tools for AI agents, such as Google Search, DELL·E, Stable Diffusion and WolframAlpha.
|
||||
You can define agents based on LLM Function Calling or ReAct, and add pre-built or custom tools for the agent. Dify provides 50+ built-in tools for AI agents, such as Google Search, DALL·E, Stable Diffusion and WolframAlpha.
|
||||
|
||||
**6. LLMOps**:
|
||||
Monitor and analyze application logs and performance over time. You could continuously improve prompts, datasets, and models based on production data and annotations.
|
||||
|
|
@ -150,7 +152,7 @@ Quickly get Dify running in your environment with this [starter guide](#quick-st
|
|||
Use our [documentation](https://docs.dify.ai) for further references and more in-depth instructions.
|
||||
|
||||
- **Dify for enterprise / organizations</br>**
|
||||
We provide additional enterprise-centric features. [Schedule a meeting with us](https://cal.com/guchenhe/30min) or [send us an email](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs. </br>
|
||||
We provide additional enterprise-centric features. [Log your questions for us through this chatbot](https://udify.app/chat/22L1zSxg6yW1cWQg) or [send us an email](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs. </br>
|
||||
> For startups and small businesses using AWS, check out [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) and deploy it to your own AWS VPC with one-click. It's an affordable AMI offering with the option to create apps with custom logo and branding.
|
||||
|
||||
|
||||
|
|
@ -219,23 +221,6 @@ At the same time, please consider supporting Dify by sharing it on social media
|
|||
* [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.
|
||||
|
||||
Or, schedule a meeting directly with a team member:
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<th>Point of Contact</th>
|
||||
<th>Purpose</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
|
||||
<td>Business enquiries & product feedback</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
|
||||
<td>Contributions, issues & feature requests</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
## Star history
|
||||
|
||||
[](https://star-history.com/#langgenius/dify&Date)
|
||||
|
|
|
|||
23
README_AR.md
23
README_AR.md
|
|
@ -4,7 +4,7 @@
|
|||
<a href="https://cloud.dify.ai">Dify Cloud</a> ·
|
||||
<a href="https://docs.dify.ai/getting-started/install-self-hosted">الاستضافة الذاتية</a> ·
|
||||
<a href="https://docs.dify.ai">التوثيق</a> ·
|
||||
<a href="https://cal.com/guchenhe/60-min-meeting">استفسارات الشركات</a>
|
||||
<a href="https://udify.app/chat/22L1zSxg6yW1cWQg">استفسار الشركات (للإنجليزية فقط)</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
|
|
@ -37,6 +37,8 @@
|
|||
<a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
|
||||
<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>
|
||||
|
||||
<div style="text-align: right;">
|
||||
|
|
@ -56,7 +58,7 @@
|
|||
|
||||
**4. خط أنابيب RAG**: قدرات RAG الواسعة التي تغطي كل شيء من استيعاب الوثائق إلى الاسترجاع، مع الدعم الفوري لاستخراج النص من ملفات PDF و PPT وتنسيقات الوثائق الشائعة الأخرى.
|
||||
|
||||
**5. قدرات الوكيل**: يمكنك تعريف الوكلاء بناءً على أمر وظيفة LLM أو ReAct، وإضافة أدوات مدمجة أو مخصصة للوكيل. توفر Dify أكثر من 50 أداة مدمجة لوكلاء الذكاء الاصطناعي، مثل البحث في Google و DELL·E وStable Diffusion و WolframAlpha.
|
||||
**5. قدرات الوكيل**: يمكنك تعريف الوكلاء بناءً على أمر وظيفة LLM أو ReAct، وإضافة أدوات مدمجة أو مخصصة للوكيل. توفر Dify أكثر من 50 أداة مدمجة لوكلاء الذكاء الاصطناعي، مثل البحث في Google و DALL·E وStable Diffusion و WolframAlpha.
|
||||
|
||||
**6. الـ LLMOps**: راقب وتحلل سجلات التطبيق والأداء على مر الزمن. يمكنك تحسين الأوامر والبيانات والنماذج باستمرار استنادًا إلى البيانات الإنتاجية والتعليقات.
|
||||
|
||||
|
|
@ -202,23 +204,6 @@ docker compose up -d
|
|||
* [Discord](https://discord.gg/FngNHpbcY7). الأفضل لـ: مشاركة تطبيقاتك والترفيه مع المجتمع.
|
||||
* [تويتر](https://twitter.com/dify_ai). الأفضل لـ: مشاركة تطبيقاتك والترفيه مع المجتمع.
|
||||
|
||||
أو، قم بجدولة اجتماع مباشرة مع أحد أعضاء الفريق:
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<th>نقطة الاتصال</th>
|
||||
<th>الغرض</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
|
||||
<td>استفسارات الأعمال واقتراحات حول المنتج</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
|
||||
<td>المساهمات والمشكلات وطلبات الميزات</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
## تاريخ النجمة
|
||||
|
||||
[](https://star-history.com/#langgenius/dify&Date)
|
||||
|
|
|
|||
23
README_CN.md
23
README_CN.md
|
|
@ -4,7 +4,7 @@
|
|||
<a href="https://cloud.dify.ai">Dify 云服务</a> ·
|
||||
<a href="https://docs.dify.ai/getting-started/install-self-hosted">自托管</a> ·
|
||||
<a href="https://docs.dify.ai">文档</a> ·
|
||||
<a href="https://cal.com/guchenhe/dify-demo">预约演示</a>
|
||||
<a href="https://udify.app/chat/22L1zSxg6yW1cWQg">（需用英文）常见问题解答 / 联系团队</a>
|
||||
</div>
|
||||
|
||||
<p align="center">
|
||||
|
|
@ -29,13 +29,16 @@
|
|||
</p>
|
||||
|
||||
<div align="center">
|
||||
<a href="./README.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/英文-d9d9d9"></a>
|
||||
<a href="./README_CN.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
|
||||
<a href="./README_JA.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
|
||||
<a href="./README_ES.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/西班牙语-d9d9d9"></a>
|
||||
<a href="./README_KL.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/法语-d9d9d9"></a>
|
||||
<a href="./README_FR.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/克林贡语-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/韓國語-d9d9d9"></a>
|
||||
<a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
|
||||
<a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
|
||||
<a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
|
||||
<a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
|
||||
<a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
|
||||
<a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
|
||||
<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>
|
||||
</div>
|
||||
|
||||
|
||||
|
|
@ -69,7 +72,7 @@ Dify 是一个开源的 LLM 应用开发平台。其直观的界面结合了 AI
|
|||
广泛的 RAG 功能，涵盖从文档摄入到检索的所有内容，支持从 PDF、PPT 和其他常见文档格式中提取文本的开箱即用的支持。
|
||||
|
||||
**5. Agent 智能体**:
|
||||
您可以基于 LLM 函数调用或 ReAct 定义 Agent，并为 Agent 添加预构建或自定义工具。Dify 为 AI Agent 提供了50多种内置工具，如谷歌搜索、DELL·E、Stable Diffusion 和 WolframAlpha 等。
|
||||
您可以基于 LLM 函数调用或 ReAct 定义 Agent，并为 Agent 添加预构建或自定义工具。Dify 为 AI Agent 提供了50多种内置工具，如谷歌搜索、DALL·E、Stable Diffusion 和 WolframAlpha 等。
|
||||
|
||||
**6. LLMOps**:
|
||||
随时间监视和分析应用程序日志和性能。您可以根据生产数据和标注持续改进提示、数据集和模型。
|
||||
|
|
@ -155,7 +158,7 @@ Dify 是一个开源的 LLM 应用开发平台。其直观的界面结合了 AI
|
|||
使用我们的[文档](https://docs.dify.ai)进行进一步的参考和更深入的说明。
|
||||
|
||||
- **面向企业/组织的 Dify</br>**
|
||||
我们提供额外的面向企业的功能。[与我们安排会议](https://cal.com/guchenhe/30min)或[给我们发送电子邮件](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)讨论企业需求。 </br>
|
||||
我们提供额外的面向企业的功能。[给我们发送电子邮件](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)讨论企业需求。 </br>
|
||||
> 对于使用 AWS 的初创公司和中小型企业，请查看 [AWS Marketplace 上的 Dify 高级版](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6)，并使用一键部署到您自己的 AWS VPC。它是一个价格实惠的 AMI 产品，提供了使用自定义徽标和品牌创建应用程序的选项。
|
||||
|
||||
## 保持领先
|
||||
|
|
|
|||
42
README_ES.md
42
README_ES.md
|
|
@ -4,7 +4,7 @@
|
|||
<a href="https://cloud.dify.ai">Dify Cloud</a> ·
|
||||
<a href="https://docs.dify.ai/getting-started/install-self-hosted">Auto-alojamiento</a> ·
|
||||
<a href="https://docs.dify.ai">Documentación</a> ·
|
||||
<a href="https://cal.com/guchenhe/dify-demo">Programar demostración</a>
|
||||
<a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Consultas empresariales (en inglés)</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
|
|
@ -29,13 +29,16 @@
|
|||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="./README.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/Inglés-d9d9d9"></a>
|
||||
<a href="./README_CN.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
|
||||
<a href="./README_JA.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
|
||||
<a href="./README_ES.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/Español-d9d9d9"></a>
|
||||
<a href="./README_KL.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/Français-d9d9d9"></a>
|
||||
<a href="./README_FR.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
|
||||
<a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
|
||||
<a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
|
||||
<a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
|
||||
<a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
|
||||
<a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
|
||||
<a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
|
||||
<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>
|
||||
|
||||
#
|
||||
|
|
@ -69,7 +72,7 @@ Dify es una plataforma de desarrollo de aplicaciones de LLM de código abierto.
|
|||
**5. Capacidades de agente**:
|
||||
Puedes definir agent
|
||||
|
||||
es basados en LLM Function Calling o ReAct, y agregar herramientas preconstruidas o personalizadas para el agente. Dify proporciona más de 50 herramientas integradas para agentes de IA, como Búsqueda de Google, DELL·E, Difusión Estable y WolframAlpha.
|
||||
es basados en LLM Function Calling o ReAct, y agregar herramientas preconstruidas o personalizadas para el agente. Dify proporciona más de 50 herramientas integradas para agentes de IA, como Búsqueda de Google, DALL·E, Difusión Estable y WolframAlpha.
|
||||
|
||||
**6. LLMOps**:
|
||||
Supervisa y analiza registros de aplicaciones y rendimiento a lo largo del tiempo. Podrías mejorar continuamente prompts, conjuntos de datos y modelos basados en datos de producción y anotaciones.
|
||||
|
|
@ -155,7 +158,7 @@ Pon rápidamente Dify en funcionamiento en tu entorno con esta [guía de inicio
|
|||
Usa nuestra [documentación](https://docs.dify.ai) para más referencias e instrucciones más detalladas.
|
||||
|
||||
- **Dify para Empresas / Organizaciones</br>**
|
||||
Proporcionamos características adicionales centradas en la empresa. [Programa una reunión con nosotros](https://cal.com/guchenhe/30min) o [envíanos un correo electrónico](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) para discutir las necesidades empresariales. </br>
|
||||
Proporcionamos características adicionales centradas en la empresa. [Envíanos un correo electrónico](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) para discutir las necesidades empresariales. </br>
|
||||
> Para startups y pequeñas empresas que utilizan AWS, echa un vistazo a [Dify Premium en AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) e impleméntalo en tu propio VPC de AWS con un clic. Es una AMI asequible que ofrece la opción de crear aplicaciones con logotipo y marca personalizados.
|
||||
|
||||
|
||||
|
|
@ -227,23 +230,6 @@ Al mismo tiempo, considera apoyar a Dify compartiéndolo en redes sociales y en
|
|||
* [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.
|
||||
|
||||
O, programa una reunión directamente con un miembro del equipo:
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<th>Punto de Contacto</th>
|
||||
<th>Propósito</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
|
||||
<td>Consultas comerciales y retroalimentación del producto</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
|
||||
<td>Contribuciones, problemas y solicitudes de características</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
## Historial de Estrellas
|
||||
|
||||
[](https://star-history.com/#langgenius/dify&Date)
|
||||
|
|
@ -255,4 +241,4 @@ Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En
|
|||
|
||||
## Licencia
|
||||
|
||||
Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.
|
||||
Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.
|
||||
|
|
|
|||
40
README_FR.md
40
README_FR.md
|
|
@ -4,7 +4,7 @@
|
|||
<a href="https://cloud.dify.ai">Dify Cloud</a> ·
|
||||
<a href="https://docs.dify.ai/getting-started/install-self-hosted">Auto-hébergement</a> ·
|
||||
<a href="https://docs.dify.ai">Documentation</a> ·
|
||||
<a href="https://cal.com/guchenhe/dify-demo">Planifier une démo</a>
|
||||
<a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Demande d’entreprise (en anglais seulement)</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
|
|
@ -29,13 +29,16 @@
|
|||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="./README.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/Anglais-d9d9d9"></a>
|
||||
<a href="./README_CN.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
|
||||
<a href="./README_JA.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
|
||||
<a href="./README_ES.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/Español-d9d9d9"></a>
|
||||
<a href="./README_KL.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/Français-d9d9d9"></a>
|
||||
<a href="./README_FR.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
|
||||
<a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
|
||||
<a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
|
||||
<a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
|
||||
<a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
|
||||
<a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
|
||||
<a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
|
||||
<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>
|
||||
|
||||
#
|
||||
|
|
@ -69,7 +72,7 @@ Dify est une plateforme de développement d'applications LLM open source. Son in
|
|||
**5. Capac
|
||||
|
||||
ités d'agent**:
|
||||
Vous pouvez définir des agents basés sur l'appel de fonction LLM ou ReAct, et ajouter des outils pré-construits ou personnalisés pour l'agent. Dify fournit plus de 50 outils intégrés pour les agents d'IA, tels que la recherche Google, DELL·E, Stable Diffusion et WolframAlpha.
|
||||
Vous pouvez définir des agents basés sur l'appel de fonction LLM ou ReAct, et ajouter des outils pré-construits ou personnalisés pour l'agent. Dify fournit plus de 50 outils intégrés pour les agents d'IA, tels que la recherche Google, DALL·E, Stable Diffusion et WolframAlpha.
|
||||
|
||||
**6. LLMOps**:
|
||||
Surveillez et analysez les journaux d'application et les performances au fil du temps. Vous pouvez continuellement améliorer les prompts, les ensembles de données et les modèles en fonction des données de production et des annotations.
|
||||
|
|
@ -155,7 +158,7 @@ Lancez rapidement Dify dans votre environnement avec ce [guide de démarrage](#q
|
|||
Utilisez notre [documentation](https://docs.dify.ai) pour plus de références et des instructions plus détaillées.
|
||||
|
||||
- **Dify pour les entreprises / organisations</br>**
|
||||
Nous proposons des fonctionnalités supplémentaires adaptées aux entreprises. [Planifiez une réunion avec nous](https://cal.com/guchenhe/30min) ou [envoyez-nous un e-mail](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) pour discuter des besoins de l'entreprise. </br>
|
||||
Nous proposons des fonctionnalités supplémentaires adaptées aux entreprises. [Envoyez-nous un e-mail](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) pour discuter des besoins de l'entreprise. </br>
|
||||
> Pour les startups et les petites entreprises utilisant AWS, consultez [Dify Premium sur AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) et déployez-le dans votre propre VPC AWS en un clic. C'est une offre AMI abordable avec la possibilité de créer des applications avec un logo et une marque personnalisés.
|
||||
|
||||
|
||||
|
|
@ -225,23 +228,6 @@ Dans le même temps, veuillez envisager de soutenir Dify en le partageant sur le
|
|||
* [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.
|
||||
|
||||
Ou, planifiez directement une réunion avec un membre de l'équipe:
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<th>Point de contact</th>
|
||||
<th>Objectif</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
|
||||
<td>Demandes commerciales & retours produit</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
|
||||
<td>Contributions, problèmes & demandes de fonctionnalités</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
## Historique des étoiles
|
||||
|
||||
[](https://star-history.com/#langgenius/dify&Date)
|
||||
|
|
|
|||
45
README_JA.md
45
README_JA.md
|
|
@ -4,7 +4,7 @@
|
|||
<a href="https://cloud.dify.ai">Dify Cloud</a> ·
|
||||
<a href="https://docs.dify.ai/getting-started/install-self-hosted">セルフホスティング</a> ·
|
||||
<a href="https://docs.dify.ai">ドキュメント</a> ·
|
||||
<a href="https://cal.com/guchenhe/dify-demo">デモの予約</a>
|
||||
<a href="https://udify.app/chat/22L1zSxg6yW1cWQg">企業のお問い合わせ（英語のみ）</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
|
|
@ -29,13 +29,16 @@
|
|||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="./README.md"><img alt="先月のコミット" src="https://img.shields.io/badge/English-d9d9d9"></a>
|
||||
<a href="./README_CN.md"><img alt="先月のコミット" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
|
||||
<a href="./README_JA.md"><img alt="先月のコミット" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
|
||||
<a href="./README_ES.md"><img alt="先月のコミット" src="https://img.shields.io/badge/Español-d9d9d9"></a>
|
||||
<a href="./README_KL.md"><img alt="先月のコミット" src="https://img.shields.io/badge/Français-d9d9d9"></a>
|
||||
<a href="./README_FR.md"><img alt="先月のコミット" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="先月のコミット" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
|
||||
<a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
|
||||
<a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
|
||||
<a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
|
||||
<a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
|
||||
<a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
|
||||
<a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
|
||||
<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>
|
||||
|
||||
#
|
||||
|
|
@ -68,7 +71,7 @@ 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
|
|||
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。
|
||||
|
||||
**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、DELL·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。
|
||||
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。
|
||||
|
||||
**6. LLMOps**:
|
||||
アプリケーションのログやパフォーマンスを監視と分析し、生産のデータと注釈に基づいて、プロンプト、データセット、モデルを継続的に改善できます。
|
||||
|
|
@ -154,7 +157,7 @@ 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
|
|||
詳しくは[ドキュメント](https://docs.dify.ai)をご覧ください。
|
||||
|
||||
- **企業/組織向けのDify</br>**
|
||||
企業中心の機能を提供しています。[こちらからミーティングを予約](https://cal.com/guchenhe/30min)したり、[メールを送信](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)して企業のニーズについて相談してください。 </br>
|
||||
企業中心の機能を提供しています。[メールを送信](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)して企業のニーズについて相談してください。 </br>
|
||||
> AWSを使用しているスタートアップ企業や中小企業の場合は、[AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6)のDify Premiumをチェックして、ワンクリックで自分のAWS VPCにデプロイできます。さらに、手頃な価格のAMIオファリングどして、ロゴやブランディングをカスタマイズしてアプリケーションを作成するオプションがあります。
|
||||
|
||||
|
||||
|
|
@ -224,28 +227,6 @@ docker compose up -d
|
|||
* [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。
|
||||
|
||||
または、直接チームメンバーとミーティングをスケジュール：
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<th>連絡先</th>
|
||||
<th>目的</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='https://cal.com
|
||||
|
||||
/guchenhe/30min'>ミーティング</a></td>
|
||||
<td>無料の30分間のミーティングをスケジュール</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='https://github.com/langgenius/dify/issues'>技術サポート</a></td>
|
||||
<td>技術的な問題やサポートに関する質問</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry'>営業担当</a></td>
|
||||
<td>法人ライセンスに関するお問い合わせ</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
|
||||
## ライセンス
|
||||
|
|
|
|||
42
README_KL.md
42
README_KL.md
|
|
@ -4,7 +4,7 @@
|
|||
<a href="https://cloud.dify.ai">Dify Cloud</a> ·
|
||||
<a href="https://docs.dify.ai/getting-started/install-self-hosted">Self-hosting</a> ·
|
||||
<a href="https://docs.dify.ai">Documentation</a> ·
|
||||
<a href="https://cal.com/guchenhe/dify-demo">Schedule demo</a>
|
||||
<a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Commercial enquiries</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
|
|
@ -29,13 +29,16 @@
|
|||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="./README.md"><img alt="Commits last month" src="https://img.shields.io/badge/English-d9d9d9"></a>
|
||||
<a href="./README_CN.md"><img alt="Commits last month" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
|
||||
<a href="./README_JA.md"><img alt="Commits last month" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
|
||||
<a href="./README_ES.md"><img alt="Commits last month" src="https://img.shields.io/badge/Español-d9d9d9"></a>
|
||||
<a href="./README_KL.md"><img alt="Commits last month" src="https://img.shields.io/badge/Français-d9d9d9"></a>
|
||||
<a href="./README_FR.md"><img alt="Commits last month" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="Commits last month" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
|
||||
<a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
|
||||
<a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
|
||||
<a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
|
||||
<a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
|
||||
<a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
|
||||
<a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
|
||||
<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>
|
||||
|
||||
#
|
||||
|
|
@ -67,7 +70,7 @@ Dify is an open-source LLM app development platform. Its intuitive interface com
|
|||
Extensive RAG capabilities that cover everything from document ingestion to retrieval, with out-of-box support for text extraction from PDFs, PPTs, and other common document formats.
|
||||
|
||||
**5. Agent capabilities**:
|
||||
You can define agents based on LLM Function Calling or ReAct, and add pre-built or custom tools for the agent. Dify provides 50+ built-in tools for AI agents, such as Google Search, DELL·E, Stable Diffusion and WolframAlpha.
|
||||
You can define agents based on LLM Function Calling or ReAct, and add pre-built or custom tools for the agent. Dify provides 50+ built-in tools for AI agents, such as Google Search, DALL·E, Stable Diffusion and WolframAlpha.
|
||||
|
||||
**6. LLMOps**:
|
||||
Monitor and analyze application logs and performance over time. You could continuously improve prompts, datasets, and models based on production data and annotations.
|
||||
|
|
@ -155,7 +158,7 @@ Quickly get Dify running in your environment with this [starter guide](#quick-st
|
|||
Use our [documentation](https://docs.dify.ai) for further references and more in-depth instructions.
|
||||
|
||||
- **Dify for Enterprise / Organizations</br>**
|
||||
We provide additional enterprise-centric features. [Schedule a meeting with us](https://cal.com/guchenhe/30min) or [send us an email](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs. </br>
|
||||
We provide additional enterprise-centric features. [Send us an email](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs. </br>
|
||||
> For startups and small businesses using AWS, check out [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) and deploy it to your own AWS VPC with one-click. It's an affordable AMI offering with the option to create apps with custom logo and branding.
|
||||
|
||||
|
||||
|
|
@ -227,23 +230,6 @@ At the same time, please consider supporting Dify by sharing it on social media
|
|||
* [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.
|
||||
|
||||
Or, schedule a meeting directly with a team member:
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<th>Point of Contact</th>
|
||||
<th>Purpose</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
|
||||
<td>Business enquiries & product feedback</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
|
||||
<td>Contributions, issues & feature requests</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
## Star History
|
||||
|
||||
[](https://star-history.com/#langgenius/dify&Date)
|
||||
|
|
@ -255,4 +241,4 @@ To protect your privacy, please avoid posting security issues on GitHub. Instead
|
|||
|
||||
## License
|
||||
|
||||
This repository is available under the [Dify Open Source License](LICENSE), which is essentially Apache 2.0 with a few additional restrictions.
|
||||
This repository is available under the [Dify Open Source License](LICENSE), which is essentially Apache 2.0 with a few additional restrictions.
