Files
LocalAI/main.go
Ettore Di Giacinto 2d64269763
Some checks failed
Explorer deployment / build-linux (push) Has been cancelled
GPU tests / ubuntu-latest (1.21.x) (push) Has been cancelled
generate and publish intel docker caches / generate_caches (intel/oneapi-basekit:2025.1.0-0-devel-ubuntu22.04, linux/amd64, ubuntu-latest) (push) Has been cancelled
build container images / hipblas-jobs (-aio-gpu-hipblas, rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, core, latest-gpu-hipblas, latest-aio-gpu-hipblas, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas) (push) Has been cancelled
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, ) (push) Has been cancelled
build container images / core-image-build (-aio-gpu-intel-f16, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, core, latest-gpu-intel-f16, latest-aio-gpu-intel-f16, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16) (push) Has been cancelled
build container images / core-image-build (-aio-gpu-intel-f32, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, core, latest-gpu-intel-f32, latest-aio-gpu-intel-f32, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32) (push) Has been cancelled
build container images / core-image-build (-aio-gpu-nvidia-cuda-11, ubuntu:22.04, cublas, 11, 7, true, core, latest-gpu-nvidia-cuda-11, latest-aio-gpu-nvidia-cuda-11, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda11) (push) Has been cancelled
build container images / core-image-build (-aio-gpu-nvidia-cuda-12, ubuntu:22.04, cublas, 12, 0, true, core, latest-gpu-nvidia-cuda-12, latest-aio-gpu-nvidia-cuda-12, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda12) (push) Has been cancelled
build container images / core-image-build (-aio-gpu-vulkan, ubuntu:22.04, vulkan, true, core, latest-gpu-vulkan, latest-aio-gpu-vulkan, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -vulkan) (push) Has been cancelled
build container images / gh-runner (nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, 12, 0, true, core, latest-nvidia-l4t-arm64, --jobs=4 --output-sync=target, linux/arm64, ubuntu-24.04-arm, true, false, -nvidia-l4t-arm64) (push) Has been cancelled
build python backend container images / backend-jobs (bark, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-bark, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f16-bark) (push) Has been cancelled
build python backend container images / backend-jobs (bark, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-bark, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f32-bark) (push) Has been cancelled
build python backend container images / backend-jobs (bark, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-bark, linux/amd64, arc-runner-set, true, -gpu-rocm-hipblas-bark) (push) Has been cancelled
build python backend container images / backend-jobs (bark, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-bark, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-bark) (push) Has been cancelled
build python backend container images / backend-jobs (bark, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-bark, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-bark) (push) Has been cancelled
build python backend container images / backend-jobs (chatterbox, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-chatterbox, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-chatterbox) (push) Has been cancelled
build python backend container images / backend-jobs (chatterbox, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-chatterbox, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-chatterbox) (push) Has been cancelled
build python backend container images / backend-jobs (coqui, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-coqui, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f16-coqui) (push) Has been cancelled
build python backend container images / backend-jobs (coqui, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-coqui, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f32-coqui) (push) Has been cancelled
build python backend container images / backend-jobs (coqui, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-coqui, linux/amd64, arc-runner-set, true, -gpu-rocm-hipblas-coqui) (push) Has been cancelled
build python backend container images / backend-jobs (coqui, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-coqui, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-coqui) (push) Has been cancelled
build python backend container images / backend-jobs (coqui, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-coqui, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-coqui) (push) Has been cancelled
build python backend container images / backend-jobs (diffusers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-diffusers, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f32-diffusers) (push) Has been cancelled
build python backend container images / backend-jobs (diffusers, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-diffusers, linux/amd64, arc-runner-set, true, -gpu-rocm-hipblas-diffusers) (push) Has been cancelled
build python backend container images / backend-jobs (diffusers, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-diffusers, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-diffusers) (push) Has been cancelled
