feat: Centralized Request Processing middleware#3847

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mudler merged 8 commits into from
Feb 10, 2025
Merged

feat: Centralized Request Processing middleware #3847

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
c1f30ba
squash past, centralize request middleware PR
dave-gray101 Feb 5, 2025
5e07c3c
Merge branch 'master' into feat-request-middleware
dave-gray101 Feb 6, 2025
5b01500
Merge branch 'master' into feat-request-middleware
dave-gray101 Feb 8, 2025
aa9c995
migrate bruno request files to examples repo
dave-gray101 Feb 8, 2025
cac5f5a
fix
dave-gray101 Feb 8, 2025
a33a4d5
Merge branch 'master' into feat-request-middleware
dave-gray101 Feb 9, 2025
b717f6f
Update tests/e2e-aio/e2e_test.go
mudler Feb 10, 2025
f7dab99
Merge branch 'master' into feat-request-middleware
mudler Feb 10, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions aio/cpu/vad.yaml
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad

@mudlermudlerFeb 6, 2025

Copy link
Copy Markdown
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

👍

name: silero-vad
parameters:
model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808
2 changes: 1 addition & 1 deletion aio/entrypoint.sh
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -129,7 +129,7 @@ detect_gpu
detect_gpu_size

PROFILE="${PROFILE:-$GPU_SIZE}" # default to cpu
export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vision.yaml}"
export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vad.yaml,/aio/${PROFILE}/vision.yaml}"

check_vars

Expand Down
8 changes: 8 additions & 0 deletions aio/gpu-8g/vad.yaml
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
name: silero-vad
parameters:
model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808
8 changes: 8 additions & 0 deletions aio/intel/vad.yaml
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
name: silero-vad
parameters:
model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808
8 changes: 1 addition & 7 deletions core/application/startup.go
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -145,13 +145,7 @@ func New(opts ...config.AppOption) (*Application, error) {

if options.LoadToMemory != nil {
for _, m := range options.LoadToMemory {
cfg, err := application.BackendLoader().LoadBackendConfigFileByName(m, options.ModelPath,
config.LoadOptionDebug(options.Debug),
config.LoadOptionThreads(options.Threads),
config.LoadOptionContextSize(options.ContextSize),
config.LoadOptionF16(options.F16),
config.ModelPath(options.ModelPath),
)
cfg, err := application.BackendLoader().LoadBackendConfigFileByNameDefaultOptions(m, options)

@mudlermudlerFeb 6, 2025

Copy link
Copy Markdown
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

❤️

if err != nil {
return nil, err
}
Expand Down
6 changes: 3 additions & 3 deletions core/backend/llm.go
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -33,7 +33,7 @@ type TokenUsage struct {
TimingTokenGeneration float64
}

func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c *config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
modelFile := c.Model

// Check if the modelFile exists, if it doesn't try to load it from the gallery
Expand All@@ -48,7 +48,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im
}
}

opts := ModelOptions(c, o)
opts := ModelOptions(*c, o)
inferenceModel, err := loader.Load(opts...)
if err != nil {
return nil, err
Expand DownExpand Up@@ -84,7 +84,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im

// in GRPC, the backend is supposed to answer to 1 single token if stream is not supported
fn := func() (LLMResponse, error) {
opts := gRPCPredictOpts(c, loader.ModelPath)
opts := gRPCPredictOpts(*c, loader.ModelPath)
opts.Prompt = s
opts.Messages = protoMessages
opts.UseTokenizerTemplate = c.TemplateConfig.UseTokenizerTemplate
Expand Down
6 changes: 3 additions & 3 deletions core/backend/rerank.go
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -9,10 +9,10 @@ import (
model "github.com/mudler/LocalAI/pkg/model"
)

func Rerank(modelFile string, request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {

opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))
func Rerank(request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {
opts := ModelOptions(backendConfig, appConfig)
rerankModel, err := loader.Load(opts...)

if err != nil {
return nil, err
}
Expand Down
6 changes: 3 additions & 3 deletions core/backend/soundgeneration.go
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -13,7 +13,6 @@ import (
)

func SoundGeneration(
modelFile string,
text string,
duration *float32,
temperature *float32,
Expand All@@ -25,8 +24,9 @@ func SoundGeneration(
backendConfig config.BackendConfig,
) (string, *proto.Result, error) {

opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))
opts := ModelOptions(backendConfig, appConfig)
soundGenModel, err := loader.Load(opts...)

if err != nil {
return "", nil, err
}
Expand All@@ -44,7 +44,7 @@ func SoundGeneration(

res, err := soundGenModel.SoundGeneration(context.Background(), &proto.SoundGenerationRequest{
Text: text,
Model: modelFile,
Model: backendConfig.Model,
Dst: filePath,
Sample: doSample,
Duration: duration,
Expand Down
8 changes: 3 additions & 5 deletions core/backend/tokenize.go
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -4,19 +4,17 @@ import (
"github.com/mudler/LocalAI/core/config"
"github.com/mudler/LocalAI/core/schema"
"github.com/mudler/LocalAI/pkg/grpc"
model "github.com/mudler/LocalAI/pkg/model"
"github.com/mudler/LocalAI/pkg/model"
)

func ModelTokenize(s string, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (schema.TokenizeResponse, error) {

modelFile := backendConfig.Model

var inferenceModel grpc.Backend
var err error

opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))

opts := ModelOptions(backendConfig, appConfig)
inferenceModel, err = loader.Load(opts...)

if err != nil {
return schema.TokenizeResponse{}, err
}
Expand Down
2 changes: 1 addition & 1 deletion core/backend/transcript.go
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -47,7 +47,7 @@ func ModelTranscription(audio, language string, translate bool, ml *model.ModelL
tks = append(tks, int(t))
}
tr.Segments = append(tr.Segments,
schema.Segment{
schema.TranscriptionSegment{
Text: s.Text,
Id: int(s.Id),
Start: time.Duration(s.Start),
Expand Down
39 changes: 16 additions & 23 deletions core/backend/tts.go
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -14,28 +14,22 @@ import (
)

func ModelTTS(
backend,
text,
modelFile,
voice,
language string,
loader *model.ModelLoader,
appConfig *config.ApplicationConfig,
backendConfig config.BackendConfig,
) (string, *proto.Result, error) {
bb := backend
if bb == "" {
bb = model.PiperBackend
}

opts := ModelOptions(backendConfig, appConfig, model.WithBackendString(bb), model.WithModel(modelFile))
opts := ModelOptions(backendConfig, appConfig, model.WithDefaultBackendString(model.PiperBackend))
ttsModel, err := loader.Load(opts...)

if err != nil {
return "", nil, err
}

if ttsModel == nil {
return "", nil, fmt.Errorf("could not load piper model")
return "", nil, fmt.Errorf("could not load tts model %q", backendConfig.Model)
}

if err := os.MkdirAll(appConfig.AudioDir, 0750); err != nil {
Expand All@@ -45,22 +39,21 @@ func ModelTTS(
fileName := utils.GenerateUniqueFileName(appConfig.AudioDir, "tts", ".wav")
filePath := filepath.Join(appConfig.AudioDir, fileName)

// If the model file is not empty, we pass it joined with the model path
// We join the model name to the model path here. This seems to only be done for TTS and is HIGHLY suspect.
// This should be addressed in a follow up PR soon.
// Copying it over nearly verbatim, as TTS backends are not functional without this.
modelPath := ""
if modelFile != "" {
// If the model file is not empty, we pass it joined with the model path
// Checking first that it exists and is not outside ModelPath
// TODO: we should actually first check if the modelFile is looking like
// a FS path
mp := filepath.Join(loader.ModelPath, modelFile)
if _, err := os.Stat(mp); err == nil {
if err := utils.VerifyPath(mp, appConfig.ModelPath); err != nil {
return "", nil, err
}
modelPath = mp
} else {
modelPath = modelFile
// Checking first that it exists and is not outside ModelPath
// TODO: we should actually first check if the modelFile is looking like
// a FS path
mp := filepath.Join(loader.ModelPath, backendConfig.Model)
if _, err := os.Stat(mp); err == nil {
if err := utils.VerifyPath(mp, appConfig.ModelPath); err != nil {
return "", nil, err
}
modelPath = mp
} else {
modelPath = backendConfig.Model // skip this step if it fails?????
}

res, err := ttsModel.TTS(context.Background(), &proto.TTSRequest{
Expand Down
38 changes: 38 additions & 0 deletions core/backend/vad.go
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,38 @@
package backend

import (
"context"

"github.com/mudler/LocalAI/core/config"
"github.com/mudler/LocalAI/core/schema"
"github.com/mudler/LocalAI/pkg/grpc/proto"
"github.com/mudler/LocalAI/pkg/model"
)

func VAD(request *schema.VADRequest,
ctx context.Context,
ml *model.ModelLoader,
appConfig *config.ApplicationConfig,
backendConfig config.BackendConfig) (*schema.VADResponse, error) {
opts := ModelOptions(backendConfig, appConfig)
vadModel, err := ml.Load(opts...)
if err != nil {
return nil, err
}
req := proto.VADRequest{
Audio: request.Audio,
}
resp, err := vadModel.VAD(ctx, &req)
if err != nil {
return nil, err
}

segments := []schema.VADSegment{}
for _, s := range resp.Segments {
segments = append(segments, schema.VADSegment{Start: s.Start, End: s.End})
}

return &schema.VADResponse{
Segments: segments,
}, nil
}
3 changes: 2 additions & 1 deletion core/cli/soundgeneration.go
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -86,13 +86,14 @@ func (t *SoundGenerationCMD) Run(ctx *cliContext.Context) error {
options := config.BackendConfig{}
options.SetDefaults()
options.Backend = t.Backend
options.Model = t.Model

var inputFile *string
if t.InputFile != "" {
inputFile = &t.InputFile
}

filePath, _, err := backend.SoundGeneration(t.Model, text,
filePath, _, err := backend.SoundGeneration(text,
parseToFloat32Ptr(t.Duration), parseToFloat32Ptr(t.Temperature), &t.DoSample,
inputFile, parseToInt32Ptr(t.InputFileSampleDivisor), ml, opts, options)

Expand Down
4 changes: 3 additions & 1 deletion core/cli/tts.go
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -52,8 +52,10 @@ func (t *TTSCMD) Run(ctx *cliContext.Context) error {

options := config.BackendConfig{}
options.SetDefaults()
options.Backend = t.Backend
options.Model = t.Model

filePath, _, err := backend.ModelTTS(t.Backend, text, t.Model, t.Voice, t.Language, ml, opts, options)
filePath, _, err := backend.ModelTTS(text, t.Voice, t.Language, ml, opts, options)
if err != nil {
return err
}
Expand Down
39 changes: 28 additions & 11 deletions core/config/backend_config.go
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -437,19 +437,21 @@ func (c *BackendConfig) HasTemplate() bool {
type BackendConfigUsecases int

const (
FLAG_ANY BackendConfigUsecases = 0b000000000
FLAG_CHAT BackendConfigUsecases = 0b000000001
FLAG_COMPLETION BackendConfigUsecases = 0b000000010
FLAG_EDIT BackendConfigUsecases = 0b000000100
FLAG_EMBEDDINGS BackendConfigUsecases = 0b000001000
FLAG_RERANK BackendConfigUsecases = 0b000010000
FLAG_IMAGE BackendConfigUsecases = 0b000100000
FLAG_TRANSCRIPT BackendConfigUsecases = 0b001000000
FLAG_TTS BackendConfigUsecases = 0b010000000
FLAG_SOUND_GENERATION BackendConfigUsecases = 0b100000000
FLAG_ANY BackendConfigUsecases = 0b00000000000
FLAG_CHAT BackendConfigUsecases = 0b00000000001
FLAG_COMPLETION BackendConfigUsecases = 0b00000000010
FLAG_EDIT BackendConfigUsecases = 0b00000000100
FLAG_EMBEDDINGS BackendConfigUsecases = 0b00000001000
FLAG_RERANK BackendConfigUsecases = 0b00000010000
FLAG_IMAGE BackendConfigUsecases = 0b00000100000
FLAG_TRANSCRIPT BackendConfigUsecases = 0b00001000000
FLAG_TTS BackendConfigUsecases = 0b00010000000
FLAG_SOUND_GENERATION BackendConfigUsecases = 0b00100000000
FLAG_TOKENIZE BackendConfigUsecases = 0b01000000000
FLAG_VAD BackendConfigUsecases = 0b10000000000

// Common Subsets
FLAG_LLM BackendConfigUsecases = FLAG_CHAT & FLAG_COMPLETION & FLAG_EDIT
FLAG_LLM BackendConfigUsecases = FLAG_CHAT | FLAG_COMPLETION | FLAG_EDIT
)

func GetAllBackendConfigUsecases() map[string]BackendConfigUsecases {
Expand All@@ -464,6 +466,8 @@ func GetAllBackendConfigUsecases() map[string]BackendConfigUsecases {
"FLAG_TRANSCRIPT": FLAG_TRANSCRIPT,
"FLAG_TTS": FLAG_TTS,
"FLAG_SOUND_GENERATION": FLAG_SOUND_GENERATION,
"FLAG_TOKENIZE": FLAG_TOKENIZE,
"FLAG_VAD": FLAG_VAD,
"FLAG_LLM": FLAG_LLM,
}
}
Expand DownExpand Up@@ -549,5 +553,18 @@ func (c *BackendConfig) GuessUsecases(u BackendConfigUsecases) bool {
}
}

if (u & FLAG_TOKENIZE) == FLAG_TOKENIZE {
tokenizeCapableBackends := []string{"llama.cpp", "rwkv"}
if !slices.Contains(tokenizeCapableBackends, c.Backend) {
return false
}
}

if (u & FLAG_VAD) == FLAG_VAD {
if c.Backend != "silero-vad" {

@mudlermudlerFeb 6, 2025•
edited
Loading

Copy link
Copy Markdown
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

note for later: at some point we should think about having these constants defined to be re-usable. There are some repetitions as well in the model initializer

@dave-gray101dave-gray101Feb 8, 2025

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed - probably worth doing that as followup if you're OK with that

@mudlermudlerFeb 10, 2025

Copy link
Copy Markdown
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

definitely, was just a reminder/note

return false
}
}

return true
}
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { // Add copy buttons to all 
 blocks
(function() {
function addCopyButtons() {
document.querySelectorAll('pre code').forEach(function(codeBlock) {
if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;
codeBlock.parentElement.setAttribute('data-copy-added', 'true');
var btn = document.createElement('button');
btn.textContent = 'Copy';
btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';
btn.onmouseover = function() { this.style.opacity = '1'; };
btn.onmouseout = function() { this.style.opacity = '0.7'; };
btn.onclick = function() {
navigator.clipboard.writeText(codeBlock.textContent).then(function() {
btn.textContent = 'Copied!';
setTimeout(function() { btn.textContent = 'Copy'; }, 1500);
});
};
codeBlock.parentElement.style.position = 'relative';
codeBlock.parentElement.appendChild(btn);
});
}
addCopyButtons();
// Re-run on dynamic content
var observer = new MutationObserver(addCopyButtons);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
feat: Centralized Request Processing middleware#3847

