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>
2025-06-17 16:25:00 +00:00 · 2025-06-15 14:56:52 +02:00 · 2025-06-15 14:56:52 +02:00 · 2d64269763
commit 2d64269763
parent a7a6020328
114 changed files with 3996 additions and 1382 deletions
--- a/core/services/operation.go
+++ b/core/services/operation.go
@ -0,0 +1,81 @@
+package services
+
+import (
+	"github.com/mudler/LocalAI/core/config"
+	"github.com/mudler/LocalAI/pkg/xsync"
+)
+
+type GalleryOp[T any] struct {
+	ID                 string
+	GalleryElementName string
+	Delete             bool
+
+	Req       T
+	Galleries []config.Gallery
+}
+
+type GalleryOpStatus struct {
+	Deletion           bool    `json:"deletion"` // Deletion is true if the operation is a deletion
+	FileName           string  `json:"file_name"`
+	Error              error   `json:"error"`
+	Processed          bool    `json:"processed"`
+	Message            string  `json:"message"`
+	Progress           float64 `json:"progress"`
+	TotalFileSize      string  `json:"file_size"`
+	DownloadedFileSize string  `json:"downloaded_size"`
+	GalleryElementName string  `json:"gallery_element_name"`
+}
+
+type OpCache struct {
+	status         *xsync.SyncedMap[string, string]
+	galleryService *GalleryService
+}
+
+func NewOpCache(galleryService *GalleryService) *OpCache {
+	return &OpCache{
+		status:         xsync.NewSyncedMap[string, string](),
+		galleryService: galleryService,
+	}
+}
+
+func (m *OpCache) Set(key string, value string) {
+	m.status.Set(key, value)
+}
+
+func (m *OpCache) Get(key string) string {
+	return m.status.Get(key)
+}
+
+func (m *OpCache) DeleteUUID(uuid string) {
+	for _, k := range m.status.Keys() {
+		if m.status.Get(k) == uuid {
+			m.status.Delete(k)
+		}
+	}
+}
+
+func (m *OpCache) Map() map[string]string {
+	return m.status.Map()
+}
+
+func (m *OpCache) Exists(key string) bool {
+	return m.status.Exists(key)
+}
+
+func (m *OpCache) GetStatus() (map[string]string, map[string]string) {
+	processingModelsData := m.Map()
+
+	taskTypes := map[string]string{}
+
+	for k, v := range processingModelsData {
+		status := m.galleryService.GetStatus(v)
+		taskTypes[k] = "Installation"
+		if status != nil && status.Deletion {
+			taskTypes[k] = "Deletion"
+		} else if status == nil {
+			taskTypes[k] = "Waiting"
+		}
+	}
+
+	return processingModelsData, taskTypes
+}