LocalAI/core/application/startup.go

180 lines
5.7 KiB
Go
Raw Normal View History

package application
import (
"fmt"
"os"
"github.com/mudler/LocalAI/core/backend"
"github.com/mudler/LocalAI/core/config"
feat: Add backend gallery (#5607) * feat: Add backend gallery This PR add support to manage backends as similar to models. There is now available a backend gallery which can be used to install and remove extra backends. The backend gallery can be configured similarly as a model gallery, and API calls allows to install and remove new backends in runtime, and as well during the startup phase of LocalAI. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add backends docs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * wip: Backend Dockerfile for python backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat: drop extras images, build python backends separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixup on all backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Tweaks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop old backends leftovers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Move dockerfile upper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix proto Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Feature dropped for consistency - we prefer model galleries Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add missing packages in the build image Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * exllama is ponly available on cublas Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pin torch on chatterbox Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups to index Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Debug CI * Install accellerators deps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add target arch * Add cuda minor version Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use self-hosted runners Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: use quay for test images Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups for vllm and chatterbox Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Small fixups on CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chatterbox is only available for nvidia Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Simplify CI builds Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt test, use qwen3 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(model gallery): add jina-reranker-v1-tiny-en-gguf Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(gguf-parser): recover from potential panics that can happen while reading ggufs with gguf-parser Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use reranker from llama.cpp in AIO images Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Limit concurrent jobs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2025-06-15 12:56:52 +00:00
"github.com/mudler/LocalAI/core/gallery"
"github.com/mudler/LocalAI/core/services"
"github.com/mudler/LocalAI/internal"
coreStartup "github.com/mudler/LocalAI/core/startup"
"github.com/mudler/LocalAI/pkg/model"
"github.com/mudler/LocalAI/pkg/xsysinfo"
"github.com/rs/zerolog/log"
)
func New(opts ...config.AppOption) (*Application, error) {
options := config.NewApplicationConfig(opts...)
application := newApplication(options)
log.Info().Msgf("Starting LocalAI using %d threads, with models path: %s", options.Threads, options.ModelPath)
log.Info().Msgf("LocalAI version: %s", internal.PrintableVersion())
caps, err := xsysinfo.CPUCapabilities()
if err == nil {
log.Debug().Msgf("CPU capabilities: %v", caps)
}
gpus, err := xsysinfo.GPUs()
if err == nil {
log.Debug().Msgf("GPU count: %d", len(gpus))
for _, gpu := range gpus {
log.Debug().Msgf("GPU: %s", gpu.String())
}
}
// Make sure directories exists
if options.ModelPath == "" {
return nil, fmt.Errorf("options.ModelPath cannot be empty")
}
err = os.MkdirAll(options.ModelPath, 0750)
if err != nil {
return nil, fmt.Errorf("unable to create ModelPath: %q", err)
}
if options.GeneratedContentDir != "" {
err := os.MkdirAll(options.GeneratedContentDir, 0750)
if err != nil {
return nil, fmt.Errorf("unable to create ImageDir: %q", err)
}
}
if options.UploadDir != "" {
err := os.MkdirAll(options.UploadDir, 0750)
if err != nil {
return nil, fmt.Errorf("unable to create UploadDir: %q", err)
}
}
if err := coreStartup.InstallModels(options.Galleries, options.BackendGalleries, options.ModelPath, options.BackendsPath, options.EnforcePredownloadScans, options.AutoloadBackendGalleries, nil, options.ModelsURL...); err != nil {
log.Error().Err(err).Msg("error installing models")
}
if err := coreStartup.InstallExternalBackends(options.BackendGalleries, options.BackendsPath, nil, options.ExternalBackends...); err != nil {
feat: Add backend gallery (#5607) * feat: Add backend gallery This PR add support to manage backends as similar to models. There is now available a backend gallery which can be used to install and remove extra backends. The backend gallery can be configured similarly as a model gallery, and API calls allows to install and remove new backends in runtime, and as well during the startup phase of LocalAI. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add backends docs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * wip: Backend Dockerfile for python backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat: drop extras images, build python backends separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixup on all backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Tweaks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop old backends leftovers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Move dockerfile upper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix proto Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Feature dropped for consistency - we prefer model galleries Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add missing packages in the build image Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * exllama is ponly available on cublas Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pin torch on chatterbox Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups to index Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Debug CI * Install accellerators deps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add target arch * Add cuda minor version Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use self-hosted runners Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: use quay for test images Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups for vllm and chatterbox Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Small fixups on CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chatterbox is only available for nvidia Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Simplify CI builds Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt test, use qwen3 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(model gallery): add jina-reranker-v1-tiny-en-gguf Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(gguf-parser): recover from potential panics that can happen while reading ggufs with gguf-parser Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use reranker from llama.cpp in AIO images Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Limit concurrent jobs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2025-06-15 12:56:52 +00:00
