OpenAI¶

Configure HolmesGPT to use OpenAI's GPT models.

Setup¶

Note

Requires a paid OpenAI API key, not a ChatGPT Plus subscription.

Configuration¶

export OPENAI_API_KEY="your-openai-api-key"
holmes ask "what pods are failing?"

Using CLI Parameters¶

You can also pass the API key directly as a command-line parameter:

holmes ask "what pods are failing?" --api-key="your-api-key"

Available Models¶

# GPT-4o (default, recommended)
holmes ask "what pods are failing?"

# GPT-4o mini (faster, but results are not as accurate)
holmes ask "what pods are failing?" --model="gpt-4o-mini"

Additional Resources¶

HolmesGPT uses the LiteLLM API to support OpenAI provider. Refer to LiteLLM OpenAI docs for more details.