git/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp synced 2026-04-22 15:13:24 +02:00
Code Issues Packages Projects Releases Wiki Activity

server : remove /api endpoints (#22165)

Browse Source 
* server : remove /api endpoints

* cont : remove /api/tags
This commit is contained in:
Georgi Gerganov 2026-04-20 20:41:19 +03:00 committed by GitHub
parent fd6ae4ca1c
commit cf8b0dbda9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 0 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
tools/server/server-context.cpp
View File

@ -3653,34 +3653,6 @@ void server_routes::init_routes() {
return res;
};
this->get_api_show = [this](const server_http_req &) {
auto res = create_response();
std::string tmpl_default = common_chat_templates_source(meta->chat_params.tmpls.get(), "");
json data = {
{
"model_info", {
{ "llama.context_length", meta->slot_n_ctx },
}
},
{"modelfile", ""},
{"parameters", ""},
{"template", tmpl_default},
{"details", {
{"parent_model", ""},
{"format", "gguf"},
{"family", ""},
{"families", {""}},
{"parameter_size", ""},
{"quantization_level", ""}
}},
{"model_info", ""},
{"capabilities", meta->has_mtmd ? json({"completion","multimodal"}) : json({"completion"})}
};
res->ok(data);
return res;
};
this->post_infill = [this](const server_http_req & req) {
auto res = create_response();
// check model compatibility

1
tools/server/server-context.h
View File

@ -105,7 +105,6 @@ struct server_routes {
server_http_context::handler_t post_slots;
server_http_context::handler_t get_props;
server_http_context::handler_t post_props;
server_http_context::handler_t get_api_show;
server_http_context::handler_t post_infill;
server_http_context::handler_t post_completions;
server_http_context::handler_t post_completions_oai;

1
tools/server/server-http.cpp
View File

@ -143,7 +143,6 @@ bool server_http_context::init(const common_params & params) {
"/v1/health",
"/models",
"/v1/models",
"/api/tags",
"/",
"/index.html",
"/bundle.js",

4
tools/server/server.cpp
View File

@ -141,7 +141,6 @@ int main(int argc, char ** argv) {
// note: routes.get_health stays the same
routes.get_metrics = models_routes->proxy_get;
routes.post_props = models_routes->proxy_post;
routes.get_api_show = models_routes->proxy_get;
routes.post_completions = models_routes->proxy_post;
routes.post_completions_oai = models_routes->proxy_post;
routes.post_chat_completions = models_routes->proxy_post;
@ -174,16 +173,13 @@ int main(int argc, char ** argv) {
ctx_http.get ("/metrics", ex_wrapper(routes.get_metrics));
ctx_http.get ("/props", ex_wrapper(routes.get_props));
ctx_http.post("/props", ex_wrapper(routes.post_props));
ctx_http.post("/api/show", ex_wrapper(routes.get_api_show));
ctx_http.get ("/models", ex_wrapper(routes.get_models)); // public endpoint (no API key check)
ctx_http.get ("/v1/models", ex_wrapper(routes.get_models)); // public endpoint (no API key check)
ctx_http.get ("/api/tags", ex_wrapper(routes.get_models)); // ollama specific endpoint. public endpoint (no API key check)
ctx_http.post("/completion", ex_wrapper(routes.post_completions)); // legacy
ctx_http.post("/completions", ex_wrapper(routes.post_completions));
ctx_http.post("/v1/completions", ex_wrapper(routes.post_completions_oai));
ctx_http.post("/chat/completions", ex_wrapper(routes.post_chat_completions));
ctx_http.post("/v1/chat/completions", ex_wrapper(routes.post_chat_completions));
ctx_http.post("/api/chat", ex_wrapper(routes.post_chat_completions)); // ollama specific endpoint
ctx_http.post("/v1/responses", ex_wrapper(routes.post_responses_oai));
ctx_http.post("/responses", ex_wrapper(routes.post_responses_oai));
ctx_http.post("/v1/audio/transcriptions", ex_wrapper(routes.post_transcriptions_oai));