-
-
Notifications
You must be signed in to change notification settings - Fork 13.8k
✨ feat: Support ModelScope Provider #8026
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
@hedeqiang is attempting to deploy a commit to the LobeHub Community Team on Vercel. A member of the Team first needs to authorize it. |
Thank you for raising your pull request and contributing to our Community |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
PR Summary
Added ModelScope provider integration to LobeChat, enabling access to Alibaba Cloud's AI models including DeepSeek and Qwen series.
- Added comprehensive configuration for ModelScope in Dockerfiles with environment variables
ENABLED_MODELSCOPE
,MODELSCOPE_API_KEY
, andMODELSCOPE_MODEL_LIST
- Implemented OpenAI-compatible API client with model detection for function calling, vision, and reasoning capabilities in
/src/libs/model-runtime/modelscope
- Added detailed documentation in both English and Chinese covering setup, prerequisites (including required Alibaba Cloud account binding), and troubleshooting
- Integrated 5 initial models: DeepSeek-V3-0324, DeepSeek-V3, DeepSeek-R1-0528, Qwen3-235B-A22B, and Qwen3-32B
- Added proper type definitions and runtime mapping for ModelScope provider while maintaining consistent code patterns
💡 (2/5) Greptile learns from your feedback when you react with 👍/👎!
14 file(s) reviewed, 6 comment(s)
Edit PR Review Bot Settings | Greptile
|
||
const visionKeywords = ['qwen-vl', 'qwen2-vl', 'llava']; | ||
|
||
const reasoningKeywords = ['qwq', 'deepseek-r1']; |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
logic: 'qwq' seems like a typo in reasoningKeywords array - this may not match any actual model IDs
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #8026 +/- ##
==========================================
- Coverage 95.67% 88.37% -7.30%
==========================================
Files 14 825 +811
Lines 2519 60594 +58075
Branches 244 5511 +5267
==========================================
+ Hits 2410 53550 +51140
- Misses 109 7044 +6935
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
❤️ Great PR @hedeqiang ❤️ The growth of project is inseparable from user feedback and contribution, thanks for your contribution! If you are interesting with the lobehub developer community, please join our discord and then dm @arvinxx or @canisminor1990. They will invite you to our private developer channel. We are talking about the lobe-chat development or sharing ai newsletter around the world. |
## [Version 1.89.0](v1.88.23...v1.89.0) <sup>Released on **2025-06-01**</sup> #### ✨ Features - **misc**: Support ModelScope Provider. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's improved * **misc**: Support ModelScope Provider, closes [#8026](#8026) ([7b91dfd](7b91dfd)) </details> <div align="right"> [](#readme-top) </div>
🎉 This PR is included in version 1.89.0 🎉 The release is available on: Your semantic-release bot 📦🚀 |
## [Version 1.88.0](v1.87.2...v1.88.0) <sup>Released on **2025-06-02**</sup> #### ✨ Features - **misc**: Support ModelScope Provider, support protect page. #### 🐛 Bug Fixes - **misc**: Agent automatic completion meta not working error, disable LaTeX and Mermaid rendering in SystemRoleContent to prevent lag caused by massive rendering tasks when switching topics, fix DeepSeek new R1 Search error. #### 💄 Styles - **misc**: `+` in the welcome message can be clicked to create an assistant, Enable deploymentName for Aliyun Bailian, Enhanced reasoning_effort Slider Component, support `web_search` tool for MiniMax & Zhipu, support 01.ai proxy url, Update Hunyuan models & deepseek-r1-0528, use default deployment name when parseModelString doesn't contain deployment name. