tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : add TEI API format for /rerank endpoint (#11942)

Browse Source 
* server : add TEI API format for /rerank endpoint

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* fix

* also gitignore examples/server/*.gz.hpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Xuan-Son Nguyen
2025-02-18 14:21:41 +01:00
committed by GitHub
parent 5137da7b8c
commit 63ac128563
4 changed files with 88 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
examples/server/server.cpp
View File

@ -4263,6 +4263,11 @@ int main(int argc, char ** argv) {
// return;
//}
// if true, use TEI API format, otherwise use Jina API format
// Jina: https://jina.ai/reranker/
// TEI: https://huggingface.github.io/text-embeddings-inference/#/Text%20Embeddings%20Inference/rerank
bool is_tei_format = body.contains("texts");
json query;
if (body.count("query") == 1) {
query = body.at("query");
@ -4275,7 +4280,8 @@ int main(int argc, char ** argv) {
return;
}
std::vector<std::string> documents = json_value(body, "documents", std::vector<std::string>());
std::vector<std::string> documents = json_value(body, "documents",
json_value(body, "texts", std::vector<std::string>()));
if (documents.empty()) {
res_error(res, format_error_response("\"documents\" must be a non-empty string array", ERROR_TYPE_INVALID_REQUEST));
return;
@ -4320,7 +4326,12 @@ int main(int argc, char ** argv) {
}
// write JSON response
json root = format_response_rerank(body, responses);
json root = format_response_rerank(
body,
responses,
is_tei_format,
documents);
res_ok(res, root);
};