|
||||
|
|
|
|||
27
README_KR.md
27
README_KR.md
|
|
@ -4,7 +4,7 @@
|
|||
<a href="https://cloud.dify.ai">Dify 클라우드</a> ·
|
||||
<a href="https://docs.dify.ai/getting-started/install-self-hosted">셀프-호스팅</a> ·
|
||||
<a href="https://docs.dify.ai">문서</a> ·
|
||||
<a href="https://cal.com/guchenhe/60-min-meeting">기업 문의</a>
|
||||
<a href="https://udify.app/chat/22L1zSxg6yW1cWQg">기업 문의 (영어만 가능)</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
|
|
@ -35,7 +35,10 @@
|
|||
<a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
|
||||
<a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
|
||||
<a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="한국어 README" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
|
||||
<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>
|
||||
|
||||
|
|
@ -63,7 +66,7 @@
|
|||
문서 수집부터 검색까지 모든 것을 다루며, PDF, PPT 및 기타 일반적인 문서 형식에서 텍스트 추출을 위한 기본 지원이 포함되어 있는 광범위한 RAG 기능을 제공합니다.
|
||||
|
||||
**5. 에이전트 기능**:
|
||||
LLM 함수 호출 또는 ReAct를 기반으로 에이전트를 정의하고 에이전트에 대해 사전 구축된 도구나 사용자 정의 도구를 추가할 수 있습니다. Dify는 Google Search, DELL·E, Stable Diffusion, WolframAlpha 등 AI 에이전트를 위한 50개 이상의 내장 도구를 제공합니다.
|
||||
LLM 함수 호출 또는 ReAct를 기반으로 에이전트를 정의하고 에이전트에 대해 사전 구축된 도구나 사용자 정의 도구를 추가할 수 있습니다. Dify는 Google Search, DALL·E, Stable Diffusion, WolframAlpha 등 AI 에이전트를 위한 50개 이상의 내장 도구를 제공합니다.
|
||||
|
||||
**6. LLMOps**:
|
||||
시간 경과에 따른 애플리케이션 로그와 성능을 모니터링하고 분석합니다. 생산 데이터와 주석을 기반으로 프롬프트, 데이터세트, 모델을 지속적으로 개선할 수 있습니다.
|
||||
|
|
@ -148,7 +151,7 @@
|
|||
추가 참조 및 더 심층적인 지침은 [문서](https://docs.dify.ai)를 사용하세요.
|
||||
|
||||
- **기업 / 조직을 위한 Dify</br>**
|
||||
우리는 추가적인 기업 중심 기능을 제공합니다. 당사와 [미팅일정](https://cal.com/guchenhe/30min)을 잡거나 [이메일 보내기](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)를 통해 기업 요구 사항을 논의하십시오. </br>
|
||||
우리는 추가적인 기업 중심 기능을 제공합니다. 잡거나 [이메일 보내기](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)를 통해 기업 요구 사항을 논의하십시오. </br>
|
||||
> AWS를 사용하는 스타트업 및 중소기업의 경우 [AWS Marketplace에서 Dify Premium](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6)을 확인하고 한 번의 클릭으로 자체 AWS VPC에 배포하십시오. 맞춤형 로고와 브랜딩이 포함된 앱을 생성할 수 있는 옵션이 포함된 저렴한 AMI 제품입니다.
|
||||
|
||||
|
||||
|
|
@ -217,22 +220,6 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
|
|||
* [디스코드](https://discord.gg/FngNHpbcY7). 애플리케이션 공유 및 커뮤니티와 소통하기에 적합합니다.
|
||||
* [트위터](https://twitter.com/dify_ai). 애플리케이션 공유 및 커뮤니티와 소통하기에 적합합니다.
|
||||
|
||||
또는 팀원과 직접 미팅을 예약하세요:
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<th>연락처</th>
|
||||
<th>목적</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
|
||||
<td>비즈니스 문의 및 제품 피드백</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
|
||||
<td>기여, 이슈 및 기능 요청</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
## Star 히스토리
|
||||
|
||||
|
|
|
|||
237
README_TR.md
Normal file
237
README_TR.md
Normal file
|
|
@ -0,0 +1,237 @@
|
|||
|
||||
|
||||
<p align="center">
|
||||
<a href="https://cloud.dify.ai">Dify Bulut</a> ·
|
||||
<a href="https://docs.dify.ai/getting-started/install-self-hosted">Kendi Sunucunuzda Barındırma</a> ·
|
||||
<a href="https://docs.dify.ai">Dokümantasyon</a> ·
|
||||
<a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Yalnızca İngilizce: Kurumsal Sorgulama</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="https://dify.ai" target="_blank">
|
||||
<img alt="Statik Rozet" src="https://img.shields.io/badge/Ürün-F04438"></a>
|
||||
<a href="https://dify.ai/pricing" target="_blank">
|
||||
<img alt="Statik Rozet" src="https://img.shields.io/badge/ücretsiz-fiyatlandırma?logo=free&color=%20%23155EEF&label=fiyatlandirma&labelColor=%20%23528bff"></a>
|
||||
<a href="https://discord.gg/FngNHpbcY7" target="_blank">
|
||||
<img src="https://img.shields.io/discord/1082486657678311454?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb"
|
||||
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>
|
||||
<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">
|
||||
<img alt="Geçen ay yapılan commitler" src="https://img.shields.io/github/commit-activity/m/langgenius/dify?labelColor=%20%2332b583&color=%20%2312b76a"></a>
|
||||
<a href="https://github.com/langgenius/dify/" target="_blank">
|
||||
<img alt="Kapatılan sorunlar" src="https://img.shields.io/github/issues-search?query=repo%3Alanggenius%2Fdify%20is%3Aclosed&label=kapatilan%20sorunlar&labelColor=%20%237d89b0&color=%20%235d6b98"></a>
|
||||
<a href="https://github.com/langgenius/dify/discussions/" target="_blank">
|
||||
<img alt="Tartışma gönderileri" src="https://img.shields.io/github/discussions/langgenius/dify?labelColor=%20%239b8afb&color=%20%237a5af8"></a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
|
||||
<a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
|
||||
<a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
|
||||
<a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
|
||||
<a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
|
||||
<a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
|
||||
<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>
|
||||
|
||||
|
||||
Dify, açık kaynaklı bir LLM uygulama geliştirme platformudur. Sezgisel arayüzü, AI iş akışı, RAG pipeline'ı, ajan yetenekleri, model yönetimi, gözlemlenebilirlik özellikleri ve daha fazlasını birleştirerek, prototipten üretime hızlıca geçmenizi sağlar. İşte temel özelliklerin bir listesi:
|
||||
</br> </br>
|
||||
|
||||
**1. Workflow**:
|
||||
Görsel bir arayüz üzerinde güçlü AI iş akışları oluşturun ve test edin, aşağıdaki tüm özellikleri ve daha fazlasını kullanarak.
|
||||
|
||||
|
||||
https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
|
||||
|
||||
|
||||
|
||||
**2. Kapsamlı model desteği**:
|
||||
Çok sayıda çıkarım sağlayıcısı ve kendi kendine barındırılan çözümlerden yüzlerce özel / açık kaynaklı LLM ile sorunsuz entegrasyon sağlar. GPT, Mistral, Llama3 ve OpenAI API uyumlu tüm modelleri kapsar. Desteklenen model sağlayıcılarının tam listesine [buradan](https://docs.dify.ai/getting-started/readme/model-providers) ulaşabilirsiniz.
|
||||
|
||||
|
||||
|
||||
|
||||
Özür dilerim, haklısınız. Daha anlamlı ve akıcı bir çeviri yapmaya çalışayım. İşte güncellenmiş çeviri:
|
||||
|
||||
**3. Prompt IDE**:
|
||||
Komut istemlerini oluşturmak, model performansını karşılaştırmak ve sohbet tabanlı uygulamalara metin-konuşma gibi ek özellikler eklemek için kullanıcı dostu bir arayüz.
|
||||
|
||||
**4. RAG Pipeline**:
|
||||
Belge alımından bilgi çekmeye kadar geniş kapsamlı RAG yetenekleri. PDF'ler, PPT'ler ve diğer yaygın belge formatlarından metin çıkarma için hazır destek sunar.
|
||||
|
||||
**5. Ajan yetenekleri**:
|
||||
LLM Fonksiyon Çağırma veya ReAct'a dayalı ajanlar tanımlayabilir ve bu ajanlara önceden hazırlanmış veya özel araçlar ekleyebilirsiniz. Dify, AI ajanları için Google Arama, DALL·E, Stable Diffusion ve WolframAlpha gibi 50'den fazla yerleşik araç sağlar.
|
||||
|
||||
**6. LLMOps**:
|
||||
Uygulama loglarını ve performans metriklerini zaman içinde izleme ve analiz etme imkanı. Üretim ortamından elde edilen verilere ve kullanıcı geri bildirimlerine dayanarak, prompt'ları, veri setlerini ve modelleri sürekli olarak optimize edebilirsiniz. Bu sayede, AI uygulamanızın performansını ve doğruluğunu sürekli olarak artırabilirsiniz.
|
||||
|
||||
**7. Hizmet Olarak Backend**:
|
||||
Dify'ın tüm özellikleri ilgili API'lerle birlikte gelir, böylece Dify'ı kendi iş mantığınıza kolayca entegre edebilirsiniz.
|
||||
|
||||
|
||||
## Özellik karşılaştırması
|
||||
<table style="width: 100%;">
|
||||
<tr>
|
||||
<th align="center">Özellik</th>
|
||||
<th align="center">Dify.AI</th>
|
||||
<th align="center">LangChain</th>
|
||||
<th align="center">Flowise</th>
|
||||
<th align="center">OpenAI Assistants API</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Programlama Yaklaşımı</td>
|
||||
<td align="center">API + Uygulama odaklı</td>
|
||||
<td align="center">Python Kodu</td>
|
||||
<td align="center">Uygulama odaklı</td>
|
||||
<td align="center">API odaklı</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Desteklenen LLM'ler</td>
|
||||
<td align="center">Zengin Çeşitlilik</td>
|
||||
<td align="center">Zengin Çeşitlilik</td>
|
||||
<td align="center">Zengin Çeşitlilik</td>
|
||||
<td align="center">Yalnızca OpenAI</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">RAG Motoru</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Ajan</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
<td align="center">✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">İş Akışı</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Gözlemlenebilirlik</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
<td align="center">❌</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Kurumsal Özellikler (SSO/Erişim kontrolü)</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
<td align="center">❌</td>
|
||||
<td align="center">❌</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Yerel Dağıtım</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
## Dify'ı Kullanma
|
||||
|
||||
- **Cloud </br>**
|
||||
İşte verdiğiniz metnin Türkçe çevirisi, kod bloğu içinde:
|
||||
-
|
||||
Herkesin sıfır kurulumla denemesi için bir [Dify Cloud](https://dify.ai) hizmeti sunuyoruz. Bu hizmet, kendi kendine dağıtılan versiyonun tüm yeteneklerini sağlar ve sandbox planında 200 ücretsiz GPT-4 çağrısı içerir.
|
||||
|
||||
- **Dify Topluluk Sürümünü Kendi Sunucunuzda Barındırma</br>**
|
||||
Bu [başlangıç kılavuzu](#quick-start) ile Dify'ı kendi ortamınızda hızlıca çalıştırın.
|
||||
Daha fazla referans ve detaylı talimatlar için [dokümantasyonumuzu](https://docs.dify.ai) kullanın.
|
||||
|
||||
- **Kurumlar / organizasyonlar için Dify</br>**
|
||||
Ek kurumsal odaklı özellikler sunuyoruz. Kurumsal ihtiyaçları görüşmek için [bize bir e-posta gönderin](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry). </br>
|
||||
> AWS kullanan startuplar ve küçük işletmeler için, [AWS Marketplace'deki Dify Premium'a](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) göz atın ve tek tıklamayla kendi AWS VPC'nize dağıtın. Bu, özel logo ve marka ile uygulamalar oluşturma seçeneğine sahip uygun fiyatlı bir AMI teklifdir.
|
||||
|
||||
## Güncel Kalma
|
||||
|
||||
GitHub'da Dify'a yıldız verin ve yeni sürümlerden anında haberdar olun.
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## Hızlı başlangıç
|
||||
> Dify'ı kurmadan önce, makinenizin aşağıdaki minimum sistem gereksinimlerini karşıladığından emin olun:
|
||||
>
|
||||
>- CPU >= 2 Çekirdek
|
||||
>- RAM >= 4GB
|
||||
|
||||
</br>
|
||||
İşte verdiğiniz metnin Türkçe çevirisi, kod bloğu içinde:
|
||||
|
||||
Dify sunucusunu başlatmanın en kolay yolu, [docker-compose.yml](docker/docker-compose.yaml) dosyamızı çalıştırmaktır. Kurulum komutunu çalıştırmadan önce, makinenizde [Docker](https://docs.docker.com/get-docker/) ve [Docker Compose](https://docs.docker.com/compose/install/)'un kurulu olduğundan emin olun:
|
||||
|
||||
```bash
|
||||
cd docker
|
||||
cp .env.example .env
|
||||
docker compose up -d
|
||||
```
|
||||
|
||||
Çalıştırdıktan sonra, tarayıcınızda [http://localhost/install](http://localhost/install) adresinden Dify kontrol paneline erişebilir ve başlangıç ayarları sürecini başlatabilirsiniz.
|
||||
|
||||
> Eğer Dify'a katkıda bulunmak veya ek geliştirmeler yapmak isterseniz, [kaynak koddan dağıtım kılavuzumuza](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code) başvurun.
|
||||
|
||||
## Sonraki adımlar
|
||||
|
||||
Yapılandırmayı özelleştirmeniz gerekiyorsa, lütfen [.env.example](docker/.env.example) dosyamızdaki yorumlara bakın ve `.env` dosyanızdaki ilgili değerleri güncelleyin. Ayrıca, spesifik dağıtım ortamınıza ve gereksinimlerinize bağlı olarak `docker-compose.yaml` dosyasının kendisinde de, imaj sürümlerini, port eşlemelerini veya hacim bağlantılarını değiştirmek gibi ayarlamalar yapmanız gerekebilir. Herhangi bir değişiklik yaptıktan sonra, lütfen `docker-compose up -d` komutunu tekrar çalıştırın. Kullanılabilir tüm ortam değişkenlerinin tam listesini [burada](https://docs.dify.ai/getting-started/install-self-hosted/environments) bulabilirsiniz.
|
||||
|
||||
Yüksek kullanılabilirliğe sahip bir kurulum yapılandırmak isterseniz, Dify'ın Kubernetes üzerine dağıtılmasına olanak tanıyan topluluk katkılı [Helm Charts](https://helm.sh/) ve YAML dosyaları mevcuttur.
|
||||
|
||||
- [@LeoQuote tarafından Helm Chart](https://github.com/douban/charts/tree/master/charts/dify)
|
||||
- [@BorisPolonsky tarafından Helm Chart](https://github.com/BorisPolonsky/dify-helm)
|
||||
- [@Winson-030 tarafından YAML dosyası](https://github.com/Winson-030/dify-kubernetes)
|
||||
|
||||
#### Dağıtım için Terraform Kullanımı
|
||||
|
||||
##### 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)
|
||||
|
||||
## Katkıda Bulunma
|
||||
|
||||
Kod katkısında bulunmak isteyenler için [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakabilirsiniz.
|
||||
Aynı zamanda, lütfen Dify'ı sosyal medyada, etkinliklerde ve konferanslarda paylaşarak desteklemeyi düşünün.
|
||||
|
||||
> Dify'ı Mandarin veya İngilizce dışındaki dillere çevirmemize yardımcı olacak katkıda bulunanlara ihtiyacımız var. Yardımcı olmakla ilgileniyorsanız, lütfen daha fazla bilgi için [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) dosyasına bakın ve [Discord Topluluk Sunucumuzdaki](https://discord.gg/8Tpq4AcN9c) `global-users` kanalında bize bir yorum bırakın.
|
||||
|
||||
**Katkıda Bulunanlar**
|
||||
|
||||
<a href="https://github.com/langgenius/dify/graphs/contributors">
|
||||
<img src="https://contrib.rocks/image?repo=langgenius/dify" />
|
||||
</a>
|
||||
|
||||
## Topluluk & iletişim
|
||||
|
||||
* [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.
|
||||
|
||||
## Star history
|
||||
|
||||
[](https://star-history.com/#langgenius/dify&Date)
|
||||
|
||||
## Güvenlik açıklaması
|
||||
|
||||
Gizliliğinizi korumak için, lütfen güvenlik sorunlarını GitHub'da paylaşmaktan kaçının. Bunun yerine, sorularınızı security@dify.ai adresine gönderin ve size daha detaylı bir cevap vereceğiz.
|
||||
|
||||
## Lisans
|
||||
|
||||
Bu depo, temel olarak Apache 2.0 lisansı ve birkaç ek kısıtlama içeren [Dify Açık Kaynak Lisansı](LICENSE) altında kullanıma sunulmuştur.
|
||||
234
README_VI.md
Normal file
234
README_VI.md
Normal file
|
|
@ -0,0 +1,234 @@
|
|||
|
||||
|
||||
<p align="center">
|
||||
<a href="https://cloud.dify.ai">Dify Cloud</a> ·
|
||||
<a href="https://docs.dify.ai/getting-started/install-self-hosted">Tự triển khai</a> ·
|
||||
<a href="https://docs.dify.ai">Tài liệu</a> ·
|
||||
<a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Yêu cầu doanh nghiệp</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="https://dify.ai" target="_blank">
|
||||
<img alt="Static Badge" src="https://img.shields.io/badge/Product-F04438"></a>
|
||||
<a href="https://dify.ai/pricing" target="_blank">
|
||||
<img alt="Static Badge" src="https://img.shields.io/badge/free-pricing?logo=free&color=%20%23155EEF&label=pricing&labelColor=%20%23528bff"></a>
|
||||
<a href="https://discord.gg/FngNHpbcY7" target="_blank">
|
||||
<img src="https://img.shields.io/discord/1082486657678311454?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb"
|
||||
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>
|
||||
<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">
|
||||
<img alt="Commits tháng trước" src="https://img.shields.io/github/commit-activity/m/langgenius/dify?labelColor=%20%2332b583&color=%20%2312b76a"></a>
|
||||
<a href="https://github.com/langgenius/dify/" target="_blank">
|
||||
<img alt="Vấn đề đã đóng" src="https://img.shields.io/github/issues-search?query=repo%3Alanggenius%2Fdify%20is%3Aclosed&label=issues%20closed&labelColor=%20%237d89b0&color=%20%235d6b98"></a>
|
||||
<a href="https://github.com/langgenius/dify/discussions/" target="_blank">
|
||||
<img alt="Bài thảo luận" src="https://img.shields.io/github/discussions/langgenius/dify?labelColor=%20%239b8afb&color=%20%237a5af8"></a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
|
||||
<a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
|
||||
<a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
|
||||
<a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
|
||||
<a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
|
||||
<a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
|
||||
<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>
|
||||
|
||||
|
||||
Dify là một nền tảng phát triển ứng dụng LLM mã nguồn mở. Giao diện trực quan kết hợp quy trình làm việc AI, mô hình RAG, khả năng tác nhân, quản lý mô hình, tính năng quan sát và hơn thế nữa, cho phép bạn nhanh chóng chuyển từ nguyên mẫu sang sản phẩm. Đây là danh sách các tính năng cốt lõi:
|
||||
</br> </br>
|
||||
|
||||
**1. Quy trình làm việc**:
|
||||
Xây dựng và kiểm tra các quy trình làm việc AI mạnh mẽ trên một canvas trực quan, tận dụng tất cả các tính năng sau đây và hơn thế nữa.
|
||||
|
||||
|
||||
https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
|
||||
|
||||
|
||||
|
||||
**2. Hỗ trợ mô hình toàn diện**:
|
||||
Tích hợp liền mạch với hàng trăm mô hình LLM độc quyền / mã nguồn mở từ hàng chục nhà cung cấp suy luận và giải pháp tự lưu trữ, bao gồm GPT, Mistral, Llama3, và bất kỳ mô hình tương thích API OpenAI nào. Danh sách đầy đủ các nhà cung cấp mô hình được hỗ trợ có thể được tìm thấy [tại đây](https://docs.dify.ai/getting-started/readme/model-providers).
|
||||
|
||||
|
||||
|
||||
|
||||
**3. IDE Prompt**:
|
||||
Giao diện trực quan để tạo prompt, so sánh hiệu suất mô hình và thêm các tính năng bổ sung như chuyển văn bản thành giọng nói cho một ứng dụng dựa trên trò chuyện.
|
||||
|
||||
**4. Mô hình RAG**:
|
||||
Khả năng RAG mở rộng bao gồm mọi thứ từ nhập tài liệu đến truy xuất, với hỗ trợ sẵn có cho việc trích xuất văn bản từ PDF, PPT và các định dạng tài liệu phổ biến khác.
|
||||
|
||||
**5. Khả năng tác nhân**:
|
||||
Bạn có thể định nghĩa các tác nhân dựa trên LLM Function Calling hoặc ReAct, và thêm các công cụ được xây dựng sẵn hoặc tùy chỉnh cho tác nhân. Dify cung cấp hơn 50 công cụ tích hợp sẵn cho các tác nhân AI, như Google Search, DALL·E, Stable Diffusion và WolframAlpha.
|
||||
|
||||
**6. LLMOps**:
|
||||
Giám sát và phân tích nhật ký và hiệu suất ứng dụng theo thời gian. Bạn có thể liên tục cải thiện prompt, bộ dữ liệu và mô hình dựa trên dữ liệu sản xuất và chú thích.
|
||||
|
||||
**7. Backend-as-a-Service**:
|
||||
Tất cả các dịch vụ của Dify đều đi kèm với các API tương ứng, vì vậy bạn có thể dễ dàng tích hợp Dify vào logic kinh doanh của riêng mình.
|
||||
|
||||
|
||||
## So sánh tính năng
|
||||
<table style="width: 100%;">
|
||||
<tr>
|
||||
<th align="center">Tính năng</th>
|
||||
<th align="center">Dify.AI</th>
|
||||
<th align="center">LangChain</th>
|
||||
<th align="center">Flowise</th>
|
||||
<th align="center">OpenAI Assistants API</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Phương pháp lập trình</td>
|
||||
<td align="center">Hướng API + Ứng dụng</td>
|
||||
<td align="center">Mã Python</td>
|
||||
<td align="center">Hướng ứng dụng</td>
|
||||
<td align="center">Hướng API</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">LLMs được hỗ trợ</td>
|
||||
<td align="center">Đa dạng phong phú</td>
|
||||
<td align="center">Đa dạng phong phú</td>
|
||||
<td align="center">Đa dạng phong phú</td>
|
||||
<td align="center">Chỉ OpenAI</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">RAG Engine</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Agent</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
<td align="center">✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Quy trình làm việc</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Khả năng quan sát</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
<td align="center">❌</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Tính năng doanh nghiệp (SSO/Kiểm soát truy cập)</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
<td align="center">❌</td>
|
||||
<td align="center">❌</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Triển khai cục bộ</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
## Sử dụng Dify
|
||||
|
||||
- **Cloud </br>**
|
||||
Chúng tôi lưu trữ dịch vụ [Dify Cloud](https://dify.ai) cho bất kỳ ai muốn thử mà không cần cài đặt. Nó cung cấp tất cả các khả năng của phiên bản tự triển khai và bao gồm 200 lượt gọi GPT-4 miễn phí trong gói sandbox.
|
||||
|
||||
- **Tự triển khai Dify Community Edition</br>**
|
||||
Nhanh chóng chạy Dify trong môi trường của bạn với [hướng dẫn bắt đầu](#quick-start) này.
|
||||
Sử dụng [tài liệu](https://docs.dify.ai) của chúng tôi để tham khảo thêm và nhận hướng dẫn chi tiết hơn.
|
||||
|
||||
- **Dify cho doanh nghiệp / tổ chức</br>**
|
||||
Chúng tôi cung cấp các tính năng bổ sung tập trung vào doanh nghiệp. [Ghi lại câu hỏi của bạn cho chúng tôi thông qua chatbot này](https://udify.app/chat/22L1zSxg6yW1cWQg) hoặc [gửi email cho chúng tôi](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) để thảo luận về nhu cầu doanh nghiệp. </br>
|
||||
> Đối với các công ty khởi nghiệp và doanh nghiệp nhỏ sử dụng AWS, hãy xem [Dify Premium trên AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) và triển khai nó vào AWS VPC của riêng bạn chỉ với một cú nhấp chuột. Đây là một AMI giá cả phải chăng với tùy chọn tạo ứng dụng với logo và thương hiệu tùy chỉnh.
|
||||
|
||||
|
||||
## Luôn cập nhật
|
||||
|
||||
Yêu thích Dify trên GitHub và được thông báo ngay lập tức về các bản phát hành mới.
