mirrors/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-05-11 10:26:53 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Introduce /api/embed endpoint supporting batch embedding (#5127)

Browse source 
* Initial Batch Embedding

* Revert "Initial Batch Embedding"

This reverts commit c22d54895a.

* Initial Draft

* mock up notes

* api/embed draft

* add server function

* check normalization

* clean up

* normalization

* playing around with truncate stuff

* Truncation

* Truncation

* move normalization to go

* Integration Test Template

* Truncation Integration Tests

* Clean up

* use float32

* move normalize

* move normalize test

* refactoring

* integration float32

* input handling and handler testing

* Refactoring of legacy and new

* clear comments

* merge conflicts

* touches

* embedding type 64

* merge conflicts

* fix hanging on single string

* refactoring

* test values

* set context length

* clean up

* testing clean up

* testing clean up

* remove function closure

* Revert "remove function closure"

This reverts commit 55d48c6ed1.

* remove function closure

* remove redundant error check

* clean up

* more clean up

* clean up
This commit is contained in:
royjhan 2024-07-15 12:14:24 -07:00 • committed by GitHub
parent e9f7f36029
commit b9f5e16c80
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 452 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

16
llm/server.go
View file

@ -33,7 +33,7 @@ type LlamaServer interface {
Ping(ctx context.Context) error
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) ([][]float32, error)
Tokenize(ctx context.Context, content string) ([]int, error)
Detokenize(ctx context.Context, tokens []int) (string, error)
Close() error
@ -867,15 +867,15 @@ func (s *llmServer) Completion(ctx context.Context, req CompletionRequest, fn fu
return nil
}
type EmbeddingRequest struct {
Content string `json:"content"`
type EmbedRequest struct {
Content []string `json:"content"`
}
type EmbeddingResponse struct {
Embedding []float64 `json:"embedding"`
type EmbedResponse struct {
Embedding [][]float32 `json:"embedding"`
}
func (s *llmServer) Embedding(ctx context.Context, prompt 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
@ -890,7 +890,7 @@ func (s *llmServer) Embedding(ctx context.Context, prompt string) ([]float64, er
return nil, fmt.Errorf("unexpected server status: %s", status.ToString())
}
data, err := json.Marshal(TokenizeRequest{Content: prompt})
data, err := json.Marshal(EmbedRequest{Content: input})
if err != nil {
return nil, fmt.Errorf("error marshaling embed data: %w", err)
}
@ -917,7 +917,7 @@ func (s *llmServer) Embedding(ctx context.Context, prompt string) ([]float64, er
return nil, fmt.Errorf("%s", body)
}
var embedding EmbeddingResponse
var embedding EmbedResponse
if err := json.Unmarshal(body, &embedding); err != nil {
return nil, fmt.Errorf("unmarshal tokenize response: %w", err)
}