File size: 2,953 Bytes
7def60a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 |
package openai
import (
"encoding/json"
"fmt"
"time"
"github.com/mudler/LocalAI/core/backend"
"github.com/mudler/LocalAI/core/config"
"github.com/gofiber/fiber/v2"
"github.com/google/uuid"
"github.com/mudler/LocalAI/core/schema"
model "github.com/mudler/LocalAI/pkg/model"
"github.com/rs/zerolog/log"
)
// EditEndpoint is the OpenAI edit API endpoint
// @Summary OpenAI edit endpoint
// @Param request body schema.OpenAIRequest true "query params"
// @Success 200 {object} schema.OpenAIResponse "Response"
// @Router /v1/edits [post]
func EditEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {
return func(c *fiber.Ctx) error {
modelFile, input, err := readRequest(c, cl, ml, appConfig, true)
if err != nil {
return fmt.Errorf("failed reading parameters from request:%w", err)
}
config, input, err := mergeRequestWithConfig(modelFile, input, cl, ml, appConfig.Debug, appConfig.Threads, appConfig.ContextSize, appConfig.F16)
if err != nil {
return fmt.Errorf("failed reading parameters from request:%w", err)
}
log.Debug().Msgf("Parameter Config: %+v", config)
templateFile := ""
// A model can have a "file.bin.tmpl" file associated with a prompt template prefix
if ml.ExistsInModelPath(fmt.Sprintf("%s.tmpl", config.Model)) {
templateFile = config.Model
}
if config.TemplateConfig.Edit != "" {
templateFile = config.TemplateConfig.Edit
}
var result []schema.Choice
totalTokenUsage := backend.TokenUsage{}
for _, i := range config.InputStrings {
if templateFile != "" {
templatedInput, err := ml.EvaluateTemplateForPrompt(model.EditPromptTemplate, templateFile, model.PromptTemplateData{
Input: i,
Instruction: input.Instruction,
SystemPrompt: config.SystemPrompt,
})
if err == nil {
i = templatedInput
log.Debug().Msgf("Template found, input modified to: %s", i)
}
}
r, tokenUsage, err := ComputeChoices(input, i, config, appConfig, ml, func(s string, c *[]schema.Choice) {
*c = append(*c, schema.Choice{Text: s})
}, nil)
if err != nil {
return err
}
totalTokenUsage.Prompt += tokenUsage.Prompt
totalTokenUsage.Completion += tokenUsage.Completion
result = append(result, r...)
}
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.
Choices: result,
Object: "edit",
Usage: schema.OpenAIUsage{
PromptTokens: totalTokenUsage.Prompt,
CompletionTokens: totalTokenUsage.Completion,
TotalTokens: totalTokenUsage.Prompt + totalTokenUsage.Completion,
},
}
jsonResult, _ := json.Marshal(resp)
log.Debug().Msgf("Response: %s", jsonResult)
// Return the prediction in the response body
return c.JSON(resp)
}
}
|