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## Bắt đầu nhanh
|
||||
> Trước khi cài đặt Dify, hãy đảm bảo máy của bạn đáp ứng các yêu cầu hệ thống tối thiểu sau:
|
||||
>
|
||||
>- CPU >= 2 Core
|
||||
>- RAM >= 4GB
|
||||
|
||||
</br>
|
||||
|
||||
Cách dễ nhất để khởi động máy chủ Dify là chạy tệp [docker-compose.yml](docker/docker-compose.yaml) của chúng tôi. Trước khi chạy lệnh cài đặt, hãy đảm bảo rằng [Docker](https://docs.docker.com/get-docker/) và [Docker Compose](https://docs.docker.com/compose/install/) đã được cài đặt trên máy của bạn:
|
||||
|
||||
```bash
|
||||
cd docker
|
||||
cp .env.example .env
|
||||
docker compose up -d
|
||||
```
|
||||
|
||||
Sau khi chạy, bạn có thể truy cập bảng điều khiển Dify trong trình duyệt của bạn tại [http://localhost/install](http://localhost/install) và bắt đầu quá trình khởi tạo.
|
||||
|
||||
> Nếu bạn muốn đóng góp cho Dify hoặc phát triển thêm, hãy tham khảo [hướng dẫn triển khai từ mã nguồn](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code) của chúng tôi
|
||||
|
||||
## Các bước tiếp theo
|
||||
|
||||
Nếu bạn cần tùy chỉnh cấu hình, vui lòng tham khảo các nhận xét trong tệp [.env.example](docker/.env.example) của chúng tôi và cập nhật các giá trị tương ứng trong tệp `.env` của bạn. Ngoài ra, bạn có thể cần điều chỉnh tệp `docker-compose.yaml`, chẳng hạn như thay đổi phiên bản hình ảnh, ánh xạ cổng hoặc gắn kết khối lượng, dựa trên môi trường triển khai cụ thể và yêu cầu của bạn. Sau khi thực hiện bất kỳ thay đổi nào, vui lòng chạy lại `docker-compose up -d`. Bạn có thể tìm thấy danh sách đầy đủ các biến môi trường có sẵn [tại đây](https://docs.dify.ai/getting-started/install-self-hosted/environments).
|
||||
|
||||
Nếu bạn muốn cấu hình một cài đặt có độ sẵn sàng cao, có các [Helm Charts](https://helm.sh/) và tệp YAML do cộng đồng đóng góp cho phép Dify được triển khai trên Kubernetes.
|
||||
|
||||
- [Helm Chart bởi @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
|
||||
- [Helm Chart bởi @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
|
||||
- [Tệp YAML bởi @Winson-030](https://github.com/Winson-030/dify-kubernetes)
|
||||
|
||||
#### Sử dụng Terraform để Triển khai
|
||||
|
||||
##### 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)
|
||||
|
||||
## 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.
|
||||
Đồng thời, vui lòng xem xét hỗ trợ Dify bằng cách chia sẻ nó trên mạng xã hội và tại các sự kiện và hội nghị.
|
||||
|
||||
|
||||
> Chúng tôi đang tìm kiếm người đóng góp để giúp dịch Dify sang các ngôn ngữ khác ngoài tiếng Trung hoặc tiếng Anh. Nếu bạn quan tâm đến việc giúp đỡ, vui lòng xem [README i18n](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) để biết thêm thông tin và để lại bình luận cho chúng tôi trong kênh `global-users` của [Máy chủ Cộng đồng Discord](https://discord.gg/8Tpq4AcN9c) của chúng tôi.
|
||||
|
||||
**Người đóng góp**
|
||||
|
||||
<a href="https://github.com/langgenius/dify/graphs/contributors">
|
||||
<img src="https://contrib.rocks/image?repo=langgenius/dify" />
|
||||
</a>
|
||||
|
||||
## Cộng đồng & liên hệ
|
||||
|
||||
* [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.
|
||||
|
||||
## Lịch sử Yêu thích
|
||||
|
||||
[](https://star-history.com/#langgenius/dify&Date)
|
||||
|
||||
## Tiết lộ bảo mật
|
||||
|
||||
Để bảo vệ quyền riêng tư của bạn, vui lòng tránh đăng các vấn đề bảo mật trên GitHub. Thay vào đó, hãy gửi câu hỏi của bạn đến security@dify.ai và chúng tôi sẽ cung cấp cho bạn câu trả lời chi tiết hơn.
|
||||
|
||||
## Giấy phép
|
||||
|
||||
Kho lưu trữ này có sẵn theo [Giấy phép Mã nguồn Mở Dify](LICENSE), về cơ bản là Apache 2.0 với một vài hạn chế bổ sung.
|
||||
|
|
@ -130,6 +130,12 @@ TENCENT_VECTOR_DB_DATABASE=dify
|
|||
TENCENT_VECTOR_DB_SHARD=1
|
||||
TENCENT_VECTOR_DB_REPLICAS=2
|
||||
|
||||
# ElasticSearch configuration
|
||||
ELASTICSEARCH_HOST=127.0.0.1
|
||||
ELASTICSEARCH_PORT=9200
|
||||
ELASTICSEARCH_USERNAME=elastic
|
||||
ELASTICSEARCH_PASSWORD=elastic
|
||||
|
||||
# PGVECTO_RS configuration
|
||||
PGVECTO_RS_HOST=localhost
|
||||
PGVECTO_RS_PORT=5431
|
||||
|
|
|
|||
|
|
@ -12,6 +12,7 @@ ENV POETRY_CACHE_DIR=/tmp/poetry_cache
|
|||
ENV POETRY_NO_INTERACTION=1
|
||||
ENV POETRY_VIRTUALENVS_IN_PROJECT=true
|
||||
ENV POETRY_VIRTUALENVS_CREATE=true
|
||||
ENV POETRY_REQUESTS_TIMEOUT=15
|
||||
|
||||
FROM base AS packages
|
||||
|
||||
|
|
@ -41,8 +42,12 @@ ENV TZ=UTC
|
|||
WORKDIR /app/api
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y --no-install-recommends curl wget vim nodejs ffmpeg libgmp-dev libmpfr-dev libmpc-dev \
|
||||
&& apt-get autoremove \
|
||||
&& apt-get install -y --no-install-recommends curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
|
||||
&& echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
|
||||
&& apt-get update \
|
||||
# For Security
|
||||
&& apt-get install -y --no-install-recommends zlib1g=1:1.3.dfsg+really1.3.1-1 expat=2.6.2-1 libldap-2.5-0=2.5.18+dfsg-2 perl=5.38.2-5 libsqlite3-0=3.46.0-1 \
|
||||
&& apt-get autoremove -y \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# Copy Python environment and packages
|
||||
|
|
@ -50,6 +55,9 @@ ENV VIRTUAL_ENV=/app/api/.venv
|
|||
COPY --from=packages ${VIRTUAL_ENV} ${VIRTUAL_ENV}
|
||||
ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
|
||||
|
||||
# Download nltk data
|
||||
RUN python -c "import nltk; nltk.download('punkt')"
|
||||
|
||||
# Copy source code
|
||||
COPY . /app/api/
|
||||
|
||||
|
|
|
|||
|
|
@ -261,6 +261,7 @@ def after_request(response):
|
|||
@app.route('/health')
|
||||
def health():
|
||||
return Response(json.dumps({
|
||||
'pid': os.getpid(),
|
||||
'status': 'ok',
|
||||
'version': app.config['CURRENT_VERSION']
|
||||
}), status=200, content_type="application/json")
|
||||
|
|
@ -284,6 +285,7 @@ def threads():
|
|||
})
|
||||
|
||||
return {
|
||||
'pid': os.getpid(),
|
||||
'thread_num': num_threads,
|
||||
'threads': thread_list
|
||||
}
|
||||
|
|
@ -293,6 +295,7 @@ def threads():
|
|||
def pool_stat():
|
||||
engine = db.engine
|
||||
return {
|
||||
'pid': os.getpid(),
|
||||
'pool_size': engine.pool.size(),
|
||||
'checked_in_connections': engine.pool.checkedin(),
|
||||
'checked_out_connections': engine.pool.checkedout(),
|
||||
|
|
|
|||
|
|
@ -344,6 +344,14 @@ def migrate_knowledge_vector_database():
|
|||
"vector_store": {"class_prefix": collection_name}
|
||||
}
|
||||
dataset.index_struct = json.dumps(index_struct_dict)
|
||||
elif vector_type == VectorType.ELASTICSEARCH:
|
||||
dataset_id = dataset.id
|
||||
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)
|
||||
else:
|
||||
raise ValueError(f"Vector store {vector_type} is not supported.")
|
||||
|
||||
|
|
|
|||
|
|
@ -12,19 +12,14 @@ from configs.packaging import PackagingInfo
|
|||
class DifyConfig(
|
||||
# Packaging info
|
||||
PackagingInfo,
|
||||
|
||||
# Deployment configs
|
||||
DeploymentConfig,
|
||||
|
||||
# Feature configs
|
||||
FeatureConfig,
|
||||
|
||||
# Middleware configs
|
||||
MiddlewareConfig,
|
||||
|
||||
# Extra service configs
|
||||
ExtraServiceConfig,
|
||||
|
||||
# Enterprise feature configs
|
||||
# **Before using, please contact business@dify.ai by email to inquire about licensing matters.**
|
||||
EnterpriseFeatureConfig,
|
||||
|
|
@ -36,7 +31,6 @@ class DifyConfig(
|
|||
env_file='.env',
|
||||
env_file_encoding='utf-8',
|
||||
frozen=True,
|
||||
|
||||
# ignore extra attributes
|
||||
extra='ignore',
|
||||
)
|
||||
|
|
@ -67,3 +61,5 @@ class DifyConfig(
|
|||
SSRF_PROXY_HTTPS_URL: str | None = None
|
||||
|
||||
MODERATION_BUFFER_SIZE: int = Field(default=300, description='The buffer size for moderation.')
|
||||
|
||||
MAX_VARIABLE_SIZE: int = Field(default=5 * 1024, description='The maximum size of a variable. default is 5KB.')
|
||||
|
|
|
|||
|
|
@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
|
|||
|
||||
CURRENT_VERSION: str = Field(
|
||||
description='Dify version',
|
||||
default='0.6.15',
|
||||
default='0.7.0',
|
||||
)
|
||||
|
||||
COMMIT_SHA: str = Field(
|
||||
|
|
|
|||
|
|
@ -1,2 +1 @@
|
|||
# TODO: Update all string in code to use this constant
|
||||
HIDDEN_VALUE = '[__HIDDEN__]'
|
||||
HIDDEN_VALUE = '[__HIDDEN__]'
|
||||
|
|
|
|||
|
|
@ -15,6 +15,8 @@ language_timezone_mapping = {
|
|||
'ro-RO': 'Europe/Bucharest',
|
||||
'pl-PL': 'Europe/Warsaw',
|
||||
'hi-IN': 'Asia/Kolkata',
|
||||
'tr-TR': 'Europe/Istanbul',
|
||||
'fa-IR': 'Asia/Tehran',
|
||||
}
|
||||
|
||||
languages = list(language_timezone_mapping.keys())
|
||||
|
|
|
|||
|
|
@ -17,6 +17,7 @@ from .app import (
|
|||
audio,
|
||||
completion,
|
||||
conversation,
|
||||
conversation_variables,
|
||||
generator,
|
||||
message,
|
||||
model_config,
|
||||
|
|
|
|||
|
|
@ -23,8 +23,7 @@ class AnnotationReplyActionApi(Resource):
|
|||
@account_initialization_required
|
||||
@cloud_edition_billing_resource_check('annotation')
|
||||
def post(self, app_id, action):
|
||||
# The role of the current user in the ta table must be admin or owner
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
|
||||
app_id = str(app_id)
|
||||
|
|
@ -47,8 +46,7 @@ class AppAnnotationSettingDetailApi(Resource):
|
|||
@login_required
|
||||
@account_initialization_required
|
||||
def get(self, app_id):
|
||||
# The role of the current user in the ta table must be admin or owner
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
|
||||
app_id = str(app_id)
|
||||
|
|
@ -61,8 +59,7 @@ class AppAnnotationSettingUpdateApi(Resource):
|
|||
@login_required
|
||||
@account_initialization_required
|
||||
def post(self, app_id, annotation_setting_id):
|
||||
# The role of the current user in the ta table must be admin or owner
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
|
||||
app_id = str(app_id)
|
||||
|
|
@ -82,8 +79,7 @@ class AnnotationReplyActionStatusApi(Resource):
|
|||
@account_initialization_required
|
||||
@cloud_edition_billing_resource_check('annotation')
|
||||
def get(self, app_id, job_id, action):
|
||||
# The role of the current user in the ta table must be admin or owner
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
|
||||
job_id = str(job_id)
|
||||
|
|
@ -110,8 +106,7 @@ class AnnotationListApi(Resource):
|
|||
@login_required
|
||||
@account_initialization_required
|
||||
def get(self, app_id):
|
||||
# The role of the current user in the ta table must be admin or owner
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
|
||||
page = request.args.get('page', default=1, type=int)
|
||||
|
|
@ -135,8 +130,7 @@ class AnnotationExportApi(Resource):
|
|||
@login_required
|
||||
@account_initialization_required
|
||||
def get(self, app_id):
|
||||
# The role of the current user in the ta table must be admin or owner
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
|
||||
app_id = str(app_id)
|
||||
|
|
@ -154,8 +148,7 @@ class AnnotationCreateApi(Resource):
|
|||
@cloud_edition_billing_resource_check('annotation')
|
||||
@marshal_with(annotation_fields)
|
||||
def post(self, app_id):
|
||||
# The role of the current user in the ta table must be admin or owner
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
|
||||
app_id = str(app_id)
|
||||
|
|
@ -174,8 +167,7 @@ class AnnotationUpdateDeleteApi(Resource):
|
|||
@cloud_edition_billing_resource_check('annotation')
|
||||
@marshal_with(annotation_fields)
|
||||
def post(self, app_id, annotation_id):
|
||||
# The role of the current user in the ta table must be admin or owner
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
|
||||
app_id = str(app_id)
|
||||
|
|
@ -191,8 +183,7 @@ class AnnotationUpdateDeleteApi(Resource):
|
|||
@login_required
|
||||
@account_initialization_required
|
||||
def delete(self, app_id, annotation_id):
|
||||
# The role of the current user in the ta table must be admin or owner
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
|
||||
app_id = str(app_id)
|
||||
|
|
@ -207,8 +198,7 @@ class AnnotationBatchImportApi(Resource):
|
|||
@account_initialization_required
|
||||
@cloud_edition_billing_resource_check('annotation')
|
||||
def post(self, app_id):
|
||||
# The role of the current user in the ta table must be admin or owner
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
|
||||
app_id = str(app_id)
|
||||
|
|
@ -232,8 +222,7 @@ class AnnotationBatchImportStatusApi(Resource):
|
|||
@account_initialization_required
|
||||
@cloud_edition_billing_resource_check('annotation')
|
||||
def get(self, app_id, job_id):
|
||||
# The role of the current user in the ta table must be admin or owner
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
|
||||
job_id = str(job_id)
|
||||
|
|
@ -259,8 +248,7 @@ class AnnotationHitHistoryListApi(Resource):
|
|||
@login_required
|
||||
@account_initialization_required
|
||||
def get(self, app_id, annotation_id):
|
||||
# The role of the current user in the table must be admin or owner
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
|
||||
page = request.args.get('page', default=1, type=int)
|
||||
|
|
|
|||
|
|
@ -143,7 +143,7 @@ class ChatConversationApi(Resource):
|
|||
@get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT])
|
||||
@marshal_with(conversation_with_summary_pagination_fields)
|
||||
def get(self, app_model):
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument('keyword', type=str, location='args')
|
||||
|
|
@ -245,7 +245,7 @@ class ChatConversationDetailApi(Resource):
|
|||
@get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT])
|
||||
@marshal_with(conversation_detail_fields)
|
||||
def get(self, app_model, conversation_id):
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
conversation_id = str(conversation_id)
|
||||
|
||||
|
|
|
|||
61
api/controllers/console/app/conversation_variables.py
Normal file
61
api/controllers/console/app/conversation_variables.py
Normal file
|
|
@ -0,0 +1,61 @@
|
|||
from flask_restful import Resource, marshal_with, reqparse
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from controllers.console import api
|
||||
from controllers.console.app.wraps import get_app_model
|
||||
from controllers.console.setup import setup_required
|
||||
from controllers.console.wraps import account_initialization_required
|
||||
from extensions.ext_database import db
|
||||
from fields.conversation_variable_fields import paginated_conversation_variable_fields
|
||||
from libs.login import login_required
|
||||
from models import ConversationVariable
|
||||
from models.model import AppMode
|
||||
|
||||
|
||||
class ConversationVariablesApi(Resource):
|
||||
@setup_required
|
||||
@login_required
|
||||
@account_initialization_required
|
||||
@get_app_model(mode=AppMode.ADVANCED_CHAT)
|
||||
@marshal_with(paginated_conversation_variable_fields)
|
||||
def get(self, app_model):
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument('conversation_id', type=str, location='args')
|
||||
args = parser.parse_args()
|
||||
|
||||
stmt = (
|
||||
select(ConversationVariable)
|
||||
.where(ConversationVariable.app_id == app_model.id)
|
||||
.order_by(ConversationVariable.created_at)
|
||||
)
|
||||
if args['conversation_id']:
|
||||
stmt = stmt.where(ConversationVariable.conversation_id == args['conversation_id'])
|
||||
else:
|
||||
raise ValueError('conversation_id is required')
|
||||
|
||||
# NOTE: This is a temporary solution to avoid performance issues.
|
||||
page = 1
|
||||
page_size = 100
|
||||
stmt = stmt.limit(page_size).offset((page - 1) * page_size)
|
||||
|
||||
with Session(db.engine) as session:
|
||||
rows = session.scalars(stmt).all()
|
||||
|
||||
return {
|
||||
'page': page,
|
||||
'limit': page_size,
|
||||
'total': len(rows),
|
||||
'has_more': False,
|
||||
'data': [
|
||||
{
|
||||
'created_at': row.created_at,
|
||||
'updated_at': row.updated_at,
|
||||
**row.to_variable().model_dump(),
|
||||
}
|
||||
for row in rows
|
||||
],
|
||||
}
|
||||
|
||||
|
||||
api.add_resource(ConversationVariablesApi, '/apps/<uuid:app_id>/conversation-variables')
|
||||
|
|
@ -149,8 +149,7 @@ class MessageAnnotationApi(Resource):
|
|||
@get_app_model
|
||||
@marshal_with(annotation_fields)
|
||||
def post(self, app_model):
|
||||
# The role of the current user in the ta table must be admin or owner
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
|
||||
parser = reqparse.RequestParser()
|
||||
|
|
|
|||
|
|
@ -74,6 +74,7 @@ class DraftWorkflowApi(Resource):
|
|||
parser.add_argument('hash', type=str, required=False, location='json')
|
||||
# TODO: set this to required=True after frontend is updated
|
||||
parser.add_argument('environment_variables', type=list, required=False, location='json')
|
||||
parser.add_argument('conversation_variables', type=list, required=False, location='json')
|
||||
args = parser.parse_args()
|
||||
elif 'text/plain' in content_type:
|
||||
try:
|
||||
|
|
@ -88,7 +89,8 @@ class DraftWorkflowApi(Resource):
|
|||
'graph': data.get('graph'),
|
||||
'features': data.get('features'),
|
||||
'hash': data.get('hash'),
|
||||
'environment_variables': data.get('environment_variables')
|
||||
'environment_variables': data.get('environment_variables'),
|
||||
'conversation_variables': data.get('conversation_variables'),
|
||||
}
|
||||
except json.JSONDecodeError:
|
||||
return {'message': 'Invalid JSON data'}, 400
|
||||
|
|
@ -100,6 +102,8 @@ class DraftWorkflowApi(Resource):
|
|||
try:
|
||||
environment_variables_list = args.get('environment_variables') or []
|
||||
environment_variables = [factory.build_variable_from_mapping(obj) for obj in environment_variables_list]
|
||||
conversation_variables_list = args.get('conversation_variables') or []
|
||||
conversation_variables = [factory.build_variable_from_mapping(obj) for obj in conversation_variables_list]
|
||||
workflow = workflow_service.sync_draft_workflow(
|
||||
app_model=app_model,
|
||||
graph=args['graph'],
|
||||
|
|
@ -107,6 +111,7 @@ class DraftWorkflowApi(Resource):
|
|||
unique_hash=args.get('hash'),
|
||||
account=current_user,
|
||||
environment_variables=environment_variables,
|
||||
conversation_variables=conversation_variables,
|
||||
)
|
||||
except WorkflowHashNotEqualError:
|
||||
raise DraftWorkflowNotSync()
|
||||
|
|
|
|||
|
|
@ -17,8 +17,6 @@ from ..wraps import account_initialization_required
|
|||
|
||||
def get_oauth_providers():
|
||||
with current_app.app_context():
|
||||
if not dify_config.NOTION_CLIENT_ID or not dify_config.NOTION_CLIENT_SECRET:
|
||||
return {}
|
||||
notion_oauth = NotionOAuth(client_id=dify_config.NOTION_CLIENT_ID,
|
||||
client_secret=dify_config.NOTION_CLIENT_SECRET,
|
||||
redirect_uri=dify_config.CONSOLE_API_URL + '/console/api/oauth/data-source/callback/notion')
|
||||
|
|
|
|||
|
|
@ -189,8 +189,6 @@ class DatasetApi(Resource):
|
|||
dataset = DatasetService.get_dataset(dataset_id_str)
|
||||
if dataset is None:
|
||||
raise NotFound("Dataset not found.")
