LocalAI/core/cli/models.go
Ettore Di Giacinto 72e52c4f6a
Some checks are pending
Explorer deployment / build-linux (push) Waiting to run
GPU tests / ubuntu-latest (1.21.x) (push) Waiting to run
generate and publish GRPC docker caches / generate_caches (ubuntu:22.04, linux/amd64,linux/arm64, ubuntu-latest) (push) Waiting to run
generate and publish intel docker caches / generate_caches (intel/oneapi-basekit:2025.0.0-0-devel-ubuntu22.04, linux/amd64, ubuntu-latest) (push) Waiting to run
build container images / hipblas-jobs (-aio-gpu-hipblas, rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, extras, latest-gpu-hipblas, latest-aio-gpu-hipblas, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -hipblas-ffmpeg) (push) Waiting to run
build container images / hipblas-jobs (rocm/dev-ubuntu-22.04:6.1, hipblas, false, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas-core) (push) Waiting to run
build container images / hipblas-jobs (rocm/dev-ubuntu-22.04:6.1, hipblas, false, ubuntu:22.04, extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas) (push) Waiting to run
build container images / hipblas-jobs (rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas-ffmpeg-core) (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-intel-f16, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, extras, latest-gpu-intel-f16, latest-aio-gpu-intel-f16, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -sycl-f16-ffmpeg) (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-intel-f32, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, extras, latest-gpu-intel-f32, latest-aio-gpu-intel-f32, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -sycl-f32-ffmpeg) (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-nvidia-cuda-11, ubuntu:22.04, cublas, 11, 7, true, extras, latest-gpu-nvidia-cuda-11, latest-aio-gpu-nvidia-cuda-11, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -cublas-cuda11-ffmpeg) (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-nvidia-cuda-12, ubuntu:22.04, cublas, 12, 0, true, extras, latest-gpu-nvidia-cuda-12, latest-aio-gpu-nvidia-cuda-12, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -cublas-cuda12-ffmpeg) (push) Waiting to run
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, false, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16-core) (push) Waiting to run
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16-ffmpeg-core) (push) Waiting to run
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, false, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32-core) (push) Waiting to run
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32-ffmpeg-core) (push) Waiting to run
build container images / self-hosted-jobs (ubuntu:22.04, , , extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, ) (push) Waiting to run
build container images / self-hosted-jobs (ubuntu:22.04, , true, extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -ffmpeg) (push) Waiting to run
build container images / self-hosted-jobs (ubuntu:22.04, cublas, 11, 7, , extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda11) (push) Waiting to run
build container images / self-hosted-jobs (ubuntu:22.04, cublas, 12, 0, , extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda12) (push) Waiting to run
build container images / core-image-build (-aio-cpu, ubuntu:22.04, , true, core, latest-cpu, latest-aio-cpu, --jobs=4 --output-sync=target, linux/amd64,linux/arm64, arc-runner-set, false, auto, -ffmpeg-core) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, cublas, 11, 7, , core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda11-core) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, cublas, 11, 7, true, core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda11-ffmpeg-core) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, cublas, 12, 0, , core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda12-core) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, cublas, 12, 0, true, core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda12-ffmpeg-core) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, vulkan, true, core, latest-vulkan-ffmpeg-core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -vulkan-ffmpeg-core) (push) Waiting to run