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

mudler
merged 8 commits into

from

Feb 10, 2025
 Merged


feat: Centralized Request Processing middleware
#3847
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


8 commits


Select commit
Hold shift + click to select a range
c1f30ba

squash past, centralize request middleware PR


dave-gray101 Feb 5, 2025
5e07c3c

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 6, 2025
5b01500

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 8, 2025
aa9c995

migrate bruno request files to examples repo


dave-gray101 Feb 8, 2025
cac5f5a

fix


dave-gray101 Feb 8, 2025
a33a4d5

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 9, 2025
b717f6f

Update tests/e2e-aio/e2e_test.go


mudler Feb 10, 2025
f7dab99

Merge branch 'master' into feat-request-middleware


mudler Feb 10, 2025

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


8 changes: 8 additions & 0 deletions
aio/cpu/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
@mudlermudlerFeb 6, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

👍
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

2 changes: 1 addition & 1 deletion
aio/entrypoint.sh

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -129,7 +129,7 @@ detect_gpu
detect_gpu_size

PROFILE="${PROFILE:-$GPU_SIZE}" # default to cpu
export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vision.yaml}"
export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vad.yaml,/aio/${PROFILE}/vision.yaml}"

check_vars

Expand Down

8 changes: 8 additions & 0 deletions
aio/gpu-8g/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

8 changes: 8 additions & 0 deletions
aio/intel/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

8 changes: 1 addition & 7 deletions
core/application/startup.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -145,13 +145,7 @@ func New(opts ...config.AppOption) (*Application, error) {

	if options.LoadToMemory != nil {
 for _, m := range options.LoadToMemory {
 cfg, err := application.BackendLoader().LoadBackendConfigFileByName(m, options.ModelPath,
 config.LoadOptionDebug(options.Debug),
 config.LoadOptionThreads(options.Threads),
 config.LoadOptionContextSize(options.ContextSize),
 config.LoadOptionF16(options.F16),
 config.ModelPath(options.ModelPath),
 )
 cfg, err := application.BackendLoader().LoadBackendConfigFileByNameDefaultOptions(m, options)
@mudlermudlerFeb 6, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

❤️
 if err != nil {
 return nil, err
 }
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/llm.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -33,7 +33,7 @@ type TokenUsage struct {
	TimingTokenGeneration float64
}

func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c *config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
	modelFile := c.Model

	// Check if the modelFile exists, if it doesn't try to load it from the gallery
Expand All@@ -48,7 +48,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im
 }
	}

	opts := ModelOptions(c, o)
	opts := ModelOptions(*c, o)
	inferenceModel, err := loader.Load(opts...)
	if err != nil {
 return nil, err
Expand DownExpand Up@@ -84,7 +84,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im

	// in GRPC, the backend is supposed to answer to 1 single token if stream is not supported
	fn := func() (LLMResponse, error) {
 opts := gRPCPredictOpts(c, loader.ModelPath)
 opts := gRPCPredictOpts(*c, loader.ModelPath)
 opts.Prompt = s
 opts.Messages = protoMessages
 opts.UseTokenizerTemplate = c.TemplateConfig.UseTokenizerTemplate
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/rerank.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -9,10 +9,10 @@ import (
	model "github.com/mudler/LocalAI/pkg/model"
)

func Rerank(modelFile string, request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))
func Rerank(request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {
	opts := ModelOptions(backendConfig, appConfig)
	rerankModel, err := loader.Load(opts...)

	if err != nil {
 return nil, err
	}
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/soundgeneration.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -13,7 +13,6 @@ import (
)

func SoundGeneration(
	modelFile string,
	text string,
	duration *float32,
	temperature *float32,
Expand All@@ -25,8 +24,9 @@ func SoundGeneration(
	backendConfig config.BackendConfig,
) (string, *proto.Result, error) {

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))
	opts := ModelOptions(backendConfig, appConfig)
	soundGenModel, err := loader.Load(opts...)

	if err != nil {
 return "", nil, err
	}
Expand All@@ -44,7 +44,7 @@ func SoundGeneration(

	res, err := soundGenModel.SoundGeneration(context.Background(), &proto.SoundGenerationRequest{
 Text: text,
 Model: modelFile,
 Model: backendConfig.Model,
 Dst: filePath,
 Sample: doSample,
 Duration: duration,
Expand Down

8 changes: 3 additions & 5 deletions
core/backend/tokenize.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,19 +4,17 @@ import (
	"github.com/mudler/LocalAI/core/config"
	"github.com/mudler/LocalAI/core/schema"
	"github.com/mudler/LocalAI/pkg/grpc"
model "github.com/mudler/LocalAI/pkg/model"
	"github.com/mudler/LocalAI/pkg/model"
)

func ModelTokenize(s string, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (schema.TokenizeResponse, error) {

	modelFile := backendConfig.Model

	var inferenceModel grpc.Backend
	var err error

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))

	opts := ModelOptions(backendConfig, appConfig)
	inferenceModel, err = loader.Load(opts...)

	if err != nil {
 return schema.TokenizeResponse{}, err
	}
Expand Down

2 changes: 1 addition & 1 deletion
core/backend/transcript.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -47,7 +47,7 @@ func ModelTranscription(audio, language string, translate bool, ml *model.ModelL
 tks = append(tks, int(t))
 }
 tr.Segments = append(tr.Segments,
 schema.Segment{
 schema.TranscriptionSegment{
 Text: s.Text,
 Id: int(s.Id),
 Start: time.Duration(s.Start),
Expand Down

39 changes: 16 additions & 23 deletions
core/backend/tts.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -14,28 +14,22 @@ import (
)

func ModelTTS(
	backend,
	text,
	modelFile,
	voice,
	language string,
	loader *model.ModelLoader,
	appConfig *config.ApplicationConfig,
	backendConfig config.BackendConfig,
) (string, *proto.Result, error) {
	bb := backend
	if bb == "" {
 bb = model.PiperBackend
	}

	opts := ModelOptions(backendConfig, appConfig, model.WithBackendString(bb), model.WithModel(modelFile))
	opts := ModelOptions(backendConfig, appConfig, model.WithDefaultBackendString(model.PiperBackend))
	ttsModel, err := loader.Load(opts...)

	if err != nil {
 return "", nil, err
	}

	if ttsModel == nil {
 return "", nil, fmt.Errorf("could not load piper model")
 return "", nil, fmt.Errorf("could not load tts model %q", backendConfig.Model)
	}

	if err := os.MkdirAll(appConfig.AudioDir, 0750); err != nil {
Expand All@@ -45,22 +39,21 @@ func ModelTTS(
	fileName := utils.GenerateUniqueFileName(appConfig.AudioDir, "tts", ".wav")
	filePath := filepath.Join(appConfig.AudioDir, fileName)

	// If the model file is not empty, we pass it joined with the model path
	// We join the model name to the model path here. This seems to only be done for TTS and is HIGHLY suspect.
	// This should be addressed in a follow up PR soon.
	// Copying it over nearly verbatim, as TTS backends are not functional without this.
	modelPath := ""
	if modelFile != "" {
 // If the model file is not empty, we pass it joined with the model path
 // Checking first that it exists and is not outside ModelPath
 // TODO: we should actually first check if the modelFile is looking like
 // a FS path
 mp := filepath.Join(loader.ModelPath, modelFile)
 if _, err := os.Stat(mp); err == nil {
 if err := utils.VerifyPath(mp, appConfig.ModelPath); err != nil {
 return "", nil, err
 }
 modelPath = mp
 } else {
 modelPath = modelFile
	// Checking first that it exists and is not outside ModelPath
	// TODO: we should actually first check if the modelFile is looking like
	// a FS path
	mp := filepath.Join(loader.ModelPath, backendConfig.Model)
	if _, err := os.Stat(mp); err == nil {
 if err := utils.VerifyPath(mp, appConfig.ModelPath); err != nil {
 return "", nil, err
 }
 modelPath = mp
	} else {
 modelPath = backendConfig.Model // skip this step if it fails?????
	}

	res, err := ttsModel.TTS(context.Background(), &proto.TTSRequest{
Expand Down

38 changes: 38 additions & 0 deletions
core/backend/vad.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,38 @@
package backend

import (
	"context"

	"github.com/mudler/LocalAI/core/config"
	"github.com/mudler/LocalAI/core/schema"
	"github.com/mudler/LocalAI/pkg/grpc/proto"
	"github.com/mudler/LocalAI/pkg/model"
)

func VAD(request *schema.VADRequest,
	ctx context.Context,
	ml *model.ModelLoader,
	appConfig *config.ApplicationConfig,
	backendConfig config.BackendConfig) (*schema.VADResponse, error) {
	opts := ModelOptions(backendConfig, appConfig)
	vadModel, err := ml.Load(opts...)
	if err != nil {
 return nil, err
	}
	req := proto.VADRequest{
 Audio: request.Audio,
	}
	resp, err := vadModel.VAD(ctx, &req)
	if err != nil {
 return nil, err
	}

	segments := []schema.VADSegment{}
	for _, s := range resp.Segments {
 segments = append(segments, schema.VADSegment{Start: s.Start, End: s.End})
	}

	return &schema.VADResponse{
 Segments: segments,
	}, nil
}

3 changes: 2 additions & 1 deletion
core/cli/soundgeneration.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -86,13 +86,14 @@ func (t *SoundGenerationCMD) Run(ctx *cliContext.Context) error {
	options := config.BackendConfig{}
	options.SetDefaults()
	options.Backend = t.Backend
	options.Model = t.Model

	var inputFile *string
	if t.InputFile != "" {
 inputFile = &t.InputFile
	}

	filePath, _, err := backend.SoundGeneration(t.Model, text,
	filePath, _, err := backend.SoundGeneration(text,
 parseToFloat32Ptr(t.Duration), parseToFloat32Ptr(t.Temperature), &t.DoSample,
 inputFile, parseToInt32Ptr(t.InputFileSampleDivisor), ml, opts, options)

Expand Down

4 changes: 3 additions & 1 deletion
core/cli/tts.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -52,8 +52,10 @@ func (t *TTSCMD) Run(ctx *cliContext.Context) error {

	options := config.BackendConfig{}
	options.SetDefaults()
	options.Backend = t.Backend
	options.Model = t.Model

	filePath, _, err := backend.ModelTTS(t.Backend, text, t.Model, t.Voice, t.Language, ml, opts, options)
	filePath, _, err := backend.ModelTTS(text, t.Voice, t.Language, ml, opts, options)
	if err != nil {
 return err
	}
Expand Down

39 changes: 28 additions & 11 deletions
core/config/backend_config.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -437,19 +437,21 @@ func (c *BackendConfig) HasTemplate() bool {
type BackendConfigUsecases int

const (
	FLAG_ANY BackendConfigUsecases = 0b000000000
	FLAG_CHAT BackendConfigUsecases = 0b000000001
	FLAG_COMPLETION BackendConfigUsecases = 0b000000010
	FLAG_EDIT BackendConfigUsecases = 0b000000100
	FLAG_EMBEDDINGS BackendConfigUsecases = 0b000001000
	FLAG_RERANK BackendConfigUsecases = 0b000010000
	FLAG_IMAGE BackendConfigUsecases = 0b000100000
	FLAG_TRANSCRIPT BackendConfigUsecases = 0b001000000
	FLAG_TTS BackendConfigUsecases = 0b010000000
	FLAG_SOUND_GENERATION BackendConfigUsecases = 0b100000000
	FLAG_ANY BackendConfigUsecases = 0b00000000000
	FLAG_CHAT BackendConfigUsecases = 0b00000000001
	FLAG_COMPLETION BackendConfigUsecases = 0b00000000010
	FLAG_EDIT BackendConfigUsecases = 0b00000000100
	FLAG_EMBEDDINGS BackendConfigUsecases = 0b00000001000
	FLAG_RERANK BackendConfigUsecases = 0b00000010000
	FLAG_IMAGE BackendConfigUsecases = 0b00000100000
	FLAG_TRANSCRIPT BackendConfigUsecases = 0b00001000000
	FLAG_TTS BackendConfigUsecases = 0b00010000000
	FLAG_SOUND_GENERATION BackendConfigUsecases = 0b00100000000
	FLAG_TOKENIZE BackendConfigUsecases = 0b01000000000
	FLAG_VAD BackendConfigUsecases = 0b10000000000

	// Common Subsets
	FLAG_LLM BackendConfigUsecases = FLAG_CHAT & FLAG_COMPLETION & FLAG_EDIT
	FLAG_LLM BackendConfigUsecases = FLAG_CHAT | FLAG_COMPLETION | FLAG_EDIT
)

func GetAllBackendConfigUsecases() map[string]BackendConfigUsecases {
Expand All@@ -464,6 +466,8 @@ func GetAllBackendConfigUsecases() map[string]BackendConfigUsecases {
 "FLAG_TRANSCRIPT": FLAG_TRANSCRIPT,
 "FLAG_TTS": FLAG_TTS,
 "FLAG_SOUND_GENERATION": FLAG_SOUND_GENERATION,
 "FLAG_TOKENIZE": FLAG_TOKENIZE,
 "FLAG_VAD": FLAG_VAD,
 "FLAG_LLM": FLAG_LLM,
	}
}
Expand DownExpand Up@@ -549,5 +553,18 @@ func (c *BackendConfig) GuessUsecases(u BackendConfigUsecases) bool {
 }
	}

	if (u & FLAG_TOKENIZE) == FLAG_TOKENIZE {
 tokenizeCapableBackends := []string{"llama.cpp", "rwkv"}
 if !slices.Contains(tokenizeCapableBackends, c.Backend) {
 return false
 }
	}

	if (u & FLAG_VAD) == FLAG_VAD {
 if c.Backend != "silero-vad" {
@mudlermudlerFeb 6, 2025•

edited

Loading

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

note for later: at some point we should think about having these constants defined to be re-usable. There are some repetitions as well in the model initializer
@dave-gray101dave-gray101Feb 8, 2025

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed - probably worth doing that as followup if you're OK with that
@mudlermudlerFeb 10, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

definitely, was just a reminder/note
 return false
 }
	}

	return true
}
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Force GitHub README to respect dark mode
(function() {
var style = document.createElement('style');
style.textContent = '
.markdown-body {
color-scheme: dark light;
}
.markdown-body pre { background: #161b22 !important; }
.markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }
.markdown-body table th, .markdown-body table td { border-color: #30363d !important; }
.markdown-body img { background: #0d1117; }
.markdown-body blockquote { border-left-color: #8b949e; }
.markdown-body hr { border-color: #30363d; }
';
document.head.appendChild(style);
})();
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
feat: Centralized Request Processing middleware#3847

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

mudler
merged 8 commits into

from

Feb 10, 2025
 Merged


feat: Centralized Request Processing middleware
#3847
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