|
||||
# check user's model setting
|
||||
DatasetService.check_dataset_model_setting(dataset)
|
||||
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument('name', nullable=False,
|
||||
|
|
@ -215,6 +213,13 @@ class DatasetApi(Resource):
|
|||
args = parser.parse_args()
|
||||
data = request.get_json()
|
||||
|
||||
# check embedding model setting
|
||||
if data.get('indexing_technique') == 'high_quality':
|
||||
DatasetService.check_embedding_model_setting(dataset.tenant_id,
|
||||
data.get('embedding_model_provider'),
|
||||
data.get('embedding_model')
|
||||
)
|
||||
|
||||
# The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
|
||||
DatasetPermissionService.check_permission(
|
||||
current_user, dataset, data.get('permission'), data.get('partial_member_list')
|
||||
|
|
@ -233,7 +238,8 @@ class DatasetApi(Resource):
|
|||
DatasetPermissionService.update_partial_member_list(
|
||||
tenant_id, dataset_id_str, data.get('partial_member_list')
|
||||
)
|
||||
else:
|
||||
# clear partial member list when permission is only_me or all_team_members
|
||||
elif data.get('permission') == 'only_me' or data.get('permission') == 'all_team_members':
|
||||
DatasetPermissionService.clear_partial_member_list(dataset_id_str)
|
||||
|
||||
partial_member_list = DatasetPermissionService.get_dataset_partial_member_list(dataset_id_str)
|
||||
|
|
@ -551,7 +557,7 @@ class DatasetRetrievalSettingApi(Resource):
|
|||
]
|
||||
}
|
||||
case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH | (
|
||||
VectorType.ANALYTICDB) | VectorType.MYSCALE | VectorType.ORACLE | VectorType.TIDB_ON_QDRANT:
|
||||
VectorType.ANALYTICDB) | VectorType.MYSCALE | VectorType.ORACLE | VectorType.TIDB_ON_QDRANT | VectorType.ELASTICSEARCH:
|
||||
return {
|
||||
'retrieval_method': [
|
||||
RetrievalMethod.SEMANTIC_SEARCH.value,
|
||||
|
|
@ -575,7 +581,7 @@ class DatasetRetrievalSettingMockApi(Resource):
|
|||
RetrievalMethod.SEMANTIC_SEARCH.value
|
||||
]
|
||||
}
|
||||
case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH| VectorType.ANALYTICDB | VectorType.MYSCALE | VectorType.ORACLE:
|
||||
case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH| VectorType.ANALYTICDB | VectorType.MYSCALE | VectorType.ORACLE | VectorType.ELASTICSEARCH:
|
||||
return {
|
||||
'retrieval_method': [
|
||||
RetrievalMethod.SEMANTIC_SEARCH.value,
|
||||
|
|
|
|||
|
|
@ -178,11 +178,20 @@ class DatasetDocumentListApi(Resource):
|
|||
.subquery()
|
||||
|
||||
query = query.outerjoin(sub_query, sub_query.c.document_id == Document.id) \
|
||||
.order_by(sort_logic(db.func.coalesce(sub_query.c.total_hit_count, 0)))
|
||||
.order_by(
|
||||
sort_logic(db.func.coalesce(sub_query.c.total_hit_count, 0)),
|
||||
sort_logic(Document.position),
|
||||
)
|
||||
elif sort == 'created_at':
|
||||
query = query.order_by(sort_logic(Document.created_at))
|
||||
query = query.order_by(
|
||||
sort_logic(Document.created_at),
|
||||
sort_logic(Document.position),
|
||||
)
|
||||
else:
|
||||
query = query.order_by(desc(Document.created_at))
|
||||
query = query.order_by(
|
||||
desc(Document.created_at),
|
||||
desc(Document.position),
|
||||
)
|
||||
|
||||
paginated_documents = query.paginate(
|
||||
page=page, per_page=limit, max_per_page=100, error_out=False)
|
||||
|
|
|
|||
|
|
@ -223,8 +223,7 @@ class DatasetDocumentSegmentAddApi(Resource):
|
|||
document = DocumentService.get_document(dataset_id, document_id)
|
||||
if not document:
|
||||
raise NotFound('Document not found.')
|
||||
# The role of the current user in the ta table must be admin or owner
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
# check embedding model setting
|
||||
if dataset.indexing_technique == 'high_quality':
|
||||
|
|
@ -347,7 +346,7 @@ class DatasetDocumentSegmentUpdateApi(Resource):
|
|||
if not segment:
|
||||
raise NotFound('Segment not found.')
|
||||
# The role of the current user in the ta table must be admin or owner
|
||||
if not current_user.is_admin_or_owner:
|
||||
if not current_user.is_editor:
|
||||
raise Forbidden()
|
||||
try:
|
||||
DatasetService.check_dataset_permission(dataset, current_user)
|
||||
|
|
|
|||
|
|
@ -1,6 +1,7 @@
|
|||
from flask_login import current_user
|
||||
from flask_restful import Resource, marshal_with, reqparse
|
||||
|
||||
from constants import HIDDEN_VALUE
|
||||
from controllers.console import api
|
||||
from controllers.console.setup import setup_required
|
||||
from controllers.console.wraps import account_initialization_required
|
||||
|
|
@ -89,7 +90,7 @@ class APIBasedExtensionDetailAPI(Resource):
|
|||
extension_data_from_db.name = args['name']
|
||||
extension_data_from_db.api_endpoint = args['api_endpoint']
|
||||
|
||||
if args['api_key'] != '[__HIDDEN__]':
|
||||
if args['api_key'] != HIDDEN_VALUE:
|
||||
extension_data_from_db.api_key = args['api_key']
|
||||
|
||||
return APIBasedExtensionService.save(extension_data_from_db)
|
||||
|
|
|
|||
|
|
@ -19,7 +19,7 @@ def inner_api_only(view):
|
|||
# get header 'X-Inner-Api-Key'
|
||||
inner_api_key = request.headers.get('X-Inner-Api-Key')
|
||||
if not inner_api_key or inner_api_key != dify_config.INNER_API_KEY:
|
||||
abort(404)
|
||||
abort(401)
|
||||
|
||||
return view(*args, **kwargs)
|
||||
|
||||
|
|
|
|||
|
|
@ -53,7 +53,7 @@ class ConversationDetailApi(Resource):
|
|||
ConversationService.delete(app_model, conversation_id, end_user)
|
||||
except services.errors.conversation.ConversationNotExistsError:
|
||||
raise NotFound("Conversation Not Exists.")
|
||||
return {"result": "success"}, 204
|
||||
return {'result': 'success'}, 200
|
||||
|
||||
|
||||
class ConversationRenameApi(Resource):
|
||||
|
|
|
|||
|
|
@ -131,7 +131,7 @@ class MessageSuggestedApi(Resource):
|
|||
except services.errors.message.MessageNotExistsError:
|
||||
raise NotFound("Message Not Exists.")
|
||||
except SuggestedQuestionsAfterAnswerDisabledError:
|
||||
raise BadRequest("Message Not Exists.")
|
||||
raise BadRequest("Suggested Questions Is Disabled.")
|
||||
except Exception:
|
||||
logging.exception("internal server error.")
|
||||
raise InternalServerError()
|
||||
|
|
|
|||
|
|
@ -29,22 +29,21 @@ from services.app_generate_service import AppGenerateService
|
|||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
workflow_run_fields = {
|
||||
'id': fields.String,
|
||||
'workflow_id': fields.String,
|
||||
'status': fields.String,
|
||||
'inputs': fields.Raw,
|
||||
'outputs': fields.Raw,
|
||||
'error': fields.String,
|
||||
'total_steps': fields.Integer,
|
||||
'total_tokens': fields.Integer,
|
||||
'created_at': fields.DateTime,
|
||||
'finished_at': fields.DateTime,
|
||||
'elapsed_time': fields.Float,
|
||||
}
|
||||
|
||||
class WorkflowRunApi(Resource):
|
||||
workflow_run_fields = {
|
||||
'id': fields.String,
|
||||
'workflow_id': fields.String,
|
||||
'status': fields.String,
|
||||
'inputs': fields.Raw,
|
||||
'outputs': fields.Raw,
|
||||
'error': fields.String,
|
||||
'total_steps': fields.Integer,
|
||||
'total_tokens': fields.Integer,
|
||||
'created_at': fields.DateTime,
|
||||
'finished_at': fields.DateTime,
|
||||
'elapsed_time': fields.Float,
|
||||
}
|
||||
|
||||
class WorkflowRunDetailApi(Resource):
|
||||
@validate_app_token
|
||||
@marshal_with(workflow_run_fields)
|
||||
def get(self, app_model: App, workflow_id: str):
|
||||
|
|
@ -57,7 +56,7 @@ class WorkflowRunApi(Resource):
|
|||
|
||||
workflow_run = db.session.query(WorkflowRun).filter(WorkflowRun.id == workflow_id).first()
|
||||
return workflow_run
|
||||
|
||||
class WorkflowRunApi(Resource):
|
||||
@validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON, required=True))
|
||||
def post(self, app_model: App, end_user: EndUser):
|
||||
"""
|
||||
|
|
@ -117,5 +116,6 @@ class WorkflowTaskStopApi(Resource):
|
|||
}
|
||||
|
||||
|
||||
api.add_resource(WorkflowRunApi, '/workflows/run/<string:workflow_id>', '/workflows/run')
|
||||
api.add_resource(WorkflowRunApi, '/workflows/run')
|
||||
api.add_resource(WorkflowRunDetailApi, '/workflows/run/<string:workflow_id>')
|
||||
api.add_resource(WorkflowTaskStopApi, '/workflows/tasks/<string:task_id>/stop')
|
||||
|
|
|
|||
|
|
@ -79,6 +79,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):
|
|||
llm_usage.completion_tokens += usage.completion_tokens
|
||||
llm_usage.prompt_price += usage.prompt_price
|
||||
llm_usage.completion_price += usage.completion_price
|
||||
llm_usage.total_price += usage.total_price
|
||||
|
||||
model_instance = self.model_instance
|
||||
|
||||
|
|
|
|||
|
|
@ -62,6 +62,7 @@ class FunctionCallAgentRunner(BaseAgentRunner):
|
|||
llm_usage.completion_tokens += usage.completion_tokens
|
||||
llm_usage.prompt_price += usage.prompt_price
|
||||
llm_usage.completion_price += usage.completion_price
|
||||
llm_usage.total_price += usage.total_price
|
||||
|
||||
model_instance = self.model_instance
|
||||
|
||||
|
|
|
|||
|
|
@ -91,7 +91,8 @@ class DatasetConfigManager:
|
|||
top_k=dataset_configs.get('top_k', 4),
|
||||
score_threshold=dataset_configs.get('score_threshold'),
|
||||
reranking_model=dataset_configs.get('reranking_model'),
|
||||
weights=dataset_configs.get('weights')
|
||||
weights=dataset_configs.get('weights'),
|
||||
reranking_enabled=dataset_configs.get('reranking_enabled', True),
|
||||
)
|
||||
)
|
||||
|
||||
|
|
|
|||
|
|
@ -3,8 +3,9 @@ from typing import Any, Optional
|
|||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from core.file.file_obj import FileExtraConfig
|
||||
from core.model_runtime.entities.message_entities import PromptMessageRole
|
||||
from models.model import AppMode
|
||||
from models import AppMode
|
||||
|
||||
|
||||
class ModelConfigEntity(BaseModel):
|
||||
|
|
@ -158,10 +159,11 @@ class DatasetRetrieveConfigEntity(BaseModel):
|
|||
|
||||
retrieve_strategy: RetrieveStrategy
|
||||
top_k: Optional[int] = None
|
||||
score_threshold: Optional[float] = None
|
||||
score_threshold: Optional[float] = .0
|
||||
rerank_mode: Optional[str] = 'reranking_model'
|
||||
reranking_model: Optional[dict] = None
|
||||
weights: Optional[dict] = None
|
||||
reranking_enabled: Optional[bool] = True
|
||||
|
||||
|
||||
|
||||
|
|
@ -199,11 +201,6 @@ class TracingConfigEntity(BaseModel):
|
|||
tracing_provider: str
|
||||
|
||||
|
||||
class FileExtraConfig(BaseModel):
|
||||
"""
|
||||
File Upload Entity.
|
||||
"""
|
||||
image_config: Optional[dict[str, Any]] = None
|
||||
|
||||
|
||||
class AppAdditionalFeatures(BaseModel):
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
from collections.abc import Mapping
|
||||
from typing import Any, Optional
|
||||
|
||||
from core.app.app_config.entities import FileExtraConfig
|
||||
from core.file.file_obj import FileExtraConfig
|
||||
|
||||
|
||||
class FileUploadConfigManager:
|
||||
|
|
|
|||
|
|
@ -89,7 +89,8 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
|||
)
|
||||
|
||||
# get tracing instance
|
||||
trace_manager = TraceQueueManager(app_id=app_model.id)
|
||||
user_id = user.id if isinstance(user, Account) else user.session_id
|
||||
trace_manager = TraceQueueManager(app_model.id, user_id)
|
||||
|
||||
if invoke_from == InvokeFrom.DEBUGGER:
|
||||
# always enable retriever resource in debugger mode
|
||||
|
|
@ -112,7 +113,6 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
|||
contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
|
||||
|
||||
return self._generate(
|
||||
app_model=app_model,
|
||||
workflow=workflow,
|
||||
user=user,
|
||||
invoke_from=invoke_from,
|
||||
|
|
@ -179,7 +179,6 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
|||
contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
|
||||
|
||||
return self._generate(
|
||||
app_model=app_model,
|
||||
workflow=workflow,
|
||||
user=user,
|
||||
invoke_from=InvokeFrom.DEBUGGER,
|
||||
|
|
@ -188,12 +187,12 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
|||
stream=stream
|
||||
)
|
||||
|
||||
def _generate(self, app_model: App,
|
||||
def _generate(self, *,
|
||||
workflow: Workflow,
|
||||
user: Union[Account, EndUser],
|
||||
invoke_from: InvokeFrom,
|
||||
application_generate_entity: AdvancedChatAppGenerateEntity,
|
||||
conversation: Conversation = None,
|
||||
conversation: Conversation | None = None,
|
||||
stream: bool = True) \
|
||||
-> Union[dict, Generator[dict, None, None]]:
|
||||
is_first_conversation = False
|
||||
|
|
|
|||
|
|
@ -5,7 +5,12 @@ import queue
|
|||
import re
|
||||
import threading
|
||||
|
||||
from core.app.entities.queue_entities import QueueAgentMessageEvent, QueueLLMChunkEvent, QueueTextChunkEvent
|
||||
from core.app.entities.queue_entities import (
|
||||
QueueAgentMessageEvent,
|
||||
QueueLLMChunkEvent,
|
||||
QueueNodeSucceededEvent,
|
||||
QueueTextChunkEvent,
|
||||
)
|
||||
from core.model_manager import ModelManager
|
||||
from core.model_runtime.entities.model_entities import ModelType
|
||||
|
||||
|
|
@ -88,6 +93,8 @@ class AppGeneratorTTSPublisher:
|
|||
self.msg_text += message.event.chunk.delta.message.content
|
||||
elif isinstance(message.event, QueueTextChunkEvent):
|
||||
self.msg_text += message.event.text
|
||||
elif isinstance(message.event, QueueNodeSucceededEvent):
|
||||
self.msg_text += message.event.outputs.get('output', '')
|
||||
self.last_message = message
|
||||
sentence_arr, text_tmp = self._extract_sentence(self.msg_text)
|
||||
if len(sentence_arr) >= min(self.MAX_SENTENCE, 7):
|
||||
|
|
|
|||
|
|
@ -4,6 +4,9 @@ import time
|
|||
from collections.abc import Mapping
|
||||
from typing import Any, Optional, cast
|
||||
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from core.app.apps.advanced_chat.app_config_manager import AdvancedChatAppConfig
|
||||
from core.app.apps.advanced_chat.workflow_event_trigger_callback import WorkflowEventTriggerCallback
|
||||
from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom
|
||||
|
|
@ -17,11 +20,12 @@ from core.app.entities.queue_entities import QueueAnnotationReplyEvent, QueueSto
|
|||
from core.moderation.base import ModerationException
|
||||
from core.workflow.callbacks.base_workflow_callback import WorkflowCallback
|
||||
from core.workflow.entities.node_entities import SystemVariable
|
||||
from core.workflow.entities.variable_pool import VariablePool
|
||||
from core.workflow.nodes.base_node import UserFrom
|
||||
from core.workflow.workflow_engine_manager import WorkflowEngineManager
|
||||
from extensions.ext_database import db
|
||||
from models.model import App, Conversation, EndUser, Message
|
||||
from models.workflow import Workflow
|
||||
from models.workflow import ConversationVariable, Workflow
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
|
@ -31,10 +35,13 @@ class AdvancedChatAppRunner(AppRunner):
|
|||
AdvancedChat Application Runner
|
||||
"""
|
||||
|
||||
def run(self, application_generate_entity: AdvancedChatAppGenerateEntity,
|
||||
queue_manager: AppQueueManager,
|
||||
conversation: Conversation,
|
||||
message: Message) -> None:
|
||||
def run(
|
||||
self,
|
||||
application_generate_entity: AdvancedChatAppGenerateEntity,
|
||||
queue_manager: AppQueueManager,
|
||||
conversation: Conversation,
|
||||
message: Message,
|
||||
) -> None:
|
||||
"""
|
||||
Run application
|
||||
:param application_generate_entity: application generate entity
|
||||
|
|
@ -48,11 +55,11 @@ class AdvancedChatAppRunner(AppRunner):
|
|||
|
||||
app_record = db.session.query(App).filter(App.id == app_config.app_id).first()
|
||||
if not app_record:
|
||||
raise ValueError("App not found")
|
||||
raise ValueError('App not found')
|
||||
|
||||
workflow = self.get_workflow(app_model=app_record, workflow_id=app_config.workflow_id)
|
||||
if not workflow:
|
||||
raise ValueError("Workflow not initialized")
|
||||
raise ValueError('Workflow not initialized')
|
||||
|
||||
inputs = application_generate_entity.inputs
|
||||
query = application_generate_entity.query
|
||||
|
|
@ -68,35 +75,66 @@ class AdvancedChatAppRunner(AppRunner):
|
|||
|
||||
# moderation
|
||||
if self.handle_input_moderation(
|
||||
queue_manager=queue_manager,
|
||||
app_record=app_record,
|
||||
app_generate_entity=application_generate_entity,
|
||||
inputs=inputs,
|
||||
query=query,
|
||||
message_id=message.id
|
||||
queue_manager=queue_manager,
|
||||
app_record=app_record,
|
||||
app_generate_entity=application_generate_entity,
|
||||
inputs=inputs,
|
||||
query=query,
|
||||
message_id=message.id,
|
||||
):
|
||||
return
|
||||
|
||||
# annotation reply
|
||||
if self.handle_annotation_reply(
|
||||
app_record=app_record,
|
||||
message=message,
|
||||
query=query,
|
||||
queue_manager=queue_manager,
|
||||
app_generate_entity=application_generate_entity
|
||||
app_record=app_record,
|
||||
message=message,
|
||||
query=query,
|
||||
queue_manager=queue_manager,
|
||||
app_generate_entity=application_generate_entity,
|
||||
):
|
||||
return
|
||||
|
||||
db.session.close()
|
||||
|
||||
workflow_callbacks: list[WorkflowCallback] = [WorkflowEventTriggerCallback(
|
||||
queue_manager=queue_manager,
|
||||
workflow=workflow
|
||||
)]
|
||||
workflow_callbacks: list[WorkflowCallback] = [
|
||||
WorkflowEventTriggerCallback(queue_manager=queue_manager, workflow=workflow)
|
||||
]
|
||||
|
||||
if bool(os.environ.get("DEBUG", 'False').lower() == 'true'):
|
||||
if bool(os.environ.get('DEBUG', 'False').lower() == 'true'):
|
||||
workflow_callbacks.append(WorkflowLoggingCallback())
|
||||
|
||||
# Init conversation variables
|
||||
stmt = select(ConversationVariable).where(
|
||||
ConversationVariable.app_id == conversation.app_id, ConversationVariable.conversation_id == conversation.id
|
||||
)
|
||||
with Session(db.engine) as session:
|
||||
conversation_variables = session.scalars(stmt).all()
|
||||
if not conversation_variables:
|
||||
conversation_variables = [
|
||||
ConversationVariable.from_variable(
|
||||
app_id=conversation.app_id, conversation_id=conversation.id, variable=variable
|
||||
)
|
||||
for variable in workflow.conversation_variables
|
||||
]
|
||||
session.add_all(conversation_variables)
|
||||
session.commit()
|
||||
# Convert database entities to variables
|
||||
conversation_variables = [item.to_variable() for item in conversation_variables]
