fix(utf8): prevent multi-byte utf8 characters from being mangled (#981)

**Description**

This PR fixes #677 using [suggested
solution](https://github.com/go-skynet/LocalAI/issues/677#issuecomment-1695939097)
from @yantoz

before:
```
❯ curl -N http://localhost:57541/v1/completions -H "Content-Type: application/json" -d '{
     "model": "ggml-model-q4_0.bin",
     "prompt": "",
     "max_tokens": 32,
     "temperature": 0.7,
     "stream": true
   }'
data: {"object":"text_completion","model":"ggml-model-q4_0.bin","choices":[{"text":"\ufffd"}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}

data: {"object":"text_completion","model":"ggml-model-q4_0.bin","choices":[{"text":"\ufffd"}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}

data: {"object":"text_completion","model":"ggml-model-q4_0.bin","choices":[{"text":"\ufffd"}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}

data: {"object":"text_completion","model":"ggml-model-q4_0.bin","choices":[{"text":"\ufffd"}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}

data: {"object":"text_completion","model":"ggml-model-q4_0.bin","choices":[{"text":" |"}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}

data: {"object":"text_completion","model":"ggml-model-q4_0.bin","choices":[{"text":" I"}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}

data: {"object":"text_completion","model":"ggml-model-q4_0.bin","choices":[{"text":"'"}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}

data: {"object":"text_completion","model":"ggml-model-q4_0.bin","choices":[{"text":"m"}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}
```

now:
```
❯ curl -N http://localhost:57541/v1/completions -H Content-Type: application/json -d {
   "model": "ggml-model-q4_0.bin",
   "prompt": "",
   "max_tokens": 32,
   "temperature": 0.7,
   "stream": true
 }
data: {"object":"text_completion","model":"ggml-model-q4_0.bin","choices":[{"index":0,"text":"😂"}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}

data: {"object":"text_completion","model":"ggml-model-q4_0.bin","choices":[{"index":0,"text":" "}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}

data: {"object":"text_completion","model":"ggml-model-q4_0.bin","choices":[{"index":0,"text":"|"}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}

data: {"object":"text_completion","model":"ggml-model-q4_0.bin","choices":[{"index":0,"text":" "}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}

data: {"object":"text_completion","model":"ggml-model-q4_0.bin","choices":[{"index":0,"text":"I"}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}

data: {"object":"text_completion","model":"ggml-model-q4_0.bin","choices":[{"index":0,"text":"'"}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}

data: {"object":"text_completion","model":"ggml-model-q4_0.bin","choices":[{"index":0,"text":"m"}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}
```

**Notes for Reviewers**


**[Signed
commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)**
- [X] Yes, I signed my commits.
 

<!--
Thank you for contributing to LocalAI! 

Contributing Conventions:

1. Include descriptive PR titles with [<component-name>] prepended.
2. Build and test your changes before submitting a PR. 
3. Sign your commits

By following the community's contribution conventions upfront, the
review process will
be accelerated and your PR merged more quickly.
-->

Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
This commit is contained in:
Samuel Maynard 2023-08-31 01:56:59 +02:00 committed by GitHub
parent b905c07650
commit deeef5fc24
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -6,6 +6,7 @@ import (
"regexp"
"strings"
"sync"
"unicode/utf8"
config "github.com/go-skynet/LocalAI/api/config"
"github.com/go-skynet/LocalAI/api/options"
@ -97,9 +98,23 @@ func ModelInference(ctx context.Context, s string, loader *model.ModelLoader, c
if tokenCallback != nil {
ss := ""
err := inferenceModel.PredictStream(ctx, opts, func(s []byte) {
tokenCallback(string(s), tokenUsage)
ss += string(s)
var partialRune []byte
err := inferenceModel.PredictStream(ctx, opts, func(chars []byte) {
partialRune = append(partialRune, chars...)
for len(partialRune) > 0 {
r, size := utf8.DecodeRune(partialRune)
if r == utf8.RuneError {
// incomplete rune, wait for more bytes
break
}
tokenCallback(string(r), tokenUsage)
ss += string(r)
partialRune = partialRune[size:]
}
})
return LLMResponse{
Response: ss,