starred/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-04-25 18:25:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

use float32

Browse Source
This commit is contained in:
Roy Han
2024-07-02 10:30:29 -07:00
parent 512e0a7bde
commit 00a4cb26ca
6 changed files with 27 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
llm/server.go
View File

@@ -34,7 +34,7 @@ type LlamaServer interface {
WaitUntilRunning(ctx context.Context) error
Completion(ctx context.Context, req CompletionRequest, fn func(CompletionResponse)) error
Embedding(ctx context.Context, prompt string) ([]float64, error)
Embed(ctx context.Context, input []string) ([][]float64, error)
Embed(ctx context.Context, input []string) ([][]float32, error)
Tokenize(ctx context.Context, content string) ([]int, error)
Detokenize(ctx context.Context, tokens []int) (string, error)
Close() error
@@ -847,10 +847,10 @@ type EmbedRequest struct {
}
type EmbedResponse struct {
Embedding [][]float64 `json:"embedding"`
Embedding [][]float32 `json:"embedding"`
}
func (s *llmServer) Embed(ctx context.Context, input []string) ([][]float64, error) {
func (s *llmServer) Embed(ctx context.Context, input []string) ([][]float32, error) {
if err := s.sem.Acquire(ctx, 1); err != nil {
slog.Error("Failed to acquire semaphore", "error", err)
return nil, err