8 commits


Select commit
Hold shift + click to select a range
c1f30ba

squash past, centralize request middleware PR


dave-gray101 Feb 5, 2025
5e07c3c

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 6, 2025
5b01500

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 8, 2025
aa9c995

migrate bruno request files to examples repo


dave-gray101 Feb 8, 2025
cac5f5a

fix


dave-gray101 Feb 8, 2025
a33a4d5

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 9, 2025
b717f6f

Update tests/e2e-aio/e2e_test.go


mudler Feb 10, 2025
f7dab99

Merge branch 'master' into feat-request-middleware


mudler Feb 10, 2025

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


8 changes: 8 additions & 0 deletions
aio/cpu/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
@mudlermudlerFeb 6, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

👍
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

2 changes: 1 addition & 1 deletion
aio/entrypoint.sh

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -129,7 +129,7 @@ detect_gpu
detect_gpu_size

PROFILE="${PROFILE:-$GPU_SIZE}" # default to cpu
export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vision.yaml}"
export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vad.yaml,/aio/${PROFILE}/vision.yaml}"

check_vars

Expand Down

8 changes: 8 additions & 0 deletions
aio/gpu-8g/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

8 changes: 8 additions & 0 deletions
aio/intel/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

8 changes: 1 addition & 7 deletions
core/application/startup.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -145,13 +145,7 @@ func New(opts ...config.AppOption) (*Application, error) {

	if options.LoadToMemory != nil {
 for _, m := range options.LoadToMemory {
 cfg, err := application.BackendLoader().LoadBackendConfigFileByName(m, options.ModelPath,
 config.LoadOptionDebug(options.Debug),
 config.LoadOptionThreads(options.Threads),
 config.LoadOptionContextSize(options.ContextSize),
 config.LoadOptionF16(options.F16),
 config.ModelPath(options.ModelPath),
 )
 cfg, err := application.BackendLoader().LoadBackendConfigFileByNameDefaultOptions(m, options)
@mudlermudlerFeb 6, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

❤️
 if err != nil {
 return nil, err
 }
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/llm.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -33,7 +33,7 @@ type TokenUsage struct {
	TimingTokenGeneration float64
}

func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c *config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
	modelFile := c.Model

	// Check if the modelFile exists, if it doesn't try to load it from the gallery
Expand All@@ -48,7 +48,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im
 }
	}

	opts := ModelOptions(c, o)
	opts := ModelOptions(*c, o)
	inferenceModel, err := loader.Load(opts...)
	if err != nil {
 return nil, err
Expand DownExpand Up@@ -84,7 +84,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im

	// in GRPC, the backend is supposed to answer to 1 single token if stream is not supported
	fn := func() (LLMResponse, error) {
 opts := gRPCPredictOpts(c, loader.ModelPath)
 opts := gRPCPredictOpts(*c, loader.ModelPath)
 opts.Prompt = s
 opts.Messages = protoMessages
 opts.UseTokenizerTemplate = c.TemplateConfig.UseTokenizerTemplate
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/rerank.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -9,10 +9,10 @@ import (
	model "github.com/mudler/LocalAI/pkg/model"
)

func Rerank(modelFile string, request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))
func Rerank(request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {
	opts := ModelOptions(backendConfig, appConfig)
	rerankModel, err := loader.Load(opts...)

	if err != nil {
 return nil, err
	}
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/soundgeneration.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -13,7 +13,6 @@ import (
)

func SoundGeneration(
	modelFile string,
	text string,
	duration *float32,
	temperature *float32,
Expand All@@ -25,8 +24,9 @@ func SoundGeneration(
	backendConfig config.BackendConfig,
) (string, *proto.Result, error) {

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))
	opts := ModelOptions(backendConfig, appConfig)
	soundGenModel, err := loader.Load(opts...)

	if err != nil {
 return "", nil, err
	}
Expand All@@ -44,7 +44,7 @@ func SoundGeneration(

	res, err := soundGenModel.SoundGeneration(context.Background(), &proto.SoundGenerationRequest{
 Text: text,
 Model: modelFile,
 Model: backendConfig.Model,
 Dst: filePath,
 Sample: doSample,
 Duration: duration,
Expand Down

8 changes: 3 additions & 5 deletions
core/backend/tokenize.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,19 +4,17 @@ import (
	"github.com/mudler/LocalAI/core/config"
	"github.com/mudler/LocalAI/core/schema"
	"github.com/mudler/LocalAI/pkg/grpc"
model "github.com/mudler/LocalAI/pkg/model"
	"github.com/mudler/LocalAI/pkg/model"
)

func ModelTokenize(s string, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (schema.TokenizeResponse, error) {

	modelFile := backendConfig.Model

	var inferenceModel grpc.Backend
	var err error

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))

	opts := ModelOptions(backendConfig, appConfig)
	inferenceModel, err = loader.Load(opts...)

	if err != nil {
 return schema.TokenizeResponse{}, err
	}
Expand Down

2 changes: 1 addition & 1 deletion
core/backend/transcript.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -47,7 +47,7 @@ func ModelTranscription(audio, language string, translate bool, ml *model.ModelL
 tks = append(tks, int(t))
 }
 tr.Segments = append(tr.Segments,
 schema.Segment{
 schema.TranscriptionSegment{
 Text: s.Text,
 Id: int(s.Id),
 Start: time.Duration(s.Start),
Expand Down

39 changes: 16 additions & 23 deletions
core/backend/tts.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -14,28 +14,22 @@ import (
)

func ModelTTS(
	backend,
	text,
	modelFile,
	voice,
	language string,
	loader *model.ModelLoader,
	appConfig *config.ApplicationConfig,
	backendConfig config.BackendConfig,
) (string, *proto.Result, error) {
	bb := backend
	if bb == "" {
 bb = model.PiperBackend
	}

	opts := ModelOptions(backendConfig, appConfig, model.WithBackendString(bb), model.WithModel(modelFile))
	opts := ModelOptions(backendConfig, appConfig, model.WithDefaultBackendString(model.PiperBackend))
	ttsModel, err := loader.Load(opts...)

	if err != nil {
 return "", nil, err
	}

	if ttsModel == nil {
 return "", nil, fmt.Errorf("could not load piper model")
 return "", nil, fmt.Errorf("could not load tts model %q", backendConfig.Model)
	}

	if err := os.MkdirAll(appConfig.AudioDir, 0750); err != nil {
Expand All@@ -45,22 +39,21 @@ func ModelTTS(
	fileName := utils.GenerateUniqueFileName(appConfig.AudioDir, "tts", ".wav")
	filePath := filepath.Join(appConfig.AudioDir, fileName)

	// If the model file is not empty, we pass it joined with the model path
	// We join the model name to the model path here. This seems to only be done for TTS and is HIGHLY suspect.
	// This should be addressed in a follow up PR soon.
	// Copying it over nearly verbatim, as TTS backends are not functional without this.
	modelPath := ""
	if modelFile != "" {
 // If the model file is not empty, we pass it joined with the model path
 // Checking first that it exists and is not outside ModelPath
 // TODO: we should actually first check if the modelFile is looking like
 // a FS path
 mp := filepath.Join(loader.ModelPath, modelFile)
 if _, err := os.Stat(mp); err == nil {
 if err := utils.VerifyPath(mp, appConfig.ModelPath); err != nil {
 return "", nil, err
 }
 modelPath = mp
 } else {
 modelPath = modelFile
	// Checking first that it exists and is not outside ModelPath
	// TODO: we should actually first check if the modelFile is looking like
	// a FS path
	mp := filepath.Join(loader.ModelPath, backendConfig.Model)
	if _, err := os.Stat(mp); err == nil {
 if err := utils.VerifyPath(mp, appConfig.ModelPath); err != nil {
 return "", nil, err
 }
 modelPath = mp
	} else {
 modelPath = backendConfig.Model // skip this step if it fails?????
	}

	res, err := ttsModel.TTS(context.Background(), &proto.TTSRequest{
Expand Down

38 changes: 38 additions & 0 deletions
core/backend/vad.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,38 @@
package backend

import (
	"context"

	"github.com/mudler/LocalAI/core/config"
	"github.com/mudler/LocalAI/core/schema"
	"github.com/mudler/LocalAI/pkg/grpc/proto"
	"github.com/mudler/LocalAI/pkg/model"
)

func VAD(request *schema.VADRequest,
	ctx context.Context,
	ml *model.ModelLoader,
	appConfig *config.ApplicationConfig,
	backendConfig config.BackendConfig) (*schema.VADResponse, error) {
	opts := ModelOptions(backendConfig, appConfig)
	vadModel, err := ml.Load(opts...)
	if err != nil {
 return nil, err
	}
	req := proto.VADRequest{
 Audio: request.Audio,
	}
	resp, err := vadModel.VAD(ctx, &req)
	if err != nil {
 return nil, err
	}

	segments := []schema.VADSegment{}
	for _, s := range resp.Segments {
 segments = append(segments, schema.VADSegment{Start: s.Start, End: s.End})
	}

	return &schema.VADResponse{
 Segments: segments,
	}, nil
}

3 changes: 2 additions & 1 deletion
core/cli/soundgeneration.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -86,13 +86,14 @@ func (t *SoundGenerationCMD) Run(ctx *cliContext.Context) error {
	options := config.BackendConfig{}
	options.SetDefaults()
	options.Backend = t.Backend
	options.Model = t.Model

	var inputFile *string
	if t.InputFile != "" {
 inputFile = &t.InputFile
	}

	filePath, _, err := backend.SoundGeneration(t.Model, text,
	filePath, _, err := backend.SoundGeneration(text,
 parseToFloat32Ptr(t.Duration), parseToFloat32Ptr(t.Temperature), &t.DoSample,
 inputFile, parseToInt32Ptr(t.InputFileSampleDivisor), ml, opts, options)

Expand Down

4 changes: 3 additions & 1 deletion
core/cli/tts.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -52,8 +52,10 @@ func (t *TTSCMD) Run(ctx *cliContext.Context) error {

	options := config.BackendConfig{}
	options.SetDefaults()
	options.Backend = t.Backend
	options.Model = t.Model

	filePath, _, err := backend.ModelTTS(t.Backend, text, t.Model, t.Voice, t.Language, ml, opts, options)
	filePath, _, err := backend.ModelTTS(text, t.Voice, t.Language, ml, opts, options)
	if err != nil {
 return err
	}
Expand Down

39 changes: 28 additions & 11 deletions
core/config/backend_config.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -437,19 +437,21 @@ func (c *BackendConfig) HasTemplate() bool {
type BackendConfigUsecases int

const (
	FLAG_ANY BackendConfigUsecases = 0b000000000
	FLAG_CHAT BackendConfigUsecases = 0b000000001
	FLAG_COMPLETION BackendConfigUsecases = 0b000000010
	FLAG_EDIT BackendConfigUsecases = 0b000000100
	FLAG_EMBEDDINGS BackendConfigUsecases = 0b000001000
	FLAG_RERANK BackendConfigUsecases = 0b000010000
	FLAG_IMAGE BackendConfigUsecases = 0b000100000
	FLAG_TRANSCRIPT BackendConfigUsecases = 0b001000000
	FLAG_TTS BackendConfigUsecases = 0b010000000
	FLAG_SOUND_GENERATION BackendConfigUsecases = 0b100000000
	FLAG_ANY BackendConfigUsecases = 0b00000000000
	FLAG_CHAT BackendConfigUsecases = 0b00000000001
	FLAG_COMPLETION BackendConfigUsecases = 0b00000000010
	FLAG_EDIT BackendConfigUsecases = 0b00000000100
	FLAG_EMBEDDINGS BackendConfigUsecases = 0b00000001000
	FLAG_RERANK BackendConfigUsecases = 0b00000010000
	FLAG_IMAGE BackendConfigUsecases = 0b00000100000
	FLAG_TRANSCRIPT BackendConfigUsecases = 0b00001000000
	FLAG_TTS BackendConfigUsecases = 0b00010000000
	FLAG_SOUND_GENERATION BackendConfigUsecases = 0b00100000000
	FLAG_TOKENIZE BackendConfigUsecases = 0b01000000000
	FLAG_VAD BackendConfigUsecases = 0b10000000000

	// Common Subsets
	FLAG_LLM BackendConfigUsecases = FLAG_CHAT & FLAG_COMPLETION & FLAG_EDIT
	FLAG_LLM BackendConfigUsecases = FLAG_CHAT | FLAG_COMPLETION | FLAG_EDIT
)

func GetAllBackendConfigUsecases() map[string]BackendConfigUsecases {
Expand All@@ -464,6 +466,8 @@ func GetAllBackendConfigUsecases() map[string]BackendConfigUsecases {
 "FLAG_TRANSCRIPT": FLAG_TRANSCRIPT,
 "FLAG_TTS": FLAG_TTS,
 "FLAG_SOUND_GENERATION": FLAG_SOUND_GENERATION,
 "FLAG_TOKENIZE": FLAG_TOKENIZE,
 "FLAG_VAD": FLAG_VAD,
 "FLAG_LLM": FLAG_LLM,
	}
}
Expand DownExpand Up@@ -549,5 +553,18 @@ func (c *BackendConfig) GuessUsecases(u BackendConfigUsecases) bool {
 }
	}

	if (u & FLAG_TOKENIZE) == FLAG_TOKENIZE {
 tokenizeCapableBackends := []string{"llama.cpp", "rwkv"}
 if !slices.Contains(tokenizeCapableBackends, c.Backend) {
 return false
 }
	}

	if (u & FLAG_VAD) == FLAG_VAD {
 if c.Backend != "silero-vad" {
@mudlermudlerFeb 6, 2025•

edited

Loading

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

note for later: at some point we should think about having these constants defined to be re-usable. There are some repetitions as well in the model initializer
@dave-gray101dave-gray101Feb 8, 2025

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed - probably worth doing that as followup if you're OK with that
@mudlermudlerFeb 10, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

definitely, was just a reminder/note
 return false
 }
	}

	return true
}
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Highlight search terms from Google/DuckDuckGo/Bing referrer
(function() {
var ref = document.referrer;
var terms = [];
if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {
var url = new URL(ref);
var q = url.searchParams.get('q') || url.searchParams.get('p');
if (q) {
terms = q.split(/\s+/).filter(function(t) { return t.length > 2; });
}
}
if (terms.length === 0) return;
var style = document.createElement('style');
style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';
document.head.appendChild(style);
function highlight(node) {
if (node.nodeType === 3) { // text node
var text = node.textContent;
var found = false;
terms.forEach(function(term) {
var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\]\\]/g, '\\') + ')', 'gi');
if (regex.test(text)) {
found = true;
var frag = document.createDocumentFragment();
var parts = text.split(regex);
parts.forEach(function(part, i) {
if (i % 2 === 0) {
frag.appendChild(document.createTextNode(part));
} else {
var span = document.createElement('span');
span.className = 'userscript-highlight';
span.textContent = part;
frag.appendChild(span);
}
});
node.parentNode.replaceChild(frag, node);
}
});
} else if (node.nodeType === 1 && node.childNodes) { // element
var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];
if (!skipTags.includes(node.tagName)) {
Array.from(node.childNodes).forEach(highlight);
}
}
}
highlight(document.body);
// Re-highlight on dynamic content
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1 || node.nodeType === 3) highlight(node);
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
feat: Centralized Request Processing middleware#3847

