dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-28 06:25:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 12

feat: add machine tag and inference timings (#4577)

Browse source 
* Add machine tag option, add extraUsage option, grpc-server -> proto -> endpoint extraUsage data is broken for now

Signed-off-by: mintyleaf <mintyleafdev@gmail.com>

* remove redurant timing fields, fix not working timings output

Signed-off-by: mintyleaf <mintyleafdev@gmail.com>

* use middleware for Machine-Tag only if tag is specified

Signed-off-by: mintyleaf <mintyleafdev@gmail.com>

---------

Signed-off-by: mintyleaf <mintyleafdev@gmail.com>
This commit is contained in:
mintyleaf 2025-01-17 20:05:58 +04:00 • committed by GitHub
parent 8027fdf1c7
commit 96f8ec0402
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 137 additions and 48 deletions
Download patch file Download diff file Expand all files Collapse all files

21
core/http/endpoints/openai/edit.go
View file

@ -25,6 +25,9 @@ import (
func EditEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, evaluator *templates.Evaluator, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {
return func(c *fiber.Ctx) error {
// Opt-in extra usage flag
extraUsage := c.Get("LocalAI-Extra-Usage", "") != ""
modelFile, input, err := readRequest(c, cl, ml, appConfig, true)
if err != nil {
return fmt.Errorf("failed reading parameters from request:%w", err)
@ -61,8 +64,20 @@ func EditEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, evaluat
totalTokenUsage.Prompt += tokenUsage.Prompt
totalTokenUsage.Completion += tokenUsage.Completion
totalTokenUsage.TimingTokenGeneration += tokenUsage.TimingTokenGeneration
totalTokenUsage.TimingPromptProcessing += tokenUsage.TimingPromptProcessing
result = append(result, r...)
}
usage := schema.OpenAIUsage{
PromptTokens: totalTokenUsage.Prompt,
CompletionTokens: totalTokenUsage.Completion,
TotalTokens: totalTokenUsage.Prompt + totalTokenUsage.Completion,
}
if extraUsage {
usage.TimingTokenGeneration = totalTokenUsage.TimingTokenGeneration
usage.TimingPromptProcessing = totalTokenUsage.TimingPromptProcessing
}
id := uuid.New().String()
created := int(time.Now().Unix())
@ -72,11 +87,7 @@ func EditEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, evaluat
Model: input.Model, // we have to return what the user sent here, due to OpenAI spec.
Choices: result,
Object: "edit",
Usage: schema.OpenAIUsage{
PromptTokens: totalTokenUsage.Prompt,
CompletionTokens: totalTokenUsage.Completion,
TotalTokens: totalTokenUsage.Prompt + totalTokenUsage.Completion,
},
Usage: usage,
}
jsonResult, _ := json.Marshal(resp)