CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : fix endpoint checks (#10135)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2024-11-02 18:34:00 +02:00
committed by GitHub
parent 1926d6e39d
commit 45950415ed
1 changed files with 7 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
examples/server/server.cpp
View File

@@ -2703,8 +2703,8 @@ int main(int argc, char ** argv) {
}; };
const auto handle_completions_generic = [&ctx_server, &res_error, &res_ok](server_task_inf_type inf_type, json & data, httplib::Response & res) { const auto handle_completions_generic = [&ctx_server, &res_error, &res_ok](server_task_inf_type inf_type, json & data, httplib::Response & res) {
if (ctx_server.params.embedding || ctx_server.params.reranking) { if (ctx_server.params.embedding) {
res_error(res, format_error_response("This server does not support completions. Start it without `--embeddings` or `--reranking`", ERROR_TYPE_NOT_SUPPORTED)); res_error(res, format_error_response("This server does not support completions. Start it without `--embeddings`", ERROR_TYPE_NOT_SUPPORTED));
return; return;
} }
@@ -2809,8 +2809,8 @@ int main(int argc, char ** argv) {
// TODO: maybe merge this function with "handle_completions_generic" // TODO: maybe merge this function with "handle_completions_generic"
const auto handle_chat_completions = [&ctx_server, &params, &res_error, &res_ok, verbose](const httplib::Request & req, httplib::Response & res) { const auto handle_chat_completions = [&ctx_server, &params, &res_error, &res_ok, verbose](const httplib::Request & req, httplib::Response & res) {
if (ctx_server.params.embedding || ctx_server.params.reranking) { if (ctx_server.params.embedding) {
res_error(res, format_error_response("This server does not support completions. Start it without `--embeddings` or `--reranking`", ERROR_TYPE_NOT_SUPPORTED)); res_error(res, format_error_response("This server does not support completions. Start it without `--embeddings`", ERROR_TYPE_NOT_SUPPORTED));
return; return;
} }
@@ -2935,11 +2935,6 @@ int main(int argc, char ** argv) {
}; };
const auto handle_embeddings = [&ctx_server, &res_error, &res_ok](const httplib::Request & req, httplib::Response & res) { const auto handle_embeddings = [&ctx_server, &res_error, &res_ok](const httplib::Request & req, httplib::Response & res) {
// TODO: somehow clean up this checks in the future
if (!ctx_server.params.embedding || ctx_server.params.reranking) {
res_error(res, format_error_response("This server does not support embeddings. Start it with `--embeddings` and without `--reranking`", ERROR_TYPE_NOT_SUPPORTED));
return;
}
const json body = json::parse(req.body); const json body = json::parse(req.body);
bool is_openai = false; bool is_openai = false;
@@ -2991,10 +2986,11 @@ int main(int argc, char ** argv) {
}; };
const auto handle_rerank = [&ctx_server, &res_error, &res_ok](const httplib::Request & req, httplib::Response & res) { const auto handle_rerank = [&ctx_server, &res_error, &res_ok](const httplib::Request & req, httplib::Response & res) {
if (!ctx_server.params.reranking) { if (!ctx_server.params.reranking || ctx_server.params.embedding) {
res_error(res, format_error_response("This server does not support reranking. Start it with `--reranking`", ERROR_TYPE_NOT_SUPPORTED)); res_error(res, format_error_response("This server does not support reranking. Start it with `--reranking` and without `--embedding`", ERROR_TYPE_NOT_SUPPORTED));
return; return;
} }
const json body = json::parse(req.body); const json body = json::parse(req.body);
// TODO: implement // TODO: implement