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

mudler
merged 8 commits into

from

Feb 10, 2025
 Merged


feat: Centralized Request Processing middleware
#3847
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


8 commits


Select commit
Hold shift + click to select a range
c1f30ba

squash past, centralize request middleware PR


dave-gray101 Feb 5, 2025
5e07c3c

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 6, 2025
5b01500

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 8, 2025
aa9c995

migrate bruno request files to examples repo


dave-gray101 Feb 8, 2025
cac5f5a

fix


dave-gray101 Feb 8, 2025
a33a4d5

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 9, 2025
b717f6f

Update tests/e2e-aio/e2e_test.go


mudler Feb 10, 2025
f7dab99

Merge branch 'master' into feat-request-middleware


mudler Feb 10, 2025

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


8 changes: 8 additions & 0 deletions
aio/cpu/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
@mudlermudlerFeb 6, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

👍
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

2 changes: 1 addition & 1 deletion
aio/entrypoint.sh

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -129,7 +129,7 @@ detect_gpu
detect_gpu_size

PROFILE="${PROFILE:-$GPU_SIZE}" # default to cpu
export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vision.yaml}"
export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vad.yaml,/aio/${PROFILE}/vision.yaml}"

check_vars

Expand Down

8 changes: 8 additions & 0 deletions
aio/gpu-8g/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

8 changes: 8 additions & 0 deletions
aio/intel/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

8 changes: 1 addition & 7 deletions
core/application/startup.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -145,13 +145,7 @@ func New(opts ...config.AppOption) (*Application, error) {

	if options.LoadToMemory != nil {
 for _, m := range options.LoadToMemory {
 cfg, err := application.BackendLoader().LoadBackendConfigFileByName(m, options.ModelPath,
 config.LoadOptionDebug(options.Debug),
 config.LoadOptionThreads(options.Threads),
 config.LoadOptionContextSize(options.ContextSize),
 config.LoadOptionF16(options.F16),
 config.ModelPath(options.ModelPath),
 )
 cfg, err := application.BackendLoader().LoadBackendConfigFileByNameDefaultOptions(m, options)
@mudlermudlerFeb 6, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

❤️
 if err != nil {
 return nil, err
 }
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/llm.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -33,7 +33,7 @@ type TokenUsage struct {
	TimingTokenGeneration float64
}

func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c *config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
	modelFile := c.Model

	// Check if the modelFile exists, if it doesn't try to load it from the gallery
Expand All@@ -48,7 +48,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im
 }
	}

	opts := ModelOptions(c, o)
	opts := ModelOptions(*c, o)
	inferenceModel, err := loader.Load(opts...)
	if err != nil {
 return nil, err
Expand DownExpand Up@@ -84,7 +84,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im

	// in GRPC, the backend is supposed to answer to 1 single token if stream is not supported
	fn := func() (LLMResponse, error) {
 opts := gRPCPredictOpts(c, loader.ModelPath)
 opts := gRPCPredictOpts(*c, loader.ModelPath)
 opts.Prompt = s
 opts.Messages = protoMessages
 opts.UseTokenizerTemplate = c.TemplateConfig.UseTokenizerTemplate
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/rerank.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -9,10 +9,10 @@ import (
	model "github.com/mudler/LocalAI/pkg/model"
)

func Rerank(modelFile string, request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))
func Rerank(request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {
	opts := ModelOptions(backendConfig, appConfig)
	rerankModel, err := loader.Load(opts...)

	if err != nil {
 return nil, err
	}
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/soundgeneration.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -13,7 +13,6 @@ import (
)

func SoundGeneration(
	modelFile string,
	text string,
	duration *float32,
	temperature *float32,
Expand All@@ -25,8 +24,9 @@ func SoundGeneration(
	backendConfig config.BackendConfig,
) (string, *proto.Result, error) {

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))
	opts := ModelOptions(backendConfig, appConfig)
	soundGenModel, err := loader.Load(opts...)

	if err != nil {
 return "", nil, err
	}
Expand All@@ -44,7 +44,7 @@ func SoundGeneration(

	res, err := soundGenModel.SoundGeneration(context.Background(), &proto.SoundGenerationRequest{
 Text: text,
 Model: modelFile,
 Model: backendConfig.Model,
 Dst: filePath,
 Sample: doSample,
 Duration: duration,
Expand Down

8 changes: 3 additions & 5 deletions
core/backend/tokenize.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,19 +4,17 @@ import (
	"github.com/mudler/LocalAI/core/config"
	"github.com/mudler/LocalAI/core/schema"
	"github.com/mudler/LocalAI/pkg/grpc"
model "github.com/mudler/LocalAI/pkg/model"
	"github.com/mudler/LocalAI/pkg/model"
)

func ModelTokenize(s string, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (schema.TokenizeResponse, error) {

	modelFile := backendConfig.Model

	var inferenceModel grpc.Backend
	var err error

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))

	opts := ModelOptions(backendConfig, appConfig)
	inferenceModel, err = loader.Load(opts...)

	if err != nil {
 return schema.TokenizeResponse{}, err
	}
Expand Down

2 changes: 1 addition & 1 deletion
core/backend/transcript.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -47,7 +47,7 @@ func ModelTranscription(audio, language string, translate bool, ml *model.ModelL
 tks = append(tks, int(t))
 }
 tr.Segments = append(tr.Segments,
 schema.Segment{
 schema.TranscriptionSegment{
 Text: s.Text,
 Id: int(s.Id),
 Start: time.Duration(s.Start),
Expand Down

39 changes: 16 additions & 23 deletions
core/backend/tts.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -14,28 +14,22 @@ import (
)

func ModelTTS(
	backend,
	text,
	modelFile,
	voice,
	language string,
	loader *model.ModelLoader,
	appConfig *config.ApplicationConfig,
	backendConfig config.BackendConfig,
) (string, *proto.Result, error) {
	bb := backend
	if bb == "" {
 bb = model.PiperBackend
	}

	opts := ModelOptions(backendConfig, appConfig, model.WithBackendString(bb), model.WithModel(modelFile))
	opts := ModelOptions(backendConfig, appConfig, model.WithDefaultBackendString(model.PiperBackend))
	ttsModel, err := loader.Load(opts...)

	if err != nil {
 return "", nil, err
	}

	if ttsModel == nil {
 return "", nil, fmt.Errorf("could not load piper model")
 return "", nil, fmt.Errorf("could not load tts model %q", backendConfig.Model)
	}

	if err := os.MkdirAll(appConfig.AudioDir, 0750); err != nil {
Expand All@@ -45,22 +39,21 @@ func ModelTTS(
	fileName := utils.GenerateUniqueFileName(appConfig.AudioDir, "tts", ".wav")
	filePath := filepath.Join(appConfig.AudioDir, fileName)

	// If the model file is not empty, we pass it joined with the model path
	// We join the model name to the model path here. This seems to only be done for TTS and is HIGHLY suspect.
	// This should be addressed in a follow up PR soon.
	// Copying it over nearly verbatim, as TTS backends are not functional without this.
	modelPath := ""
	if modelFile != "" {
 // If the model file is not empty, we pass it joined with the model path
 // Checking first that it exists and is not outside ModelPath
 // TODO: we should actually first check if the modelFile is looking like
 // a FS path
 mp := filepath.Join(loader.ModelPath, modelFile)
 if _, err := os.Stat(mp); err == nil {
 if err := utils.VerifyPath(mp, appConfig.ModelPath); err != nil {
 return "", nil, err
 }
 modelPath = mp
 } else {
 modelPath = modelFile
	// Checking first that it exists and is not outside ModelPath
	// TODO: we should actually first check if the modelFile is looking like
	// a FS path
	mp := filepath.Join(loader.ModelPath, backendConfig.Model)
	if _, err := os.Stat(mp); err == nil {
 if err := utils.VerifyPath(mp, appConfig.ModelPath); err != nil {
 return "", nil, err
 }
 modelPath = mp
	} else {
 modelPath = backendConfig.Model // skip this step if it fails?????
	}

	res, err := ttsModel.TTS(context.Background(), &proto.TTSRequest{
Expand Down

38 changes: 38 additions & 0 deletions
core/backend/vad.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,38 @@
package backend

import (
	"context"

	"github.com/mudler/LocalAI/core/config"
	"github.com/mudler/LocalAI/core/schema"
	"github.com/mudler/LocalAI/pkg/grpc/proto"
	"github.com/mudler/LocalAI/pkg/model"
)

func VAD(request *schema.VADRequest,
	ctx context.Context,
	ml *model.ModelLoader,
	appConfig *config.ApplicationConfig,
	backendConfig config.BackendConfig) (*schema.VADResponse, error) {
	opts := ModelOptions(backendConfig, appConfig)
	vadModel, err := ml.Load(opts...)
	if err != nil {
 return nil, err
	}
	req := proto.VADRequest{
 Audio: request.Audio,
	}
	resp, err := vadModel.VAD(ctx, &req)
	if err != nil {
 return nil, err
	}

	segments := []schema.VADSegment{}
	for _, s := range resp.Segments {
 segments = append(segments, schema.VADSegment{Start: s.Start, End: s.End})
	}

	return &schema.VADResponse{
 Segments: segments,
	}, nil
}

3 changes: 2 additions & 1 deletion
core/cli/soundgeneration.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -86,13 +86,14 @@ func (t *SoundGenerationCMD) Run(ctx *cliContext.Context) error {
	options := config.BackendConfig{}
	options.SetDefaults()
	options.Backend = t.Backend
	options.Model = t.Model

	var inputFile *string
	if t.InputFile != "" {
 inputFile = &t.InputFile
	}

	filePath, _, err := backend.SoundGeneration(t.Model, text,
	filePath, _, err := backend.SoundGeneration(text,
 parseToFloat32Ptr(t.Duration), parseToFloat32Ptr(t.Temperature), &t.DoSample,
 inputFile, parseToInt32Ptr(t.InputFileSampleDivisor), ml, opts, options)

Expand Down

4 changes: 3 additions & 1 deletion
core/cli/tts.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -52,8 +52,10 @@ func (t *TTSCMD) Run(ctx *cliContext.Context) error {

	options := config.BackendConfig{}
	options.SetDefaults()
	options.Backend = t.Backend
	options.Model = t.Model

	filePath, _, err := backend.ModelTTS(t.Backend, text, t.Model, t.Voice, t.Language, ml, opts, options)
	filePath, _, err := backend.ModelTTS(text, t.Voice, t.Language, ml, opts, options)
	if err != nil {
 return err
	}
Expand Down

39 changes: 28 additions & 11 deletions
core/config/backend_config.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -437,19 +437,21 @@ func (c *BackendConfig) HasTemplate() bool {
type BackendConfigUsecases int

const (
	FLAG_ANY BackendConfigUsecases = 0b000000000
	FLAG_CHAT BackendConfigUsecases = 0b000000001
	FLAG_COMPLETION BackendConfigUsecases = 0b000000010
	FLAG_EDIT BackendConfigUsecases = 0b000000100
	FLAG_EMBEDDINGS BackendConfigUsecases = 0b000001000
	FLAG_RERANK BackendConfigUsecases = 0b000010000
	FLAG_IMAGE BackendConfigUsecases = 0b000100000
	FLAG_TRANSCRIPT BackendConfigUsecases = 0b001000000
	FLAG_TTS BackendConfigUsecases = 0b010000000
	FLAG_SOUND_GENERATION BackendConfigUsecases = 0b100000000
	FLAG_ANY BackendConfigUsecases = 0b00000000000
	FLAG_CHAT BackendConfigUsecases = 0b00000000001
	FLAG_COMPLETION BackendConfigUsecases = 0b00000000010
	FLAG_EDIT BackendConfigUsecases = 0b00000000100
	FLAG_EMBEDDINGS BackendConfigUsecases = 0b00000001000
	FLAG_RERANK BackendConfigUsecases = 0b00000010000
	FLAG_IMAGE BackendConfigUsecases = 0b00000100000
	FLAG_TRANSCRIPT BackendConfigUsecases = 0b00001000000
	FLAG_TTS BackendConfigUsecases = 0b00010000000
	FLAG_SOUND_GENERATION BackendConfigUsecases = 0b00100000000
	FLAG_TOKENIZE BackendConfigUsecases = 0b01000000000
	FLAG_VAD BackendConfigUsecases = 0b10000000000

	// Common Subsets
	FLAG_LLM BackendConfigUsecases = FLAG_CHAT & FLAG_COMPLETION & FLAG_EDIT
	FLAG_LLM BackendConfigUsecases = FLAG_CHAT | FLAG_COMPLETION | FLAG_EDIT
)

func GetAllBackendConfigUsecases() map[string]BackendConfigUsecases {
Expand All@@ -464,6 +466,8 @@ func GetAllBackendConfigUsecases() map[string]BackendConfigUsecases {
 "FLAG_TRANSCRIPT": FLAG_TRANSCRIPT,
 "FLAG_TTS": FLAG_TTS,
 "FLAG_SOUND_GENERATION": FLAG_SOUND_GENERATION,
 "FLAG_TOKENIZE": FLAG_TOKENIZE,
 "FLAG_VAD": FLAG_VAD,
 "FLAG_LLM": FLAG_LLM,
	}
}
Expand DownExpand Up@@ -549,5 +553,18 @@ func (c *BackendConfig) GuessUsecases(u BackendConfigUsecases) bool {
 }
	}

	if (u & FLAG_TOKENIZE) == FLAG_TOKENIZE {
 tokenizeCapableBackends := []string{"llama.cpp", "rwkv"}
 if !slices.Contains(tokenizeCapableBackends, c.Backend) {
 return false
 }
	}

	if (u & FLAG_VAD) == FLAG_VAD {
 if c.Backend != "silero-vad" {
@mudlermudlerFeb 6, 2025•

edited

Loading

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

note for later: at some point we should think about having these constants defined to be re-usable. There are some repetitions as well in the model initializer
@dave-gray101dave-gray101Feb 8, 2025

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed - probably worth doing that as followup if you're OK with that
@mudlermudlerFeb 10, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

definitely, was just a reminder/note
 return false
 }
	}

	return true
}
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Strip utm_, fbclid, gclid, etc. from all links on page
(function() {
var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',
'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',
'ref', 'ref_src', 'source', 'medium', 'campaign'];
function cleanUrl(url) {
try {
var u = new URL(url, window.location.origin);
var changed = false;
trackingParams.forEach(function(p) {
if (u.searchParams.has(p)) {
u.searchParams.delete(p);
changed = true;
}
});
return changed ? u.toString() : url;
} catch (e) {
return url;
}
}
function cleanLinks() {
document.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
cleanLinks();
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1) {
if (node.tagName === 'A') cleanLinks();
node.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
feat: Centralized Request Processing middleware#3847

