mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-06-27 23:50:20 -05:00
099b579acb
* ui: model status and load progress via /models/sse feed * ui: centralize SSE wire-format delimiters into shared constants for the chat and /models/sse parsers * ui: type /models/sse event names as a ServerModelsSseEventType enum Address review from allozaur
26 lines
586 B
TypeScript
26 lines
586 B
TypeScript
export const API_MODELS = {
|
|
LIST: '/v1/models',
|
|
LOAD: '/models/load',
|
|
UNLOAD: '/models/unload',
|
|
SSE: '/models/sse'
|
|
};
|
|
|
|
// chat completion routes, the control route drives realtime inference (e.g. end reasoning)
|
|
export const API_CHAT = {
|
|
COMPLETIONS: './v1/chat/completions',
|
|
CONTROL: './v1/chat/completions/control'
|
|
};
|
|
|
|
// slot introspection, requires the --slots flag on the server
|
|
export const API_SLOTS = {
|
|
LIST: './slots'
|
|
};
|
|
|
|
export const API_TOOLS = {
|
|
LIST: '/tools',
|
|
EXECUTE: '/tools'
|
|
};
|
|
|
|
/** CORS proxy endpoint path */
|
|
export const CORS_PROXY_ENDPOINT = '/cors-proxy';
|