vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

server : add /apply-template endpoint for additional use cases of Minja functionality (#11489)

Browse source 
* add /apply-template endpoint to server

* remove unnecessary line

* add /apply-template documentation

* return only "prompt" field in /apply-template

* use suggested idea instead of my overly verbose way
This commit is contained in:
Nigel Bosch 2025-01-29 12:45:44 -06:00 • committed by GitHub
parent 66ee4f297c
commit eb7cf15a80
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 32 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

9
examples/server/server.cpp
View file

@ -4124,6 +4124,14 @@ int main(int argc, char ** argv) {
res_ok(res, root);
};
const auto handle_apply_template = [&ctx_server, &params, &res_ok](const httplib::Request & req, httplib::Response & res) {
auto body = json::parse(req.body);
const auto & chat_template = body.contains("tools") && ctx_server.chat_templates.template_tool_use ? *ctx_server.chat_templates.template_tool_use : *ctx_server.chat_templates.template_default;
json data = oaicompat_completion_params_parse(body, chat_template, params.use_jinja);
res_ok(res, {{ "prompt", data.at("prompt") }});
};
const auto handle_embeddings = [&handle_embeddings_impl](const httplib::Request & req, httplib::Response & res) {
handle_embeddings_impl(req, res, OAICOMPAT_TYPE_NONE);
};
@ -4300,6 +4308,7 @@ int main(int argc, char ** argv) {
svr->Post("/v1/reranking", handle_rerank);
svr->Post("/tokenize", handle_tokenize);
svr->Post("/detokenize", handle_detokenize);
svr->Post("/apply-template", handle_apply_template);
// LoRA adapters hotswap
svr->Get ("/lora-adapters", handle_lora_adapters_list);
svr->Post("/lora-adapters", handle_lora_adapters_apply);