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

mudler
merged 8 commits into

from

Feb 10, 2025
 Merged


feat: Centralized Request Processing middleware
#3847
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


8 commits


Select commit
Hold shift + click to select a range
c1f30ba

squash past, centralize request middleware PR


dave-gray101 Feb 5, 2025
5e07c3c

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 6, 2025
5b01500

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 8, 2025
aa9c995

migrate bruno request files to examples repo


dave-gray101 Feb 8, 2025
cac5f5a

fix


dave-gray101 Feb 8, 2025
a33a4d5

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 9, 2025
b717f6f

Update tests/e2e-aio/e2e_test.go


mudler Feb 10, 2025
f7dab99

Merge branch 'master' into feat-request-middleware


mudler Feb 10, 2025

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


8 changes: 8 additions & 0 deletions
aio/cpu/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
@mudlermudlerFeb 6, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

👍
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

2 changes: 1 addition & 1 deletion
aio/entrypoint.sh

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -129,7 +129,7 @@ detect_gpu
detect_gpu_size

PROFILE="${PROFILE:-$GPU_SIZE}" # default to cpu
export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vision.yaml}"
export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vad.yaml,/aio/${PROFILE}/vision.yaml}"

check_vars

Expand Down

8 changes: 8 additions & 0 deletions
aio/gpu-8g/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

8 changes: 8 additions & 0 deletions
aio/intel/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

8 changes: 1 addition & 7 deletions
core/application/startup.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -145,13 +145,7 @@ func New(opts ...config.AppOption) (*Application, error) {

	if options.LoadToMemory != nil {
 for _, m := range options.LoadToMemory {
 cfg, err := application.BackendLoader().LoadBackendConfigFileByName(m, options.ModelPath,
 config.LoadOptionDebug(options.Debug),
 config.LoadOptionThreads(options.Threads),
 config.LoadOptionContextSize(options.ContextSize),
 config.LoadOptionF16(options.F16),
 config.ModelPath(options.ModelPath),
 )
 cfg, err := application.BackendLoader().LoadBackendConfigFileByNameDefaultOptions(m, options)
@mudlermudlerFeb 6, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

❤️
 if err != nil {
 return nil, err
 }
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/llm.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -33,7 +33,7 @@ type TokenUsage struct {
	TimingTokenGeneration float64
}

func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c *config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
	modelFile := c.Model

	// Check if the modelFile exists, if it doesn't try to load it from the gallery
Expand All@@ -48,7 +48,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im
 }
	}

	opts := ModelOptions(c, o)
	opts := ModelOptions(*c, o)
	inferenceModel, err := loader.Load(opts...)
	if err != nil {
 return nil, err
Expand DownExpand Up@@ -84,7 +84,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im

	// in GRPC, the backend is supposed to answer to 1 single token if stream is not supported
	fn := func() (LLMResponse, error) {
 opts := gRPCPredictOpts(c, loader.ModelPath)
 opts := gRPCPredictOpts(*c, loader.ModelPath)
 opts.Prompt = s
 opts.Messages = protoMessages
 opts.UseTokenizerTemplate = c.TemplateConfig.UseTokenizerTemplate
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/rerank.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -9,10 +9,10 @@ import (
	model "github.com/mudler/LocalAI/pkg/model"
)

func Rerank(modelFile string, request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))
func Rerank(request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {
	opts := ModelOptions(backendConfig, appConfig)
	rerankModel, err := loader.Load(opts...)

	if err != nil {
 return nil, err
	}
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/soundgeneration.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -13,7 +13,6 @@ import (
)

func SoundGeneration(
	modelFile string,
	text string,
	duration *float32,
	temperature *float32,
Expand All@@ -25,8 +24,9 @@ func SoundGeneration(
	backendConfig config.BackendConfig,
) (string, *proto.Result, error) {

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))
	opts := ModelOptions(backendConfig, appConfig)
	soundGenModel, err := loader.Load(opts...)

	if err != nil {
 return "", nil, err
	}
Expand All@@ -44,7 +44,7 @@ func SoundGeneration(

	res, err := soundGenModel.SoundGeneration(context.Background(), &proto.SoundGenerationRequest{
 Text: text,
 Model: modelFile,
 Model: backendConfig.Model,
 Dst: filePath,
 Sample: doSample,
 Duration: duration,
Expand Down

8 changes: 3 additions & 5 deletions
core/backend/tokenize.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,19 +4,17 @@ import (
	"github.com/mudler/LocalAI/core/config"
	"github.com/mudler/LocalAI/core/schema"
	"github.com/mudler/LocalAI/pkg/grpc"
model "github.com/mudler/LocalAI/pkg/model"
	"github.com/mudler/LocalAI/pkg/model"
)

func ModelTokenize(s string, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (schema.TokenizeResponse, error) {

	modelFile := backendConfig.Model

	var inferenceModel grpc.Backend
	var err error

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))

	opts := ModelOptions(backendConfig, appConfig)
	inferenceModel, err = loader.Load(opts...)

	if err != nil {
 return schema.TokenizeResponse{}, err
	}
Expand Down

2 changes: 1 addition & 1 deletion
core/backend/transcript.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -47,7 +47,7 @@ func ModelTranscription(audio, language string, translate bool, ml *model.ModelL
 tks = append(tks, int(t))
 }
 tr.Segments = append(tr.Segments,
 schema.Segment{
 schema.TranscriptionSegment{
 Text: s.Text,
 Id: int(s.Id),
 Start: time.Duration(s.Start),
Expand Down

39 changes: 16 additions & 23 deletions
core/backend/tts.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -14,28 +14,22 @@ import (
)

func ModelTTS(
	backend,
	text,
	modelFile,
	voice,
	language string,
	loader *model.ModelLoader,
	appConfig *config.ApplicationConfig,
	backendConfig config.BackendConfig,
) (string, *proto.Result, error) {
	bb := backend
	if bb == "" {
 bb = model.PiperBackend
	}

	opts := ModelOptions(backendConfig, appConfig, model.WithBackendString(bb), model.WithModel(modelFile))
	opts := ModelOptions(backendConfig, appConfig, model.WithDefaultBackendString(model.PiperBackend))
	ttsModel, err := loader.Load(opts...)

	if err != nil {
 return "", nil, err
	}

	if ttsModel == nil {
 return "", nil, fmt.Errorf("could not load piper model")
 return "", nil, fmt.Errorf("could not load tts model %q", backendConfig.Model)
	}

	if err := os.MkdirAll(appConfig.AudioDir, 0750); err != nil {
Expand All@@ -45,22 +39,21 @@ func ModelTTS(
	fileName := utils.GenerateUniqueFileName(appConfig.AudioDir, "tts", ".wav")
	filePath := filepath.Join(appConfig.AudioDir, fileName)

	// If the model file is not empty, we pass it joined with the model path
	// We join the model name to the model path here. This seems to only be done for TTS and is HIGHLY suspect.
	// This should be addressed in a follow up PR soon.
	// Copying it over nearly verbatim, as TTS backends are not functional without this.
	modelPath := ""
	if modelFile != "" {
 // If the model file is not empty, we pass it joined with the model path
 // Checking first that it exists and is not outside ModelPath
 // TODO: we should actually first check if the modelFile is looking like
 // a FS path
 mp := filepath.Join(loader.ModelPath, modelFile)
 if _, err := os.Stat(mp); err == nil {
 if err := utils.VerifyPath(mp, appConfig.ModelPath); err != nil {
 return "", nil, err
 }
 modelPath = mp
 } else {
 modelPath = modelFile
	// Checking first that it exists and is not outside ModelPath
	// TODO: we should actually first check if the modelFile is looking like
	// a FS path
	mp := filepath.Join(loader.ModelPath, backendConfig.Model)
	if _, err := os.Stat(mp); err == nil {
 if err := utils.VerifyPath(mp, appConfig.ModelPath); err != nil {
 return "", nil, err
 }
 modelPath = mp
	} else {
 modelPath = backendConfig.Model // skip this step if it fails?????
	}

	res, err := ttsModel.TTS(context.Background(), &proto.TTSRequest{
Expand Down

38 changes: 38 additions & 0 deletions
core/backend/vad.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,38 @@
package backend

import (
	"context"

	"github.com/mudler/LocalAI/core/config"
	"github.com/mudler/LocalAI/core/schema"
	"github.com/mudler/LocalAI/pkg/grpc/proto"
	"github.com/mudler/LocalAI/pkg/model"
)

func VAD(request *schema.VADRequest,
	ctx context.Context,
	ml *model.ModelLoader,
	appConfig *config.ApplicationConfig,
	backendConfig config.BackendConfig) (*schema.VADResponse, error) {
	opts := ModelOptions(backendConfig, appConfig)
	vadModel, err := ml.Load(opts...)
	if err != nil {
 return nil, err
	}
	req := proto.VADRequest{
 Audio: request.Audio,
	}
	resp, err := vadModel.VAD(ctx, &req)
	if err != nil {
 return nil, err
	}

	segments := []schema.VADSegment{}
	for _, s := range resp.Segments {
 segments = append(segments, schema.VADSegment{Start: s.Start, End: s.End})
	}

	return &schema.VADResponse{
 Segments: segments,
	}, nil
}

3 changes: 2 additions & 1 deletion
core/cli/soundgeneration.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -86,13 +86,14 @@ func (t *SoundGenerationCMD) Run(ctx *cliContext.Context) error {
	options := config.BackendConfig{}
	options.SetDefaults()
	options.Backend = t.Backend
	options.Model = t.Model

	var inputFile *string
	if t.InputFile != "" {
 inputFile = &t.InputFile
	}

	filePath, _, err := backend.SoundGeneration(t.Model, text,
	filePath, _, err := backend.SoundGeneration(text,
 parseToFloat32Ptr(t.Duration), parseToFloat32Ptr(t.Temperature), &t.DoSample,
 inputFile, parseToInt32Ptr(t.InputFileSampleDivisor), ml, opts, options)

Expand Down

4 changes: 3 additions & 1 deletion
core/cli/tts.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -52,8 +52,10 @@ func (t *TTSCMD) Run(ctx *cliContext.Context) error {

	options := config.BackendConfig{}
	options.SetDefaults()
	options.Backend = t.Backend
	options.Model = t.Model

	filePath, _, err := backend.ModelTTS(t.Backend, text, t.Model, t.Voice, t.Language, ml, opts, options)
	filePath, _, err := backend.ModelTTS(text, t.Voice, t.Language, ml, opts, options)
	if err != nil {
 return err
	}
Expand Down

39 changes: 28 additions & 11 deletions
core/config/backend_config.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -437,19 +437,21 @@ func (c *BackendConfig) HasTemplate() bool {
type BackendConfigUsecases int

const (
	FLAG_ANY BackendConfigUsecases = 0b000000000
	FLAG_CHAT BackendConfigUsecases = 0b000000001
	FLAG_COMPLETION BackendConfigUsecases = 0b000000010
	FLAG_EDIT BackendConfigUsecases = 0b000000100
	FLAG_EMBEDDINGS BackendConfigUsecases = 0b000001000
	FLAG_RERANK BackendConfigUsecases = 0b000010000
	FLAG_IMAGE BackendConfigUsecases = 0b000100000
	FLAG_TRANSCRIPT BackendConfigUsecases = 0b001000000
	FLAG_TTS BackendConfigUsecases = 0b010000000
	FLAG_SOUND_GENERATION BackendConfigUsecases = 0b100000000
	FLAG_ANY BackendConfigUsecases = 0b00000000000
	FLAG_CHAT BackendConfigUsecases = 0b00000000001
	FLAG_COMPLETION BackendConfigUsecases = 0b00000000010
	FLAG_EDIT BackendConfigUsecases = 0b00000000100
	FLAG_EMBEDDINGS BackendConfigUsecases = 0b00000001000
	FLAG_RERANK BackendConfigUsecases = 0b00000010000
	FLAG_IMAGE BackendConfigUsecases = 0b00000100000
	FLAG_TRANSCRIPT BackendConfigUsecases = 0b00001000000
	FLAG_TTS BackendConfigUsecases = 0b00010000000
	FLAG_SOUND_GENERATION BackendConfigUsecases = 0b00100000000
	FLAG_TOKENIZE BackendConfigUsecases = 0b01000000000
	FLAG_VAD BackendConfigUsecases = 0b10000000000

	// Common Subsets
	FLAG_LLM BackendConfigUsecases = FLAG_CHAT & FLAG_COMPLETION & FLAG_EDIT
	FLAG_LLM BackendConfigUsecases = FLAG_CHAT | FLAG_COMPLETION | FLAG_EDIT
)

func GetAllBackendConfigUsecases() map[string]BackendConfigUsecases {
Expand All@@ -464,6 +466,8 @@ func GetAllBackendConfigUsecases() map[string]BackendConfigUsecases {
 "FLAG_TRANSCRIPT": FLAG_TRANSCRIPT,
 "FLAG_TTS": FLAG_TTS,
 "FLAG_SOUND_GENERATION": FLAG_SOUND_GENERATION,
 "FLAG_TOKENIZE": FLAG_TOKENIZE,
 "FLAG_VAD": FLAG_VAD,
 "FLAG_LLM": FLAG_LLM,
	}
}
Expand DownExpand Up@@ -549,5 +553,18 @@ func (c *BackendConfig) GuessUsecases(u BackendConfigUsecases) bool {
 }
	}

	if (u & FLAG_TOKENIZE) == FLAG_TOKENIZE {
 tokenizeCapableBackends := []string{"llama.cpp", "rwkv"}
 if !slices.Contains(tokenizeCapableBackends, c.Backend) {
 return false
 }
	}

	if (u & FLAG_VAD) == FLAG_VAD {
 if c.Backend != "silero-vad" {
@mudlermudlerFeb 6, 2025•

edited

Loading

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

note for later: at some point we should think about having these constants defined to be re-usable. There are some repetitions as well in the model initializer
@dave-gray101dave-gray101Feb 8, 2025

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed - probably worth doing that as followup if you're OK with that
@mudlermudlerFeb 10, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

definitely, was just a reminder/note
 return false
 }
	}

	return true
}
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Auto-enable theater mode on YouTube
(function() {
function tryTheater() {
var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]');
if (btn && !btn.classList.contains('activated')) {
btn.click();
}
}
// Try immediately
tryTheater();
// Try after navigation (SPA)
var lastUrl = location.href;
setInterval(function() {
if (location.href !== lastUrl) {
lastUrl = location.href;
setTimeout(tryTheater, 500);
}
}, 1000);
// Also try on player load
var observer = new MutationObserver(tryTheater);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
feat: Centralized Request Processing middleware#3847

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

mudler
merged 8 commits into

from

Feb 10, 2025
 Merged


feat: Centralized Request Processing middleware
#3847
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


