dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 10:35:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

refactor: backend/service split, channel-based llm flow (#1963)

Browse source 
Refactor: channel based llm flow and services split

---------

Signed-off-by: Dave Lee <dave@gray101.com>
This commit is contained in:
Dave 2024-04-13 03:45:34 -04:00 • committed by GitHub
parent 1981154f49
commit eed5706994
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
52 changed files with 3064 additions and 2279 deletions
Download patch file Download diff file Expand all files Collapse all files

65
core/http/endpoints/openai/embeddings.go
View file

@ -3,14 +3,9 @@ package openai
import (
"encoding/json"
"fmt"
"time"
"github.com/go-skynet/LocalAI/core/backend"
"github.com/go-skynet/LocalAI/core/config"
"github.com/go-skynet/LocalAI/pkg/model"
"github.com/go-skynet/LocalAI/core/schema"
"github.com/google/uuid"
fiberContext "github.com/go-skynet/LocalAI/core/http/ctx"
"github.com/gofiber/fiber/v2"
"github.com/rs/zerolog/log"
@ -21,63 +16,25 @@ import (
// @Param request body schema.OpenAIRequest true "query params"
// @Success 200 {object} schema.OpenAIResponse "Response"
// @Router /v1/embeddings [post]
func EmbeddingsEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {
func EmbeddingsEndpoint(fce *fiberContext.FiberContextExtractor, ebs *backend.EmbeddingsBackendService) func(c *fiber.Ctx) error {
return func(c *fiber.Ctx) error {
model, input, err := readRequest(c, ml, appConfig, true)
_, input, err := fce.OpenAIRequestFromContext(c, true)
if err != nil {
return fmt.Errorf("failed reading parameters from request:%w", err)
}
config, input, err := mergeRequestWithConfig(model, input, cl, ml, appConfig.Debug, appConfig.Threads, appConfig.ContextSize, appConfig.F16)
if err != nil {
return fmt.Errorf("failed reading parameters from request:%w", err)
responseChannel := ebs.Embeddings(input)
rawResponse := <-responseChannel
if rawResponse.Error != nil {
return rawResponse.Error
}
log.Debug().Msgf("Parameter Config: %+v", config)
items := []schema.Item{}
for i, s := range config.InputToken {
// get the model function to call for the result
embedFn, err := backend.ModelEmbedding("", s, ml, *config, appConfig)
if err != nil {
return err
}
embeddings, err := embedFn()
if err != nil {
return err
}
items = append(items, schema.Item{Embedding: embeddings, Index: i, Object: "embedding"})
}
for i, s := range config.InputStrings {
// get the model function to call for the result
embedFn, err := backend.ModelEmbedding(s, []int{}, ml, *config, appConfig)
if err != nil {
return err
}
embeddings, err := embedFn()
if err != nil {
return err
}
items = append(items, schema.Item{Embedding: embeddings, Index: i, Object: "embedding"})
}
id := uuid.New().String()
created := int(time.Now().Unix())
resp := &schema.OpenAIResponse{
ID: id,
Created: created,
Model: input.Model, // we have to return what the user sent here, due to OpenAI spec.
Data: items,
Object: "list",
}
jsonResult, _ := json.Marshal(resp)
jsonResult, _ := json.Marshal(rawResponse.Value)
log.Debug().Msgf("Response: %s", jsonResult)
// Return the prediction in the response body
return c.JSON(resp)
return c.JSON(rawResponse.Value)
}
}