async fn make_llm_request(
chat_request: LLMRequest,
endpoint: &Url,
api_key: &SecretString,
) -> Result<LLMResponse>Expand description
Makes a non-streaming request to an LLM
async fn make_llm_request(
chat_request: LLMRequest,
endpoint: &Url,
api_key: &SecretString,
) -> Result<LLMResponse>Makes a non-streaming request to an LLM