mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-05-02 00:00:27 -05:00
Code Issues Packages Projects Releases Wiki Activity

feat: refactor build process, drop embedded backends (#5875)

Browse Source 
* feat: split remaining backends and drop embedded backends

- Drop silero-vad, huggingface, and stores backend from embedded
  binaries
- Refactor Makefile and Dockerfile to avoid building grpc backends
- Drop golang code that was used to embed backends
- Simplify building by using goreleaser

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(gallery): be specific with llama-cpp backend templates

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(docs): update

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(ci): minor fixes

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore: drop all ffmpeg references

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix: run protogen-go

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Always enable p2p mode

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Update gorelease file

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(stores): do not always load

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fix linting issues

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Simplify

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Mac OS fixup

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
2025-07-22 16:31:04 +02:00
committed by GitHub
parent e29b2c3aff
commit 98e5291afc
118 changed files with 631 additions and 1339 deletions
Download Patch File Download Diff File Expand all files Collapse all files
core/cli/context/context.go
-7
View File
@@ -1,13 +1,6 @@
package cliContext
import (
rice "github.com/GeertJohan/go.rice"
)
type Context struct {
Debug bool `env:"LOCALAI_DEBUG,DEBUG" default:"false" hidden:"" help:"DEPRECATED, use --log-level=debug instead. Enable debug logging"`
LogLevel *string `env:"LOCALAI_LOG_LEVEL" enum:"error,warn,info,debug,trace" help:"Set the level of logs to output [${enum}]"`
// This field is not a command line argument/flag, the struct tag excludes it from the parsed CLI
BackendAssets *rice.Box `kong:"-"`
}
core/cli/run.go
-5
View File
@@ -23,7 +23,6 @@ type RunCMD struct {
ExternalBackends []string `env:"LOCALAI_EXTERNAL_BACKENDS,EXTERNAL_BACKENDS" help:"A list of external backends to load from gallery on boot" group:"backends"`
BackendsPath string `env:"LOCALAI_BACKENDS_PATH,BACKENDS_PATH" type:"path" default:"${basepath}/backends" help:"Path containing backends used for inferencing" group:"backends"`
ModelsPath string `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
BackendAssetsPath string `env:"LOCALAI_BACKEND_ASSETS_PATH,BACKEND_ASSETS_PATH" type:"path" default:"/tmp/localai/backend_data" help:"Path used to extract libraries that are required by some of the backends in runtime" group:"storage"`
GeneratedContentPath string `env:"LOCALAI_GENERATED_CONTENT_PATH,GENERATED_CONTENT_PATH" type:"path" default:"/tmp/generated/content" help:"Location for generated content (e.g. images, audio, videos)" group:"storage"`
UploadPath string `env:"LOCALAI_UPLOAD_PATH,UPLOAD_PATH" type:"path" default:"/tmp/localai/upload" help:"Path to store uploads from files api" group:"storage"`
ConfigPath string `env:"LOCALAI_CONFIG_PATH,CONFIG_PATH" default:"/tmp/localai/config" group:"storage"`
@@ -46,7 +45,6 @@ type RunCMD struct {
Address string `env:"LOCALAI_ADDRESS,ADDRESS" default:":8080" help:"Bind address for the API server" group:"api"`
CORS bool `env:"LOCALAI_CORS,CORS" help:"" group:"api"`
CORSAllowOrigins string `env:"LOCALAI_CORS_ALLOW_ORIGINS,CORS_ALLOW_ORIGINS" group:"api"`
LibraryPath string `env:"LOCALAI_LIBRARY_PATH,LIBRARY_PATH" help:"Path to the library directory (for e.g. external libraries used by backends)" default:"/usr/share/local-ai/libs" group:"backends"`
CSRF bool `env:"LOCALAI_CSRF" help:"Enables fiber CSRF middleware" group:"api"`
UploadLimit int `env:"LOCALAI_UPLOAD_LIMIT,UPLOAD_LIMIT" default:"15" help:"Default upload-limit in MB" group:"api"`
APIKeys []string `env:"LOCALAI_API_KEY,API_KEY" help:"List of API Keys to enable API authentication. When this is set, all the requests must be authenticated with one of these API keys" group:"api"`
@@ -99,10 +97,7 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
config.WithCors(r.CORS),
config.WithCorsAllowOrigins(r.CORSAllowOrigins),
