mirror of
https://github.com/mudler/LocalAI.git
synced 2025-04-26 05:50:01 +00:00
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 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
feat(loader): enhance single active backend by treating at singleton Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
92 lines
4.0 KiB
Go
92 lines
4.0 KiB
Go
package routes
|
|
|
|
import (
|
|
"github.com/gofiber/fiber/v2"
|
|
"github.com/gofiber/swagger"
|
|
"github.com/mudler/LocalAI/core/config"
|
|
"github.com/mudler/LocalAI/core/http/endpoints/localai"
|
|
"github.com/mudler/LocalAI/core/http/middleware"
|
|
"github.com/mudler/LocalAI/core/p2p"
|
|
"github.com/mudler/LocalAI/core/schema"
|
|
"github.com/mudler/LocalAI/core/services"
|
|
"github.com/mudler/LocalAI/internal"
|
|
"github.com/mudler/LocalAI/pkg/model"
|
|
)
|
|
|
|
func RegisterLocalAIRoutes(router *fiber.App,
|
|
requestExtractor *middleware.RequestExtractor,
|
|
cl *config.BackendConfigLoader,
|
|
ml *model.ModelLoader,
|
|
appConfig *config.ApplicationConfig,
|
|
galleryService *services.GalleryService) {
|
|
|
|
router.Get("/swagger/*", swagger.HandlerDefault) // default
|
|
|
|
// LocalAI API endpoints
|
|
if !appConfig.DisableGalleryEndpoint {
|
|
modelGalleryEndpointService := localai.CreateModelGalleryEndpointService(appConfig.Galleries, appConfig.ModelPath, galleryService)
|
|
router.Post("/models/apply", modelGalleryEndpointService.ApplyModelGalleryEndpoint())
|
|
router.Post("/models/delete/:name", modelGalleryEndpointService.DeleteModelGalleryEndpoint())
|
|
|
|
router.Get("/models/available", modelGalleryEndpointService.ListModelFromGalleryEndpoint())
|
|
router.Get("/models/galleries", modelGalleryEndpointService.ListModelGalleriesEndpoint())
|
|
router.Post("/models/galleries", modelGalleryEndpointService.AddModelGalleryEndpoint())
|
|
router.Delete("/models/galleries", modelGalleryEndpointService.RemoveModelGalleryEndpoint())
|
|
router.Get("/models/jobs/:uuid", modelGalleryEndpointService.GetOpStatusEndpoint())
|
|
router.Get("/models/jobs", modelGalleryEndpointService.GetAllStatusEndpoint())
|
|
}
|
|
|
|
router.Post("/tts",
|
|
requestExtractor.BuildFilteredFirstAvailableDefaultModel(config.BuildUsecaseFilterFn(config.FLAG_TTS)),
|
|
requestExtractor.SetModelAndConfig(func() schema.LocalAIRequest { return new(schema.TTSRequest) }),
|
|
localai.TTSEndpoint(cl, ml, appConfig))
|
|
|
|
vadChain := []fiber.Handler{
|
|
requestExtractor.BuildFilteredFirstAvailableDefaultModel(config.BuildUsecaseFilterFn(config.FLAG_VAD)),
|
|
requestExtractor.SetModelAndConfig(func() schema.LocalAIRequest { return new(schema.VADRequest) }),
|
|
localai.VADEndpoint(cl, ml, appConfig),
|
|
}
|
|
router.Post("/vad", vadChain...)
|
|
router.Post("/v1/vad", vadChain...)
|
|
|
|
// Stores
|
|
router.Post("/stores/set", localai.StoresSetEndpoint(ml, appConfig))
|
|
router.Post("/stores/delete", localai.StoresDeleteEndpoint(ml, appConfig))
|
|
router.Post("/stores/get", localai.StoresGetEndpoint(ml, appConfig))
|
|
router.Post("/stores/find", localai.StoresFindEndpoint(ml, appConfig))
|
|
|
|
if !appConfig.DisableMetrics {
|
|
router.Get("/metrics", localai.LocalAIMetricsEndpoint())
|
|
}
|
|
|
|
// Backend Statistics Module
|
|
// TODO: Should these use standard middlewares? Refactor later, they are extremely simple.
|
|
backendMonitorService := services.NewBackendMonitorService(ml, cl, appConfig) // Split out for now
|
|
router.Get("/backend/monitor", localai.BackendMonitorEndpoint(backendMonitorService))
|
|
router.Post("/backend/shutdown", localai.BackendShutdownEndpoint(backendMonitorService))
|
|
// The v1/* urls are exactly the same as above - makes local e2e testing easier if they are registered.
|
|
router.Get("/v1/backend/monitor", localai.BackendMonitorEndpoint(backendMonitorService))
|
|
router.Post("/v1/backend/shutdown", localai.BackendShutdownEndpoint(backendMonitorService))
|
|
|
|
// p2p
|
|
if p2p.IsP2PEnabled() {
|
|
router.Get("/api/p2p", localai.ShowP2PNodes(appConfig))
|
|
router.Get("/api/p2p/token", localai.ShowP2PToken(appConfig))
|
|
}
|
|
|
|
router.Get("/version", func(c *fiber.Ctx) error {
|
|
return c.JSON(struct {
|
|
Version string `json:"version"`
|
|
}{Version: internal.PrintableVersion()})
|
|
})
|
|
|
|
router.Get("/system", localai.SystemInformations(ml, appConfig))
|
|
|
|
// misc
|
|
router.Post("/v1/tokenize",
|
|
requestExtractor.BuildFilteredFirstAvailableDefaultModel(config.BuildUsecaseFilterFn(config.FLAG_TOKENIZE)),
|
|
requestExtractor.SetModelAndConfig(func() schema.LocalAIRequest { return new(schema.TokenizeRequest) }),
|
|
localai.TokenizeEndpoint(cl, ml, appConfig))
|
|
|
|
}
|