|
||||
|
||||
# Create a variable pool.
|
||||
system_inputs = {
|
||||
SystemVariable.QUERY: query,
|
||||
SystemVariable.FILES: files,
|
||||
SystemVariable.CONVERSATION_ID: conversation.id,
|
||||
SystemVariable.USER_ID: user_id,
|
||||
}
|
||||
variable_pool = VariablePool(
|
||||
system_variables=system_inputs,
|
||||
user_inputs=inputs,
|
||||
environment_variables=workflow.environment_variables,
|
||||
conversation_variables=conversation_variables,
|
||||
)
|
||||
|
||||
# RUN WORKFLOW
|
||||
workflow_engine_manager = WorkflowEngineManager()
|
||||
workflow_engine_manager.run_workflow(
|
||||
|
|
@ -106,43 +144,30 @@ class AdvancedChatAppRunner(AppRunner):
|
|||
if application_generate_entity.invoke_from in [InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER]
|
||||
else UserFrom.END_USER,
|
||||
invoke_from=application_generate_entity.invoke_from,
|
||||
user_inputs=inputs,
|
||||
system_inputs={
|
||||
SystemVariable.QUERY: query,
|
||||
SystemVariable.FILES: files,
|
||||
SystemVariable.CONVERSATION_ID: conversation.id,
|
||||
SystemVariable.USER_ID: user_id
|
||||
},
|
||||
callbacks=workflow_callbacks,
|
||||
call_depth=application_generate_entity.call_depth
|
||||
call_depth=application_generate_entity.call_depth,
|
||||
variable_pool=variable_pool,
|
||||
)
|
||||
|
||||
def single_iteration_run(self, app_id: str, workflow_id: str,
|
||||
queue_manager: AppQueueManager,
|
||||
inputs: dict, node_id: str, user_id: str) -> None:
|
||||
def single_iteration_run(
|
||||
self, app_id: str, workflow_id: str, queue_manager: AppQueueManager, inputs: dict, node_id: str, user_id: str
|
||||
) -> None:
|
||||
"""
|
||||
Single iteration run
|
||||
"""
|
||||
app_record: App = db.session.query(App).filter(App.id == app_id).first()
|
||||
if not app_record:
|
||||
raise ValueError("App not found")
|
||||
|
||||
raise ValueError('App not found')
|
||||
|
||||
workflow = self.get_workflow(app_model=app_record, workflow_id=workflow_id)
|
||||
if not workflow:
|
||||
raise ValueError("Workflow not initialized")
|
||||
|
||||
workflow_callbacks = [WorkflowEventTriggerCallback(
|
||||
queue_manager=queue_manager,
|
||||
workflow=workflow
|
||||
)]
|
||||
raise ValueError('Workflow not initialized')
|
||||
|
||||
workflow_callbacks = [WorkflowEventTriggerCallback(queue_manager=queue_manager, workflow=workflow)]
|
||||
|
||||
workflow_engine_manager = WorkflowEngineManager()
|
||||
workflow_engine_manager.single_step_run_iteration_workflow_node(
|
||||
workflow=workflow,
|
||||
node_id=node_id,
|
||||
user_id=user_id,
|
||||
user_inputs=inputs,
|
||||
callbacks=workflow_callbacks
|
||||
workflow=workflow, node_id=node_id, user_id=user_id, user_inputs=inputs, callbacks=workflow_callbacks
|
||||
)
|
||||
|
||||
def get_workflow(self, app_model: App, workflow_id: str) -> Optional[Workflow]:
|
||||
|
|
@ -150,22 +175,25 @@ class AdvancedChatAppRunner(AppRunner):
|
|||
Get workflow
|
||||
"""
|
||||
# fetch workflow by workflow_id
|
||||
workflow = db.session.query(Workflow).filter(
|
||||
Workflow.tenant_id == app_model.tenant_id,
|
||||
Workflow.app_id == app_model.id,
|
||||
Workflow.id == workflow_id
|
||||
).first()
|
||||
workflow = (
|
||||
db.session.query(Workflow)
|
||||
.filter(
|
||||
Workflow.tenant_id == app_model.tenant_id, Workflow.app_id == app_model.id, Workflow.id == workflow_id
|
||||
)
|
||||
.first()
|
||||
)
|
||||
|
||||
# return workflow
|
||||
return workflow
|
||||
|
||||
def handle_input_moderation(
|
||||
self, queue_manager: AppQueueManager,
|
||||
app_record: App,
|
||||
app_generate_entity: AdvancedChatAppGenerateEntity,
|
||||
inputs: Mapping[str, Any],
|
||||
query: str,
|
||||
message_id: str
|
||||
self,
|
||||
queue_manager: AppQueueManager,
|
||||
app_record: App,
|
||||
app_generate_entity: AdvancedChatAppGenerateEntity,
|
||||
inputs: Mapping[str, Any],
|
||||
query: str,
|
||||
message_id: str,
|
||||
) -> bool:
|
||||
"""
|
||||
Handle input moderation
|
||||
|
|
@ -192,17 +220,20 @@ class AdvancedChatAppRunner(AppRunner):
|
|||
queue_manager=queue_manager,
|
||||
text=str(e),
|
||||
stream=app_generate_entity.stream,
|
||||
stopped_by=QueueStopEvent.StopBy.INPUT_MODERATION
|
||||
stopped_by=QueueStopEvent.StopBy.INPUT_MODERATION,
|
||||
)
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
def handle_annotation_reply(self, app_record: App,
|
||||
message: Message,
|
||||
query: str,
|
||||
queue_manager: AppQueueManager,
|
||||
app_generate_entity: AdvancedChatAppGenerateEntity) -> bool:
|
||||
def handle_annotation_reply(
|
||||
self,
|
||||
app_record: App,
|
||||
message: Message,
|
||||
query: str,
|
||||
queue_manager: AppQueueManager,
|
||||
app_generate_entity: AdvancedChatAppGenerateEntity,
|
||||
) -> bool:
|
||||
"""
|
||||
Handle annotation reply
|
||||
:param app_record: app record
|
||||
|
|
@ -217,29 +248,27 @@ class AdvancedChatAppRunner(AppRunner):
|
|||
message=message,
|
||||
query=query,
|
||||
user_id=app_generate_entity.user_id,
|
||||
invoke_from=app_generate_entity.invoke_from
|
||||
invoke_from=app_generate_entity.invoke_from,
|
||||
)
|
||||
|
||||
if annotation_reply:
|
||||
queue_manager.publish(
|
||||
QueueAnnotationReplyEvent(message_annotation_id=annotation_reply.id),
|
||||
PublishFrom.APPLICATION_MANAGER
|
||||
QueueAnnotationReplyEvent(message_annotation_id=annotation_reply.id), PublishFrom.APPLICATION_MANAGER
|
||||
)
|
||||
|
||||
self._stream_output(
|
||||
queue_manager=queue_manager,
|
||||
text=annotation_reply.content,
|
||||
stream=app_generate_entity.stream,
|
||||
stopped_by=QueueStopEvent.StopBy.ANNOTATION_REPLY
|
||||
stopped_by=QueueStopEvent.StopBy.ANNOTATION_REPLY,
|
||||
)
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
def _stream_output(self, queue_manager: AppQueueManager,
|
||||
text: str,
|
||||
stream: bool,
|
||||
stopped_by: QueueStopEvent.StopBy) -> None:
|
||||
def _stream_output(
|
||||
self, queue_manager: AppQueueManager, text: str, stream: bool, stopped_by: QueueStopEvent.StopBy
|
||||
) -> None:
|
||||
"""
|
||||
Direct output
|
||||
:param queue_manager: application queue manager
|
||||
|
|
@ -250,21 +279,10 @@ class AdvancedChatAppRunner(AppRunner):
|
|||
if stream:
|
||||
index = 0
|
||||
for token in text:
|
||||
queue_manager.publish(
|
||||
QueueTextChunkEvent(
|
||||
text=token
|
||||
), PublishFrom.APPLICATION_MANAGER
|
||||
)
|
||||
queue_manager.publish(QueueTextChunkEvent(text=token), PublishFrom.APPLICATION_MANAGER)
|
||||
index += 1
|
||||
time.sleep(0.01)
|
||||
else:
|
||||
queue_manager.publish(
|
||||
QueueTextChunkEvent(
|
||||
text=text
|
||||
), PublishFrom.APPLICATION_MANAGER
|
||||
)
|
||||
queue_manager.publish(QueueTextChunkEvent(text=text), PublishFrom.APPLICATION_MANAGER)
|
||||
|
||||
queue_manager.publish(
|
||||
QueueStopEvent(stopped_by=stopped_by),
|
||||
PublishFrom.APPLICATION_MANAGER
|
||||
)
|
||||
queue_manager.publish(QueueStopEvent(stopped_by=stopped_by), PublishFrom.APPLICATION_MANAGER)
|
||||
|
|
|
|||
|
|
@ -244,7 +244,16 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
|
|||
:return:
|
||||
"""
|
||||
for message in self._queue_manager.listen():
|
||||
if publisher:
|
||||
if (message.event
|
||||
and hasattr(message.event, 'metadata')
|
||||
and message.event.metadata
|
||||
and message.event.metadata.get('is_answer_previous_node', False)
|
||||
and publisher):
|
||||
publisher.publish(message=message)
|
||||
elif (hasattr(message.event, 'execution_metadata')
|
||||
and message.event.execution_metadata
|
||||
and message.event.execution_metadata.get('is_answer_previous_node', False)
|
||||
and publisher):
|
||||
publisher.publish(message=message)
|
||||
event = message.event
|
||||
|
||||
|
|
|
|||
|
|
@ -110,7 +110,8 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
|
|||
)
|
||||
|
||||
# get tracing instance
|
||||
trace_manager = TraceQueueManager(app_model.id)
|
||||
user_id = user.id if isinstance(user, Account) else user.session_id
|
||||
trace_manager = TraceQueueManager(app_model.id, user_id)
|
||||
|
||||
# init application generate entity
|
||||
application_generate_entity = AgentChatAppGenerateEntity(
|
||||
|
|
|
|||
|
|
@ -74,7 +74,8 @@ class WorkflowAppGenerator(BaseAppGenerator):
|
|||
)
|
||||
|
||||
# get tracing instance
|
||||
trace_manager = TraceQueueManager(app_model.id)
|
||||
user_id = user.id if isinstance(user, Account) else user.session_id
|
||||
trace_manager = TraceQueueManager(app_model.id, user_id)
|
||||
|
||||
# init application generate entity
|
||||
application_generate_entity = WorkflowAppGenerateEntity(
|
||||
|
|
|
|||
|
|
@ -12,6 +12,7 @@ from core.app.entities.app_invoke_entities import (
|
|||
)
|
||||
from core.workflow.callbacks.base_workflow_callback import WorkflowCallback
|
||||
from core.workflow.entities.node_entities import SystemVariable
|
||||
from core.workflow.entities.variable_pool import VariablePool
|
||||
from core.workflow.nodes.base_node import UserFrom
|
||||
from core.workflow.workflow_engine_manager import WorkflowEngineManager
|
||||
from extensions.ext_database import db
|
||||
|
|
@ -26,8 +27,7 @@ class WorkflowAppRunner:
|
|||
Workflow Application Runner
|
||||
"""
|
||||
|
||||
def run(self, application_generate_entity: WorkflowAppGenerateEntity,
|
||||
queue_manager: AppQueueManager) -> None:
|
||||
def run(self, application_generate_entity: WorkflowAppGenerateEntity, queue_manager: AppQueueManager) -> None:
|
||||
"""
|
||||
Run application
|
||||
:param application_generate_entity: application generate entity
|
||||
|
|
@ -47,25 +47,36 @@ class WorkflowAppRunner:
|
|||
|
||||
app_record = db.session.query(App).filter(App.id == app_config.app_id).first()
|
||||
if not app_record:
|
||||
raise ValueError("App not found")
|
||||
raise ValueError('App not found')
|
||||
|
||||
workflow = self.get_workflow(app_model=app_record, workflow_id=app_config.workflow_id)
|
||||
if not workflow:
|
||||
raise ValueError("Workflow not initialized")
|
||||
raise ValueError('Workflow not initialized')
|
||||
|
||||
inputs = application_generate_entity.inputs
|
||||
files = application_generate_entity.files
|
||||
|
||||
db.session.close()
|
||||
|
||||
workflow_callbacks: list[WorkflowCallback] = [WorkflowEventTriggerCallback(
|
||||
queue_manager=queue_manager,
|
||||
workflow=workflow
|
||||
)]
|
||||
workflow_callbacks: list[WorkflowCallback] = [
|
||||
WorkflowEventTriggerCallback(queue_manager=queue_manager, workflow=workflow)
|
||||
]
|
||||
|
||||
if bool(os.environ.get("DEBUG", 'False').lower() == 'true'):
|
||||
if bool(os.environ.get('DEBUG', 'False').lower() == 'true'):
|
||||
workflow_callbacks.append(WorkflowLoggingCallback())
|
||||
|
||||
# Create a variable pool.
|
||||
system_inputs = {
|
||||
SystemVariable.FILES: files,
|
||||
SystemVariable.USER_ID: user_id,
|
||||
}
|
||||
variable_pool = VariablePool(
|
||||
system_variables=system_inputs,
|
||||
user_inputs=inputs,
|
||||
environment_variables=workflow.environment_variables,
|
||||
conversation_variables=[],
|
||||
)
|
||||
|
||||
# RUN WORKFLOW
|
||||
workflow_engine_manager = WorkflowEngineManager()
|
||||
workflow_engine_manager.run_workflow(
|
||||
|
|
@ -75,44 +86,33 @@ class WorkflowAppRunner:
|
|||
if application_generate_entity.invoke_from in [InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER]
|
||||
else UserFrom.END_USER,
|
||||
invoke_from=application_generate_entity.invoke_from,
|
||||
user_inputs=inputs,
|
||||
system_inputs={
|
||||
SystemVariable.FILES: files,
|
||||
SystemVariable.USER_ID: user_id
|
||||
},
|
||||
callbacks=workflow_callbacks,
|
||||
call_depth=application_generate_entity.call_depth
|
||||
call_depth=application_generate_entity.call_depth,
|
||||
variable_pool=variable_pool,
|
||||
)
|
||||
|
||||
def single_iteration_run(self, app_id: str, workflow_id: str,
|
||||
queue_manager: AppQueueManager,
|
||||
inputs: dict, node_id: str, user_id: str) -> None:
|
||||
def single_iteration_run(
|
||||
self, app_id: str, workflow_id: str, queue_manager: AppQueueManager, inputs: dict, node_id: str, user_id: str
|
||||
) -> None:
|
||||
"""
|
||||
Single iteration run
|
||||
"""
|
||||
app_record: App = db.session.query(App).filter(App.id == app_id).first()
|
||||
app_record = db.session.query(App).filter(App.id == app_id).first()
|
||||
if not app_record:
|
||||
raise ValueError("App not found")
|
||||
|
||||
raise ValueError('App not found')
|
||||
|
||||
if not app_record.workflow_id:
|
||||
raise ValueError("Workflow not initialized")
|
||||
raise ValueError('Workflow not initialized')
|
||||
|
||||
workflow = self.get_workflow(app_model=app_record, workflow_id=workflow_id)
|
||||
if not workflow:
|
||||
raise ValueError("Workflow not initialized")
|
||||
|
||||
workflow_callbacks = [WorkflowEventTriggerCallback(
|
||||
queue_manager=queue_manager,
|
||||
workflow=workflow
|
||||
)]
|
||||
raise ValueError('Workflow not initialized')
|
||||
|
||||
workflow_callbacks = [WorkflowEventTriggerCallback(queue_manager=queue_manager, workflow=workflow)]
|
||||
|
||||
workflow_engine_manager = WorkflowEngineManager()
|
||||
workflow_engine_manager.single_step_run_iteration_workflow_node(
|
||||
workflow=workflow,
|
||||
node_id=node_id,
|
||||
user_id=user_id,
|
||||
user_inputs=inputs,
|
||||
callbacks=workflow_callbacks
|
||||
workflow=workflow, node_id=node_id, user_id=user_id, user_inputs=inputs, callbacks=workflow_callbacks
|
||||
)
|
||||
|
||||
def get_workflow(self, app_model: App, workflow_id: str) -> Optional[Workflow]:
|
||||
|
|
@ -120,11 +120,13 @@ class WorkflowAppRunner:
|
|||
Get workflow
|
||||
"""
|
||||
# fetch workflow by workflow_id
|
||||
workflow = db.session.query(Workflow).filter(
|
||||
Workflow.tenant_id == app_model.tenant_id,
|
||||
Workflow.app_id == app_model.id,
|
||||
Workflow.id == workflow_id
|
||||
).first()
|
||||
workflow = (
|
||||
db.session.query(Workflow)
|
||||
.filter(
|
||||
Workflow.tenant_id == app_model.tenant_id, Workflow.app_id == app_model.id, Workflow.id == workflow_id
|
||||
)
|
||||
.first()
|
||||
)
|
||||
|
||||
# return workflow
|
||||
return workflow
|
||||
|
|
|
|||
|
|
@ -1,6 +1,7 @@
|
|||
from .segment_group import SegmentGroup
|
||||
from .segments import (
|
||||
ArrayAnySegment,
|
||||
ArraySegment,
|
||||
FileSegment,
|
||||
FloatSegment,
|
||||
IntegerSegment,
|
||||
|
|
@ -50,4 +51,5 @@ __all__ = [
|
|||
'ArrayNumberVariable',
|
||||
'ArrayObjectVariable',
|
||||
'ArrayFileVariable',
|
||||
'ArraySegment',
|
||||
]
|
||||
|
|
|
|||
2
api/core/app/segments/exc.py
Normal file
2
api/core/app/segments/exc.py
Normal file
|
|
@ -0,0 +1,2 @@
|
|||
class VariableError(Exception):
|
||||
pass
|
||||
|
|
@ -1,8 +1,10 @@
|
|||
from collections.abc import Mapping
|
||||
from typing import Any
|
||||
|
||||
from configs import dify_config
|
||||
from core.file.file_obj import FileVar
|
||||
|
||||
from .exc import VariableError
|
||||
from .segments import (
|
||||
ArrayAnySegment,
|
||||
FileSegment,
|
||||
|
|
@ -29,39 +31,43 @@ from .variables import (
|
|||
)
|
||||
|
||||
|
||||
def build_variable_from_mapping(m: Mapping[str, Any], /) -> Variable:
|
||||
if (value_type := m.get('value_type')) is None:
|
||||
raise ValueError('missing value type')
|
||||
if not m.get('name'):
|
||||
raise ValueError('missing name')
|
||||
if (value := m.get('value')) is None:
|
||||
raise ValueError('missing value')
|
||||
def build_variable_from_mapping(mapping: Mapping[str, Any], /) -> Variable:
|
||||
if (value_type := mapping.get('value_type')) is None:
|
||||
raise VariableError('missing value type')
|
||||
if not mapping.get('name'):
|
||||
raise VariableError('missing name')
|
||||
if (value := mapping.get('value')) is None:
|
||||
raise VariableError('missing value')
|
||||
match value_type:
|
||||
case SegmentType.STRING:
|
||||
return StringVariable.model_validate(m)
|
||||
result = StringVariable.model_validate(mapping)
|
||||
case SegmentType.SECRET:
|
||||
return SecretVariable.model_validate(m)
|
||||
result = SecretVariable.model_validate(mapping)
|
||||
case SegmentType.NUMBER if isinstance(value, int):
|
||||
return IntegerVariable.model_validate(m)
|
||||
result = IntegerVariable.model_validate(mapping)
|
||||
case SegmentType.NUMBER if isinstance(value, float):
|
||||
return FloatVariable.model_validate(m)
|
||||
result = FloatVariable.model_validate(mapping)
|
||||
case SegmentType.NUMBER if not isinstance(value, float | int):
|
||||
raise ValueError(f'invalid number value {value}')
|
||||
raise VariableError(f'invalid number value {value}')
|
||||
case SegmentType.FILE:
|
||||
return FileVariable.model_validate(m)
|
||||
result = FileVariable.model_validate(mapping)
|
||||
case SegmentType.OBJECT if isinstance(value, dict):
|
||||
return ObjectVariable.model_validate(
|
||||
{**m, 'value': {k: build_variable_from_mapping(v) for k, v in value.items()}}
|
||||
)
|
||||
result = ObjectVariable.model_validate(mapping)
|
||||
case SegmentType.ARRAY_STRING if isinstance(value, list):
|
||||
return ArrayStringVariable.model_validate({**m, 'value': [build_variable_from_mapping(v) for v in value]})
|
||||
result = ArrayStringVariable.model_validate(mapping)
|
||||
case SegmentType.ARRAY_NUMBER if isinstance(value, list):
|
||||
return ArrayNumberVariable.model_validate({**m, 'value': [build_variable_from_mapping(v) for v in value]})
|
||||
result = ArrayNumberVariable.model_validate(mapping)
|
||||
case SegmentType.ARRAY_OBJECT if isinstance(value, list):
|
||||
return ArrayObjectVariable.model_validate({**m, 'value': [build_variable_from_mapping(v) for v in value]})
|
||||
result = ArrayObjectVariable.model_validate(mapping)
|
||||
case SegmentType.ARRAY_FILE if isinstance(value, list):
|
||||
return ArrayFileVariable.model_validate({**m, 'value': [build_variable_from_mapping(v) for v in value]})
|
||||
raise ValueError(f'not supported value type {value_type}')
|
||||
mapping = dict(mapping)
|
||||
mapping['value'] = [{'value': v} for v in value]
|
||||
result = ArrayFileVariable.model_validate(mapping)
|
||||
case _:
|
||||
raise VariableError(f'not supported value type {value_type}')
|
||||
if result.size > dify_config.MAX_VARIABLE_SIZE:
|
||||
raise VariableError(f'variable size {result.size} exceeds limit {dify_config.MAX_VARIABLE_SIZE}')
|
||||
return result
|
||||
|
||||
|
||||
def build_segment(value: Any, /) -> Segment:
|
||||
|
|
@ -74,13 +80,9 @@ def build_segment(value: Any, /) -> Segment:
|
|||
if isinstance(value, float):
|
||||
return FloatSegment(value=value)
|
||||
if isinstance(value, dict):
|
||||
# TODO: Limit the depth of the object
|
||||
obj = {k: build_segment(v) for k, v in value.items()}
|
||||
return ObjectSegment(value=obj)
|
||||
return ObjectSegment(value=value)
|
||||
if isinstance(value, list):
|
||||
# TODO: Limit the depth of the array
|
||||
elements = [build_segment(v) for v in value]
|
||||
return ArrayAnySegment(value=elements)
|
||||
return ArrayAnySegment(value=value)
|
||||
if isinstance(value, FileVar):
|
||||
return FileSegment(value=value)
|
||||
raise ValueError(f'not supported value {value}')
|
||||
|
|
|
|||
|
|
@ -1,4 +1,5 @@
|
|||
import json
|
||||
import sys
|
||||
from collections.abc import Mapping, Sequence
|
||||
from typing import Any
|
||||
|
||||
|
|
@ -37,6 +38,10 @@ class Segment(BaseModel):
|
|||
def markdown(self) -> str:
|
||||
return str(self.value)
|
||||
|
||||
@property
|
||||
def size(self) -> int:
|
||||
return sys.getsizeof(self.value)
|
||||
|
||||
def to_object(self) -> Any:
|
||||
return self.value
|
||||
|
||||
|
|
@ -85,54 +90,45 @@ class FileSegment(Segment):
|
|||
|
||||
class ObjectSegment(Segment):
|
||||
value_type: SegmentType = SegmentType.OBJECT
|
||||
value: Mapping[str, Segment]
|
||||
value: Mapping[str, Any]
|
||||
|
||||
@property
|
||||
def text(self) -> str:
|
||||
# TODO: Process variables.
|
||||
return json.dumps(self.model_dump()['value'], ensure_ascii=False)
|
||||
|
||||
@property
|
||||
def log(self) -> str:
