mirror of
https://github.com/mudler/LocalAI.git
synced 2024-12-30 09:28:51 +00:00
af9e5a2d05
* Revert "fix(fncall): fix regression introduced in #1963 (#2048)" This reverts commit6b06d4e0af
. * Revert "fix: action-tmate back to upstream, dead code removal (#2038)" This reverts commitfdec8a9d00
. * Revert "feat(grpc): return consumed token count and update response accordingly (#2035)" This reverts commite843d7df0e
. * Revert "refactor: backend/service split, channel-based llm flow (#1963)" This reverts commiteed5706994
. * feat(grpc): return consumed token count and update response accordingly Fixes: #1920 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
109 lines
2.8 KiB
Go
109 lines
2.8 KiB
Go
package base
|
|
|
|
// This is a wrapper to statisfy the GRPC service interface
|
|
// It is meant to be used by the main executable that is the server for the specific backend type (falcon, gpt3, etc)
|
|
import (
|
|
"fmt"
|
|
"os"
|
|
|
|
"github.com/go-skynet/LocalAI/core/schema"
|
|
pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
|
|
gopsutil "github.com/shirou/gopsutil/v3/process"
|
|
)
|
|
|
|
// Base is a base class for all backends to implement
|
|
// Note: the backends that does not support multiple requests
|
|
// should use SingleThread instead
|
|
type Base struct {
|
|
}
|
|
|
|
func (llm *Base) Locking() bool {
|
|
return false
|
|
}
|
|
|
|
func (llm *Base) Lock() {
|
|
panic("not implemented")
|
|
}
|
|
|
|
func (llm *Base) Unlock() {
|
|
panic("not implemented")
|
|
}
|
|
|
|
func (llm *Base) Busy() bool {
|
|
return false
|
|
}
|
|
|
|
func (llm *Base) Load(opts *pb.ModelOptions) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) Predict(opts *pb.PredictOptions) (string, error) {
|
|
return "", fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) PredictStream(opts *pb.PredictOptions, results chan string) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) Embeddings(opts *pb.PredictOptions) ([]float32, error) {
|
|
return []float32{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) GenerateImage(*pb.GenerateImageRequest) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) AudioTranscription(*pb.TranscriptRequest) (schema.Result, error) {
|
|
return schema.Result{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) TTS(*pb.TTSRequest) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) TokenizeString(opts *pb.PredictOptions) (pb.TokenizationResponse, error) {
|
|
return pb.TokenizationResponse{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
// backends may wish to call this to capture the gopsutil info, then enhance with additional memory usage details?
|
|
func (llm *Base) Status() (pb.StatusResponse, error) {
|
|
return pb.StatusResponse{
|
|
Memory: memoryUsage(),
|
|
}, nil
|
|
}
|
|
|
|
func (llm *Base) StoresSet(*pb.StoresSetOptions) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) StoresGet(*pb.StoresGetOptions) (pb.StoresGetResult, error) {
|
|
return pb.StoresGetResult{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) StoresDelete(*pb.StoresDeleteOptions) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) StoresFind(*pb.StoresFindOptions) (pb.StoresFindResult, error) {
|
|
return pb.StoresFindResult{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func memoryUsage() *pb.MemoryUsageData {
|
|
mud := pb.MemoryUsageData{
|
|
Breakdown: make(map[string]uint64),
|
|
}
|
|
|
|
pid := int32(os.Getpid())
|
|
|
|
backendProcess, err := gopsutil.NewProcess(pid)
|
|
|
|
if err == nil {
|
|
memInfo, err := backendProcess.MemoryInfo()
|
|
if err == nil {
|
|
mud.Total = memInfo.VMS // TEST, but rss seems reasonable first guess. Does include swap, but we might care about that.
|
|
mud.Breakdown["gopsutil-RSS"] = memInfo.RSS
|
|
}
|
|
}
|
|
return &mud
|
|
}
|