8 commits


Select commit
Hold shift + click to select a range
c1f30ba

squash past, centralize request middleware PR


dave-gray101 Feb 5, 2025
5e07c3c

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 6, 2025
5b01500

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 8, 2025
aa9c995

migrate bruno request files to examples repo


dave-gray101 Feb 8, 2025
cac5f5a

fix


dave-gray101 Feb 8, 2025
a33a4d5

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 9, 2025
b717f6f

Update tests/e2e-aio/e2e_test.go


mudler Feb 10, 2025
f7dab99

Merge branch 'master' into feat-request-middleware


mudler Feb 10, 2025

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


8 changes: 8 additions & 0 deletions
aio/cpu/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
@mudlermudlerFeb 6, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

👍
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

2 changes: 1 addition & 1 deletion
aio/entrypoint.sh

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -129,7 +129,7 @@ detect_gpu
detect_gpu_size

PROFILE="${PROFILE:-$GPU_SIZE}" # default to cpu
export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vision.yaml}"
export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vad.yaml,/aio/${PROFILE}/vision.yaml}"

check_vars

Expand Down

8 changes: 8 additions & 0 deletions
aio/gpu-8g/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

8 changes: 8 additions & 0 deletions
aio/intel/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

8 changes: 1 addition & 7 deletions
core/application/startup.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -145,13 +145,7 @@ func New(opts ...config.AppOption) (*Application, error) {

	if options.LoadToMemory != nil {
 for _, m := range options.LoadToMemory {
 cfg, err := application.BackendLoader().LoadBackendConfigFileByName(m, options.ModelPath,
 config.LoadOptionDebug(options.Debug),
 config.LoadOptionThreads(options.Threads),
 config.LoadOptionContextSize(options.ContextSize),
 config.LoadOptionF16(options.F16),
 config.ModelPath(options.ModelPath),
 )
 cfg, err := application.BackendLoader().LoadBackendConfigFileByNameDefaultOptions(m, options)
@mudlermudlerFeb 6, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

❤️
 if err != nil {
 return nil, err
 }
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/llm.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -33,7 +33,7 @@ type TokenUsage struct {
	TimingTokenGeneration float64
}

func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c *config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
	modelFile := c.Model

	// Check if the modelFile exists, if it doesn't try to load it from the gallery
Expand All@@ -48,7 +48,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im
 }
	}

	opts := ModelOptions(c, o)
	opts := ModelOptions(*c, o)
	inferenceModel, err := loader.Load(opts...)
	if err != nil {
 return nil, err
Expand DownExpand Up@@ -84,7 +84,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im

	// in GRPC, the backend is supposed to answer to 1 single token if stream is not supported
	fn := func() (LLMResponse, error) {
 opts := gRPCPredictOpts(c, loader.ModelPath)
 opts := gRPCPredictOpts(*c, loader.ModelPath)
 opts.Prompt = s
 opts.Messages = protoMessages
 opts.UseTokenizerTemplate = c.TemplateConfig.UseTokenizerTemplate
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/rerank.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -9,10 +9,10 @@ import (
	model "github.com/mudler/LocalAI/pkg/model"
)

func Rerank(modelFile string, request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))
func Rerank(request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {
	opts := ModelOptions(backendConfig, appConfig)
	rerankModel, err := loader.Load(opts...)

	if err != nil {
 return nil, err
	}
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/soundgeneration.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -13,7 +13,6 @@ import (
)

func SoundGeneration(
	modelFile string,
	text string,
	duration *float32,
	temperature *float32,
Expand All@@ -25,8 +24,9 @@ func SoundGeneration(
	backendConfig config.BackendConfig,
) (string, *proto.Result, error) {

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))
	opts := ModelOptions(backendConfig, appConfig)
	soundGenModel, err := loader.Load(opts...)

	if err != nil {
 return "", nil, err
	}
Expand All@@ -44,7 +44,7 @@ func SoundGeneration(

	res, err := soundGenModel.SoundGeneration(context.Background(), &proto.SoundGenerationRequest{
 Text: text,
 Model: modelFile,
 Model: backendConfig.Model,
 Dst: filePath,
 Sample: doSample,
 Duration: duration,
Expand Down

8 changes: 3 additions & 5 deletions
core/backend/tokenize.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,19 +4,17 @@ import (
	"github.com/mudler/LocalAI/core/config"
	"github.com/mudler/LocalAI/core/schema"
	"github.com/mudler/LocalAI/pkg/grpc"
model "github.com/mudler/LocalAI/pkg/model"
	"github.com/mudler/LocalAI/pkg/model"
)

func ModelTokenize(s string, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (schema.TokenizeResponse, error) {

	modelFile := backendConfig.Model

	var inferenceModel grpc.Backend
	var err error

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))

	opts := ModelOptions(backendConfig, appConfig)
	inferenceModel, err = loader.Load(opts...)

	if err != nil {
 return schema.TokenizeResponse{}, err
	}
Expand Down

2 changes: 1 addition & 1 deletion
core/backend/transcript.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -47,7 +47,7 @@ func ModelTranscription(audio, language string, translate bool, ml *model.ModelL
 tks = append(tks, int(t))
 }
 tr.Segments = append(tr.Segments,
 schema.Segment{
 schema.TranscriptionSegment{
 Text: s.Text,
 Id: int(s.Id),
 Start: time.Duration(s.Start),
Expand Down

39 changes: 16 additions & 23 deletions
core/backend/tts.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -14,28 +14,22 @@ import (
)

func ModelTTS(
	backend,
	text,
	modelFile,
	voice,
	language string,
	loader *model.ModelLoader,
	appConfig *config.ApplicationConfig,
	backendConfig config.BackendConfig,
) (string, *proto.Result, error) {
	bb := backend
	if bb == "" {
 bb = model.PiperBackend
	}

	opts := ModelOptions(backendConfig, appConfig, model.WithBackendString(bb), model.WithModel(modelFile))
	opts := ModelOptions(backendConfig, appConfig, model.WithDefaultBackendString(model.PiperBackend))
	ttsModel, err := loader.Load(opts...)

	if err != nil {
 return "", nil, err
	}

	if ttsModel == nil {
 return "", nil, fmt.Errorf("could not load piper model")
 return "", nil, fmt.Errorf("could not load tts model %q", backendConfig.Model)
	}

	if err := os.MkdirAll(appConfig.AudioDir, 0750); err != nil {
Expand All@@ -45,22 +39,21 @@ func ModelTTS(
	fileName := utils.GenerateUniqueFileName(appConfig.AudioDir, "tts", ".wav")
	filePath := filepath.Join(appConfig.AudioDir, fileName)

	// If the model file is not empty, we pass it joined with the model path
	// We join the model name to the model path here. This seems to only be done for TTS and is HIGHLY suspect.
	// This should be addressed in a follow up PR soon.
	// Copying it over nearly verbatim, as TTS backends are not functional without this.
	modelPath := ""
	if modelFile != "" {
 // If the model file is not empty, we pass it joined with the model path
 // Checking first that it exists and is not outside ModelPath
 // TODO: we should actually first check if the modelFile is looking like
 // a FS path
 mp := filepath.Join(loader.ModelPath, modelFile)
 if _, err := os.Stat(mp); err == nil {
 if err := utils.VerifyPath(mp, appConfig.ModelPath); err != nil {
 return "", nil, err
 }
 modelPath = mp
 } else {
 modelPath = modelFile
	// Checking first that it exists and is not outside ModelPath
	// TODO: we should actually first check if the modelFile is looking like
	// a FS path
	mp := filepath.Join(loader.ModelPath, backendConfig.Model)
	if _, err := os.Stat(mp); err == nil {
 if err := utils.VerifyPath(mp, appConfig.ModelPath); err != nil {
 return "", nil, err
 }
 modelPath = mp
	} else {
 modelPath = backendConfig.Model // skip this step if it fails?????
	}

	res, err := ttsModel.TTS(context.Background(), &proto.TTSRequest{
Expand Down

38 changes: 38 additions & 0 deletions
core/backend/vad.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,38 @@
package backend

import (
	"context"

	"github.com/mudler/LocalAI/core/config"
	"github.com/mudler/LocalAI/core/schema"
	"github.com/mudler/LocalAI/pkg/grpc/proto"
	"github.com/mudler/LocalAI/pkg/model"
)

func VAD(request *schema.VADRequest,
	ctx context.Context,
	ml *model.ModelLoader,
	appConfig *config.ApplicationConfig,
	backendConfig config.BackendConfig) (*schema.VADResponse, error) {
	opts := ModelOptions(backendConfig, appConfig)
	vadModel, err := ml.Load(opts...)
	if err != nil {
 return nil, err
	}
	req := proto.VADRequest{
 Audio: request.Audio,
	}
	resp, err := vadModel.VAD(ctx, &req)
	if err != nil {
 return nil, err
	}

	segments := []schema.VADSegment{}
	for _, s := range resp.Segments {
 segments = append(segments, schema.VADSegment{Start: s.Start, End: s.End})
	}

	return &schema.VADResponse{
 Segments: segments,
	}, nil
}

3 changes: 2 additions & 1 deletion
core/cli/soundgeneration.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -86,13 +86,14 @@ func (t *SoundGenerationCMD) Run(ctx *cliContext.Context) error {
	options := config.BackendConfig{}
	options.SetDefaults()
	options.Backend = t.Backend
	options.Model = t.Model

	var inputFile *string
	if t.InputFile != "" {
 inputFile = &t.InputFile
	}

	filePath, _, err := backend.SoundGeneration(t.Model, text,
	filePath, _, err := backend.SoundGeneration(text,
 parseToFloat32Ptr(t.Duration), parseToFloat32Ptr(t.Temperature), &t.DoSample,
 inputFile, parseToInt32Ptr(t.InputFileSampleDivisor), ml, opts, options)

Expand Down

4 changes: 3 additions & 1 deletion
core/cli/tts.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -52,8 +52,10 @@ func (t *TTSCMD) Run(ctx *cliContext.Context) error {

	options := config.BackendConfig{}
	options.SetDefaults()
	options.Backend = t.Backend
	options.Model = t.Model

	filePath, _, err := backend.ModelTTS(t.Backend, text, t.Model, t.Voice, t.Language, ml, opts, options)
	filePath, _, err := backend.ModelTTS(text, t.Voice, t.Language, ml, opts, options)
	if err != nil {
 return err
	}
Expand Down

39 changes: 28 additions & 11 deletions
core/config/backend_config.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -437,19 +437,21 @@ func (c *BackendConfig) HasTemplate() bool {
type BackendConfigUsecases int

const (
	FLAG_ANY BackendConfigUsecases = 0b000000000
	FLAG_CHAT BackendConfigUsecases = 0b000000001
	FLAG_COMPLETION BackendConfigUsecases = 0b000000010
	FLAG_EDIT BackendConfigUsecases = 0b000000100
	FLAG_EMBEDDINGS BackendConfigUsecases = 0b000001000
	FLAG_RERANK BackendConfigUsecases = 0b000010000
	FLAG_IMAGE BackendConfigUsecases = 0b000100000
	FLAG_TRANSCRIPT BackendConfigUsecases = 0b001000000
	FLAG_TTS BackendConfigUsecases = 0b010000000
	FLAG_SOUND_GENERATION BackendConfigUsecases = 0b100000000
	FLAG_ANY BackendConfigUsecases = 0b00000000000
	FLAG_CHAT BackendConfigUsecases = 0b00000000001
	FLAG_COMPLETION BackendConfigUsecases = 0b00000000010
	FLAG_EDIT BackendConfigUsecases = 0b00000000100
	FLAG_EMBEDDINGS BackendConfigUsecases = 0b00000001000
	FLAG_RERANK BackendConfigUsecases = 0b00000010000
	FLAG_IMAGE BackendConfigUsecases = 0b00000100000
	FLAG_TRANSCRIPT BackendConfigUsecases = 0b00001000000
	FLAG_TTS BackendConfigUsecases = 0b00010000000
	FLAG_SOUND_GENERATION BackendConfigUsecases = 0b00100000000
	FLAG_TOKENIZE BackendConfigUsecases = 0b01000000000
	FLAG_VAD BackendConfigUsecases = 0b10000000000

	// Common Subsets
	FLAG_LLM BackendConfigUsecases = FLAG_CHAT & FLAG_COMPLETION & FLAG_EDIT
	FLAG_LLM BackendConfigUsecases = FLAG_CHAT | FLAG_COMPLETION | FLAG_EDIT
)

func GetAllBackendConfigUsecases() map[string]BackendConfigUsecases {
Expand All@@ -464,6 +466,8 @@ func GetAllBackendConfigUsecases() map[string]BackendConfigUsecases {
 "FLAG_TRANSCRIPT": FLAG_TRANSCRIPT,
 "FLAG_TTS": FLAG_TTS,
 "FLAG_SOUND_GENERATION": FLAG_SOUND_GENERATION,
 "FLAG_TOKENIZE": FLAG_TOKENIZE,
 "FLAG_VAD": FLAG_VAD,
 "FLAG_LLM": FLAG_LLM,
	}
}
Expand DownExpand Up@@ -549,5 +553,18 @@ func (c *BackendConfig) GuessUsecases(u BackendConfigUsecases) bool {
 }
	}

	if (u & FLAG_TOKENIZE) == FLAG_TOKENIZE {
 tokenizeCapableBackends := []string{"llama.cpp", "rwkv"}
 if !slices.Contains(tokenizeCapableBackends, c.Backend) {
 return false
 }
	}

	if (u & FLAG_VAD) == FLAG_VAD {
 if c.Backend != "silero-vad" {
@mudlermudlerFeb 6, 2025•

edited

Loading

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

note for later: at some point we should think about having these constants defined to be re-usable. There are some repetitions as well in the model initializer
@dave-gray101dave-gray101Feb 8, 2025

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed - probably worth doing that as followup if you're OK with that
@mudlermudlerFeb 10, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

definitely, was just a reminder/note
 return false
 }
	}

	return true
}
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Remove or un-stick sticky/fixed headers that block content
(function() {
function unstick() {
document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) {
if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {
el.style.position = 'static';
el.style.top = 'auto';
el.style.zIndex = 'auto';
}
});
}
unstick();
var observer = new MutationObserver(unstick);
observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });
})();
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
feat: Centralized Request Processing middleware#3847

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

mudler
merged 8 commits into

from

Feb 10, 2025
 Merged


feat: Centralized Request Processing middleware
#3847
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


8 commits


Select commit
Hold shift + click to select a range
c1f30ba

squash past, centralize request middleware PR


dave-gray101 Feb 5, 2025
5e07c3c

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 6, 2025
5b01500

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 8, 2025
aa9c995

migrate bruno request files to examples repo


dave-gray101 Feb 8, 2025
cac5f5a

fix


dave-gray101 Feb 8, 2025
a33a4d5

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 9, 2025
b717f6f

Update tests/e2e-aio/e2e_test.go


mudler Feb 10, 2025
f7dab99

Merge branch 'master' into feat-request-middleware


mudler Feb 10, 2025

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


8 changes: 8 additions & 0 deletions
aio/cpu/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
@mudlermudlerFeb 6, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

👍
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

2 changes: 1 addition & 1 deletion
aio/entrypoint.sh

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -129,7 +129,7 @@ detect_gpu
detect_gpu_size