build python backend container images / backend-jobs (diffusers, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-diffusers, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-diffusers) (push) Has been cancelled
build python backend container images / backend-jobs (faster-whisper, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-faster-whisper, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f16-faster-whisper) (push) Has been cancelled
build python backend container images / backend-jobs (faster-whisper, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-faster-whisper, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f32-faster-whisper) (push) Has been cancelled
build python backend container images / backend-jobs (faster-whisper, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-faster-whisper, linux/amd64, arc-runner-set, true, -gpu-rocm-hipblas-faster-whisper) (push) Has been cancelled
build python backend container images / backend-jobs (faster-whisper, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-faster-whisper, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-faster-whisper) (push) Has been cancelled
build python backend container images / backend-jobs (faster-whisper, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-faster-whisper, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-faster-whisper) (push) Has been cancelled
build python backend container images / backend-jobs (kokoro, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-kokoro, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f16-kokoro) (push) Has been cancelled
build python backend container images / backend-jobs (kokoro, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-kokoro, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f32-kokoro) (push) Has been cancelled
build python backend container images / backend-jobs (kokoro, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-kokoro, linux/amd64, arc-runner-set, true, -gpu-rocm-hipblas-kokoro) (push) Has been cancelled
build python backend container images / backend-jobs (kokoro, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-kokoro, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-kokoro) (push) Has been cancelled
build python backend container images / backend-jobs (kokoro, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-kokoro, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-kokoro) (push) Has been cancelled
build python backend container images / backend-jobs (rerankers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-rerankers, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f16-rerankers) (push) Has been cancelled
build python backend container images / backend-jobs (rerankers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-rerankers, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f32-rerankers) (push) Has been cancelled
build python backend container images / backend-jobs (rerankers, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-rerankers, linux/amd64, arc-runner-set, true, -gpu-rocm-hipblas-rerankers) (push) Has been cancelled
build python backend container images / backend-jobs (rerankers, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-rerankers, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-rerankers) (push) Has been cancelled
build python backend container images / backend-jobs (rerankers, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-rerankers, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-rerankers) (push) Has been cancelled
build python backend container images / backend-jobs (transformers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-transformers, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f16-transformers) (push) Has been cancelled
build python backend container images / backend-jobs (transformers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-transformers, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f32-transformers) (push) Has been cancelled
build python backend container images / backend-jobs (transformers, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-transformers, linux/amd64, arc-runner-set, true, -gpu-rocm-hipblas-transformers) (push) Has been cancelled
build python backend container images / backend-jobs (transformers, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-transformers, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-transformers) (push) Has been cancelled
build python backend container images / backend-jobs (transformers, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-transformers, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-transformers) (push) Has been cancelled
build python backend container images / backend-jobs (vllm, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-vllm, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f16-vllm) (push) Has been cancelled
build python backend container images / backend-jobs (vllm, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-vllm, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f32-vllm) (push) Has been cancelled
