root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-13 04:00:16 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

server: catch errors in format_final_response_oaicompat instead of taking server down

Browse Source
This commit is contained in:
ochafik 2024-09-26 03:42:36 +01:00
parent 595e11cb11
commit 94377d743c
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
examples/server/server.cpp
View File

@ -2879,8 +2879,12 @@ int main(int argc, char ** argv) {
if (!stream) {
ctx_server.receive_cmpl_results(task_ids, [&](const std::vector<server_task_result> & results) {
// multitask is never support in chat completion, there is only one result
json result_oai = format_final_response_oaicompat(data, results[0].data, completion_id, /*.streaming =*/ false, verbose);
res_ok(res, result_oai);
try {
json result_oai = format_final_response_oaicompat(data, results[0].data, completion_id, /*.streaming =*/ false, verbose);
res_ok(res, result_oai);
} catch (const std::runtime_error & e) {
res_error(res, format_error_response(e.what(), ERROR_TYPE_SERVER));
}
}, [&](const json & error_data) {
res_error(res, error_data);
});