config.WithCsrf(r.CSRF),
config.WithLibPath(r.LibraryPath),
config.WithThreads(r.Threads),
config.WithBackendAssets(ctx.BackendAssets),
config.WithBackendAssetsOutput(r.BackendAssetsPath),
config.WithUploadLimitMB(r.UploadLimit),
config.WithApiKeys(r.APIKeys),
config.WithModelsURL(append(r.Models, r.ModelArgs...)...),
core/cli/soundgeneration.go
+1 -4
View File
@@ -27,7 +27,6 @@ type SoundGenerationCMD struct {
DoSample bool `short:"s" default:"true" help:"Enables sampling from the model. Better quality at the cost of speed. Defaults to enabled."`
OutputFile string `short:"o" type:"path" help:"The path to write the output wav file"`
ModelsPath string `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
BackendAssetsPath string `env:"LOCALAI_BACKEND_ASSETS_PATH,BACKEND_ASSETS_PATH" type:"path" default:"/tmp/localai/backend_data" help:"Path used to extract libraries that are required by some of the backends in runtime" group:"storage"`
ExternalGRPCBackends []string `env:"LOCALAI_EXTERNAL_GRPC_BACKENDS,EXTERNAL_GRPC_BACKENDS" help:"A list of external grpc backends" group:"backends"`
}
@@ -51,11 +50,10 @@ func parseToInt32Ptr(input string) *int32 {
func (t *SoundGenerationCMD) Run(ctx *cliContext.Context) error {
outputFile := t.OutputFile
outputDir := t.BackendAssetsPath
outputDir := os.TempDir()
if outputFile != "" {
outputDir = filepath.Dir(outputFile)
}
text := strings.Join(t.Text, " ")
externalBackends := make(map[string]string)
@@ -71,7 +69,6 @@ func (t *SoundGenerationCMD) Run(ctx *cliContext.Context) error {
ModelPath: t.ModelsPath,
Context: context.Background(),
GeneratedContentDir: outputDir,
AssetsDestination: t.BackendAssetsPath,
ExternalGRPCBackends: externalBackends,
}
ml := model.NewModelLoader(opts.ModelPath, opts.SingleBackend)
core/cli/transcript.go
+8 -10
View File
@@ -15,20 +15,18 @@ import (
type TranscriptCMD struct {
Filename string `arg:""`
Backend string `short:"b" default:"whisper" help:"Backend to run the transcription model"`
Model string `short:"m" required:"" help:"Model name to run the TTS"`
Language string `short:"l" help:"Language of the audio file"`
Translate bool `short:"c" help:"Translate the transcription to english"`
Threads int `short:"t" default:"1" help:"Number of threads used for parallel computation"`
ModelsPath string `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
BackendAssetsPath string `env:"LOCALAI_BACKEND_ASSETS_PATH,BACKEND_ASSETS_PATH" type:"path" default:"/tmp/localai/backend_data" help:"Path used to extract libraries that are required by some of the backends in runtime" group:"storage"`
Backend string `short:"b" default:"whisper" help:"Backend to run the transcription model"`
Model string `short:"m" required:"" help:"Model name to run the TTS"`
Language string `short:"l" help:"Language of the audio file"`
Translate bool `short:"c" help:"Translate the transcription to english"`
Threads int `short:"t" default:"1" help:"Number of threads used for parallel computation"`
ModelsPath string `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
}
func (t *TranscriptCMD) Run(ctx *cliContext.Context) error {
opts := &config.ApplicationConfig{
ModelPath: t.ModelsPath,
Context: context.Background(),
AssetsDestination: t.BackendAssetsPath,
ModelPath: t.ModelsPath,
Context: context.Background(),
}
cl := config.NewBackendConfigLoader(t.ModelsPath)
core/cli/tts.go
+7 -9
View File
@@ -17,18 +17,17 @@ import (
type TTSCMD struct {
Text []string `arg:""`
Backend string `short:"b" default:"piper" help:"Backend to run the TTS model"`
Model string `short:"m" required:"" help:"Model name to run the TTS"`
Voice string `short:"v" help:"Voice name to run the TTS"`
Language string `short:"l" help:"Language to use with the TTS"`
OutputFile string `short:"o" type:"path" help:"The path to write the output wav file"`
ModelsPath string `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
BackendAssetsPath string `env:"LOCALAI_BACKEND_ASSETS_PATH,BACKEND_ASSETS_PATH" type:"path" default:"/tmp/localai/backend_data" help:"Path used to extract libraries that are required by some of the backends in runtime" group:"storage"`
Backend string `short:"b" default:"piper" help:"Backend to run the TTS model"`
Model string `short:"m" required:"" help:"Model name to run the TTS"`
Voice string `short:"v" help:"Voice name to run the TTS"`
Language string `short:"l" help:"Language to use with the TTS"`