build python backend container images / backend-jobs (vllm, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-vllm, linux/amd64, arc-runner-set, true, -gpu-rocm-hipblas-vllm) (push) Has been cancelled
build python backend container images / backend-jobs (vllm, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-vllm, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-vllm) (push) Has been cancelled
build python backend container images / backend-jobs (vllm, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-vllm, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-vllm) (push) Has been cancelled
Security Scan / tests (push) Has been cancelled
Tests extras backends / tests-transformers (push) Has been cancelled
Tests extras backends / tests-rerankers (push) Has been cancelled
Tests extras backends / tests-diffusers (push) Has been cancelled
Tests extras backends / tests-coqui (push) Has been cancelled
tests / tests-linux (1.21.x) (push) Has been cancelled
tests / tests-aio-container (push) Has been cancelled
tests / tests-apple (1.21.x) (push) Has been cancelled
Update swagger / swagger (push) Has been cancelled
Check if checksums are up-to-date / checksum_check (push) Has been cancelled
Bump dependencies / bump (mudler/LocalAI) (push) Has been cancelled
Bump dependencies / bump (main, PABannier/bark.cpp, BARKCPP_VERSION) (push) Has been cancelled
Bump dependencies / bump (master, ggml-org/llama.cpp, CPPLLAMA_VERSION) (push) Has been cancelled
Bump dependencies / bump (master, ggml-org/whisper.cpp, WHISPER_CPP_VERSION) (push) Has been cancelled
Bump dependencies / bump (master, leejet/stable-diffusion.cpp, STABLEDIFFUSION_GGML_VERSION) (push) Has been cancelled
Bump dependencies / bump (master, mudler/go-piper, PIPER_VERSION) (push) Has been cancelled
Bump dependencies / bump (master, mudler/go-stable-diffusion, STABLEDIFFUSION_VERSION) (push) Has been cancelled
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

124 lines
3.4 KiB
Go

package main
import (
"os"
"os/signal"
"path/filepath"
"syscall"
"github.com/alecthomas/kong"
"github.com/joho/godotenv"
"github.com/mudler/LocalAI/core/cli"
"github.com/mudler/LocalAI/internal"
"github.com/rs/zerolog"
"github.com/rs/zerolog/log"
_ "github.com/mudler/LocalAI/swagger"
)
func main() {
var err error
// Initialize zerolog at a level of INFO, we will set the desired level after we parse the CLI options
log.Logger = log.Output(zerolog.ConsoleWriter{Out: os.Stderr})
zerolog.SetGlobalLevel(zerolog.InfoLevel)
// Catch signals from the OS requesting us to exit
go func() {
c := make(chan os.Signal, 1) // we need to reserve to buffer size 1, so the notifier are not blocked
signal.Notify(c, os.Interrupt, syscall.SIGTERM)
<-c
os.Exit(1)
}()
// handle loading environment variabled from .env files
envFiles := []string{".env", "localai.env"}
homeDir, err := os.UserHomeDir()
if err == nil {
envFiles = append(envFiles, filepath.Join(homeDir, "localai.env"), filepath.Join(homeDir, ".config/localai.env"))
}
envFiles = append(envFiles, "/etc/localai.env")
for _, envFile := range envFiles {
if _, err := os.Stat(envFile); err == nil {
log.Info().Str("envFile", envFile).Msg("env file found, loading environment variables from file")
err = godotenv.Load(envFile)
if err != nil {
log.Error().Err(err).Str("envFile", envFile).Msg("failed to load environment variables from file")
continue
}
}
}
// Actually parse the CLI options
ctx := kong.Parse(&cli.CLI,
kong.Description(
` LocalAI is a drop-in replacement OpenAI API for running LLM, GPT and genAI models locally on CPU, GPUs with consumer grade hardware.
Some of the models compatible are:
- Vicuna
- Koala
- GPT4ALL
- GPT4ALL-J
- Cerebras
- Alpaca
- StableLM (ggml quantized)
For a list of all available models for one-click install, check out: https://models.localai.io
Copyright: Ettore Di Giacinto
Version: ${version}
`,
),
kong.UsageOnError(),
kong.Vars{
"basepath": kong.ExpandPath("."),
"galleries": `[{"name":"localai", "url":"github:mudler/LocalAI/gallery/index.yaml@master"}]`,
"backends": `[{"name":"localai", "url":"github:mudler/LocalAI/backend/index.yaml@master"}]`,
"version": internal.PrintableVersion(),
},
)
// Configure the logging level before we run the application
// This is here to preserve the existing --debug flag functionality
logLevel := "info"
if cli.CLI.Debug && cli.CLI.LogLevel == nil {
logLevel = "debug"
zerolog.SetGlobalLevel(zerolog.DebugLevel)
cli.CLI.LogLevel = &logLevel
}
if cli.CLI.LogLevel == nil {
cli.CLI.LogLevel = &logLevel
}
switch *cli.CLI.LogLevel {
case "error":
zerolog.SetGlobalLevel(zerolog.ErrorLevel)
log.Info().Msg("Setting logging to error")
case "warn":
zerolog.SetGlobalLevel(zerolog.WarnLevel)
log.Info().Msg("Setting logging to warn")
case "info":
zerolog.SetGlobalLevel(zerolog.InfoLevel)
log.Info().Msg("Setting logging to info")
case "debug":
zerolog.SetGlobalLevel(zerolog.DebugLevel)
log.Debug().Msg("Setting logging to debug")
case "trace":
zerolog.SetGlobalLevel(zerolog.TraceLevel)
log.Trace().Msg("Setting logging to trace")
}
// Populate the application with the embedded backend assets
cli.CLI.Context.BackendAssets = backendAssets
// Run the thing!
err = ctx.Run(&cli.CLI.Context)
if err != nil {
log.Fatal().Err(err).Msg("Error running the application")
}
}