ExAthena.Chat.LlamaCpp (ExAthena v0.12.0)

Copy Markdown View Source

Talks to a local llama.cpp server's OpenAI-compatible HTTP API for chat-time helpers.

list_models/1 hits GET /v1/models and returns the loaded model IDs sorted alphabetically. The llama.cpp server (llama-server) typically serves one model at a time, so the list usually has a single entry.

Summary

Functions

list_models(opts \\ [])

Functions

list_models(opts \\ [])

@spec list_models(keyword()) ::
  {:ok, [String.t()]}
  | {:error, :llamacpp_unreachable | :unexpected_response | {:http, integer()}}