OutputFile string `short:"o" type:"path" help:"The path to write the output wav file"`
ModelsPath string `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
}
func (t *TTSCMD) Run(ctx *cliContext.Context) error {
outputFile := t.OutputFile
outputDir := t.BackendAssetsPath
outputDir := os.TempDir()
if outputFile != "" {
outputDir = filepath.Dir(outputFile)
}
@@ -39,7 +38,6 @@ func (t *TTSCMD) Run(ctx *cliContext.Context) error {
ModelPath: t.ModelsPath,
Context: context.Background(),
GeneratedContentDir: outputDir,
AssetsDestination: t.BackendAssetsPath,
}
ml := model.NewModelLoader(opts.ModelPath, opts.SingleBackend)
core/cli/worker/worker.go
+1 -1
View File
@@ -1,7 +1,7 @@
package worker
type WorkerFlags struct {
BackendAssetsPath string `env:"LOCALAI_BACKEND_ASSETS_PATH,BACKEND_ASSETS_PATH" type:"path" default:"/tmp/localai/backend_data" help:"Path used to extract libraries that are required by some of the backends in runtime" group:"storage"`
BackendsPath string `env:"LOCALAI_BACKENDS_PATH,BACKENDS_PATH" type:"path" default:"${basepath}/backends" help:"Path containing backends used for inferencing" group:"backends"`
ExtraLLamaCPPArgs string `name:"llama-cpp-args" env:"LOCALAI_EXTRA_LLAMA_CPP_ARGS,EXTRA_LLAMA_CPP_ARGS" help:"Extra arguments to pass to llama-cpp-rpc-server"`
}
core/cli/worker/worker_llamacpp.go
+1 -10
View File
@@ -9,8 +9,6 @@ import (
cliContext "github.com/mudler/LocalAI/core/cli/context"
"github.com/mudler/LocalAI/core/gallery"
"github.com/mudler/LocalAI/pkg/assets"
"github.com/mudler/LocalAI/pkg/library"
"github.com/rs/zerolog/log"
)
@@ -47,24 +45,17 @@ func findLLamaCPPBackend(backendSystemPath string) (string, error) {
}
func (r *LLamaCPP) Run(ctx *cliContext.Context) error {
// Extract files from the embedded FS
err := assets.ExtractFiles(ctx.BackendAssets, r.BackendAssetsPath)
log.Debug().Msgf("Extracting backend assets files to %s", r.BackendAssetsPath)
if err != nil {
log.Warn().Msgf("Failed extracting backend assets files: %s (might be required for some backends to work properly)", err)
}
if len(os.Args) < 4 {
return fmt.Errorf("usage: local-ai worker llama-cpp-rpc -- <llama-rpc-server-args>")
}
grpcProcess, err := findLLamaCPPBackend(r.BackendAssetsPath)
grpcProcess, err := findLLamaCPPBackend(r.BackendsPath)
if err != nil {
return err
}
args := strings.Split(r.ExtraLLamaCPPArgs, " ")
args, grpcProcess = library.LoadLDSO(r.BackendAssetsPath, args, grpcProcess)
args = append([]string{grpcProcess}, args...)
return syscall.Exec(
core/cli/worker/worker_nop2p.go
-16
View File
@@ -1,16 +0,0 @@
//go:build !p2p
// +build !p2p
package worker
import (
"fmt"
cliContext "github.com/mudler/LocalAI/core/cli/context"
)
type P2P struct{}
func (r *P2P) Run(ctx *cliContext.Context) error {
return fmt.Errorf("p2p mode is not enabled in this build")
}
core/cli/worker/worker_p2p.go
+1 -14
View File
@@ -1,6 +1,3 @@
//go:build p2p
// +build p2p
package worker
import (
@@ -13,8 +10,6 @@ import (
cliContext "github.com/mudler/LocalAI/core/cli/context"
"github.com/mudler/LocalAI/core/p2p"
"github.com/mudler/LocalAI/pkg/assets"
"github.com/mudler/LocalAI/pkg/library"
"github.com/phayes/freeport"
"github.com/rs/zerolog/log"
)
@@ -29,12 +24,6 @@ type P2P struct {
}
func (r *P2P) Run(ctx *cliContext.Context) error {
// Extract files from the embedded FS
err := assets.ExtractFiles(ctx.BackendAssets, r.BackendAssetsPath)
log.Debug().Msgf("Extracting backend assets files to %s", r.BackendAssetsPath)
if err != nil {
log.Warn().Msgf("Failed extracting backend assets files: %s (might be required for some backends to work properly)", err)
}
// Check if the token is set
// as we always need it.
@@ -71,7 +60,7 @@ func (r *P2P) Run(ctx *cliContext.Context) error {
for {
log.Info().Msgf("Starting llama-cpp-rpc-server on '%s:%d'", address, port)
grpcProcess, err := findLLamaCPPBackend(r.BackendAssetsPath)
grpcProcess, err := findLLamaCPPBackend(r.BackendsPath)
if err != nil {
log.Error().Err(err).Msg("Failed to find llama-cpp-rpc-server")
return
@@ -85,8 +74,6 @@ func (r *P2P) Run(ctx *cliContext.Context) error {
args := append([]string{"--host", address, "--port", fmt.Sprint(port)}, extraArgs...)
log.Debug().Msgf("Starting llama-cpp-rpc-server on '%s:%d' with args: %+v (%d)", address, port, args, len(args))
args, grpcProcess = library.LoadLDSO(r.BackendAssetsPath, args, grpcProcess)
cmd := exec.Command(
grpcProcess, args...,
)