build container images / gh-runner (nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, 12, 0, true, core, latest-nvidia-l4t-arm64-core, --jobs=4 --output-sync=target, linux/arm64, ubuntu-24.04-arm, true, false, -nvidia-l4t-arm64-core) (push) Waiting to run
Security Scan / tests (push) Waiting to run
Tests extras backends / tests-transformers (push) Waiting to run
Tests extras backends / tests-rerankers (push) Waiting to run
Tests extras backends / tests-diffusers (push) Waiting to run
Tests extras backends / tests-coqui (push) Waiting to run
tests / tests-linux (1.21.x) (push) Waiting to run
tests / tests-aio-container (push) Waiting to run
tests / tests-apple (1.21.x) (push) Waiting to run
chore: drop embedded models (#4715)
Since the remote gallery was introduced this is now completely
superseded by it. In order to keep the code clean and remove redudant
parts let's simplify the usage.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-01-30 00:03:01 +01:00

110 lines
3.3 KiB
Go

package cli
import (
"encoding/json"
"errors"
"fmt"
cliContext "github.com/mudler/LocalAI/core/cli/context"
"github.com/mudler/LocalAI/core/config"
"github.com/mudler/LocalAI/core/gallery"
"github.com/mudler/LocalAI/pkg/downloader"
"github.com/mudler/LocalAI/pkg/startup"
"github.com/rs/zerolog/log"
"github.com/schollz/progressbar/v3"
)
type ModelsCMDFlags struct {
Galleries string `env:"LOCALAI_GALLERIES,GALLERIES" help:"JSON list of galleries" group:"models" default:"${galleries}"`
ModelsPath string `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
}
type ModelsList struct {
ModelsCMDFlags `embed:""`
}
type ModelsInstall struct {
DisablePredownloadScan bool `env:"LOCALAI_DISABLE_PREDOWNLOAD_SCAN" help:"If true, disables the best-effort security scanner before downloading any files." group:"hardening" default:"false"`
ModelArgs []string `arg:"" optional:"" name:"models" help:"Model configuration URLs to load"`
ModelsCMDFlags `embed:""`
}
type ModelsCMD struct {
List ModelsList `cmd:"" help:"List the models available in your galleries" default:"withargs"`
Install ModelsInstall `cmd:"" help:"Install a model from the gallery"`
}
func (ml *ModelsList) Run(ctx *cliContext.Context) error {
var galleries []config.Gallery
if err := json.Unmarshal([]byte(ml.Galleries), &galleries); err != nil {
log.Error().Err(err).Msg("unable to load galleries")
}
models, err := gallery.AvailableGalleryModels(galleries, ml.ModelsPath)
if err != nil {
return err
}
for _, model := range models {
if model.Installed {
fmt.Printf(" * %s@%s (installed)\n", model.Gallery.Name, model.Name)
} else {
fmt.Printf(" - %s@%s\n", model.Gallery.Name, model.Name)
}
}
return nil
}
func (mi *ModelsInstall) Run(ctx *cliContext.Context) error {
var galleries []config.Gallery
if err := json.Unmarshal([]byte(mi.Galleries), &galleries); err != nil {
log.Error().Err(err).Msg("unable to load galleries")
}
for _, modelName := range mi.ModelArgs {
progressBar := progressbar.NewOptions(
1000,
progressbar.OptionSetDescription(fmt.Sprintf("downloading model %s", modelName)),
progressbar.OptionShowBytes(false),
progressbar.OptionClearOnFinish(),
)
progressCallback := func(fileName string, current string, total string, percentage float64) {
v := int(percentage * 10)
err := progressBar.Set(v)
if err != nil {
log.Error().Err(err).Str("filename", fileName).Int("value", v).Msg("error while updating progress bar")
}
}
//startup.InstallModels()
models, err := gallery.AvailableGalleryModels(galleries, mi.ModelsPath)
if err != nil {
return err
}
modelURI := downloader.URI(modelName)
if !modelURI.LooksLikeOCI() {
model := gallery.FindModel(models, modelName, mi.ModelsPath)
if model == nil {
log.Error().Str("model", modelName).Msg("model not found")
return err
}
err = gallery.SafetyScanGalleryModel(model)
if err != nil && !errors.Is(err, downloader.ErrNonHuggingFaceFile) {
return err
}
log.Info().Str("model", modelName).Str("license", model.License).Msg("installing model")
}
err = startup.InstallModels(galleries, mi.ModelsPath, !mi.DisablePredownloadScan, progressCallback, modelName)
if err != nil {
return err
}
}
return nil
}