OpenAI Messages API

documented

OpenAI-compatible chat API for TGI endpoints (example path shown in docs).

POST /v1/chat/completionsText Generation Inferenceno implementation yet0 runs

No implementation yet. Run it to have the agent write one, or open a pull request with your own.

Seed example (keychains curl)

npx -y keychains@latest curl "https://{{$hf_host}}/v1/chat/completions" \
  -X POST \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer {{HUGGINGFACE_API_KEY}}" \
  -d '{"model": "{{$model}}", "messages": [ {"role": "system", "content": "{{$system_message}}"}, {"role": "user", "content": "{{$user_message}}"} ], "stream": {{$stream}}, "max_tokens": {{$max_tokens}}, "temperature": {{$temperature}} }'