mirror of
https://github.com/mudler/LocalAI.git
synced 2025-03-13 15:56:39 +00:00
3cddf24747
* squash past, centralize request middleware PR Signed-off-by: Dave Lee <dave@gray101.com> * migrate bruno request files to examples repo Signed-off-by: Dave Lee <dave@gray101.com> * fix Signed-off-by: Dave Lee <dave@gray101.com> * Update tests/e2e-aio/e2e_test.go Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com> --------- Signed-off-by: Dave Lee <dave@gray101.com> Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com> Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
102 lines
3.1 KiB
Go
102 lines
3.1 KiB
Go
package openai
|
|
|
|
import (
|
|
"encoding/json"
|
|
"time"
|
|
|
|
"github.com/mudler/LocalAI/core/backend"
|
|
"github.com/mudler/LocalAI/core/config"
|
|
"github.com/mudler/LocalAI/core/http/middleware"
|
|
|
|
"github.com/gofiber/fiber/v2"
|
|
"github.com/google/uuid"
|
|
"github.com/mudler/LocalAI/core/schema"
|
|
|
|
"github.com/mudler/LocalAI/pkg/model"
|
|
"github.com/mudler/LocalAI/pkg/templates"
|
|
|
|
"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, evaluator *templates.Evaluator, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {
|
|
|
|
return func(c *fiber.Ctx) error {
|
|
|
|
input, ok := c.Locals(middleware.CONTEXT_LOCALS_KEY_LOCALAI_REQUEST).(*schema.OpenAIRequest)
|
|
if !ok || input.Model == "" {
|
|
return fiber.ErrBadRequest
|
|
}
|
|
// Opt-in extra usage flag
|
|
extraUsage := c.Get("Extra-Usage", "") != ""
|
|
|
|
config, ok := c.Locals(middleware.CONTEXT_LOCALS_KEY_MODEL_CONFIG).(*config.BackendConfig)
|
|
if !ok || config == nil {
|
|
return fiber.ErrBadRequest
|
|
}
|
|
|
|
log.Debug().Msgf("Edit Endpoint Input : %+v", input)
|
|
log.Debug().Msgf("Edit Endpoint Config: %+v", *config)
|
|
|
|
var result []schema.Choice
|
|
totalTokenUsage := backend.TokenUsage{}
|
|
|
|
for _, i := range config.InputStrings {
|
|
templatedInput, err := evaluator.EvaluateTemplateForPrompt(templates.EditPromptTemplate, *config, templates.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
|
|
|
|
totalTokenUsage.TimingTokenGeneration += tokenUsage.TimingTokenGeneration
|
|
totalTokenUsage.TimingPromptProcessing += tokenUsage.TimingPromptProcessing
|
|
|
|
result = append(result, r...)
|
|
}
|
|
usage := schema.OpenAIUsage{
|
|
PromptTokens: totalTokenUsage.Prompt,
|
|
CompletionTokens: totalTokenUsage.Completion,
|
|
TotalTokens: totalTokenUsage.Prompt + totalTokenUsage.Completion,
|
|
}
|
|
if extraUsage {
|
|
usage.TimingTokenGeneration = totalTokenUsage.TimingTokenGeneration
|
|
usage.TimingPromptProcessing = totalTokenUsage.TimingPromptProcessing
|
|
}
|
|
|
|
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: usage,
|
|
}
|
|
|
|
jsonResult, _ := json.Marshal(resp)
|
|
log.Debug().Msgf("Response: %s", jsonResult)
|
|
|
|
// Return the prediction in the response body
|
|
return c.JSON(resp)
|
|
}
|
|
}
|