LocalAI/core/http/endpoints/localai/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

156 lines
5.1 KiB
Go

package localai
import (
"encoding/json"
"fmt"
"github.com/gofiber/fiber/v2"
"github.com/google/uuid"
"github.com/mudler/LocalAI/core/config"
"github.com/mudler/LocalAI/core/gallery"
"github.com/mudler/LocalAI/core/http/utils"
"github.com/mudler/LocalAI/core/schema"
"github.com/mudler/LocalAI/core/services"
"github.com/rs/zerolog/log"
)
type ModelGalleryEndpointService struct {
galleries []config.Gallery
modelPath string
galleryApplier *services.GalleryService
}
type GalleryModel struct {
ID string `json:"id"`
gallery.GalleryModel
}
func CreateModelGalleryEndpointService(galleries []config.Gallery, modelPath string, galleryApplier *services.GalleryService) ModelGalleryEndpointService {
return ModelGalleryEndpointService{
galleries: galleries,
modelPath: modelPath,
galleryApplier: galleryApplier,
}
}
// GetOpStatusEndpoint returns the job status
// @Summary Returns the job status
// @Success 200 {object} services.GalleryOpStatus "Response"
// @Router /models/jobs/{uuid} [get]
func (mgs *ModelGalleryEndpointService) GetOpStatusEndpoint() func(c *fiber.Ctx) error {
return func(c *fiber.Ctx) error {
status := mgs.galleryApplier.GetStatus(c.Params("uuid"))
if status == nil {
return fmt.Errorf("could not find any status for ID")
}
return c.JSON(status)
}
}
// GetAllStatusEndpoint returns all the jobs status progress
// @Summary Returns all the jobs status progress
// @Success 200 {object} map[string]services.GalleryOpStatus "Response"
// @Router /models/jobs [get]
func (mgs *ModelGalleryEndpointService) GetAllStatusEndpoint() func(c *fiber.Ctx) error {
return func(c *fiber.Ctx) error {
return c.JSON(mgs.galleryApplier.GetAllStatus())
}
}
// ApplyModelGalleryEndpoint installs a new model to a LocalAI instance from the model gallery
// @Summary Install models to LocalAI.
// @Param request body GalleryModel true "query params"
// @Success 200 {object} schema.GalleryResponse "Response"
// @Router /models/apply [post]
func (mgs *ModelGalleryEndpointService) ApplyModelGalleryEndpoint() func(c *fiber.Ctx) error {
return func(c *fiber.Ctx) error {
input := new(GalleryModel)
// Get input data from the request body
if err := c.BodyParser(input); err != nil {
return err
}
uuid, err := uuid.NewUUID()
if err != nil {
return err
}
mgs.galleryApplier.ModelGalleryChannel <- services.GalleryOp[gallery.GalleryModel]{
Req: input.GalleryModel,
ID: uuid.String(),
GalleryElementName: input.ID,
Galleries: mgs.galleries,
}
return c.JSON(schema.GalleryResponse{ID: uuid.String(), StatusURL: fmt.Sprintf("%smodels/jobs/%s", utils.BaseURL(c), uuid.String())})
}
}
// DeleteModelGalleryEndpoint lets delete models from a LocalAI instance
// @Summary delete models to LocalAI.
// @Param name path string true "Model name"
// @Success 200 {object} schema.GalleryResponse "Response"
// @Router /models/delete/{name} [post]
func (mgs *ModelGalleryEndpointService) DeleteModelGalleryEndpoint() func(c *fiber.Ctx) error {
return func(c *fiber.Ctx) error {
modelName := c.Params("name")
mgs.galleryApplier.ModelGalleryChannel <- services.GalleryOp[gallery.GalleryModel]{
Delete: true,
GalleryElementName: modelName,
}
uuid, err := uuid.NewUUID()
if err != nil {
return err
}
return c.JSON(schema.GalleryResponse{ID: uuid.String(), StatusURL: fmt.Sprintf("%smodels/jobs/%s", utils.BaseURL(c), uuid.String())})
}
}
// ListModelFromGalleryEndpoint list the available models for installation from the active galleries
// @Summary List installable models.
// @Success 200 {object} []gallery.GalleryModel "Response"
// @Router /models/available [get]
func (mgs *ModelGalleryEndpointService) ListModelFromGalleryEndpoint() func(c *fiber.Ctx) error {
return func(c *fiber.Ctx) error {
models, err := gallery.AvailableGalleryModels(mgs.galleries, mgs.modelPath)
if err != nil {
log.Error().Err(err).Msg("could not list models from galleries")
return err
}
log.Debug().Msgf("Available %d models from %d galleries\n", len(models), len(mgs.galleries))
m := []gallery.Metadata{}
for _, mm := range models {
m = append(m, mm.Metadata)
}
log.Debug().Msgf("Models %#v", m)
dat, err := json.Marshal(m)
if err != nil {
return fmt.Errorf("could not marshal models: %w", err)
}
return c.Send(dat)
}
}
// ListModelGalleriesEndpoint list the available galleries configured in LocalAI
// @Summary List all Galleries
// @Success 200 {object} []config.Gallery "Response"
// @Router /models/galleries [get]
// NOTE: This is different (and much simpler!) than above! This JUST lists the model galleries that have been loaded, not their contents!
func (mgs *ModelGalleryEndpointService) ListModelGalleriesEndpoint() func(c *fiber.Ctx) error {
return func(c *fiber.Ctx) error {
log.Debug().Msgf("Listing model galleries %+v", mgs.galleries)
dat, err := json.Marshal(mgs.galleries)
if err != nil {
return err
}
return c.Send(dat)
}
}