DeepSeek
DeepSeek's OpenAI-compatible chat-completions endpoint, selected with LLM_PROVIDER=deepseek, used to extract facts from conversations.
Enable it
bash
LLM_PROVIDER=deepseek
OPENAI_API_KEY=<deepseek-api-key>
OPENAI_BASE_URL=https://api.deepseek.com
OPENAI_LLM_MODEL=deepseek-chatConfiguration
| Variable | Default | Description |
|---|---|---|
LLM_PROVIDER | openai | Set to deepseek. |
OPENAI_API_KEY | (none) | DeepSeek API key, sent as a bearer token. |
OPENAI_BASE_URL | https://api.openai.com/v1 | Point at DeepSeek's endpoint: https://api.deepseek.com. |
OPENAI_LLM_MODEL | gpt-4.1-nano | A DeepSeek model, e.g. deepseek-chat. |
Notes
- OpenAI-compatible: the provider reuses the OpenAI request handling and only differs by base URL, key, and model.
- You must override
OPENAI_BASE_URLto DeepSeek's endpoint; its default points at OpenAI.