log.Error().Err(err).Msg("error installing external backends")
}
configLoaderOpts := options.ToConfigLoaderOptions()
if err := application.BackendLoader().LoadBackendConfigsFromPath(options.ModelPath, configLoaderOpts...); err != nil {
log.Error().Err(err).Msg("error loading config files")
}
feat: Add backend gallery (#5607) * feat: Add backend gallery This PR add support to manage backends as similar to models. There is now available a backend gallery which can be used to install and remove extra backends. The backend gallery can be configured similarly as a model gallery, and API calls allows to install and remove new backends in runtime, and as well during the startup phase of LocalAI. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add backends docs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * wip: Backend Dockerfile for python backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat: drop extras images, build python backends separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixup on all backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Tweaks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop old backends leftovers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Move dockerfile upper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix proto Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Feature dropped for consistency - we prefer model galleries Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add missing packages in the build image Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * exllama is ponly available on cublas Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pin torch on chatterbox Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups to index Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Debug CI * Install accellerators deps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add target arch * Add cuda minor version Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use self-hosted runners Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: use quay for test images Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups for vllm and chatterbox Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Small fixups on CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chatterbox is only available for nvidia Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Simplify CI builds Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt test, use qwen3 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(model gallery): add jina-reranker-v1-tiny-en-gguf Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(gguf-parser): recover from potential panics that can happen while reading ggufs with gguf-parser Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use reranker from llama.cpp in AIO images Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Limit concurrent jobs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2025-06-15 12:56:52 +00:00
if err := gallery.RegisterBackends(options.BackendsPath, application.ModelLoader()); err != nil {
log.Error().Err(err).Msg("error registering external backends")
}
if options.ConfigFile != "" {
if err := application.BackendLoader().LoadMultipleBackendConfigsSingleFile(options.ConfigFile, configLoaderOpts...); err != nil {
log.Error().Err(err).Msg("error loading config file")
}
}
if err := application.BackendLoader().Preload(options.ModelPath); err != nil {
log.Error().Err(err).Msg("error downloading models")
}
if options.PreloadJSONModels != "" {
if err := services.ApplyGalleryFromString(options.ModelPath, options.BackendsPath, options.EnforcePredownloadScans, options.AutoloadBackendGalleries, options.Galleries, options.BackendGalleries, options.PreloadJSONModels); err != nil {
return nil, err
}
}
if options.PreloadModelsFromPath != "" {
if err := services.ApplyGalleryFromFile(options.ModelPath, options.BackendsPath, options.EnforcePredownloadScans, options.AutoloadBackendGalleries, options.Galleries, options.BackendGalleries, options.PreloadModelsFromPath); err != nil {
return nil, err
}
}
if options.Debug {
for _, v := range application.BackendLoader().GetAllBackendConfigs() {
log.Debug().Msgf("Model: %s (config: %+v)", v.Name, v)
}
}
// turn off any process that was started by GRPC if the context is canceled
go func() {
<-options.Context.Done()
log.Debug().Msgf("Context canceled, shutting down")
err := application.ModelLoader().StopAllGRPC()
if err != nil {
log.Error().Err(err).Msg("error while stopping all grpc backends")
}
}()
if options.WatchDog {
wd := model.NewWatchDog(
application.ModelLoader(),
options.WatchDogBusyTimeout,
options.WatchDogIdleTimeout,
options.WatchDogBusy,
options.WatchDogIdle)
application.ModelLoader().SetWatchDog(wd)
go wd.Run()
go func() {
<-options.Context.Done()
log.Debug().Msgf("Context canceled, shutting down")
wd.Shutdown()
}()
}
if options.LoadToMemory != nil && !options.SingleBackend {
for _, m := range options.LoadToMemory {
cfg, err := application.BackendLoader().LoadBackendConfigFileByNameDefaultOptions(m, options)
if err != nil {
return nil, err
}
log.Debug().Msgf("Auto loading model %s into memory from file: %s", m, cfg.Model)
o := backend.ModelOptions(*cfg, options)
var backendErr error
_, backendErr = application.ModelLoader().Load(o...)
if backendErr != nil {
return nil, err
}
}
}
// Watch the configuration directory
startWatcher(options)
log.Info().Msg("core/startup process completed!")
return application, nil
}
func startWatcher(options *config.ApplicationConfig) {
if options.DynamicConfigsDir == "" {
// No need to start the watcher if the directory is not set
return
}
if _, err := os.Stat(options.DynamicConfigsDir); err != nil {
if os.IsNotExist(err) {
// We try to create the directory if it does not exist and was specified
if err := os.MkdirAll(options.DynamicConfigsDir, 0700); err != nil {
log.Error().Err(err).Msg("failed creating DynamicConfigsDir")
}
} else {
// something else happened, we log the error and don't start the watcher
log.Error().Err(err).Msg("failed to read DynamicConfigsDir, watcher will not be started")
return
}
}
configHandler := newConfigFileHandler(options)
if err := configHandler.Watch(); err != nil {
log.Error().Err(err).Msg("failed creating watcher")
}
}