llm-inference / library
Groq Python SDK
Capability: Groq Python SDK
Use it when
- use low-latency hosted inference through an OpenAI-style client
- prototype streaming chat against Groq-hosted models
What it solves
Not the fit when
- requires a Groq account and supported hosted model
Install
pip install groq
Invoke
Create `Groq()`, then call `client.chat.completions.create(model=..., messages=[...])`.
Alternatives
No reviewed alternatives recorded yet.