dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 10:35:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

Revert "feat: include tokens usage for streamed output (#4282)"

Browse source 
This reverts commit 0d6c3a7d57.
This commit is contained in:
Ettore Di Giacinto 2024-12-08 16:31:48 +01:00
parent 87b7648591
commit 184fbc26bf
5 changed files with 10 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

12
core/backend/llm.go
View file

@ -117,12 +117,8 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im
ss := ""
var partialRune []byte
err := inferenceModel.PredictStream(ctx, opts, func(reply *proto.Reply) {
msg := reply.GetMessage()
partialRune = append(partialRune, msg...)
tokenUsage.Prompt = int(reply.PromptTokens)
tokenUsage.Completion = int(reply.Tokens)
err := inferenceModel.PredictStream(ctx, opts, func(chars []byte) {
partialRune = append(partialRune, chars...)
for len(partialRune) > 0 {
r, size := utf8.DecodeRune(partialRune)
@ -136,10 +132,6 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im
partialRune = partialRune[size:]
}
if len(msg) == 0 {
tokenCallback("", tokenUsage)
}
})
return LLMResponse{
Response: ss,