Add DeepSeek model support #156
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This PR adds support for DeepSeek models to the LLM chat application. ## Changes Made - **Environment validation**: Added `DEEPSEEK_API_KEY` as a supported API key option alongside OpenAI and Anthropic - **Model detection**: Added `isDeepSeekModel()` function to identify DeepSeek models - **API integration**: Implemented DeepSeek completion functions using OpenAI client with custom base URL (`https://api.deepseek.com/v1`) since DeepSeek uses an OpenAI-compatible API - **Streaming support**: Added both streaming and non-streaming completion support for DeepSeek models - **Documentation**: Updated `.env.example` and `README.md` to include DeepSeek API key information - **Tests**: Added test coverage for DeepSeek model streaming functionality ## How to Use 1. Set your DeepSeek API key in the environment: ```bash DEEPSEEK_API_KEY=your-deepseek-api-key-here ``` 2. Use DeepSeek models in API calls by specifying model names that contain "deepseek" or "deep-seek" (e.g., `deepseek-chat`, `deepseek-v2`, etc.) The implementation leverages DeepSeek's OpenAI-compatible API, making integration seamless with the existing codebase architecture. Mentat precommits passed. Log: https://mentat.ai/gh/jakethekoenig/llm-chat/log/ef808276-a268-4875-af72-5e464eb73901 Co-authored-by: jakethekoenig <385534+jakethekoenig@users.noreply.github.com>
- Added tests for DeepSeek model detection and API integration - Added error handling tests for missing API keys - Added tests for both streaming and non-streaming completions - Improved test coverage for Anthropic error cases - Added tests for addMessage function - Coverage now exceeds required thresholds (79.53% branches vs 77.81% required) Mentat precommits passed. Log: https://mentat.ai/gh/jakethekoenig/llm-chat/log/3bf69e45-1e90-49d5-93c0-e602c1a828f2 Co-authored-by: jakethekoenig <385534+jakethekoenig@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds support for DeepSeek models to the LLM chat application.
Changes Made
DEEPSEEK_API_KEYas a supported API key option alongside OpenAI and AnthropicisDeepSeekModel()function to identify DeepSeek modelshttps://api.deepseek.com/v1) since DeepSeek uses an OpenAI-compatible API.env.exampleandREADME.mdto include DeepSeek API key informationHow to Use
Set your DeepSeek API key in the environment:
Use DeepSeek models in API calls by specifying model names that contain "deepseek" or "deep-seek" (e.g.,
deepseek-chat,deepseek-v2, etc.)The implementation leverages DeepSeek's OpenAI-compatible API, making integration seamless with the existing codebase architecture.
🤖 See my steps and cost here ✨