Expand description
The seam between cerno and whatever runs the model.
A host knows nothing about Noul, Choice or Score. It answers exactly one question: given a
prompt, what is the probability distribution over the first token the model would generate?
All primitive logic lives in cerno-core and therefore holds for every host equally.
Two adapters cover the runtimes: OllamaHost for Ollama’s native API, and
OpenAiCompatHost for everything speaking /v1/chat/completions. connect picks one
from a HostKind.
Structs§
- First
Token Distribution - The distribution over the first generated token.
- First
Token Request - One prompt, one token, full distribution.
- Host
Capabilities - What a host can and cannot do.
cerno-corereads this to size its label alphabet. - Ollama
Host - Open
AiCompat Host - Unknown
Host Kind
Enums§
- Flavour
- Which OpenAI-compatible runtime is on the other end.
- Host
Error - Host
Kind - Which runtime a server talks to. One per process.
Traits§
Functions§
- connect
- Build the adapter for
kind. Ollama takes no API key; the others send it as a bearer token.