Skip to content

server / ranking : add sorting and management of top_n #16403

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 5 commits into
base: master
Choose a base branch
from
+39 −48
Open

server / ranking : add sorting and management of top_n #16403

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
374b648
server / ranking : add sorting and management of top_n
YannFollet Oct 3, 2025
b86bfdb
Make the retro compatible if no top_n will return
YannFollet Oct 4, 2025
fd143c7
use resize() instead for(...)
YannFollet Oct 9, 2025
a200520
simplify top_n init since no need to return error
YannFollet Oct 9, 2025
314c218
Merge remote-tracking branch 'origin/master' into rerank-top_n
YannFollet Oct 9, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 7 additions & 10 deletions tools/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5060,15 +5060,6 @@ int main(int argc, char ** argv) {

const json body = json::parse(req.body);

// TODO: implement
//int top_n = 1;
//if (body.count("top_n") != 1) {
// top_n = body.at("top_n");
//} else {
// res_error(res, format_error_response("\"top_n\" must be provided", ERROR_TYPE_INVALID_REQUEST));
// 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
Expand All @@ -5093,6 +5084,11 @@ int main(int argc, char ** argv) {
return;
}

int top_n = documents.size(); // no top_n will return all the documents
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

does this work?

Suggested change
int top_n = documents.size(); // no top_n will return all the documents
int top_n = json_value(body, "top_n", (int)documents.size());

if (body.count("top_n") == 1) {
top_n = body.at("top_n");
}

// create and queue the task
json responses = json::array();
bool error = false;
Expand Down Expand Up @@ -5133,7 +5129,8 @@ int main(int argc, char ** argv) {
body,
responses,
is_tei_format,
documents);
documents,
top_n);

res_ok(res, root);
};
Expand Down
75 changes: 38 additions & 37 deletions tools/server/utils.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -849,46 +849,47 @@ static json format_response_rerank(
const json & request,
const json & ranks,
bool is_tei_format,
std::vector<std::string> & texts) {
json res;
if (is_tei_format) {
// TEI response format
res = json::array();
bool return_text = json_value(request, "return_text", false);
for (const auto & rank : ranks) {
int index = json_value(rank, "index", 0);
json elem = json{
{"index", index},
{"score", json_value(rank, "score", 0.0)},
};
if (return_text) {
elem["text"] = std::move(texts[index]);
}
res.push_back(elem);
}
} else {
// Jina response format
json results = json::array();
int32_t n_tokens = 0;
for (const auto & rank : ranks) {
results.push_back(json{
{"index", json_value(rank, "index", 0)},
{"relevance_score", json_value(rank, "score", 0.0)},
});

n_tokens += json_value(rank, "tokens_evaluated", 0);
std::vector<std::string> & texts,
int top_n) {
json results;
int32_t n_tokens = 0;
bool return_text = is_tei_format && json_value(request, "return_text", false);
std::vector<json> elements; // Temporary vector to hold unsorted elements
std::string score_label = is_tei_format ? "score" : "relevance_score";
for (const auto & rank : ranks) {
int index = json_value(rank, "index", 0);
json elem = json{
{"index", index},
{score_label, json_value(rank, "score", 0.0)},
};
n_tokens += json_value(rank, "tokens_evaluated", 0);
if (return_text) {
elem["text"] = std::move(texts[index]);
}
elements.push_back(elem);
}

std::sort(elements.begin(), elements.end(), [score_label](const json& a, const json& b) {
return json_value(a, score_label, 0.0) > json_value(b, score_label, 0.0);
});

res = json{
{"model", json_value(request, "model", std::string(DEFAULT_OAICOMPAT_MODEL))},
{"object", "list"},
{"usage", json{
{"prompt_tokens", n_tokens},
{"total_tokens", n_tokens}
}},
{"results", results}
};
results = json::array();
int count = 0;
for (const auto & elem : elements) {
if (++count > top_n) break;
results.push_back(elem);
}
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This part is probably redundant, as you can simply resize() the elements vector

if (is_tei_format) return results;

json res = json{
{"model", json_value(request, "model", std::string(DEFAULT_OAICOMPAT_MODEL))},
{"object", "list"},
{"usage", json{
{"prompt_tokens", n_tokens},
{"total_tokens", n_tokens}
}},
{"results", results}
};

return res;
}
Expand Down
Loading