LocalAI/core/services/gallery.go
Ettore Di Giacinto 2d64269763
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 14:56:52 +02:00

85 lines
2.1 KiB
Go

package services
import (
"context"
"fmt"
"sync"
"github.com/mudler/LocalAI/core/config"
"github.com/mudler/LocalAI/core/gallery"
"github.com/mudler/LocalAI/pkg/model"
)
type GalleryService struct {
appConfig *config.ApplicationConfig
sync.Mutex
ModelGalleryChannel chan GalleryOp[gallery.GalleryModel]
BackendGalleryChannel chan GalleryOp[gallery.GalleryBackend]
modelLoader *model.ModelLoader
statuses map[string]*GalleryOpStatus
}
func NewGalleryService(appConfig *config.ApplicationConfig, ml *model.ModelLoader) *GalleryService {
return &GalleryService{
appConfig: appConfig,
ModelGalleryChannel: make(chan GalleryOp[gallery.GalleryModel]),
BackendGalleryChannel: make(chan GalleryOp[gallery.GalleryBackend]),
modelLoader: ml,
statuses: make(map[string]*GalleryOpStatus),
}
}
func (g *GalleryService) UpdateStatus(s string, op *GalleryOpStatus) {
g.Lock()
defer g.Unlock()
g.statuses[s] = op
}
func (g *GalleryService) GetStatus(s string) *GalleryOpStatus {
g.Lock()
defer g.Unlock()
return g.statuses[s]
}
func (g *GalleryService) GetAllStatus() map[string]*GalleryOpStatus {
g.Lock()
defer g.Unlock()
return g.statuses
}
func (g *GalleryService) Start(c context.Context, cl *config.BackendConfigLoader) {
// updates the status with an error
var updateError func(id string, e error)
if !g.appConfig.OpaqueErrors {
updateError = func(id string, e error) {
g.UpdateStatus(id, &GalleryOpStatus{Error: e, Processed: true, Message: "error: " + e.Error()})
}
} else {
updateError = func(id string, _ error) {
g.UpdateStatus(id, &GalleryOpStatus{Error: fmt.Errorf("an error occurred"), Processed: true})
}
}
go func() {
for {
select {
case <-c.Done():
return
case op := <-g.BackendGalleryChannel:
err := g.backendHandler(&op)
if err != nil {
updateError(op.ID, err)
}
case op := <-g.ModelGalleryChannel:
err := g.modelHandler(&op, cl)
if err != nil {
updateError(op.ID, err)
}
}
}
}()
}