mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-05-19 05:58:05 -04:00
Code Issues Packages Projects Releases Wiki Activity

feat: refactor build process, drop embedded backends (#5875)

Browse Source 
* feat: split remaining backends and drop embedded backends

- Drop silero-vad, huggingface, and stores backend from embedded
  binaries
- Refactor Makefile and Dockerfile to avoid building grpc backends
- Drop golang code that was used to embed backends
- Simplify building by using goreleaser

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(gallery): be specific with llama-cpp backend templates

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(docs): update

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(ci): minor fixes

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore: drop all ffmpeg references

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix: run protogen-go

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Always enable p2p mode

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Update gorelease file

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(stores): do not always load

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fix linting issues

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Simplify

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Mac OS fixup

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
2025-07-22 16:31:04 +02:00
committed by GitHub
parent e29b2c3aff
commit 98e5291afc
118 changed files with 631 additions and 1339 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
core/cli/worker/worker.go
View File

@@ -1,7 +1,7 @@
package worker
type WorkerFlags struct {
BackendAssetsPath string `env:"LOCALAI_BACKEND_ASSETS_PATH,BACKEND_ASSETS_PATH" type:"path" default:"/tmp/localai/backend_data" help:"Path used to extract libraries that are required by some of the backends in runtime" group:"storage"`
BackendsPath string `env:"LOCALAI_BACKENDS_PATH,BACKENDS_PATH" type:"path" default:"${basepath}/backends" help:"Path containing backends used for inferencing" group:"backends"`
ExtraLLamaCPPArgs string `name:"llama-cpp-args" env:"LOCALAI_EXTRA_LLAMA_CPP_ARGS,EXTRA_LLAMA_CPP_ARGS" help:"Extra arguments to pass to llama-cpp-rpc-server"`
}

11
core/cli/worker/worker_llamacpp.go
View File

@@ -9,8 +9,6 @@ import (
cliContext "github.com/mudler/LocalAI/core/cli/context"
"github.com/mudler/LocalAI/core/gallery"
"github.com/mudler/LocalAI/pkg/assets"
"github.com/mudler/LocalAI/pkg/library"
"github.com/rs/zerolog/log"
)
@@ -47,24 +45,17 @@ func findLLamaCPPBackend(backendSystemPath string) (string, error) {
}
func (r *LLamaCPP) Run(ctx *cliContext.Context) error {
// Extract files from the embedded FS
err := assets.ExtractFiles(ctx.BackendAssets, r.BackendAssetsPath)
log.Debug().Msgf("Extracting backend assets files to %s", r.BackendAssetsPath)
if err != nil {
log.Warn().Msgf("Failed extracting backend assets files: %s (might be required for some backends to work properly)", err)
}
if len(os.Args) < 4 {
return fmt.Errorf("usage: local-ai worker llama-cpp-rpc -- <llama-rpc-server-args>")
}
grpcProcess, err := findLLamaCPPBackend(r.BackendAssetsPath)
grpcProcess, err := findLLamaCPPBackend(r.BackendsPath)
if err != nil {
return err
}
args := strings.Split(r.ExtraLLamaCPPArgs, " ")
args, grpcProcess = library.LoadLDSO(r.BackendAssetsPath, args, grpcProcess)
args = append([]string{grpcProcess}, args...)
return syscall.Exec(

16
core/cli/worker/worker_nop2p.go
View File

@@ -1,16 +0,0 @@
//go:build !p2p
// +build !p2p
package worker
import (
"fmt"
cliContext "github.com/mudler/LocalAI/core/cli/context"
)
type P2P struct{}
func (r *P2P) Run(ctx *cliContext.Context) error {
return fmt.Errorf("p2p mode is not enabled in this build")
}

15
core/cli/worker/worker_p2p.go
View File

@@ -1,6 +1,3 @@
//go:build p2p
// +build p2p
package worker
import (
@@ -13,8 +10,6 @@ import (
cliContext "github.com/mudler/LocalAI/core/cli/context"
"github.com/mudler/LocalAI/core/p2p"
"github.com/mudler/LocalAI/pkg/assets"
"github.com/mudler/LocalAI/pkg/library"
"github.com/phayes/freeport"
"github.com/rs/zerolog/log"
)
@@ -29,12 +24,6 @@ type P2P struct {
}
func (r *P2P) Run(ctx *cliContext.Context) error {
// Extract files from the embedded FS
err := assets.ExtractFiles(ctx.BackendAssets, r.BackendAssetsPath)
log.Debug().Msgf("Extracting backend assets files to %s", r.BackendAssetsPath)
if err != nil {
log.Warn().Msgf("Failed extracting backend assets files: %s (might be required for some backends to work properly)", err)
}
// Check if the token is set
// as we always need it.
@@ -71,7 +60,7 @@ func (r *P2P) Run(ctx *cliContext.Context) error {
for {
log.Info().Msgf("Starting llama-cpp-rpc-server on '%s:%d'", address, port)
grpcProcess, err := findLLamaCPPBackend(r.BackendAssetsPath)
grpcProcess, err := findLLamaCPPBackend(r.BackendsPath)
if err != nil {
log.Error().Err(err).Msg("Failed to find llama-cpp-rpc-server")
return
@@ -85,8 +74,6 @@ func (r *P2P) Run(ctx *cliContext.Context) error {
args := append([]string{"--host", address, "--port", fmt.Sprint(port)}, extraArgs...)
log.Debug().Msgf("Starting llama-cpp-rpc-server on '%s:%d' with args: %+v (%d)", address, port, args, len(args))
args, grpcProcess = library.LoadLDSO(r.BackendAssetsPath, args, grpcProcess)
cmd := exec.Command(
grpcProcess, args...,
)