Skip to content

server : output embeddings for all tokens when pooling = none #10861

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

Merged
merged 12 commits into from
Dec 18, 2024
Merged

server : output embeddings for all tokens when pooling = none #10861

Changes from 1 commit
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
44eeb6a
server : add "tokens" output
ggerganov Dec 16, 2024
07946a3
server : output embeddings for all tokens when pooling = none
ggerganov Dec 17, 2024
d424afa
server : update readme [no ci]
ggerganov Dec 17, 2024
2dea487
server : fix spacing [no ci]
ggerganov Dec 17, 2024
2a94c33
server : be explicit about the pooling type in the tests
ggerganov Dec 17, 2024
abf33e2
server : update /embeddings and /v1/embeddings endpoints
ggerganov Dec 17, 2024
7e693f9
server : do not normalize embeddings when there is no pooling
ggerganov Dec 17, 2024
3a7c001
server : update readme
ggerganov Dec 17, 2024
87df601
server : fixes
ggerganov Dec 18, 2024
2a5510e
tests : update server tests
ggerganov Dec 18, 2024
600cebc
server : update readme [no ci]
ggerganov Dec 18, 2024
2dcdd48
server : remove rebase artifact
ggerganov Dec 18, 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
Next Next commit
server : fix spacing [no ci] 
Co-authored-by: Xuan Son Nguyen <[email protected]>
  • Loading branch information
@ggerganov @ngxson
ggerganov and ngxson committed Dec 18, 2024
commit 2dea48758e3935bbc20255619888ec220a969765
2 changes: 1 addition & 1 deletion examples/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -736,7 +736,7 @@ struct server_task_result_embd : server_task_result {
}

virtual json to_json() override {
if (embedding.size() == 1){
if (embedding.size() == 1) {
// to be OAI compatible
return json {
{"index", index},
Expand Down