Expand description
TranslatingLlmClient — the crate’s single public entry point: encode a neutral
request, call the configured backend over HTTP, decode the neutral response.
Structs§
- Model
Config - How one model is served: the
default_backendused when the request does not pin a wire format, plus anyother_backendsreachable over additional formats. - Translating
LlmClient - A client that dispatches neutral-IR requests to per-model HTTP backends.