|
||||
# TODO: Process variables.
|
||||
return json.dumps(self.model_dump()['value'], ensure_ascii=False, indent=2)
|
||||
|
||||
@property
|
||||
def markdown(self) -> str:
|
||||
# TODO: Use markdown code block
|
||||
return json.dumps(self.model_dump()['value'], ensure_ascii=False, indent=2)
|
||||
|
||||
def to_object(self):
|
||||
return {k: v.to_object() for k, v in self.value.items()}
|
||||
|
||||
|
||||
class ArraySegment(Segment):
|
||||
@property
|
||||
def markdown(self) -> str:
|
||||
return '\n'.join(['- ' + item.markdown for item in self.value])
|
||||
|
||||
def to_object(self):
|
||||
return [v.to_object() for v in self.value]
|
||||
|
||||
|
||||
class ArrayAnySegment(ArraySegment):
|
||||
value_type: SegmentType = SegmentType.ARRAY_ANY
|
||||
value: Sequence[Segment]
|
||||
value: Sequence[Any]
|
||||
|
||||
|
||||
class ArrayStringSegment(ArraySegment):
|
||||
value_type: SegmentType = SegmentType.ARRAY_STRING
|
||||
value: Sequence[StringSegment]
|
||||
value: Sequence[str]
|
||||
|
||||
|
||||
class ArrayNumberSegment(ArraySegment):
|
||||
value_type: SegmentType = SegmentType.ARRAY_NUMBER
|
||||
value: Sequence[FloatSegment | IntegerSegment]
|
||||
value: Sequence[float | int]
|
||||
|
||||
|
||||
class ArrayObjectSegment(ArraySegment):
|
||||
value_type: SegmentType = SegmentType.ARRAY_OBJECT
|
||||
value: Sequence[ObjectSegment]
|
||||
value: Sequence[Mapping[str, Any]]
|
||||
|
||||
|
||||
class ArrayFileSegment(ArraySegment):
|
||||
|
|
|
|||
|
|
@ -48,7 +48,8 @@ from core.model_runtime.entities.message_entities import (
|
|||
)
|
||||
from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
|
||||
from core.model_runtime.utils.encoders import jsonable_encoder
|
||||
from core.ops.ops_trace_manager import TraceQueueManager, TraceTask, TraceTaskName
|
||||
from core.ops.entities.trace_entity import TraceTaskName
|
||||
from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
|
||||
from core.prompt.utils.prompt_message_util import PromptMessageUtil
|
||||
from core.prompt.utils.prompt_template_parser import PromptTemplateParser
|
||||
from events.message_event import message_was_created
|
||||
|
|
|
|||
|
|
@ -22,7 +22,8 @@ from core.app.entities.task_entities import (
|
|||
from core.app.task_pipeline.workflow_iteration_cycle_manage import WorkflowIterationCycleManage
|
||||
from core.file.file_obj import FileVar
|
||||
from core.model_runtime.utils.encoders import jsonable_encoder
|
||||
from core.ops.ops_trace_manager import TraceQueueManager, TraceTask, TraceTaskName
|
||||
from core.ops.entities.trace_entity import TraceTaskName
|
||||
from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
|
||||
from core.tools.tool_manager import ToolManager
|
||||
from core.workflow.entities.node_entities import NodeRunMetadataKey, NodeType
|
||||
from core.workflow.nodes.tool.entities import ToolNodeData
|
||||
|
|
@ -40,6 +41,7 @@ from models.workflow import (
|
|||
WorkflowRunStatus,
|
||||
WorkflowRunTriggeredFrom,
|
||||
)
|
||||
from services.workflow_service import WorkflowService
|
||||
|
||||
|
||||
class WorkflowCycleManage(WorkflowIterationCycleManage):
|
||||
|
|
@ -97,7 +99,6 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
|
|||
|
||||
def _workflow_run_success(
|
||||
self, workflow_run: WorkflowRun,
|
||||
start_at: float,
|
||||
total_tokens: int,
|
||||
total_steps: int,
|
||||
outputs: Optional[str] = None,
|
||||
|
|
@ -107,7 +108,6 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
|
|||
"""
|
||||
Workflow run success
|
||||
:param workflow_run: workflow run
|
||||
:param start_at: start time
|
||||
:param total_tokens: total tokens
|
||||
:param total_steps: total steps
|
||||
:param outputs: outputs
|
||||
|
|
@ -116,7 +116,7 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
|
|||
"""
|
||||
workflow_run.status = WorkflowRunStatus.SUCCEEDED.value
|
||||
workflow_run.outputs = outputs
|
||||
workflow_run.elapsed_time = time.perf_counter() - start_at
|
||||
workflow_run.elapsed_time = WorkflowService.get_elapsed_time(workflow_run_id=workflow_run.id)
|
||||
workflow_run.total_tokens = total_tokens
|
||||
workflow_run.total_steps = total_steps
|
||||
workflow_run.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
|
||||
|
|
@ -131,6 +131,7 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
|
|||
TraceTaskName.WORKFLOW_TRACE,
|
||||
workflow_run=workflow_run,
|
||||
conversation_id=conversation_id,
|
||||
user_id=trace_manager.user_id,
|
||||
)
|
||||
)
|
||||
|
||||
|
|
@ -138,7 +139,6 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
|
|||
|
||||
def _workflow_run_failed(
|
||||
self, workflow_run: WorkflowRun,
|
||||
start_at: float,
|
||||
total_tokens: int,
|
||||
total_steps: int,
|
||||
status: WorkflowRunStatus,
|
||||
|
|
@ -149,7 +149,6 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
|
|||
"""
|
||||
Workflow run failed
|
||||
:param workflow_run: workflow run
|
||||
:param start_at: start time
|
||||
:param total_tokens: total tokens
|
||||
:param total_steps: total steps
|
||||
:param status: status
|
||||
|
|
@ -158,7 +157,7 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
|
|||
"""
|
||||
workflow_run.status = status.value
|
||||
workflow_run.error = error
|
||||
workflow_run.elapsed_time = time.perf_counter() - start_at
|
||||
workflow_run.elapsed_time = WorkflowService.get_elapsed_time(workflow_run_id=workflow_run.id)
|
||||
workflow_run.total_tokens = total_tokens
|
||||
workflow_run.total_steps = total_steps
|
||||
workflow_run.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
|
||||
|
|
@ -173,6 +172,7 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
|
|||
TraceTaskName.WORKFLOW_TRACE,
|
||||
workflow_run=workflow_run,
|
||||
conversation_id=conversation_id,
|
||||
user_id=trace_manager.user_id,
|
||||
)
|
||||
)
|
||||
|
||||
|
|
@ -540,7 +540,6 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
|
|||
if isinstance(event, QueueStopEvent):
|
||||
workflow_run = self._workflow_run_failed(
|
||||
workflow_run=workflow_run,
|
||||
start_at=self._task_state.start_at,
|
||||
total_tokens=self._task_state.total_tokens,
|
||||
total_steps=self._task_state.total_steps,
|
||||
status=WorkflowRunStatus.STOPPED,
|
||||
|
|
@ -563,7 +562,6 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
|
|||
elif isinstance(event, QueueWorkflowFailedEvent):
|
||||
workflow_run = self._workflow_run_failed(
|
||||
workflow_run=workflow_run,
|
||||
start_at=self._task_state.start_at,
|
||||
total_tokens=self._task_state.total_tokens,
|
||||
total_steps=self._task_state.total_steps,
|
||||
status=WorkflowRunStatus.FAILED,
|
||||
|
|
@ -581,7 +579,6 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
|
|||
|
||||
workflow_run = self._workflow_run_success(
|
||||
workflow_run=workflow_run,
|
||||
start_at=self._task_state.start_at,
|
||||
total_tokens=self._task_state.total_tokens,
|
||||
total_steps=self._task_state.total_steps,
|
||||
outputs=outputs,
|
||||
|
|
|
|||
|
|
@ -4,7 +4,8 @@ from typing import Any, Optional, TextIO, Union
|
|||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from core.ops.ops_trace_manager import TraceQueueManager, TraceTask, TraceTaskName
|
||||
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
|
||||
|
||||
_TEXT_COLOR_MAPPING = {
|
||||
|
|
|
|||
|
|
@ -8,6 +8,7 @@ from typing import Optional
|
|||
|
||||
from pydantic import BaseModel, ConfigDict
|
||||
|
||||
from constants import HIDDEN_VALUE
|
||||
from core.entities.model_entities import ModelStatus, ModelWithProviderEntity, SimpleModelProviderEntity
|
||||
from core.entities.provider_entities import (
|
||||
CustomConfiguration,
|
||||
|
|
@ -202,7 +203,7 @@ class ProviderConfiguration(BaseModel):
|
|||
for key, value in credentials.items():
|
||||
if key in provider_credential_secret_variables:
|
||||
# if send [__HIDDEN__] in secret input, it will be same as original value
|
||||
if value == '[__HIDDEN__]' and key in original_credentials:
|
||||
if value == HIDDEN_VALUE and key in original_credentials:
|
||||
credentials[key] = encrypter.decrypt_token(self.tenant_id, original_credentials[key])
|
||||
|
||||
credentials = model_provider_factory.provider_credentials_validate(
|
||||
|
|
@ -345,7 +346,7 @@ class ProviderConfiguration(BaseModel):
|
|||
for key, value in credentials.items():
|
||||
if key in provider_credential_secret_variables:
|
||||
# if send [__HIDDEN__] in secret input, it will be same as original value
|
||||
if value == '[__HIDDEN__]' and key in original_credentials:
|
||||
if value == HIDDEN_VALUE and key in original_credentials:
|
||||
credentials[key] = encrypter.decrypt_token(self.tenant_id, original_credentials[key])
|
||||
|
||||
credentials = model_provider_factory.model_credentials_validate(
|
||||
|
|
|
|||
|
|
@ -1,14 +1,19 @@
|
|||
import enum
|
||||
from typing import Optional
|
||||
from typing import Any, Optional
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from core.app.app_config.entities import FileExtraConfig
|
||||
from core.file.tool_file_parser import ToolFileParser
|
||||
from core.file.upload_file_parser import UploadFileParser
|
||||
from core.model_runtime.entities.message_entities import ImagePromptMessageContent
|
||||
from extensions.ext_database import db
|
||||
from models.model import UploadFile
|
||||
|
||||
|
||||
class FileExtraConfig(BaseModel):
|
||||
"""
|
||||
File Upload Entity.
|
||||
"""
|
||||
image_config: Optional[dict[str, Any]] = None
|
||||
|
||||
|
||||
class FileType(enum.Enum):
|
||||
|
|
@ -114,6 +119,7 @@ class FileVar(BaseModel):
|
|||
)
|
||||
|
||||
def _get_data(self, force_url: bool = False) -> Optional[str]:
|
||||
from models.model import UploadFile
|
||||
if self.type == FileType.IMAGE:
|
||||
if self.transfer_method == FileTransferMethod.REMOTE_URL:
|
||||
return self.url
|
||||
|
|
|
|||
|
|
@ -1,10 +1,11 @@
|
|||
import re
|
||||
from collections.abc import Mapping, Sequence
|
||||
from typing import Any, Union
|
||||
from urllib.parse import parse_qs, urlparse
|
||||
|
||||
import requests
|
||||
|
||||
from core.app.app_config.entities import FileExtraConfig
|
||||
from core.file.file_obj import FileBelongsTo, FileTransferMethod, FileType, FileVar
|
||||
from core.file.file_obj import FileBelongsTo, FileExtraConfig, FileTransferMethod, FileType, FileVar
|
||||
from extensions.ext_database import db
|
||||
from models.account import Account
|
||||
from models.model import EndUser, MessageFile, UploadFile
|
||||
|
|
@ -186,6 +187,30 @@ class MessageFileParser:
|
|||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
|
||||
}
|
||||
|
||||
def is_s3_presigned_url(url):
|
||||
try:
|
||||
parsed_url = urlparse(url)
|
||||
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:
|
||||
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
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
if is_s3_presigned_url(url):
|
||||
response = requests.get(url, headers=headers, allow_redirects=True)
|
||||
if response.status_code in {200, 304}:
|
||||
return True, ""
|
||||
|
||||
response = requests.head(url, headers=headers, allow_redirects=True)
|
||||
if response.status_code in {200, 304}:
|
||||
return True, ""
|
||||
|
|
|
|||
|
|
@ -107,11 +107,11 @@ class CodeExecutor:
|
|||
response = response.json()
|
||||
except:
|
||||
raise CodeExecutionException('Failed to parse response')
|
||||
|
||||
if (code := response.get('code')) != 0:
|
||||
raise CodeExecutionException(f"Got error code: {code}. Got error msg: {response.get('message')}")
|
||||
|
||||
response = CodeExecutionResponse(**response)
|
||||
|
||||
if response.code != 0:
|
||||
raise CodeExecutionException(response.message)
|
||||
|
||||
if response.data.error:
|
||||
raise CodeExecutionException(response.data.error)
|
||||
|
|
|
|||
|
|
@ -2,7 +2,6 @@ import base64
|
|||
|
||||
from extensions.ext_database import db
|
||||
from libs import rsa
|
||||
from models.account import Tenant
|
||||
|
||||
|
||||
def obfuscated_token(token: str):
|
||||
|
|
@ -14,6 +13,7 @@ def obfuscated_token(token: str):
|
|||
|
||||
|
||||
def encrypt_token(tenant_id: str, token: str):
|
||||
from models.account import Tenant
|
||||
if not (tenant := db.session.query(Tenant).filter(Tenant.id == tenant_id).first()):
|
||||
raise ValueError(f'Tenant with id {tenant_id} not found')
|
||||
encrypted_token = rsa.encrypt(token, tenant.encrypt_public_key)
|
||||
|
|
|
|||
|
|
@ -73,6 +73,8 @@ class HostingConfiguration:
|
|||
quota_limit=hosted_quota_limit,
|
||||
restrict_models=[
|
||||
RestrictModel(model="gpt-4", base_model_name="gpt-4", model_type=ModelType.LLM),
|
||||
RestrictModel(model="gpt-4o", base_model_name="gpt-4o", model_type=ModelType.LLM),
|
||||
RestrictModel(model="gpt-4o-mini", base_model_name="gpt-4o-mini", model_type=ModelType.LLM),
|
||||
RestrictModel(model="gpt-4-32k", base_model_name="gpt-4-32k", model_type=ModelType.LLM),
|
||||
RestrictModel(model="gpt-4-1106-preview", base_model_name="gpt-4-1106-preview", model_type=ModelType.LLM),
|
||||
RestrictModel(model="gpt-4-vision-preview", base_model_name="gpt-4-vision-preview", model_type=ModelType.LLM),
|
||||
|
|
|
|||
|
|
@ -14,7 +14,8 @@ from core.model_manager import ModelManager
|
|||
from core.model_runtime.entities.message_entities import SystemPromptMessage, UserPromptMessage
|
||||
from core.model_runtime.entities.model_entities import ModelType
|
||||
from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
|
||||
from core.ops.ops_trace_manager import TraceQueueManager, TraceTask, TraceTaskName
|
||||
from core.ops.entities.trace_entity import TraceTaskName
|
||||
from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
|
||||
from core.ops.utils import measure_time
|
||||
from core.prompt.utils.prompt_template_parser import PromptTemplateParser
|
||||
|
||||
|
|
|
|||
|
|
@ -1,18 +1,16 @@
|
|||
import hashlib
|
||||
import logging
|
||||
import re
|
||||
import subprocess
|
||||
import uuid
|
||||
from abc import abstractmethod
|
||||
from typing import Optional
|
||||
|
||||
from pydantic import ConfigDict
|
||||
|
||||
from core.model_runtime.entities.model_entities import ModelPropertyKey, ModelType
|
||||
from core.model_runtime.errors.invoke import InvokeBadRequestError
|
||||
from core.model_runtime.model_providers.__base.ai_model import AIModel
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class TTSModel(AIModel):
|
||||
"""
|
||||
Model class for ttstext model.
|
||||
|
|
@ -37,8 +35,6 @@ class TTSModel(AIModel):
|
|||
:return: translated audio file
|
||||
"""
|
||||
try:
|
||||
logger.info(f"Invoke TTS model: {model} , invoke content : {content_text}")
|
||||
self._is_ffmpeg_installed()
|
||||
return self._invoke(model=model, credentials=credentials, user=user,
|
||||
content_text=content_text, voice=voice, tenant_id=tenant_id)
|
||||
except Exception as e:
|
||||
|
|
@ -75,7 +71,8 @@ class TTSModel(AIModel):
|
|||
if model_schema and ModelPropertyKey.VOICES in model_schema.model_properties:
|
||||
voices = model_schema.model_properties[ModelPropertyKey.VOICES]
|
||||
if language:
|
||||
return [{'name': d['name'], 'value': d['mode']} for d in voices if language and language in d.get('language')]
|
||||
return [{'name': d['name'], 'value': d['mode']} for d in voices if
|
||||
language and language in d.get('language')]
|
||||
else:
|
||||
return [{'name': d['name'], 'value': d['mode']} for d in voices]
|
||||
|
||||
|
|
@ -146,28 +143,3 @@ class TTSModel(AIModel):
|
|||
if one_sentence != '':
|
||||
result.append(one_sentence)
|
||||
return result
|
||||
|
||||
@staticmethod
|
||||
def _is_ffmpeg_installed():
|
||||
try:
|
||||
output = subprocess.check_output("ffmpeg -version", shell=True)
|
||||
if "ffmpeg version" in output.decode("utf-8"):
|
||||
return True
|
||||
else:
|
||||
raise InvokeBadRequestError("ffmpeg is not installed, "
|
||||
"details: https://docs.dify.ai/getting-started/install-self-hosted"
|
||||
"/install-faq#id-14.-what-to-do-if-this-error-occurs-in-text-to-speech")
|
||||
except Exception:
|
||||
raise InvokeBadRequestError("ffmpeg is not installed, "
|
||||
"details: https://docs.dify.ai/getting-started/install-self-hosted"
|
||||
"/install-faq#id-14.-what-to-do-if-this-error-occurs-in-text-to-speech")
|
||||
|
||||
# Todo: To improve the streaming function
|
||||
@staticmethod
|
||||
def _get_file_name(file_content: str) -> str:
|
||||
hash_object = hashlib.sha256(file_content.encode())
|
||||
hex_digest = hash_object.hexdigest()
|
||||
|
||||
namespace_uuid = uuid.UUID('a5da6ef9-b303-596f-8e88-bf8fa40f4b31')
|
||||
unique_uuid = uuid.uuid5(namespace_uuid, hex_digest)
|
||||
return str(unique_uuid)
|
||||
|
|
|
|||
|
|
@ -6,6 +6,7 @@
|
|||
- nvidia
|
||||
- nvidia_nim
|
||||
- cohere
|
||||
- upstage
|
||||
- bedrock
|
||||
- togetherai
|
||||
- openrouter
|
||||
|
|
@ -35,3 +36,4 @@
|
|||
- hunyuan
|
||||
- siliconflow
|
||||
- perfxcloud
|
||||
- zhinao
|
||||
|
|
|
|||
|
|
@ -116,7 +116,8 @@ class AnthropicLargeLanguageModel(LargeLanguageModel):
|
|||
# Add the new header for claude-3-5-sonnet-20240620 model
|
||||
extra_headers = {}
|
||||
if model == "claude-3-5-sonnet-20240620":
|
||||
extra_headers["anthropic-beta"] = "max-tokens-3-5-sonnet-2024-07-15"
|
||||
if model_parameters.get('max_tokens') > 4096:
|
||||
extra_headers["anthropic-beta"] = "max-tokens-3-5-sonnet-2024-07-15"
|
||||
|
||||
if tools:
|
||||
extra_model_kwargs['tools'] = [
|
||||
|
|
|
|||
|
|
@ -496,6 +496,158 @@ LLM_BASE_MODELS = [
|
|||
)
|
||||
)
|
||||
),
|
||||
AzureBaseModel(
|
||||
base_model_name='gpt-4o-mini',
|
||||
entity=AIModelEntity(
|
||||
model='fake-deployment-name',
|
||||
label=I18nObject(
|
||||
en_US='fake-deployment-name-label',
|
||||
),
|
||||
model_type=ModelType.LLM,
|
||||
features=[
|
||||
ModelFeature.AGENT_THOUGHT,
|
||||
ModelFeature.VISION,
|
||||
ModelFeature.MULTI_TOOL_CALL,
|
||||
ModelFeature.STREAM_TOOL_CALL,
|
||||
],
|
||||
fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
|
||||
model_properties={
|
||||
ModelPropertyKey.MODE: LLMMode.CHAT.value,
|
||||
ModelPropertyKey.CONTEXT_SIZE: 128000,
|
||||
},
|
||||
parameter_rules=[
|
||||
ParameterRule(
|
||||
name='temperature',
|
||||
**PARAMETER_RULE_TEMPLATE[DefaultParameterName.TEMPERATURE],
|
||||
),
|
||||
ParameterRule(
|
||||
name='top_p',
|
||||
**PARAMETER_RULE_TEMPLATE[DefaultParameterName.TOP_P],
|
||||
),
|
||||
ParameterRule(
|
||||
name='presence_penalty',
|
||||
**PARAMETER_RULE_TEMPLATE[DefaultParameterName.PRESENCE_PENALTY],
|
||||
),
|
||||
ParameterRule(
|
||||
name='frequency_penalty',
|
||||
**PARAMETER_RULE_TEMPLATE[DefaultParameterName.FREQUENCY_PENALTY],
|
||||
),
|
||||
_get_max_tokens(default=512, min_val=1, max_val=16384),
|
||||
ParameterRule(
|
||||
name='seed',
|
||||
label=I18nObject(
|
||||
zh_Hans='种子',
|
||||
en_US='Seed'
|
||||
),
|
||||
type='int',
|
||||
help=I18nObject(
|
||||
zh_Hans='如果指定，模型将尽最大努力进行确定性采样，使得重复的具有相同种子和参数的请求应该返回相同的结果。不能保证确定性，您应该参考 system_fingerprint 响应参数来监视变化。',
|
||||
en_US='If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.'
|
||||
),
|
||||
required=False,
|
||||
precision=2,
|
||||
min=0,
|
||||
max=1,
|
||||
),
|
||||
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']
|
||||
),
|
||||
],
|
||||
pricing=PriceConfig(
|
||||
input=0.150,
|
||||
output=0.600,
|
||||
unit=0.000001,
|
||||
currency='USD',
|
||||
)
|
||||
)
|
||||
),
|
||||
AzureBaseModel(
|
||||
base_model_name='gpt-4o-mini-2024-07-18',
|
||||
entity=AIModelEntity(
|
||||
model='fake-deployment-name',
|
||||
label=I18nObject(
|
||||
en_US='fake-deployment-name-label',
|
||||
),
|
||||
model_type=ModelType.LLM,
|
||||
features=[
|
||||
ModelFeature.AGENT_THOUGHT,
|
||||
ModelFeature.VISION,
|
||||
ModelFeature.MULTI_TOOL_CALL,
|
||||
ModelFeature.STREAM_TOOL_CALL,
|
||||
],
|
||||
fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
|
||||
model_properties={
|
||||
ModelPropertyKey.MODE: LLMMode.CHAT.value,
|
||||
ModelPropertyKey.CONTEXT_SIZE: 128000,
|
||||
},
|
||||
parameter_rules=[
|
||||
ParameterRule(
|
||||
name='temperature',
|
||||
**PARAMETER_RULE_TEMPLATE[DefaultParameterName.TEMPERATURE],
|
||||
),
|
||||
ParameterRule(
|
||||
name='top_p',
|
||||
**PARAMETER_RULE_TEMPLATE[DefaultParameterName.TOP_P],
|
||||
),
|
||||
ParameterRule(
|
||||
name='presence_penalty',
|
||||
**PARAMETER_RULE_TEMPLATE[DefaultParameterName.PRESENCE_PENALTY],
|
||||
),
|
||||
ParameterRule(
|
||||
name='frequency_penalty',
|
||||
**PARAMETER_RULE_TEMPLATE[DefaultParameterName.FREQUENCY_PENALTY],
|
||||
),
|
||||
_get_max_tokens(default=512, min_val=1, max_val=16384),
|
||||
ParameterRule(
|
||||
name='seed',
|
||||
label=I18nObject(
|
||||
zh_Hans='种子',
|
||||
en_US='Seed'
|
||||
),
|
||||
type='int',
|
||||
help=I18nObject(
|
||||
zh_Hans='如果指定，模型将尽最大努力进行确定性采样，使得重复的具有相同种子和参数的请求应该返回相同的结果。不能保证确定性，您应该参考 system_fingerprint 响应参数来监视变化。',
|
||||
en_US='If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.'
