deepseek-v3
https://github.com/deepseek-ai/deepseek-v3
Python
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to deepseek-v3
Help out
- Issues
- Os Qualia tabula rasa 1808 HappinessEV
- [BUG]
- [Feature Request] Unified Multimodal Interface & Native Image Generation for DeepSeek
- [Feature Request] Voice Capabilities, Message Reading & Enhanced Intelligence for DeepSeek
- [BUG] 回复时突然切换到德语 (语言切换错误)
- Project CCL — Knowledge Management Architecture for DeepSeek
- [API Interop] /v1/responses endpoint: "No tool call found for tool output with call_id" on V4 series during multi-turn tool calling (client: Cherry Studio / Vercel AI SDK)
- [BUG]deepseek-v4-flash-vision-exp: thinking mode consumes the entire max_tokens budget and returns empty content
- Feature Suggestions to Enhance Conversation Management in DeepSeek
- Multimodal model overlooks clearly provided frames, misses visible duplicate characters, and hallucinates events when analyzing image sequences
- Docs
- Python not yet supported