mirror of
https://github.com/mudler/LocalAI.git
synced 2025-06-17 16:25:00 +00:00

* 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>
138 lines
4.7 KiB
Go
138 lines
4.7 KiB
Go
package startup
|
|
|
|
import (
|
|
"errors"
|
|
"fmt"
|
|
"os"
|
|
"path/filepath"
|
|
"strings"
|
|
|
|
"github.com/mudler/LocalAI/core/config"
|
|
"github.com/mudler/LocalAI/core/gallery"
|
|
"github.com/mudler/LocalAI/pkg/downloader"
|
|
"github.com/mudler/LocalAI/pkg/utils"
|
|
"github.com/rs/zerolog/log"
|
|
)
|
|
|
|
// InstallModels will preload models from the given list of URLs and galleries
|
|
// It will download the model if it is not already present in the model path
|
|
// It will also try to resolve if the model is an embedded model YAML configuration
|
|
func InstallModels(galleries []config.Gallery, modelPath string, enforceScan bool, downloadStatus func(string, string, string, float64), models ...string) error {
|
|
// create an error that groups all errors
|
|
var err error
|
|
|
|
for _, url := range models {
|
|
// As a best effort, try to resolve the model from the remote library
|
|
// if it's not resolved we try with the other method below
|
|
|
|
uri := downloader.URI(url)
|
|
|
|
switch {
|
|
case uri.LooksLikeOCI():
|
|
log.Debug().Msgf("[startup] resolved OCI model to download: %s", url)
|
|
|
|
// convert OCI image name to a file name.
|
|
ociName := strings.TrimPrefix(url, downloader.OCIPrefix)
|
|
ociName = strings.TrimPrefix(ociName, downloader.OllamaPrefix)
|
|
ociName = strings.ReplaceAll(ociName, "/", "__")
|
|
ociName = strings.ReplaceAll(ociName, ":", "__")
|
|
|
|
// check if file exists
|
|
if _, e := os.Stat(filepath.Join(modelPath, ociName)); errors.Is(e, os.ErrNotExist) {
|
|
modelDefinitionFilePath := filepath.Join(modelPath, ociName)
|
|
e := uri.DownloadFile(modelDefinitionFilePath, "", 0, 0, func(fileName, current, total string, percent float64) {
|
|
utils.DisplayDownloadFunction(fileName, current, total, percent)
|
|
})
|
|
if e != nil {
|
|
log.Error().Err(e).Str("url", url).Str("filepath", modelDefinitionFilePath).Msg("error downloading model")
|
|
err = errors.Join(err, e)
|
|
}
|
|
}
|
|
|
|
log.Info().Msgf("[startup] installed model from OCI repository: %s", ociName)
|
|
case uri.LooksLikeURL():
|
|
log.Debug().Msgf("[startup] downloading %s", url)
|
|
|
|
// Extract filename from URL
|
|
fileName, e := uri.FilenameFromUrl()
|
|
if e != nil {
|
|
log.Warn().Err(e).Str("url", url).Msg("error extracting filename from URL")
|
|
err = errors.Join(err, e)
|
|
continue
|
|
}
|
|
|
|
modelPath := filepath.Join(modelPath, fileName)
|
|
|
|
if e := utils.VerifyPath(fileName, modelPath); e != nil {
|
|
log.Error().Err(e).Str("filepath", modelPath).Msg("error verifying path")
|
|
err = errors.Join(err, e)
|
|
continue
|
|
}
|
|
|
|
// check if file exists
|
|
if _, e := os.Stat(modelPath); errors.Is(e, os.ErrNotExist) {
|
|
e := uri.DownloadFile(modelPath, "", 0, 0, func(fileName, current, total string, percent float64) {
|
|
utils.DisplayDownloadFunction(fileName, current, total, percent)
|
|
})
|
|
if e != nil {
|
|
log.Error().Err(e).Str("url", url).Str("filepath", modelPath).Msg("error downloading model")
|
|
err = errors.Join(err, e)
|
|
}
|
|
}
|
|
default:
|
|
if _, e := os.Stat(url); e == nil {
|
|
log.Debug().Msgf("[startup] resolved local model: %s", url)
|
|
// copy to modelPath
|
|
md5Name := utils.MD5(url)
|
|
|
|
modelYAML, e := os.ReadFile(url)
|
|
if e != nil {
|
|
log.Error().Err(e).Str("filepath", url).Msg("error reading model definition")
|
|
err = errors.Join(err, e)
|
|
continue
|
|
}
|
|
|
|
modelDefinitionFilePath := filepath.Join(modelPath, md5Name) + ".yaml"
|
|
if e := os.WriteFile(modelDefinitionFilePath, modelYAML, 0600); e != nil {
|
|
log.Error().Err(err).Str("filepath", modelDefinitionFilePath).Msg("error loading model: %s")
|
|
err = errors.Join(err, e)
|
|
}
|
|
} else {
|
|
// Check if it's a model gallery, or print a warning
|
|
e, found := installModel(galleries, url, modelPath, downloadStatus, enforceScan)
|
|
if e != nil && found {
|
|
log.Error().Err(err).Msgf("[startup] failed installing model '%s'", url)
|
|
err = errors.Join(err, e)
|
|
} else if !found {
|
|
log.Warn().Msgf("[startup] failed resolving model '%s'", url)
|
|
err = errors.Join(err, fmt.Errorf("failed resolving model '%s'", url))
|
|
}
|
|
}
|
|
}
|
|
}
|
|
return err
|
|
}
|
|
|
|
func installModel(galleries []config.Gallery, modelName, modelPath string, downloadStatus func(string, string, string, float64), enforceScan bool) (error, bool) {
|
|
models, err := gallery.AvailableGalleryModels(galleries, modelPath)
|
|
if err != nil {
|
|
return err, false
|
|
}
|
|
|
|
model := gallery.FindGalleryElement(models, modelName, modelPath)
|
|
if model == nil {
|
|
return err, false
|
|
}
|
|
|
|
if downloadStatus == nil {
|
|
downloadStatus = utils.DisplayDownloadFunction
|
|
}
|
|
|
|
log.Info().Str("model", modelName).Str("license", model.License).Msg("installing model")
|
|
err = gallery.InstallModelFromGallery(galleries, modelName, modelPath, gallery.GalleryModel{}, downloadStatus, enforceScan)
|
|
if err != nil {
|
|
return err, true
|
|
}
|
|
|
|
return nil, true
|
|
}
|