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's improved * **misc**: Support ModelScope Provider, closes [lobehub#8026](https://github.com/jaworldwideorg/OneJA-Bot/issues/8026) ([7b91dfd](7b91dfd)) * **misc**: Support protect page, closes [lobehub#8024](https://github.com/jaworldwideorg/OneJA-Bot/issues/8024) ([d61a9f5](d61a9f5)) #### What's fixed * **misc**: Agent automatic completion meta not working error, closes [lobehub#8003](https://github.com/jaworldwideorg/OneJA-Bot/issues/8003) ([c5307bf](c5307bf)) * **misc**: Disable LaTeX and Mermaid rendering in SystemRoleContent to prevent lag caused by massive rendering tasks when switching topics, closes [lobehub#8034](https://github.com/jaworldwideorg/OneJA-Bot/issues/8034) ([5b42ee2](5b42ee2)) * **misc**: Fix DeepSeek new R1 Search error, closes [lobehub#8035](https://github.com/jaworldwideorg/OneJA-Bot/issues/8035) ([cf58628](cf58628)) #### Styles * **misc**: `+` in the welcome message can be clicked to create an assistant, closes [lobehub#7984](https://github.com/jaworldwideorg/OneJA-Bot/issues/7984) ([9f07e4c](9f07e4c)) * **misc**: Enable deploymentName for Aliyun Bailian, closes [lobehub#7576](https://github.com/jaworldwideorg/OneJA-Bot/issues/7576) ([169e598](169e598)) * **misc**: Enhanced reasoning_effort Slider Component, closes [lobehub#7998](https://github.com/jaworldwideorg/OneJA-Bot/issues/7998) ([750b26a](750b26a)) * **misc**: Support `web_search` tool for MiniMax & Zhipu, closes [lobehub#7980](https://github.com/jaworldwideorg/OneJA-Bot/issues/7980) ([28cdafb](28cdafb)) * **misc**: Support 01.ai proxy url, closes [lobehub#8025](https://github.com/jaworldwideorg/OneJA-Bot/issues/8025) ([e0442b8](e0442b8)) * **misc**: Update Hunyuan models & deepseek-r1-0528, closes [lobehub#7993](https://github.com/jaworldwideorg/OneJA-Bot/issues/7993) ([2eb198c](2eb198c)) * **misc**: Use default deployment name when parseModelString doesn't contain deployment name, closes [lobehub#7719](https://github.com/jaworldwideorg/OneJA-Bot/issues/7719) ([aef19f4](aef19f4)) </details> <div align="right"> [](#readme-top) </div>
* feat: support modelscop * feat: support modelscop * style: update llm.ts * style: update modelscope
## [Version 1.89.0](lobehub/lobe-chat@v1.88.23...v1.89.0) <sup>Released on **2025-06-01**</sup> #### ✨ Features - **misc**: Support ModelScope Provider. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's improved * **misc**: Support ModelScope Provider, closes [lobehub#8026](lobehub#8026) ([7b91dfd](lobehub@7b91dfd)) </details> <div align="right"> [](#readme-top) </div>
* feat: support modelscop * feat: support modelscop * style: update llm.ts * style: update modelscope
## [Version 1.89.0](lobehub/lobe-chat@v1.88.23...v1.89.0) <sup>Released on **2025-06-01**</sup> #### ✨ Features - **misc**: Support ModelScope Provider. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's improved * **misc**: Support ModelScope Provider, closes [lobehub#8026](lobehub#8026) ([7b91dfd](lobehub@7b91dfd)) </details> <div align="right"> [](#readme-top) </div>
* feat: support modelscop * feat: support modelscop * style: update llm.ts * style: update modelscope
## [Version 1.89.0](lobehub/lobe-chat@v1.88.23...v1.89.0) <sup>Released on **2025-06-01**</sup> #### ✨ Features - **misc**: Support ModelScope Provider. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's improved * **misc**: Support ModelScope Provider, closes [lobehub#8026](lobehub#8026) ([6e2b50d](lobehub@6e2b50d)) </details> <div align="right"> [](#readme-top) </div>
💻 变更类型 | Change Type
🔀 变更说明 | Description of Change
新增魔塔服务商
📝 补充信息 | Additional Information