|
||||
),
|
||||
required=False,
|
||||
precision=2,
|
||||
min=0,
|
||||
max=1,
|
||||
),
|
||||
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']
|
||||
),
|
||||
],
|
||||
pricing=PriceConfig(
|
||||
input=0.150,
|
||||
output=0.600,
|
||||
unit=0.000001,
|
||||
currency='USD',
|
||||
)
|
||||
)
|
||||
),
|
||||
AzureBaseModel(
|
||||
base_model_name='gpt-4o',
|
||||
entity=AIModelEntity(
|
||||
|
|
|
|||
|
|
@ -114,6 +114,18 @@ model_credential_schema:
|
|||
show_on:
|
||||
- variable: __model_type
|
||||
value: llm
|
||||
- label:
|
||||
en_US: gpt-4o-mini
|
||||
value: gpt-4o-mini
|
||||
show_on:
|
||||
- variable: __model_type
|
||||
value: llm
|
||||
- label:
|
||||
en_US: gpt-4o-mini-2024-07-18
|
||||
value: gpt-4o-mini-2024-07-18
|
||||
show_on:
|
||||
- variable: __model_type
|
||||
value: llm
|
||||
- label:
|
||||
en_US: gpt-4o
|
||||
value: gpt-4o
|
||||
|
|
|
|||
|
|
@ -1,12 +1,8 @@
|
|||
import concurrent.futures
|
||||
import copy
|
||||
from functools import reduce
|
||||
from io import BytesIO
|
||||
from typing import Optional
|
||||
|
||||
from flask import Response
|
||||
from openai import AzureOpenAI
|
||||
from pydub import AudioSegment
|
||||
|
||||
from core.model_runtime.entities.model_entities import AIModelEntity
|
||||
from core.model_runtime.errors.invoke import InvokeBadRequestError
|
||||
|
|
@ -51,7 +47,7 @@ class AzureOpenAIText2SpeechModel(_CommonAzureOpenAI, TTSModel):
|
|||
:return: text translated to audio file
|
||||
"""
|
||||
try:
|
||||
self._tts_invoke(
|
||||
self._tts_invoke_streaming(
|
||||
model=model,
|
||||
credentials=credentials,
|
||||
content_text='Hello Dify!',
|
||||
|
|
@ -60,45 +56,6 @@ class AzureOpenAIText2SpeechModel(_CommonAzureOpenAI, TTSModel):
|
|||
except Exception as ex:
|
||||
raise CredentialsValidateFailedError(str(ex))
|
||||
|
||||
def _tts_invoke(self, model: str, credentials: dict, content_text: str, voice: str) -> Response:
|
||||
"""
|
||||
_tts_invoke text2speech model
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:param content_text: text content to be translated
|
||||
:param voice: model timbre
|
||||
:return: text translated to audio file
|
||||
"""
|
||||
audio_type = self._get_model_audio_type(model, credentials)
|
||||
word_limit = self._get_model_word_limit(model, credentials)
|
||||
max_workers = self._get_model_workers_limit(model, credentials)
|
||||
try:
|
||||
sentences = list(self._split_text_into_sentences(org_text=content_text, max_length=word_limit))
|
||||
audio_bytes_list = []
|
||||
|
||||
# Create a thread pool and map the function to the list of sentences
|
||||
with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
|
||||
futures = [executor.submit(self._process_sentence, sentence=sentence, model=model, voice=voice,
|
||||
credentials=credentials) for sentence in sentences]
|
||||
for future in futures:
|
||||
try:
|
||||
if future.result():
|
||||
audio_bytes_list.append(future.result())
|
||||
except Exception as ex:
|
||||
raise InvokeBadRequestError(str(ex))
|
||||
|
||||
if len(audio_bytes_list) > 0:
|
||||
audio_segments = [AudioSegment.from_file(BytesIO(audio_bytes), format=audio_type) for audio_bytes in
|
||||
audio_bytes_list if audio_bytes]
|
||||
combined_segment = reduce(lambda x, y: x + y, audio_segments)
|
||||
buffer: BytesIO = BytesIO()
|
||||
combined_segment.export(buffer, format=audio_type)
|
||||
buffer.seek(0)
|
||||
return Response(buffer.read(), status=200, mimetype=f"audio/{audio_type}")
|
||||
except Exception as ex:
|
||||
raise InvokeBadRequestError(str(ex))
|
||||
|
||||
def _tts_invoke_streaming(self, model: str, credentials: dict, content_text: str,
|
||||
voice: str) -> any:
|
||||
"""
|
||||
|
|
@ -144,7 +101,6 @@ class AzureOpenAIText2SpeechModel(_CommonAzureOpenAI, TTSModel):
|
|||
:param sentence: text content to be translated
|
||||
:return: text translated to audio file
|
||||
"""
|
||||
# transform credentials to kwargs for model instance
|
||||
credentials_kwargs = self._to_credential_kwargs(credentials)
|
||||
client = AzureOpenAI(**credentials_kwargs)
|
||||
response = client.audio.speech.create(model=model, voice=voice, input=sentence.strip())
|
||||
|
|
|
|||
|
|
@ -12,6 +12,7 @@
|
|||
- cohere.command-r-v1.0
|
||||
- meta.llama3-1-8b-instruct-v1:0
|
||||
- meta.llama3-1-70b-instruct-v1:0
|
||||
- meta.llama3-1-405b-instruct-v1:0
|
||||
- meta.llama3-8b-instruct-v1:0
|
||||
- meta.llama3-70b-instruct-v1:0
|
||||
- meta.llama2-13b-chat-v1
|
||||
|
|
|
|||
|
|
@ -3,8 +3,7 @@ label:
|
|||
en_US: Command R+
|
||||
model_type: llm
|
||||
features:
|
||||
#- multi-tool-call
|
||||
- agent-thought
|
||||
- tool-call
|
||||
#- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
|
|
|
|||
|
|
@ -3,9 +3,7 @@ label:
|
|||
en_US: Command R
|
||||
model_type: llm
|
||||
features:
|
||||
#- multi-tool-call
|
||||
- agent-thought
|
||||
#- stream-tool-call
|
||||
- tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 128000
|
||||
|
|
|
|||
|
|
@ -17,7 +17,6 @@ from botocore.exceptions import (
|
|||
ServiceNotInRegionError,
|
||||
UnknownServiceError,
|
||||
)
|
||||
from cohere import ChatMessage
|
||||
|
||||
# local import
|
||||
from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta
|
||||
|
|
@ -42,7 +41,6 @@ from core.model_runtime.errors.invoke import (
|
|||
)
|
||||
from core.model_runtime.errors.validate import CredentialsValidateFailedError
|
||||
from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
|
||||
from core.model_runtime.model_providers.cohere.llm.llm import CohereLargeLanguageModel
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
|
@ -59,6 +57,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
|
|||
{'prefix': 'mistral.mixtral-8x7b-instruct', 'support_system_prompts': False, 'support_tool_use': False},
|
||||
{'prefix': 'mistral.mistral-large', 'support_system_prompts': True, 'support_tool_use': True},
|
||||
{'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}
|
||||
]
|
||||
|
||||
|
|
@ -94,86 +93,8 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
|
|||
model_info['model'] = model
|
||||
# invoke models via boto3 converse API
|
||||
return self._generate_with_converse(model_info, credentials, prompt_messages, model_parameters, stop, stream, user, tools)
|
||||
# invoke Cohere models via boto3 client
|
||||
if "cohere.command-r" in model:
|
||||
return self._generate_cohere_chat(model, credentials, prompt_messages, model_parameters, stop, stream, user, tools)
|
||||
# invoke other models via boto3 client
|
||||
return self._generate(model, credentials, prompt_messages, model_parameters, stop, stream, user)
|
||||
|
||||
def _generate_cohere_chat(
|
||||
self, model: str, credentials: dict, prompt_messages: list[PromptMessage], model_parameters: dict,
|
||||
stop: Optional[list[str]] = None, stream: bool = True, user: Optional[str] = None,
|
||||
tools: Optional[list[PromptMessageTool]] = None,) -> Union[LLMResult, Generator]:
|
||||
cohere_llm = CohereLargeLanguageModel()
|
||||
client_config = Config(
|
||||
region_name=credentials["aws_region"]
|
||||
)
|
||||
|
||||
runtime_client = boto3.client(
|
||||
service_name='bedrock-runtime',
|
||||
config=client_config,
|
||||
aws_access_key_id=credentials["aws_access_key_id"],
|
||||
aws_secret_access_key=credentials["aws_secret_access_key"]
|
||||
)
|
||||
|
||||
extra_model_kwargs = {}
|
||||
if stop:
|
||||
extra_model_kwargs['stop_sequences'] = stop
|
||||
|
||||
if tools:
|
||||
tools = cohere_llm._convert_tools(tools)
|
||||
model_parameters['tools'] = tools
|
||||
|
||||
message, chat_histories, tool_results \
|
||||
= cohere_llm._convert_prompt_messages_to_message_and_chat_histories(prompt_messages)
|
||||
|
||||
if tool_results:
|
||||
model_parameters['tool_results'] = tool_results
|
||||
|
||||
payload = {
|
||||
**model_parameters,
|
||||
"message": message,
|
||||
"chat_history": chat_histories,
|
||||
}
|
||||
|
||||
# need workaround for ai21 models which doesn't support streaming
|
||||
if stream:
|
||||
invoke = runtime_client.invoke_model_with_response_stream
|
||||
else:
|
||||
invoke = runtime_client.invoke_model
|
||||
|
||||
def serialize(obj):
|
||||
if isinstance(obj, ChatMessage):
|
||||
return obj.__dict__
|
||||
raise TypeError(f"Type {type(obj)} not serializable")
|
||||
|
||||
try:
|
||||
body_jsonstr=json.dumps(payload, default=serialize)
|
||||
response = invoke(
|
||||
modelId=model,
|
||||
contentType="application/json",
|
||||
accept="*/*",
|
||||
body=body_jsonstr
|
||||
)
|
||||
except ClientError as ex:
|
||||
error_code = ex.response['Error']['Code']
|
||||
full_error_msg = f"{error_code}: {ex.response['Error']['Message']}"
|
||||
raise self._map_client_to_invoke_error(error_code, full_error_msg)
|
||||
|
||||
except (EndpointConnectionError, NoRegionError, ServiceNotInRegionError) as ex:
|
||||
raise InvokeConnectionError(str(ex))
|
||||
|
||||
except UnknownServiceError as ex:
|
||||
raise InvokeServerUnavailableError(str(ex))
|
||||
|
||||
except Exception as ex:
|
||||
raise InvokeError(str(ex))
|
||||
|
||||
if stream:
|
||||
return self._handle_generate_stream_response(model, credentials, response, prompt_messages)
|
||||
|
||||
return self._handle_generate_response(model, credentials, response, prompt_messages)
|
||||
|
||||
|
||||
def _generate_with_converse(self, model_info: dict, credentials: dict, prompt_messages: list[PromptMessage], model_parameters: dict,
|
||||
stop: Optional[list[str]] = None, stream: bool = True, user: Optional[str] = None, tools: Optional[list[PromptMessageTool]] = None,) -> Union[LLMResult, Generator]:
|
||||
|
|
@ -458,8 +379,12 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
|
|||
if not message_content.data.startswith("data:"):
|
||||
# fetch image data from url
|
||||
try:
|
||||
image_content = requests.get(message_content.data).content
|
||||
mime_type, _ = mimetypes.guess_type(message_content.data)
|
||||
url = message_content.data
|
||||
image_content = requests.get(url).content
|
||||
if '?' in url:
|
||||
url = url.split('?')[0]
|
||||
mime_type, _ = mimetypes.guess_type(url)
|
||||
base64_data = base64.b64encode(image_content).decode('utf-8')
|
||||
except Exception as ex:
|
||||
raise ValueError(f"Failed to fetch image data from url {message_content.data}, {ex}")
|
||||
else:
|
||||
|
|
@ -581,38 +506,9 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
|
|||
:param message: PromptMessage to convert.
|
||||
:return: String representation of the message.
|
||||
"""
|
||||
|
||||
if model_prefix == "anthropic":
|
||||
human_prompt_prefix = "\n\nHuman:"
|
||||
human_prompt_postfix = ""
|
||||
ai_prompt = "\n\nAssistant:"
|
||||
|
||||
elif model_prefix == "meta":
|
||||
# LLAMA3
|
||||
if model_name.startswith("llama3"):
|
||||
human_prompt_prefix = "<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n"
|
||||
human_prompt_postfix = "<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
|
||||
ai_prompt = "\n\nAssistant:"
|
||||
else:
|
||||
# LLAMA2
|
||||
human_prompt_prefix = "\n[INST]"
|
||||
human_prompt_postfix = "[\\INST]\n"
|
||||
ai_prompt = ""
|
||||
|
||||
elif model_prefix == "mistral":
|
||||
human_prompt_prefix = "<s>[INST]"
|
||||
human_prompt_postfix = "[\\INST]\n"
|
||||
ai_prompt = "\n\nAssistant:"
|
||||
|
||||
elif model_prefix == "amazon":
|
||||
human_prompt_prefix = "\n\nUser:"
|
||||
human_prompt_postfix = ""
|
||||
ai_prompt = "\n\nBot:"
|
||||
|
||||
else:
|
||||
human_prompt_prefix = ""
|
||||
human_prompt_postfix = ""
|
||||
ai_prompt = ""
|
||||
human_prompt_prefix = ""
|
||||
human_prompt_postfix = ""
|
||||
ai_prompt = ""
|
||||
|
||||
content = message.content
|
||||
|
||||
|
|
@ -663,13 +559,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
|
|||
model_prefix = model.split('.')[0]
|
||||
model_name = model.split('.')[1]
|
||||
|
||||
if model_prefix == "amazon":
|
||||
payload["textGenerationConfig"] = { **model_parameters }
|
||||
payload["textGenerationConfig"]["stopSequences"] = ["User:"]
|
||||
|
||||
payload["inputText"] = self._convert_messages_to_prompt(prompt_messages, model_prefix)
|
||||
|
||||
elif model_prefix == "ai21":
|
||||
if model_prefix == "ai21":
|
||||
payload["temperature"] = model_parameters.get("temperature")
|
||||
payload["topP"] = model_parameters.get("topP")
|
||||
payload["maxTokens"] = model_parameters.get("maxTokens")
|
||||
|
|
@ -681,28 +571,12 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
|
|||
payload["frequencyPenalty"] = {model_parameters.get("frequencyPenalty")}
|
||||
if model_parameters.get("countPenalty"):
|
||||
payload["countPenalty"] = {model_parameters.get("countPenalty")}
|
||||
|
||||
elif model_prefix == "mistral":
|
||||
payload["temperature"] = model_parameters.get("temperature")
|
||||
payload["top_p"] = model_parameters.get("top_p")
|
||||
payload["max_tokens"] = model_parameters.get("max_tokens")
|
||||
payload["prompt"] = self._convert_messages_to_prompt(prompt_messages, model_prefix)
|
||||
payload["stop"] = stop[:10] if stop else []
|
||||
|
||||
elif model_prefix == "anthropic":
|
||||
payload = { **model_parameters }
|
||||
payload["prompt"] = self._convert_messages_to_prompt(prompt_messages, model_prefix)
|
||||
payload["stop_sequences"] = ["\n\nHuman:"] + (stop if stop else [])
|
||||
|
||||
|
||||
elif model_prefix == "cohere":
|
||||
payload = { **model_parameters }
|
||||
payload["prompt"] = prompt_messages[0].content
|
||||
payload["stream"] = stream
|
||||
|
||||
elif model_prefix == "meta":
|
||||
payload = { **model_parameters }
|
||||
payload["prompt"] = self._convert_messages_to_prompt(prompt_messages, model_prefix, model_name)
|
||||
|
||||
else:
|
||||
raise ValueError(f"Got unknown model prefix {model_prefix}")
|
||||
|
||||
|
|
@ -793,36 +667,16 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
|
|||
# get output text and calculate num tokens based on model / provider
|
||||
model_prefix = model.split('.')[0]
|
||||
|
||||
if model_prefix == "amazon":
|
||||
output = response_body.get("results")[0].get("outputText").strip('\n')
|
||||
prompt_tokens = response_body.get("inputTextTokenCount")
|
||||
completion_tokens = response_body.get("results")[0].get("tokenCount")
|
||||
|
||||
elif model_prefix == "ai21":
|
||||
if model_prefix == "ai21":
|
||||
output = response_body.get('completions')[0].get('data').get('text')
|
||||
prompt_tokens = len(response_body.get("prompt").get("tokens"))
|
||||
completion_tokens = len(response_body.get('completions')[0].get('data').get('tokens'))
|
||||
|
||||
elif model_prefix == "anthropic":
|
||||
output = response_body.get("completion")
|
||||
prompt_tokens = self.get_num_tokens(model, credentials, prompt_messages)
|
||||
completion_tokens = self.get_num_tokens(model, credentials, output if output else '')
|
||||
|
||||
elif model_prefix == "cohere":
|
||||
output = response_body.get("generations")[0].get("text")
|
||||
prompt_tokens = self.get_num_tokens(model, credentials, prompt_messages)
|
||||
completion_tokens = self.get_num_tokens(model, credentials, output if output else '')
|
||||
|
||||
elif model_prefix == "meta":
|
||||
output = response_body.get("generation").strip('\n')
|
||||
prompt_tokens = response_body.get("prompt_token_count")
|
||||
completion_tokens = response_body.get("generation_token_count")
|
||||
|
||||
elif model_prefix == "mistral":
|
||||
output = response_body.get("outputs")[0].get("text")
|
||||
prompt_tokens = response.get('ResponseMetadata').get('HTTPHeaders').get('x-amzn-bedrock-input-token-count')
|
||||
completion_tokens = response.get('ResponseMetadata').get('HTTPHeaders').get('x-amzn-bedrock-output-token-count')
|
||||
|
||||
|
||||
else:
|
||||
raise ValueError(f"Got unknown model prefix {model_prefix} when handling block response")
|
||||
|
||||
|
|
@ -893,26 +747,10 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
|
|||
payload = json.loads(chunk.get('bytes').decode())
|
||||
|
||||
model_prefix = model.split('.')[0]
|
||||
if model_prefix == "amazon":
|
||||
content_delta = payload.get("outputText").strip('\n')
|
||||
finish_reason = payload.get("completion_reason")
|
||||
|
||||
elif model_prefix == "anthropic":
|
||||
content_delta = payload.get("completion")
|
||||
finish_reason = payload.get("stop_reason")
|
||||
|
||||
elif model_prefix == "cohere":
|
||||
if model_prefix == "cohere":
|
||||
content_delta = payload.get("text")
|
||||
finish_reason = payload.get("finish_reason")
|
||||
|
||||
elif model_prefix == "mistral":
|
||||
content_delta = payload.get('outputs')[0].get("text")
|
||||
finish_reason = payload.get('outputs')[0].get("stop_reason")
|
||||
|
||||
elif model_prefix == "meta":
|
||||
content_delta = payload.get("generation").strip('\n')
|
||||
finish_reason = payload.get("stop_reason")
|
||||
|
||||
else:
|
||||
raise ValueError(f"Got unknown model prefix {model_prefix} when handling stream response")
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,25 @@
|
|||
model: meta.llama3-1-405b-instruct-v1:0
|
||||
label:
|
||||
en_US: Llama 3.1 405B Instruct
|
||||
model_type: llm
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 0.5
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
default: 0.9
|
||||
- name: max_gen_len
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 512
|
||||
min: 1
|
||||
max: 2048
|
||||
pricing:
|
||||
input: '0.00532'
|
||||
output: '0.016'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
|
|
@ -5,6 +5,8 @@ label:
|
|||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- multi-tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 128000
|
||||
|
|
|
|||
|
|
@ -5,6 +5,8 @@ label:
|
|||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- multi-tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 128000
|
||||
|
|
|
|||
|
|
@ -19,7 +19,7 @@ parameter_rules:
|
|||
min: 1
|
||||
max: 8192
|
||||
pricing:
|
||||
input: '0.05'
|
||||
output: '0.1'
|
||||
input: '0.59'
|
||||
output: '0.79'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
|
|
|
|||
|
|
@ -19,7 +19,7 @@ parameter_rules:
|
|||
min: 1
|
||||
max: 8192
|
||||
pricing:
|
||||
input: '0.59'
|
||||
output: '0.79'
|
||||
input: '0.05'
|
||||
output: '0.08'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
|
|
|
|||
|
|
@ -0,0 +1,11 @@
|
|||
import logging
|
||||
|
||||
from core.model_runtime.model_providers.__base.model_provider import ModelProvider
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class HuggingfaceTeiProvider(ModelProvider):
|
||||
|
||||
def validate_provider_credentials(self, credentials: dict) -> None:
|
||||
pass
|
||||
|
|
@ -0,0 +1,36 @@
|
|||
provider: huggingface_tei
|
||||
label:
|
||||
en_US: Text Embedding Inference
|
||||
description:
|
||||
en_US: A blazing fast inference solution for text embeddings models.
|
||||
zh_Hans: 用于文本嵌入模型的超快速推理解决方案。
|
||||
background: "#FFF8DC"
|
||||
help:
|
||||
title:
|
||||
en_US: How to deploy Text Embedding Inference
|
||||
zh_Hans: 如何部署 Text Embedding Inference
|
||||
url:
|
||||
en_US: https://github.com/huggingface/text-embeddings-inference
|
||||
supported_model_types:
|
||||
- text-embedding
|
||||
- rerank
|
||||
configurate_methods:
|
||||
- customizable-model
|
||||
model_credential_schema:
|
||||
model:
|
||||
label:
|
||||
en_US: Model Name
|
||||
zh_Hans: 模型名称
|
||||
placeholder:
|
||||
en_US: Enter your model name
|
||||
zh_Hans: 输入模型名称
|
||||
credential_form_schemas:
|
||||
- variable: server_url
|
||||
label:
|
||||
zh_Hans: 服务器URL
|
||||
en_US: Server url
|
||||
type: secret-input
|
||||
required: true
|
||||
placeholder:
|
||||
zh_Hans: 在此输入Text Embedding Inference的服务器地址，如 http://192.168.1.100:8080
|
||||
en_US: Enter the url of your Text Embedding Inference, e.g. http://192.168.1.100:8080
|
||||
|
|
@ -0,0 +1,137 @@
|
|||
from typing import Optional
|
||||
|
||||
import httpx
|
||||
|
||||
from core.model_runtime.entities.common_entities import I18nObject
|
||||
from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType
|
||||
from core.model_runtime.entities.rerank_entities import RerankDocument, RerankResult
|
||||
from core.model_runtime.errors.invoke import (
|
||||
InvokeAuthorizationError,
|
||||
InvokeBadRequestError,
|
||||
InvokeConnectionError,
|
||||
InvokeError,
|
||||
InvokeRateLimitError,
|
||||
InvokeServerUnavailableError,
|
||||
)
|
||||
from core.model_runtime.errors.validate import CredentialsValidateFailedError
|
||||
from core.model_runtime.model_providers.__base.rerank_model import RerankModel
|
||||
from core.model_runtime.model_providers.huggingface_tei.tei_helper import TeiHelper
|
||||
|
||||
|
||||
class HuggingfaceTeiRerankModel(RerankModel):
|
||||
"""
|
||||
Model class for Text Embedding Inference rerank model.
