mirrors/ollama-for-amd
1
0
Fork 0
mirror of https://github.com/likelovewant/ollama-for-amd.git synced 2025-12-21 22:33:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

runner: always truncate embeddings requests (#12714)

Browse Source
This commit is contained in:
Jeffrey Morgan
2025-10-20 16:47:05 -07:00
committed by GitHub
parent d2b63c19b3
commit 5fe7ba1b9b
3 changed files with 29 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
runner/llamarunner/runner.go
View File

@@ -697,7 +697,14 @@ func (s *Server) embeddings(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "application/json")
seq, err := s.NewSequence(req.Content, nil, NewSequenceParams{embedding: true})
seq, err := s.NewSequence(req.Content, nil, NewSequenceParams{
embedding: true,
// TODO (jmorganca): this should be provided by the server via the
// request options and truncated here in the runner, instead of relying on
// the server's truncate logic
truncate: true,
})
if err != nil {
http.Error(w, fmt.Sprintf("Failed to create new sequence: %v", err), http.StatusInternalServerError)
return