PROFILE="${PROFILE:-$GPU_SIZE}" # default to cpu
export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vision.yaml}"
export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vad.yaml,/aio/${PROFILE}/vision.yaml}"

check_vars

Expand Down

8 changes: 8 additions & 0 deletions
aio/gpu-8g/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

8 changes: 8 additions & 0 deletions
aio/intel/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

8 changes: 1 addition & 7 deletions
core/application/startup.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -145,13 +145,7 @@ func New(opts ...config.AppOption) (*Application, error) {

	if options.LoadToMemory != nil {
 for _, m := range options.LoadToMemory {
 cfg, err := application.BackendLoader().LoadBackendConfigFileByName(m, options.ModelPath,
 config.LoadOptionDebug(options.Debug),
 config.LoadOptionThreads(options.Threads),
 config.LoadOptionContextSize(options.ContextSize),
 config.LoadOptionF16(options.F16),
 config.ModelPath(options.ModelPath),
 )
 cfg, err := application.BackendLoader().LoadBackendConfigFileByNameDefaultOptions(m, options)
@mudlermudlerFeb 6, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

❤️
 if err != nil {
 return nil, err
 }
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/llm.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -33,7 +33,7 @@ type TokenUsage struct {
	TimingTokenGeneration float64
}

func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c *config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
	modelFile := c.Model

	// Check if the modelFile exists, if it doesn't try to load it from the gallery
Expand All@@ -48,7 +48,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im
 }
	}

	opts := ModelOptions(c, o)
	opts := ModelOptions(*c, o)
	inferenceModel, err := loader.Load(opts...)
	if err != nil {
 return nil, err
Expand DownExpand Up@@ -84,7 +84,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im

	// in GRPC, the backend is supposed to answer to 1 single token if stream is not supported
	fn := func() (LLMResponse, error) {
 opts := gRPCPredictOpts(c, loader.ModelPath)
 opts := gRPCPredictOpts(*c, loader.ModelPath)
 opts.Prompt = s
 opts.Messages = protoMessages
 opts.UseTokenizerTemplate = c.TemplateConfig.UseTokenizerTemplate
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/rerank.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -9,10 +9,10 @@ import (
	model "github.com/mudler/LocalAI/pkg/model"
)

func Rerank(modelFile string, request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))
func Rerank(request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {
	opts := ModelOptions(backendConfig, appConfig)
	rerankModel, err := loader.Load(opts...)

	if err != nil {
 return nil, err
	}
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/soundgeneration.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -13,7 +13,6 @@ import (
)

func SoundGeneration(
	modelFile string,
	text string,
	duration *float32,
	temperature *float32,
Expand All@@ -25,8 +24,9 @@ func SoundGeneration(
	backendConfig config.BackendConfig,
) (string, *proto.Result, error) {

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))
	opts := ModelOptions(backendConfig, appConfig)
	soundGenModel, err := loader.Load(opts...)

	if err != nil {
 return "", nil, err
	}
Expand All@@ -44,7 +44,7 @@ func SoundGeneration(

	res, err := soundGenModel.SoundGeneration(context.Background(), &proto.SoundGenerationRequest{
 Text: text,
 Model: modelFile,
 Model: backendConfig.Model,
 Dst: filePath,
 Sample: doSample,
 Duration: duration,
Expand Down

8 changes: 3 additions & 5 deletions
core/backend/tokenize.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,19 +4,17 @@ import (
	"github.com/mudler/LocalAI/core/config"
	"github.com/mudler/LocalAI/core/schema"
	"github.com/mudler/LocalAI/pkg/grpc"
model "github.com/mudler/LocalAI/pkg/model"
	"github.com/mudler/LocalAI/pkg/model"
)

func ModelTokenize(s string, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (schema.TokenizeResponse, error) {

	modelFile := backendConfig.Model

	var inferenceModel grpc.Backend
	var err error

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))

	opts := ModelOptions(backendConfig, appConfig)
	inferenceModel, err = loader.Load(opts...)

	if err != nil {
 return schema.TokenizeResponse{}, err
	}
Expand Down

2 changes: 1 addition & 1 deletion
core/backend/transcript.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -47,7 +47,7 @@ func ModelTranscription(audio, language string, translate bool, ml *model.ModelL
 tks = append(tks, int(t))
 }
 tr.Segments = append(tr.Segments,
 schema.Segment{
 schema.TranscriptionSegment{
 Text: s.Text,
 Id: int(s.Id),
 Start: time.Duration(s.Start),
Expand Down

39 changes: 16 additions & 23 deletions
core/backend/tts.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -14,28 +14,22 @@ import (
)

func ModelTTS(
	backend,
	text,
	modelFile,
	voice,
	language string,
	loader *model.ModelLoader,
	appConfig *config.ApplicationConfig,
	backendConfig config.BackendConfig,
) (string, *proto.Result, error) {
	bb := backend
	if bb == "" {
 bb = model.PiperBackend
	}

	opts := ModelOptions(backendConfig, appConfig, model.WithBackendString(bb), model.WithModel(modelFile))
	opts := ModelOptions(backendConfig, appConfig, model.WithDefaultBackendString(model.PiperBackend))
	ttsModel, err := loader.Load(opts...)

	if err != nil {
 return "", nil, err
	}

	if ttsModel == nil {
 return "", nil, fmt.Errorf("could not load piper model")
 return "", nil, fmt.Errorf("could not load tts model %q", backendConfig.Model)
	}

	if err := os.MkdirAll(appConfig.AudioDir, 0750); err != nil {
Expand All@@ -45,22 +39,21 @@ func ModelTTS(
	fileName := utils.GenerateUniqueFileName(appConfig.AudioDir, "tts", ".wav")
	filePath := filepath.Join(appConfig.AudioDir, fileName)

	// If the model file is not empty, we pass it joined with the model path
	// We join the model name to the model path here. This seems to only be done for TTS and is HIGHLY suspect.
	// This should be addressed in a follow up PR soon.
	// Copying it over nearly verbatim, as TTS backends are not functional without this.
	modelPath := ""
	if modelFile != "" {
 // If the model file is not empty, we pass it joined with the model path
 // Checking first that it exists and is not outside ModelPath
 // TODO: we should actually first check if the modelFile is looking like
 // a FS path
 mp := filepath.Join(loader.ModelPath, modelFile)
 if _, err := os.Stat(mp); err == nil {
 if err := utils.VerifyPath(mp, appConfig.ModelPath); err != nil {
 return "", nil, err
 }
 modelPath = mp
 } else {
 modelPath = modelFile
	// Checking first that it exists and is not outside ModelPath
	// TODO: we should actually first check if the modelFile is looking like
	// a FS path
	mp := filepath.Join(loader.ModelPath, backendConfig.Model)
	if _, err := os.Stat(mp); err == nil {
 if err := utils.VerifyPath(mp, appConfig.ModelPath); err != nil {
 return "", nil, err
 }
 modelPath = mp
	} else {
 modelPath = backendConfig.Model // skip this step if it fails?????
	}

	res, err := ttsModel.TTS(context.Background(), &proto.TTSRequest{
Expand Down

38 changes: 38 additions & 0 deletions
core/backend/vad.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,38 @@
package backend

import (
	"context"

	"github.com/mudler/LocalAI/core/config"
	"github.com/mudler/LocalAI/core/schema"
	"github.com/mudler/LocalAI/pkg/grpc/proto"
	"github.com/mudler/LocalAI/pkg/model"
)

func VAD(request *schema.VADRequest,
	ctx context.Context,
	ml *model.ModelLoader,
	appConfig *config.ApplicationConfig,
	backendConfig config.BackendConfig) (*schema.VADResponse, error) {
	opts := ModelOptions(backendConfig, appConfig)
	vadModel, err := ml.Load(opts...)
	if err != nil {
 return nil, err
	}
	req := proto.VADRequest{
 Audio: request.Audio,
	}
	resp, err := vadModel.VAD(ctx, &req)
	if err != nil {
 return nil, err
	}

	segments := []schema.VADSegment{}
	for _, s := range resp.Segments {
 segments = append(segments, schema.VADSegment{Start: s.Start, End: s.End})
	}

	return &schema.VADResponse{
 Segments: segments,
	}, nil
}

3 changes: 2 additions & 1 deletion
core/cli/soundgeneration.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -86,13 +86,14 @@ func (t *SoundGenerationCMD) Run(ctx *cliContext.Context) error {
	options := config.BackendConfig{}
	options.SetDefaults()
	options.Backend = t.Backend
	options.Model = t.Model

	var inputFile *string
	if t.InputFile != "" {
 inputFile = &t.InputFile
	}

	filePath, _, err := backend.SoundGeneration(t.Model, text,
	filePath, _, err := backend.SoundGeneration(text,
 parseToFloat32Ptr(t.Duration), parseToFloat32Ptr(t.Temperature), &t.DoSample,
 inputFile, parseToInt32Ptr(t.InputFileSampleDivisor), ml, opts, options)

Expand Down

4 changes: 3 additions & 1 deletion
core/cli/tts.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -52,8 +52,10 @@ func (t *TTSCMD) Run(ctx *cliContext.Context) error {

	options := config.BackendConfig{}
	options.SetDefaults()
	options.Backend = t.Backend
	options.Model = t.Model

	filePath, _, err := backend.ModelTTS(t.Backend, text, t.Model, t.Voice, t.Language, ml, opts, options)
	filePath, _, err := backend.ModelTTS(text, t.Voice, t.Language, ml, opts, options)
	if err != nil {
 return err
	}
Expand Down

39 changes: 28 additions & 11 deletions
core/config/backend_config.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -437,19 +437,21 @@ func (c *BackendConfig) HasTemplate() bool {
type BackendConfigUsecases int

const (
	FLAG_ANY BackendConfigUsecases = 0b000000000
	FLAG_CHAT BackendConfigUsecases = 0b000000001
	FLAG_COMPLETION BackendConfigUsecases = 0b000000010
	FLAG_EDIT BackendConfigUsecases = 0b000000100
	FLAG_EMBEDDINGS BackendConfigUsecases = 0b000001000
	FLAG_RERANK BackendConfigUsecases = 0b000010000
	FLAG_IMAGE BackendConfigUsecases = 0b000100000
	FLAG_TRANSCRIPT BackendConfigUsecases = 0b001000000
	FLAG_TTS BackendConfigUsecases = 0b010000000
	FLAG_SOUND_GENERATION BackendConfigUsecases = 0b100000000
	FLAG_ANY BackendConfigUsecases = 0b00000000000
	FLAG_CHAT BackendConfigUsecases = 0b00000000001
	FLAG_COMPLETION BackendConfigUsecases = 0b00000000010
	FLAG_EDIT BackendConfigUsecases = 0b00000000100
	FLAG_EMBEDDINGS BackendConfigUsecases = 0b00000001000
	FLAG_RERANK BackendConfigUsecases = 0b00000010000
	FLAG_IMAGE BackendConfigUsecases = 0b00000100000
	FLAG_TRANSCRIPT BackendConfigUsecases = 0b00001000000
	FLAG_TTS BackendConfigUsecases = 0b00010000000
	FLAG_SOUND_GENERATION BackendConfigUsecases = 0b00100000000
	FLAG_TOKENIZE BackendConfigUsecases = 0b01000000000
	FLAG_VAD BackendConfigUsecases = 0b10000000000

	// Common Subsets
	FLAG_LLM BackendConfigUsecases = FLAG_CHAT & FLAG_COMPLETION & FLAG_EDIT
	FLAG_LLM BackendConfigUsecases = FLAG_CHAT | FLAG_COMPLETION | FLAG_EDIT
)

func GetAllBackendConfigUsecases() map[string]BackendConfigUsecases {
Expand All@@ -464,6 +466,8 @@ func GetAllBackendConfigUsecases() map[string]BackendConfigUsecases {
 "FLAG_TRANSCRIPT": FLAG_TRANSCRIPT,
 "FLAG_TTS": FLAG_TTS,
 "FLAG_SOUND_GENERATION": FLAG_SOUND_GENERATION,
 "FLAG_TOKENIZE": FLAG_TOKENIZE,
 "FLAG_VAD": FLAG_VAD,
 "FLAG_LLM": FLAG_LLM,
	}
}
Expand DownExpand Up@@ -549,5 +553,18 @@ func (c *BackendConfig) GuessUsecases(u BackendConfigUsecases) bool {
 }
	}

	if (u & FLAG_TOKENIZE) == FLAG_TOKENIZE {
 tokenizeCapableBackends := []string{"llama.cpp", "rwkv"}
 if !slices.Contains(tokenizeCapableBackends, c.Backend) {
 return false
 }
	}

	if (u & FLAG_VAD) == FLAG_VAD {
 if c.Backend != "silero-vad" {
@mudlermudlerFeb 6, 2025•

edited

Loading

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

note for later: at some point we should think about having these constants defined to be re-usable. There are some repetitions as well in the model initializer
@dave-gray101dave-gray101Feb 8, 2025

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed - probably worth doing that as followup if you're OK with that
@mudlermudlerFeb 10, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

definitely, was just a reminder/note
 return false
 }
	}

	return true
}
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Universal Dark Mode - works on any site
(function() {
var enabled = true;
function applyDarkMode() {
if (!enabled) return;
// Create style element if it doesn't exist
var style = document.getElementById('universal-dark-mode-style');
if (!style) {
style = document.createElement('style');
style.id = 'universal-dark-mode-style';
document.head.appendChild(style);
}
// Dark mode CSS - inverts colors but preserves images/video
style.textContent = '
/* Invert everything except media */
html {
filter: invert(1) hue-rotate(180deg) !important;
background: #1a1a2e !important;
}
/* Restore images, videos, iframes, canvas */
img, video, iframe, canvas, svg, picture, [style*="background-image"] {
filter: invert(1) hue-rotate(180deg) !important;
}
/* Preserve specific elements that should not be inverted */
.no-dark-mode, .no-dark-mode *,
[data-theme="light"], [data-theme="light"],
.ace_editor, .ace_editor *,
.CodeMirror, .CodeMirror *,
.monaco-editor, .monaco-editor *,
.markdown-body pre, .markdown-body pre *,
.highlight, .highlight *,
pre code, pre code * {
filter: none !important;
}
/* Fix common UI elements */
.modal, .popup, .dropdown-menu, .tooltip, .popover {
filter: invert(1) hue-rotate(180deg) !important;
background: #2d2d44 !important;
border-color: #444 !important;
}
/* Scrollbars */
::-webkit-scrollbar { background: #1a1a2e !important; }
::-webkit-scrollbar-thumb { background: #444 !important; }
::-webkit-scrollbar-thumb:hover { background: #555 !important; }
/* Selection */
::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
';
}
function removeDarkMode() {
var style = document.getElementById('universal-dark-mode-style');
if (style) style.remove();
}
// Toggle with Alt+Shift+D
document.addEventListener('keydown', function(e) {
if (e.altKey && e.shiftKey && e.key === 'D') {
e.preventDefault();
enabled = !enabled;
if (enabled) {
applyDarkMode();
console.log('[Universal Dark Mode] Enabled');
} else {
removeDarkMode();
console.log('[Universal Dark Mode] Disabled');
}
}
});
// Apply on load
applyDarkMode();
// Re-apply on dynamic content
var observer = new MutationObserver(function(mutations) {
if (enabled && !document.getElementById('universal-dark-mode-style')) {
applyDarkMode();
}
});
observer.observe(document.head, { childList: true });
console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');
})();
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
feat: Centralized Request Processing middleware#3847

