matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-10 15:57:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add Metrics to api\embed response (#5709)

Browse Source 
* add prompt tokens to embed response

* rm slog

* metrics

* types

* prompt n

* clean up

* reset submodule

* update tests

* test name

* list metrics
This commit is contained in:
royjhan
2024-07-30 13:12:21 -07:00
committed by GitHub
parent cef2c6054d
commit 1b44d873e7
6 changed files with 39 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
llm/ext_server/server.cpp vendored
View File

@@ -1221,6 +1221,7 @@ struct llama_server_context
res.result_json = json
{
{"embedding", std::vector<float>(embd, embd + n_embd)},
{"timings", slot.get_formated_timings()},
};
}
}
@@ -3203,11 +3204,15 @@ int main(int argc, char **argv) {
responses = result.result_json.value("results", std::vector<json>{result.result_json});
json embeddings = json::array();
int prompt_n = 0;
for (auto & elem : responses) {
embeddings.push_back(elem.at("embedding"));
prompt_n += elem.at("timings").at("prompt_n").get<int>();
}
// send the result
json embedding_res = json{{"embedding", embeddings}};
json embedding_res = json{{"embedding", embeddings}, {"prompt_n", prompt_n}};
return res.set_content(embedding_res.dump(), "application/json; charset=utf-8");
}
});

13
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
Embed(ctx context.Context, input []string) ([][]float32, error)
Embed(ctx context.Context, input []string) (*EmbedResponse, error)
Tokenize(ctx context.Context, content string) ([]int, error)
Detokenize(ctx context.Context, tokens []int) (string, error)
Close() error
@@ -879,10 +879,11 @@ type EmbedRequest struct {
}
type EmbedResponse struct {
Embedding [][]float32 `json:"embedding"`
Embedding [][]float32 `json:"embedding"`
PromptEvalCount int `json:"prompt_n"`
}
func (s *llmServer) Embed(ctx context.Context, input []string) ([][]float32, error) {
func (s *llmServer) Embed(ctx context.Context, input []string) (*EmbedResponse, error) {
if err := s.sem.Acquire(ctx, 1); err != nil {
slog.Error("Failed to acquire semaphore", "error", err)
return nil, err
@@ -924,12 +925,12 @@ func (s *llmServer) Embed(ctx context.Context, input []string) ([][]float32, err
return nil, fmt.Errorf("%s", body)
}
var embedding EmbedResponse
if err := json.Unmarshal(body, &embedding); err != nil {
var e EmbedResponse
if err := json.Unmarshal(body, &e); err != nil {
return nil, fmt.Errorf("unmarshal tokenize response: %w", err)
}
return embedding.Embedding, nil
return &e, nil
}
type TokenizeRequest struct {