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

8
server/sched_test.go
View file

@ -642,8 +642,8 @@ type mockLlm struct {
pingResp error
waitResp error
completionResp error
embeddingResp []float64
embeddingRespErr error
embedResp [][]float32
embedRespErr error
tokenizeResp []int
tokenizeRespErr error
detokenizeResp string
@ -660,8 +660,8 @@ func (s *mockLlm) WaitUntilRunning(ctx context.Context) error { return s.waitRes
func (s *mockLlm) Completion(ctx context.Context, req llm.CompletionRequest, fn func(llm.CompletionResponse)) error {
return s.completionResp
}
func (s *mockLlm) Embedding(ctx context.Context, prompt string) ([]float64, error) {
return s.embeddingResp, s.embeddingRespErr
func (s *mockLlm) Embed(ctx context.Context, input []string) ([][]float32, error) {
return s.embedResp, s.embedRespErr
}
func (s *mockLlm) Tokenize(ctx context.Context, content string) ([]int, error) {
return s.tokenizeResp, s.tokenizeRespErr