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

mudler
merged 8 commits into

from

Feb 10, 2025
 Merged


feat: Centralized Request Processing middleware
#3847
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


8 commits


Select commit
Hold shift + click to select a range
c1f30ba

squash past, centralize request middleware PR


dave-gray101 Feb 5, 2025
5e07c3c

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 6, 2025
5b01500

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 8, 2025
aa9c995

migrate bruno request files to examples repo


dave-gray101 Feb 8, 2025
cac5f5a

fix


dave-gray101 Feb 8, 2025
a33a4d5

Merge branch 'master' into feat-request-middleware


dave-gray101 Feb 9, 2025
b717f6f

Update tests/e2e-aio/e2e_test.go


mudler Feb 10, 2025
f7dab99

Merge branch 'master' into feat-request-middleware


mudler Feb 10, 2025

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


8 changes: 8 additions & 0 deletions
aio/cpu/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
@mudlermudlerFeb 6, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

👍
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

2 changes: 1 addition & 1 deletion
aio/entrypoint.sh

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -129,7 +129,7 @@ detect_gpu
detect_gpu_size

PROFILE="${PROFILE:-$GPU_SIZE}" # default to cpu
export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vision.yaml}"
export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vad.yaml,/aio/${PROFILE}/vision.yaml}"

check_vars

Expand Down

8 changes: 8 additions & 0 deletions
aio/gpu-8g/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

8 changes: 8 additions & 0 deletions
aio/intel/vad.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
backend: silero-vad
name: silero-vad
parameters:
 model: silero-vad.onnx
download_files:
- filename: silero-vad.onnx
 uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
 sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

8 changes: 1 addition & 7 deletions
core/application/startup.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -145,13 +145,7 @@ func New(opts ...config.AppOption) (*Application, error) {

	if options.LoadToMemory != nil {
 for _, m := range options.LoadToMemory {
 cfg, err := application.BackendLoader().LoadBackendConfigFileByName(m, options.ModelPath,
 config.LoadOptionDebug(options.Debug),
 config.LoadOptionThreads(options.Threads),
 config.LoadOptionContextSize(options.ContextSize),
 config.LoadOptionF16(options.F16),
 config.ModelPath(options.ModelPath),
 )
 cfg, err := application.BackendLoader().LoadBackendConfigFileByNameDefaultOptions(m, options)
@mudlermudlerFeb 6, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

❤️
 if err != nil {
 return nil, err
 }
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/llm.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -33,7 +33,7 @@ type TokenUsage struct {
	TimingTokenGeneration float64
}

func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c *config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
	modelFile := c.Model

	// Check if the modelFile exists, if it doesn't try to load it from the gallery
Expand All@@ -48,7 +48,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im
 }
	}

	opts := ModelOptions(c, o)
	opts := ModelOptions(*c, o)
	inferenceModel, err := loader.Load(opts...)
	if err != nil {
 return nil, err
Expand DownExpand Up@@ -84,7 +84,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im

	// in GRPC, the backend is supposed to answer to 1 single token if stream is not supported
	fn := func() (LLMResponse, error) {
 opts := gRPCPredictOpts(c, loader.ModelPath)
 opts := gRPCPredictOpts(*c, loader.ModelPath)
 opts.Prompt = s
 opts.Messages = protoMessages
 opts.UseTokenizerTemplate = c.TemplateConfig.UseTokenizerTemplate
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/rerank.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -9,10 +9,10 @@ import (
	model "github.com/mudler/LocalAI/pkg/model"
)

func Rerank(modelFile string, request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))
func Rerank(request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {
	opts := ModelOptions(backendConfig, appConfig)
	rerankModel, err := loader.Load(opts...)

	if err != nil {
 return nil, err
	}
Expand Down

6 changes: 3 additions & 3 deletions
core/backend/soundgeneration.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -13,7 +13,6 @@ import (
)

func SoundGeneration(
	modelFile string,
	text string,
	duration *float32,
	temperature *float32,
Expand All@@ -25,8 +24,9 @@ func SoundGeneration(
	backendConfig config.BackendConfig,
) (string, *proto.Result, error) {

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))
	opts := ModelOptions(backendConfig, appConfig)
	soundGenModel, err := loader.Load(opts...)

	if err != nil {
 return "", nil, err
	}
Expand All@@ -44,7 +44,7 @@ func SoundGeneration(

	res, err := soundGenModel.SoundGeneration(context.Background(), &proto.SoundGenerationRequest{
 Text: text,
 Model: modelFile,
 Model: backendConfig.Model,
 Dst: filePath,
 Sample: doSample,
 Duration: duration,
Expand Down

8 changes: 3 additions & 5 deletions
core/backend/tokenize.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,19 +4,17 @@ import (
	"github.com/mudler/LocalAI/core/config"
	"github.com/mudler/LocalAI/core/schema"
	"github.com/mudler/LocalAI/pkg/grpc"
model "github.com/mudler/LocalAI/pkg/model"
	"github.com/mudler/LocalAI/pkg/model"
)

func ModelTokenize(s string, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (schema.TokenizeResponse, error) {

	modelFile := backendConfig.Model

	var inferenceModel grpc.Backend
	var err error

	opts := ModelOptions(backendConfig, appConfig, model.WithModel(modelFile))

	opts := ModelOptions(backendConfig, appConfig)
	inferenceModel, err = loader.Load(opts...)

	if err != nil {
 return schema.TokenizeResponse{}, err
	}
Expand Down

2 changes: 1 addition & 1 deletion
core/backend/transcript.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -47,7 +47,7 @@ func ModelTranscription(audio, language string, translate bool, ml *model.ModelL
 tks = append(tks, int(t))
 }
 tr.Segments = append(tr.Segments,
 schema.Segment{
 schema.TranscriptionSegment{
 Text: s.Text,
 Id: int(s.Id),
 Start: time.Duration(s.Start),
Expand Down

39 changes: 16 additions & 23 deletions
core/backend/tts.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -14,28 +14,22 @@ import (
)

func ModelTTS(
	backend,
	text,
	modelFile,
	voice,
	language string,
	loader *model.ModelLoader,
	appConfig *config.ApplicationConfig,
	backendConfig config.BackendConfig,
) (string, *proto.Result, error) {
	bb := backend
	if bb == "" {
 bb = model.PiperBackend
	}

	opts := ModelOptions(backendConfig, appConfig, model.WithBackendString(bb), model.WithModel(modelFile))
	opts := ModelOptions(backendConfig, appConfig, model.WithDefaultBackendString(model.PiperBackend))
	ttsModel, err := loader.Load(opts...)

	if err != nil {
 return "", nil, err
	}

	if ttsModel == nil {
 return "", nil, fmt.Errorf("could not load piper model")
 return "", nil, fmt.Errorf("could not load tts model %q", backendConfig.Model)
	}

	if err := os.MkdirAll(appConfig.AudioDir, 0750); err != nil {
Expand All@@ -45,22 +39,21 @@ func ModelTTS(
	fileName := utils.GenerateUniqueFileName(appConfig.AudioDir, "tts", ".wav")
	filePath := filepath.Join(appConfig.AudioDir, fileName)

	// If the model file is not empty, we pass it joined with the model path
	// We join the model name to the model path here. This seems to only be done for TTS and is HIGHLY suspect.
	// This should be addressed in a follow up PR soon.
	// Copying it over nearly verbatim, as TTS backends are not functional without this.
	modelPath := ""
	if modelFile != "" {
 // If the model file is not empty, we pass it joined with the model path
 // Checking first that it exists and is not outside ModelPath
 // TODO: we should actually first check if the modelFile is looking like
 // a FS path
 mp := filepath.Join(loader.ModelPath, modelFile)
 if _, err := os.Stat(mp); err == nil {
 if err := utils.VerifyPath(mp, appConfig.ModelPath); err != nil {
 return "", nil, err
 }
 modelPath = mp
 } else {
 modelPath = modelFile
	// Checking first that it exists and is not outside ModelPath
	// TODO: we should actually first check if the modelFile is looking like
	// a FS path
	mp := filepath.Join(loader.ModelPath, backendConfig.Model)
	if _, err := os.Stat(mp); err == nil {
 if err := utils.VerifyPath(mp, appConfig.ModelPath); err != nil {
 return "", nil, err
 }
 modelPath = mp
	} else {
 modelPath = backendConfig.Model // skip this step if it fails?????
	}

	res, err := ttsModel.TTS(context.Background(), &proto.TTSRequest{
Expand Down

38 changes: 38 additions & 0 deletions
core/backend/vad.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,38 @@
package backend

import (
	"context"

	"github.com/mudler/LocalAI/core/config"
	"github.com/mudler/LocalAI/core/schema"
	"github.com/mudler/LocalAI/pkg/grpc/proto"
	"github.com/mudler/LocalAI/pkg/model"
)

func VAD(request *schema.VADRequest,
	ctx context.Context,
	ml *model.ModelLoader,
	appConfig *config.ApplicationConfig,
	backendConfig config.BackendConfig) (*schema.VADResponse, error) {
	opts := ModelOptions(backendConfig, appConfig)
	vadModel, err := ml.Load(opts...)
	if err != nil {
 return nil, err
	}
	req := proto.VADRequest{
 Audio: request.Audio,
	}
	resp, err := vadModel.VAD(ctx, &req)
	if err != nil {
 return nil, err
	}

	segments := []schema.VADSegment{}
	for _, s := range resp.Segments {
 segments = append(segments, schema.VADSegment{Start: s.Start, End: s.End})
	}

	return &schema.VADResponse{
 Segments: segments,
	}, nil
}

3 changes: 2 additions & 1 deletion
core/cli/soundgeneration.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -86,13 +86,14 @@ func (t *SoundGenerationCMD) Run(ctx *cliContext.Context) error {
	options := config.BackendConfig{}
	options.SetDefaults()
	options.Backend = t.Backend
	options.Model = t.Model

	var inputFile *string
	if t.InputFile != "" {
 inputFile = &t.InputFile
	}

	filePath, _, err := backend.SoundGeneration(t.Model, text,
	filePath, _, err := backend.SoundGeneration(text,
 parseToFloat32Ptr(t.Duration), parseToFloat32Ptr(t.Temperature), &t.DoSample,
 inputFile, parseToInt32Ptr(t.InputFileSampleDivisor), ml, opts, options)

Expand Down

4 changes: 3 additions & 1 deletion
core/cli/tts.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -52,8 +52,10 @@ func (t *TTSCMD) Run(ctx *cliContext.Context) error {

	options := config.BackendConfig{}
	options.SetDefaults()
	options.Backend = t.Backend
	options.Model = t.Model

	filePath, _, err := backend.ModelTTS(t.Backend, text, t.Model, t.Voice, t.Language, ml, opts, options)
	filePath, _, err := backend.ModelTTS(text, t.Voice, t.Language, ml, opts, options)
	if err != nil {
 return err
	}
Expand Down

39 changes: 28 additions & 11 deletions
core/config/backend_config.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -437,19 +437,21 @@ func (c *BackendConfig) HasTemplate() bool {
type BackendConfigUsecases int

const (
	FLAG_ANY BackendConfigUsecases = 0b000000000
	FLAG_CHAT BackendConfigUsecases = 0b000000001
	FLAG_COMPLETION BackendConfigUsecases = 0b000000010
	FLAG_EDIT BackendConfigUsecases = 0b000000100
	FLAG_EMBEDDINGS BackendConfigUsecases = 0b000001000
	FLAG_RERANK BackendConfigUsecases = 0b000010000
	FLAG_IMAGE BackendConfigUsecases = 0b000100000
	FLAG_TRANSCRIPT BackendConfigUsecases = 0b001000000
	FLAG_TTS BackendConfigUsecases = 0b010000000
	FLAG_SOUND_GENERATION BackendConfigUsecases = 0b100000000
	FLAG_ANY BackendConfigUsecases = 0b00000000000
	FLAG_CHAT BackendConfigUsecases = 0b00000000001
	FLAG_COMPLETION BackendConfigUsecases = 0b00000000010
	FLAG_EDIT BackendConfigUsecases = 0b00000000100
	FLAG_EMBEDDINGS BackendConfigUsecases = 0b00000001000
	FLAG_RERANK BackendConfigUsecases = 0b00000010000
	FLAG_IMAGE BackendConfigUsecases = 0b00000100000
	FLAG_TRANSCRIPT BackendConfigUsecases = 0b00001000000
	FLAG_TTS BackendConfigUsecases = 0b00010000000
	FLAG_SOUND_GENERATION BackendConfigUsecases = 0b00100000000
	FLAG_TOKENIZE BackendConfigUsecases = 0b01000000000
	FLAG_VAD BackendConfigUsecases = 0b10000000000

	// Common Subsets
	FLAG_LLM BackendConfigUsecases = FLAG_CHAT & FLAG_COMPLETION & FLAG_EDIT
	FLAG_LLM BackendConfigUsecases = FLAG_CHAT | FLAG_COMPLETION | FLAG_EDIT
)

func GetAllBackendConfigUsecases() map[string]BackendConfigUsecases {
Expand All@@ -464,6 +466,8 @@ func GetAllBackendConfigUsecases() map[string]BackendConfigUsecases {
 "FLAG_TRANSCRIPT": FLAG_TRANSCRIPT,
 "FLAG_TTS": FLAG_TTS,
 "FLAG_SOUND_GENERATION": FLAG_SOUND_GENERATION,
 "FLAG_TOKENIZE": FLAG_TOKENIZE,
 "FLAG_VAD": FLAG_VAD,
 "FLAG_LLM": FLAG_LLM,
	}
}
Expand DownExpand Up@@ -549,5 +553,18 @@ func (c *BackendConfig) GuessUsecases(u BackendConfigUsecases) bool {
 }
	}

	if (u & FLAG_TOKENIZE) == FLAG_TOKENIZE {
 tokenizeCapableBackends := []string{"llama.cpp", "rwkv"}
 if !slices.Contains(tokenizeCapableBackends, c.Backend) {
 return false
 }
	}

	if (u & FLAG_VAD) == FLAG_VAD {
 if c.Backend != "silero-vad" {
@mudlermudlerFeb 6, 2025•

edited

Loading

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

note for later: at some point we should think about having these constants defined to be re-usable. There are some repetitions as well in the model initializer
@dave-gray101dave-gray101Feb 8, 2025

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed - probably worth doing that as followup if you're OK with that
@mudlermudlerFeb 10, 2025

Copy link


Copy Markdown

Owner
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

definitely, was just a reminder/note
 return false
 }
	}

	return true
}
Loading