|
||||
"""
|
||||
|
||||
def _invoke(
|
||||
self,
|
||||
model: str,
|
||||
credentials: dict,
|
||||
query: str,
|
||||
docs: list[str],
|
||||
score_threshold: Optional[float] = None,
|
||||
top_n: Optional[int] = None,
|
||||
user: Optional[str] = None,
|
||||
) -> RerankResult:
|
||||
"""
|
||||
Invoke rerank model
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:param query: search query
|
||||
:param docs: docs for reranking
|
||||
:param score_threshold: score threshold
|
||||
:param top_n: top n
|
||||
:param user: unique user id
|
||||
:return: rerank result
|
||||
"""
|
||||
if len(docs) == 0:
|
||||
return RerankResult(model=model, docs=[])
|
||||
server_url = credentials['server_url']
|
||||
|
||||
if server_url.endswith('/'):
|
||||
server_url = server_url[:-1]
|
||||
|
||||
try:
|
||||
results = TeiHelper.invoke_rerank(server_url, query, docs)
|
||||
|
||||
rerank_documents = []
|
||||
for result in results:
|
||||
rerank_document = RerankDocument(
|
||||
index=result['index'],
|
||||
text=result['text'],
|
||||
score=result['score'],
|
||||
)
|
||||
if score_threshold is None or result['score'] >= score_threshold:
|
||||
rerank_documents.append(rerank_document)
|
||||
if top_n is not None and len(rerank_documents) >= top_n:
|
||||
break
|
||||
|
||||
return RerankResult(model=model, docs=rerank_documents)
|
||||
except httpx.HTTPStatusError as e:
|
||||
raise InvokeServerUnavailableError(str(e))
|
||||
|
||||
def validate_credentials(self, model: str, credentials: dict) -> None:
|
||||
"""
|
||||
Validate model credentials
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:return:
|
||||
"""
|
||||
try:
|
||||
server_url = credentials['server_url']
|
||||
extra_args = TeiHelper.get_tei_extra_parameter(server_url, model)
|
||||
if extra_args.model_type != 'reranker':
|
||||
raise CredentialsValidateFailedError('Current model is not a rerank model')
|
||||
|
||||
credentials['context_size'] = extra_args.max_input_length
|
||||
|
||||
self.invoke(
|
||||
model=model,
|
||||
credentials=credentials,
|
||||
query='Whose kasumi',
|
||||
docs=[
|
||||
'Kasumi is a girl\'s name of Japanese origin meaning "mist".',
|
||||
'Her music is a kawaii bass, a mix of future bass, pop, and kawaii music ',
|
||||
'and she leads a team named PopiParty.',
|
||||
],
|
||||
score_threshold=0.8,
|
||||
)
|
||||
except Exception as ex:
|
||||
raise CredentialsValidateFailedError(str(ex))
|
||||
|
||||
@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
|
||||
"""
|
||||
return {
|
||||
InvokeConnectionError: [InvokeConnectionError],
|
||||
InvokeServerUnavailableError: [InvokeServerUnavailableError],
|
||||
InvokeRateLimitError: [InvokeRateLimitError],
|
||||
InvokeAuthorizationError: [InvokeAuthorizationError],
|
||||
InvokeBadRequestError: [InvokeBadRequestError, KeyError, ValueError],
|
||||
}
|
||||
|
||||
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.RERANK,
|
||||
model_properties={
|
||||
ModelPropertyKey.CONTEXT_SIZE: int(credentials.get('context_size', 512)),
|
||||
},
|
||||
parameter_rules=[],
|
||||
)
|
||||
|
||||
return entity
|
||||
|
|
@ -0,0 +1,183 @@
|
|||
from threading import Lock
|
||||
from time import time
|
||||
from typing import Optional
|
||||
|
||||
import httpx
|
||||
from requests.adapters import HTTPAdapter
|
||||
from requests.exceptions import ConnectionError, MissingSchema, Timeout
|
||||
from requests.sessions import Session
|
||||
from yarl import URL
|
||||
|
||||
|
||||
class TeiModelExtraParameter:
|
||||
model_type: str
|
||||
max_input_length: int
|
||||
max_client_batch_size: int
|
||||
|
||||
def __init__(self, model_type: str, max_input_length: int, max_client_batch_size: Optional[int] = None) -> None:
|
||||
self.model_type = model_type
|
||||
self.max_input_length = max_input_length
|
||||
self.max_client_batch_size = max_client_batch_size
|
||||
|
||||
|
||||
cache = {}
|
||||
cache_lock = Lock()
|
||||
|
||||
|
||||
class TeiHelper:
|
||||
@staticmethod
|
||||
def get_tei_extra_parameter(server_url: str, model_name: str) -> TeiModelExtraParameter:
|
||||
TeiHelper._clean_cache()
|
||||
with cache_lock:
|
||||
if model_name not in cache:
|
||||
cache[model_name] = {
|
||||
'expires': time() + 300,
|
||||
'value': TeiHelper._get_tei_extra_parameter(server_url),
|
||||
}
|
||||
return cache[model_name]['value']
|
||||
|
||||
@staticmethod
|
||||
def _clean_cache() -> None:
|
||||
try:
|
||||
with cache_lock:
|
||||
expired_keys = [model_uid for model_uid, model in cache.items() if model['expires'] < time()]
|
||||
for model_uid in expired_keys:
|
||||
del cache[model_uid]
|
||||
except RuntimeError as e:
|
||||
pass
|
||||
|
||||
@staticmethod
|
||||
def _get_tei_extra_parameter(server_url: str) -> TeiModelExtraParameter:
|
||||
"""
|
||||
get tei model extra parameter like model_type, max_input_length, max_batch_requests
|
||||
"""
|
||||
|
||||
url = str(URL(server_url) / 'info')
|
||||
|
||||
# this method is surrounded by a lock, and default requests may hang forever, so we just set a Adapter with max_retries=3
|
||||
session = Session()
|
||||
session.mount('http://', HTTPAdapter(max_retries=3))
|
||||
session.mount('https://', HTTPAdapter(max_retries=3))
|
||||
|
||||
try:
|
||||
response = session.get(url, timeout=10)
|
||||
except (MissingSchema, ConnectionError, Timeout) as e:
|
||||
raise RuntimeError(f'get tei model extra parameter failed, url: {url}, error: {e}')
|
||||
if response.status_code != 200:
|
||||
raise RuntimeError(
|
||||
f'get tei model extra parameter failed, status code: {response.status_code}, response: {response.text}'
|
||||
)
|
||||
|
||||
response_json = response.json()
|
||||
|
||||
model_type = response_json.get('model_type', {})
|
||||
if len(model_type.keys()) < 1:
|
||||
raise RuntimeError('model_type is empty')
|
||||
model_type = list(model_type.keys())[0]
|
||||
if model_type not in ['embedding', 'reranker']:
|
||||
raise RuntimeError(f'invalid model_type: {model_type}')
|
||||
|
||||
max_input_length = response_json.get('max_input_length', 512)
|
||||
max_client_batch_size = response_json.get('max_client_batch_size', 1)
|
||||
|
||||
return TeiModelExtraParameter(
|
||||
model_type=model_type,
|
||||
max_input_length=max_input_length,
|
||||
max_client_batch_size=max_client_batch_size
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def invoke_tokenize(server_url: str, texts: list[str]) -> list[list[dict]]:
|
||||
"""
|
||||
Invoke tokenize endpoint
|
||||
|
||||
Example response:
|
||||
[
|
||||
[
|
||||
{
|
||||
"id": 0,
|
||||
"text": "<s>",
|
||||
"special": true,
|
||||
"start": null,
|
||||
"stop": null
|
||||
},
|
||||
{
|
||||
"id": 7704,
|
||||
"text": "str",
|
||||
"special": false,
|
||||
"start": 0,
|
||||
"stop": 3
|
||||
},
|
||||
< MORE TOKENS >
|
||||
]
|
||||
]
|
||||
|
||||
:param server_url: server url
|
||||
:param texts: texts to tokenize
|
||||
"""
|
||||
resp = httpx.post(
|
||||
f'{server_url}/tokenize',
|
||||
json={'inputs': texts},
|
||||
)
|
||||
resp.raise_for_status()
|
||||
return resp.json()
|
||||
|
||||
@staticmethod
|
||||
def invoke_embeddings(server_url: str, texts: list[str]) -> dict:
|
||||
"""
|
||||
Invoke embeddings endpoint
|
||||
|
||||
Example response:
|
||||
{
|
||||
"object": "list",
|
||||
"data": [
|
||||
{
|
||||
"object": "embedding",
|
||||
"embedding": [...],
|
||||
"index": 0
|
||||
}
|
||||
],
|
||||
"model": "MODEL_NAME",
|
||||
"usage": {
|
||||
"prompt_tokens": 3,
|
||||
"total_tokens": 3
|
||||
}
|
||||
}
|
||||
|
||||
:param server_url: server url
|
||||
:param texts: texts to embed
|
||||
"""
|
||||
# Use OpenAI compatible API here, which has usage tracking
|
||||
resp = httpx.post(
|
||||
f'{server_url}/v1/embeddings',
|
||||
json={'input': texts},
|
||||
)
|
||||
resp.raise_for_status()
|
||||
return resp.json()
|
||||
|
||||
@staticmethod
|
||||
def invoke_rerank(server_url: str, query: str, docs: list[str]) -> list[dict]:
|
||||
"""
|
||||
Invoke rerank endpoint
|
||||
|
||||
Example response:
|
||||
[
|
||||
{
|
||||
"index": 0,
|
||||
"text": "Deep Learning is ...",
|
||||
"score": 0.9950755
|
||||
}
|
||||
]
|
||||
|
||||
:param server_url: server url
|
||||
:param texts: texts to rerank
|
||||
:param candidates: candidates to rerank
|
||||
"""
|
||||
params = {'query': query, 'texts': docs, 'return_text': True}
|
||||
|
||||
response = httpx.post(
|
||||
server_url + '/rerank',
|
||||
json=params,
|
||||
)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
|
|
@ -0,0 +1,204 @@
|
|||
import time
|
||||
from typing import Optional
|
||||
|
||||
from core.model_runtime.entities.common_entities import I18nObject
|
||||
from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType, PriceType
|
||||
from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
|
||||
from core.model_runtime.errors.invoke import (
|
||||
InvokeAuthorizationError,
|
||||
InvokeBadRequestError,
|
||||
InvokeConnectionError,
|
||||
InvokeError,
|
||||
InvokeRateLimitError,
|
||||
InvokeServerUnavailableError,
|
||||
)
|
||||
from core.model_runtime.errors.validate import CredentialsValidateFailedError
|
||||
from core.model_runtime.model_providers.__base.text_embedding_model import TextEmbeddingModel
|
||||
from core.model_runtime.model_providers.huggingface_tei.tei_helper import TeiHelper
|
||||
|
||||
|
||||
class HuggingfaceTeiTextEmbeddingModel(TextEmbeddingModel):
|
||||
"""
|
||||
Model class for Text Embedding Inference text embedding model.
|
||||
"""
|
||||
|
||||
def _invoke(
|
||||
self, model: str, credentials: dict, texts: list[str], user: Optional[str] = None
|
||||
) -> TextEmbeddingResult:
|
||||
"""
|
||||
Invoke text embedding model
|
||||
|
||||
credentials should be like:
|
||||
{
|
||||
'server_url': 'server url',
|
||||
'model_uid': 'model uid',
|
||||
}
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:param texts: texts to embed
|
||||
:param user: unique user id
|
||||
:return: embeddings result
|
||||
"""
|
||||
server_url = credentials['server_url']
|
||||
|
||||
if server_url.endswith('/'):
|
||||
server_url = server_url[:-1]
|
||||
|
||||
|
||||
# get model properties
|
||||
context_size = self._get_context_size(model, credentials)
|
||||
max_chunks = self._get_max_chunks(model, credentials)
|
||||
|
||||
inputs = []
|
||||
indices = []
|
||||
used_tokens = 0
|
||||
|
||||
# get tokenized results from TEI
|
||||
batched_tokenize_result = TeiHelper.invoke_tokenize(server_url, texts)
|
||||
|
||||
for i, (text, tokenize_result) in enumerate(zip(texts, batched_tokenize_result)):
|
||||
|
||||
# Check if the number of tokens is larger than the context size
|
||||
num_tokens = len(tokenize_result)
|
||||
|
||||
if num_tokens >= context_size:
|
||||
# Find the best cutoff point
|
||||
pre_special_token_count = 0
|
||||
for token in tokenize_result:
|
||||
if token['special']:
|
||||
pre_special_token_count += 1
|
||||
else:
|
||||
break
|
||||
rest_special_token_count = len([token for token in tokenize_result if token['special']]) - pre_special_token_count
|
||||
|
||||
# Calculate the cutoff point, leave 20 extra space to avoid exceeding the limit
|
||||
token_cutoff = context_size - rest_special_token_count - 20
|
||||
|
||||
# Find the cutoff index
|
||||
cutpoint_token = tokenize_result[token_cutoff]
|
||||
cutoff = cutpoint_token['start']
|
||||
|
||||
inputs.append(text[0: cutoff])
|
||||
else:
|
||||
inputs.append(text)
|
||||
indices += [i]
|
||||
|
||||
batched_embeddings = []
|
||||
_iter = range(0, len(inputs), max_chunks)
|
||||
|
||||
try:
|
||||
used_tokens = 0
|
||||
for i in _iter:
|
||||
iter_texts = inputs[i : i + max_chunks]
|
||||
results = TeiHelper.invoke_embeddings(server_url, iter_texts)
|
||||
embeddings = results['data']
|
||||
embeddings = [embedding['embedding'] for embedding in embeddings]
|
||||
batched_embeddings.extend(embeddings)
|
||||
|
||||
usage = results['usage']
|
||||
used_tokens += usage['total_tokens']
|
||||
except RuntimeError as e:
|
||||
raise InvokeServerUnavailableError(str(e))
|
||||
|
||||
usage = self._calc_response_usage(model=model, credentials=credentials, tokens=used_tokens)
|
||||
|
||||
result = TextEmbeddingResult(model=model, embeddings=batched_embeddings, usage=usage)
|
||||
|
||||
return result
|
||||
|
||||
def get_num_tokens(self, model: str, credentials: dict, texts: list[str]) -> int:
|
||||
"""
|
||||
Get number of tokens for given prompt messages
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:param texts: texts to embed
|
||||
:return:
|
||||
"""
|
||||
num_tokens = 0
|
||||
server_url = credentials['server_url']
|
||||
|
||||
if server_url.endswith('/'):
|
||||
server_url = server_url[:-1]
|
||||
|
||||
batch_tokens = TeiHelper.invoke_tokenize(server_url, texts)
|
||||
num_tokens = sum(len(tokens) for tokens in batch_tokens)
|
||||
return num_tokens
|
||||
|
||||
def validate_credentials(self, model: str, credentials: dict) -> None:
|
||||
"""
|
||||
Validate model credentials
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:return:
|
||||
"""
|
||||
try:
|
||||
server_url = credentials['server_url']
|
||||
extra_args = TeiHelper.get_tei_extra_parameter(server_url, model)
|
||||
print(extra_args)
|
||||
if extra_args.model_type != 'embedding':
|
||||
raise CredentialsValidateFailedError('Current model is not a embedding model')
|
||||
|
||||
credentials['context_size'] = extra_args.max_input_length
|
||||
credentials['max_chunks'] = extra_args.max_client_batch_size
|
||||
self._invoke(model=model, credentials=credentials, texts=['ping'])
|
||||
except Exception as ex:
|
||||
raise CredentialsValidateFailedError(str(ex))
|
||||
|
||||
@property
|
||||
def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
|
||||
return {
|
||||
InvokeConnectionError: [InvokeConnectionError],
|
||||
InvokeServerUnavailableError: [InvokeServerUnavailableError],
|
||||
InvokeRateLimitError: [InvokeRateLimitError],
|
||||
InvokeAuthorizationError: [InvokeAuthorizationError],
|
||||
InvokeBadRequestError: [KeyError],
|
||||
}
|
||||
|
||||
def _calc_response_usage(self, model: str, credentials: dict, tokens: int) -> EmbeddingUsage:
|
||||
"""
|
||||
Calculate response usage
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:param tokens: input tokens
|
||||
:return: usage
|
||||
"""
|
||||
# get input price info
|
||||
input_price_info = self.get_price(
|
||||
model=model, credentials=credentials, price_type=PriceType.INPUT, tokens=tokens
|
||||
)
|
||||
|
||||
# transform usage
|
||||
usage = EmbeddingUsage(
|
||||
tokens=tokens,
|
||||
total_tokens=tokens,
|
||||
unit_price=input_price_info.unit_price,
|
||||
price_unit=input_price_info.unit,
|
||||
total_price=input_price_info.total_amount,
|
||||
currency=input_price_info.currency,
|
||||
latency=time.perf_counter() - self.started_at,
|
||||
)
|
||||
|
||||
return usage
|
||||
|
||||
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.TEXT_EMBEDDING,
|
||||
model_properties={
|
||||
ModelPropertyKey.MAX_CHUNKS: int(credentials.get('max_chunks', 1)),
|
||||
ModelPropertyKey.CONTEXT_SIZE: int(credentials.get('context_size', 512)),
|
||||
},
|
||||
parameter_rules=[],
|
||||
)
|
||||
|
||||
return entity
|
||||
|
|
@ -21,6 +21,16 @@ parameter_rules:
|
|||
default: 1024
|
||||
min: 1
|
||||
max: 32000
|
||||
- name: enable_enhance
|
||||
label:
|
||||
zh_Hans: 功能增强
|
||||
en_US: Enable Enhancement
|
||||
type: boolean
|
||||
help:
|
||||
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
|
||||
en_US: Allow the model to perform external search to enhance the generation results.
|
||||
required: false
|
||||
default: true
|
||||
pricing:
|
||||
input: '0.03'
|
||||
output: '0.10'
|
||||
|
|
|
|||
|
|
@ -21,6 +21,16 @@ parameter_rules:
|
|||
default: 1024
|
||||
min: 1
|
||||
max: 256000
|
||||
- name: enable_enhance
|
||||
label:
|
||||
zh_Hans: 功能增强
|
||||
en_US: Enable Enhancement
|
||||
type: boolean
|
||||
help:
|
||||
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
|
||||
en_US: Allow the model to perform external search to enhance the generation results.
|
||||
required: false
|
||||
default: true
|
||||
pricing:
|
||||
input: '0.015'
|
||||
output: '0.06'
|
||||
|
|
|
|||
|
|
@ -21,6 +21,16 @@ parameter_rules:
|
|||
default: 1024
|
||||
min: 1
|
||||
max: 32000
|
||||
- name: enable_enhance
|
||||
label:
|
||||
zh_Hans: 功能增强
|
||||
en_US: Enable Enhancement
|
||||
type: boolean
|
||||
help:
|
||||
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
|
||||
en_US: Allow the model to perform external search to enhance the generation results.
|
||||
required: false
|
||||
default: true
|
||||
pricing:
|
||||
input: '0.0045'
|
||||
output: '0.0005'
|
||||
|
|
|
|||
|
|
@ -36,7 +36,8 @@ class HunyuanLargeLanguageModel(LargeLanguageModel):
|
|||
|
||||
custom_parameters = {
|
||||
'Temperature': model_parameters.get('temperature', 0.0),
|
||||
'TopP': model_parameters.get('top_p', 1.0)
|
||||
'TopP': model_parameters.get('top_p', 1.0),
|
||||
'EnableEnhancement': model_parameters.get('enable_enhance', True)
|
||||
}
|
||||
|
||||
params = {
|
||||
|
|
@ -213,7 +214,7 @@ class HunyuanLargeLanguageModel(LargeLanguageModel):
|
|||
def _handle_chat_response(self, credentials, model, prompt_messages, response):
|
||||
usage = self._calc_response_usage(model, credentials, response.Usage.PromptTokens,
|
||||
response.Usage.CompletionTokens)
|
||||
assistant_prompt_message = PromptMessage(role="assistant")
|
||||
assistant_prompt_message = AssistantPromptMessage()
|
||||
assistant_prompt_message.content = response.Choices[0].Message.Content
|
||||
result = LLMResult(
|
||||
model=model,
|
||||
|
|
|
|||
|
|
@ -1,4 +1,4 @@
|
|||
model: jina-reranker-v2-base-multilingual
|
||||
model_type: rerank
|
||||
model_properties:
|
||||
context_size: 8192
|
||||
context_size: 1024
|
||||
|
|
|
|||
|
|
@ -2,10 +2,16 @@
|
|||
- google/codegemma-7b
|
||||
- google/recurrentgemma-2b
|
||||
- meta/llama2-70b
|
||||
- meta/llama-3.1-8b-instruct
|
||||
- meta/llama-3.1-70b-instruct
|
||||
- meta/llama-3.1-405b-instruct
|
||||
- meta/llama3-8b-instruct
|
||||
- meta/llama3-70b-instruct
|
||||
- mistralai/mistral-large
|
||||
- mistralai/mixtral-8x7b-instruct-v0.1
|
||||
- mistralai/mixtral-8x22b-instruct-v0.1
|
||||
- nvidia/nemotron-4-340b-instruct
|
||||
- microsoft/phi-3-medium-128k-instruct
|
||||
- microsoft/phi-3-mini-128k-instruct
|
||||
- fuyu-8b
|
||||
- snowflake/arctic
|
||||
|
|
|
|||
|
|
@ -0,0 +1,36 @@
|
|||
model: meta/llama-3.1-405b-instruct
|
||||
label:
|
||||
zh_Hans: meta/llama-3.1-405b-instruct
|
||||
en_US: meta/llama-3.1-405b-instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 1
|
||||
default: 0.5
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 4096
|
||||
default: 1024
|
||||
- name: frequency_penalt
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
|
|
@ -0,0 +1,36 @@
|
|||
model: meta/llama-3.1-70b-instruct
|
||||
label:
|
||||
zh_Hans: meta/llama-3.1-70b-instruct
|
||||
en_US: meta/llama-3.1-70b-instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 1
|
||||
default: 0.5
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 4096
|
||||
default: 1024
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
|
|
@ -0,0 +1,36 @@
|
|||
model: meta/llama-3.1-8b-instruct
|
||||
label:
|
||||
zh_Hans: meta/llama-3.1-8b-instruct
|
||||
en_US: meta/llama-3.1-8b-instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 1
|
||||
default: 0.5
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 4096
|
||||
default: 1024
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
|
|
@ -31,8 +31,13 @@ class NVIDIALargeLanguageModel(OAIAPICompatLargeLanguageModel):
|
|||
'meta/llama2-70b': '',
|
||||
'meta/llama3-8b-instruct': '',
|
||||
'meta/llama3-70b-instruct': '',
|
||||
'google/recurrentgemma-2b': ''
|
||||
|
||||
'meta/llama-3.1-8b-instruct': '',
|
||||
'meta/llama-3.1-70b-instruct': '',
|
||||
'meta/llama-3.1-405b-instruct': '',
|
||||
'google/recurrentgemma-2b': '',
|
||||
'nvidia/nemotron-4-340b-instruct': '',
|
||||
'microsoft/phi-3-medium-128k-instruct':'',
|
||||
'microsoft/phi-3-mini-128k-instruct':''
|
||||
}
|
||||
|
||||
def _invoke(self, model: str, credentials: dict,
|
||||
|
|
|
|||
|
|
@ -0,0 +1,36 @@
|
|||
model: nvidia/nemotron-4-340b-instruct
|
||||
label:
|
||||
zh_Hans: nvidia/nemotron-4-340b-instruct
|
||||
en_US: nvidia/nemotron-4-340b-instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 1
|
||||
default: 0.5
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 4096
|
||||
default: 1024
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
|
|
@ -0,0 +1,36 @@
|
|||
model: microsoft/phi-3-medium-128k-instruct
|
||||
label:
|
||||
zh_Hans: microsoft/phi-3-medium-128k-instruct
|
||||
en_US: microsoft/phi-3-medium-128k-instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 1
|
||||
default: 0.5
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 4096
|
||||
default: 1024
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
|
|
@ -0,0 +1,36 @@
|
|||
model: microsoft/phi-3-mini-128k-instruct
|
||||
label:
|
||||
zh_Hans: microsoft/phi-3-mini-128k-instruct
|
||||
en_US: microsoft/phi-3-mini-128k-instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 1
|
||||
default: 0.5
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 4096
|
||||
default: 1024
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
|
|
@ -59,7 +59,7 @@ class OllamaEmbeddingModel(TextEmbeddingModel):
|
|||
if not endpoint_url.endswith('/'):
|
||||
endpoint_url += '/'
|
||||
|
||||
endpoint_url = urljoin(endpoint_url, 'api/embeddings')
|
||||
endpoint_url = urljoin(endpoint_url, 'api/embed')
|
||||
|
||||
# get model properties
|
||||
context_size = self._get_context_size(model, credentials)
|
||||
|
|
@ -72,38 +72,34 @@ class OllamaEmbeddingModel(TextEmbeddingModel):
|
|||
num_tokens = self._get_num_tokens_by_gpt2(text)
|
||||
|
||||
if num_tokens >= context_size:
|
||||
cutoff = int(len(text) * (np.floor(context_size / num_tokens)))
|
||||
cutoff = int(np.floor(len(text) * (context_size / num_tokens)))
|
||||
# if num tokens is larger than context length, only use the start
|
||||
inputs.append(text[0: cutoff])
|
||||
else:
|
||||
inputs.append(text)
|
||||
|
||||
batched_embeddings = []
|
||||
# Prepare the payload for the request
|
||||
payload = {
|
||||
'input': inputs,
|
||||
'model': model,
|
||||
}
|
||||
|
||||
for text in inputs:
|
||||
# Prepare the payload for the request
|
||||
payload = {
|
||||
'prompt': text,
|
||||
'model': model,
|
||||
}
|
||||
# Make the request to the OpenAI API
|
||||
response = requests.post(
|
||||
endpoint_url,
|
||||
headers=headers,
|
||||
data=json.dumps(payload),
|
||||
timeout=(10, 300)
|
||||
)
|
||||
|
||||
# Make the request to the OpenAI API
|
||||
response = requests.post(
|
||||
endpoint_url,
|
||||
headers=headers,
|
||||
data=json.dumps(payload),
|
||||
timeout=(10, 300)
|
||||
)
|
||||
response.raise_for_status() # Raise an exception for HTTP errors
|
||||
response_data = response.json()
|
||||
|
||||
response.raise_for_status() # Raise an exception for HTTP errors
|
||||
response_data = response.json()
|
||||
# Extract embeddings and used tokens from the response
|
||||
embeddings = response_data['embeddings']
|
||||
embedding_used_tokens = self.get_num_tokens(model, credentials, inputs)
|
||||
|
||||
# Extract embeddings and used tokens from the response
|
||||
embeddings = response_data['embedding']
|
||||
embedding_used_tokens = self.get_num_tokens(model, credentials, [text])
|
||||
|
||||
used_tokens += embedding_used_tokens
|
||||
batched_embeddings.append(embeddings)
|
||||
used_tokens += embedding_used_tokens
|
||||
|
||||
# calc usage
|
||||
usage = self._calc_response_usage(
|
||||
|
|
@ -113,7 +109,7 @@ class OllamaEmbeddingModel(TextEmbeddingModel):
|
|||
)
|
||||
|
||||
return TextEmbeddingResult(
|
||||
embeddings=batched_embeddings,
|
||||
embeddings=embeddings,
|
||||
usage=usage,
|
||||
model=model
|
||||
)
|
||||
|
|
|
|||
|
|
@ -1,6 +1,7 @@
|
|||
- gpt-4
|
||||
- gpt-4o
|
||||
- gpt-4o-2024-05-13
|
||||
- gpt-4o-2024-08-06
|
||||
- gpt-4o-mini
|
||||
- gpt-4o-mini-2024-07-18
|
||||
- gpt-4-turbo
|
||||
|
|
|
|||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue
Block a user