Skip to content
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

server : fill usage info in embeddings and rerank responses #10852

Merged
merged 2 commits into from
Dec 17, 2024
Merged

server : fill usage info in embeddings and rerank responses #10852

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
357a7ba
server : fill usage info in embeddings response
krystiancha Dec 16, 2024
88cc971
server : fill usage info in reranking response
krystiancha Dec 16, 2024
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
Prev Previous commit
server : fill usage info in reranking response
  • Loading branch information
@krystiancha
krystiancha committed Dec 17, 2024
commit 88cc9719c449a8b6ef7669f7be6eebd8eb5cafa2
8 changes: 6 additions & 2 deletions examples/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -738,14 +738,17 @@ struct server_task_result_rerank : server_task_result {
int index = 0;
float score = -1e6;

int32_t n_tokens;

virtual int get_index() override {
return index;
}

virtual json to_json() override {
return json {
{"index", index},
{"score", score},
{"index", index},
{"score", score},
{"tokens_evaluated", n_tokens},
};
}
};
Expand Down Expand Up @@ -2034,6 +2037,7 @@ struct server_context {
auto res = std::make_unique<server_task_result_rerank>();
res->id = slot.id_task;
res->index = slot.index;
res->n_tokens = slot.n_prompt_tokens;

for (int i = 0; i < batch.n_tokens; ++i) {
if (!batch.logits[i] || batch.seq_id[i][0] != slot.id) {
Expand Down
23 changes: 23 additions & 0 deletions examples/server/tests/unit/test_rerank.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,3 +53,26 @@ def test_invalid_rerank_req(documents):
})
assert res.status_code == 400
assert "error" in res.body


@pytest.mark.parametrize(
"query,doc1,doc2,n_tokens",
[
("Machine learning is", "A machine", "Learning is", 19),
("Which city?", "Machine learning is ", "Paris, capitale de la", 26),
]
)
def test_rerank_usage(query, doc1, doc2, n_tokens):
global server
server.start()

res = server.make_request("POST", "/rerank", data={
"query": query,
"documents": [
doc1,
doc2,
]
})
assert res.status_code == 200
assert res.body['usage']['prompt_tokens'] == res.body['usage']['total_tokens']
assert res.body['usage']['prompt_tokens'] == n_tokens
9 changes: 6 additions & 3 deletions examples/server/utils.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -587,20 +587,23 @@ static json format_embeddings_response_oaicompat(const json & request, const jso

static json format_response_rerank(const json & request, const json & ranks) {
json data = json::array();
int32_t n_tokens = 0;
int i = 0;
for (const auto & rank : ranks) {
data.push_back(json{
{"index", i++},
{"relevance_score", json_value(rank, "score", 0.0)},
});

n_tokens += json_value(rank, "tokens_evaluated", 0);
}

json res = json {
{"model", json_value(request, "model", std::string(DEFAULT_OAICOMPAT_MODEL))},
{"object", "list"},
{"usage", json { // TODO: fill
{"prompt_tokens", 0},
{"total_tokens", 0}
{"usage", json {
{"prompt_tokens", n_tokens},
{"total_tokens", n_tokens}
}},
{"results", data}
};
Expand Down
Loading