Files
LocalAI/core/schema/openai.go
Andres b6459ddd57 feat(api): Add transcribe response format request parameter & adjust STT backends (#8318)
* WIP response format implementation for audio transcriptions

(cherry picked from commit e271dd764bbc13846accf3beb8b6522153aa276f)
Signed-off-by: Andres Smith <andressmithdev@pm.me>

* Rework transcript response_format and add more formats

(cherry picked from commit 6a93a8f63e2ee5726bca2980b0c9cf4ef8b7aeb8)
Signed-off-by: Andres Smith <andressmithdev@pm.me>

* Add test and replace go-openai package with official openai go client

(cherry picked from commit f25d1a04e46526429c89db4c739e1e65942ca893)
Signed-off-by: Andres Smith <andressmithdev@pm.me>

* Fix faster-whisper backend and refactor transcription formatting to also work on CLI

Signed-off-by: Andres Smith <andressmithdev@pm.me>
(cherry picked from commit 69a93977d5e113eb7172bd85a0f918592d3d2168)
Signed-off-by: Andres Smith <andressmithdev@pm.me>

---------

Signed-off-by: Andres Smith <andressmithdev@pm.me>
Co-authored-by: nanoandrew4 <nanoandrew4@gmail.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2026-02-01 17:33:17 +01:00

195 lines
6.0 KiB
Go

package schema
import (
"context"
functions "github.com/mudler/LocalAI/pkg/functions"
)
// APIError provides error information returned by the OpenAI API.
type APIError struct {
Code any `json:"code,omitempty"`
Message string `json:"message"`
Param *string `json:"param,omitempty"`
Type string `json:"type"`
}
type ErrorResponse struct {
Error *APIError `json:"error,omitempty"`
}
type InputTokensDetails struct {
TextTokens int `json:"text_tokens"`
ImageTokens int `json:"image_tokens"`
}
type OpenAIUsage struct {
PromptTokens int `json:"prompt_tokens"`
CompletionTokens int `json:"completion_tokens"`
TotalTokens int `json:"total_tokens"`
// Fields for image generation API compatibility
InputTokens int `json:"input_tokens,omitempty"`
OutputTokens int `json:"output_tokens,omitempty"`
InputTokensDetails *InputTokensDetails `json:"input_tokens_details,omitempty"`
// Extra timing data, disabled by default as is't not a part of OpenAI specification
TimingPromptProcessing float64 `json:"timing_prompt_processing,omitempty"`
TimingTokenGeneration float64 `json:"timing_token_generation,omitempty"`
}
type Item struct {
Embedding []float32 `json:"embedding"`
Index int `json:"index"`
Object string `json:"object,omitempty"`
// Images
URL string `json:"url,omitempty"`
B64JSON string `json:"b64_json,omitempty"`
}
type OpenAIResponse struct {
Created int `json:"created,omitempty"`
Object string `json:"object,omitempty"`
ID string `json:"id,omitempty"`
Model string `json:"model,omitempty"`
Choices []Choice `json:"choices,omitempty"`
Data []Item `json:"data,omitempty"`
Usage OpenAIUsage `json:"usage"`
}
type Choice struct {
Index int `json:"index"`
FinishReason *string `json:"finish_reason"`
Message *Message `json:"message,omitempty"`
Delta *Message `json:"delta,omitempty"`
Text string `json:"text,omitempty"`
Logprobs *Logprobs `json:"logprobs,omitempty"`
}
type Logprobs struct {
Content []LogprobContent `json:"content,omitempty"`
}
type LogprobContent struct {
ID int32 `json:"id"`
Token string `json:"token"`
Bytes []int `json:"bytes,omitempty"`
Logprob float64 `json:"logprob"`
TopLogprobs []LogprobContent `json:"top_logprobs,omitempty"`
}
type Content struct {
Type string `json:"type" yaml:"type"`
Text string `json:"text" yaml:"text"`
ImageURL ContentURL `json:"image_url" yaml:"image_url"`
AudioURL ContentURL `json:"audio_url" yaml:"audio_url"`
VideoURL ContentURL `json:"video_url" yaml:"video_url"`
InputAudio InputAudio `json:"input_audio" yaml:"input_audio"`
}
type ContentURL struct {
URL string `json:"url" yaml:"url"`
}
type InputAudio struct {
// Format identifies the audio format, e.g. 'wav'.
Format string `json:"format" yaml:"format"`
// Data holds the base64-encoded audio data.
Data string `json:"data" yaml:"data"`
}
type OpenAIModel struct {
ID string `json:"id"`
Object string `json:"object"`
}
type ImageGenerationResponseFormat string
type ChatCompletionResponseFormatType string
type TranscriptionResponseFormatType string
const (
TranscriptionResponseFormatText = TranscriptionResponseFormatType("txt")
TranscriptionResponseFormatSrt = TranscriptionResponseFormatType("srt")
TranscriptionResponseFormatVtt = TranscriptionResponseFormatType("vtt")
TranscriptionResponseFormatLrc = TranscriptionResponseFormatType("lrc")
TranscriptionResponseFormatJson = TranscriptionResponseFormatType("json")
TranscriptionResponseFormatJsonVerbose = TranscriptionResponseFormatType("json_verbose")
)
type ChatCompletionResponseFormat struct {
Type ChatCompletionResponseFormatType `json:"type,omitempty"`
}
type JsonSchemaRequest struct {
Type string `json:"type"`
JsonSchema JsonSchema `json:"json_schema"`
}
type JsonSchema struct {
Name string `json:"name"`
Strict bool `json:"strict"`
Schema functions.Item `json:"schema"`
}
type OpenAIRequest struct {
PredictionOptions
Context context.Context `json:"-"`
Cancel context.CancelFunc `json:"-"`
// whisper
File string `json:"file" validate:"required"`
// Multiple input images for img2img or inpainting
Files []string `json:"files,omitempty"`
// Reference images for models that support them (e.g., Flux Kontext)
RefImages []string `json:"ref_images,omitempty"`
//whisper/image
ResponseFormat interface{} `json:"response_format,omitempty"`
// image
Size string `json:"size"`
// Prompt is read only by completion/image API calls
Prompt interface{} `json:"prompt" yaml:"prompt"`
// Edit endpoint
Instruction string `json:"instruction" yaml:"instruction"`
Input interface{} `json:"input" yaml:"input"`
Stop interface{} `json:"stop" yaml:"stop"`
// Messages is read only by chat/completion API calls
Messages []Message `json:"messages" yaml:"messages"`
// A list of available functions to call
Functions functions.Functions `json:"functions" yaml:"functions"`
FunctionCall interface{} `json:"function_call" yaml:"function_call"` // might be a string or an object
Tools []functions.Tool `json:"tools,omitempty" yaml:"tools"`
ToolsChoice interface{} `json:"tool_choice,omitempty" yaml:"tool_choice"`
Stream bool `json:"stream"`
// Image (not supported by OpenAI)
Quality string `json:"quality"`
Step int `json:"step"`
// A grammar to constrain the LLM output
Grammar string `json:"grammar" yaml:"grammar"`
JSONFunctionGrammarObject *functions.JSONFunctionStructure `json:"grammar_json_functions" yaml:"grammar_json_functions"`
Backend string `json:"backend" yaml:"backend"`
ModelBaseName string `json:"model_base_name" yaml:"model_base_name"`
ReasoningEffort string `json:"reasoning_effort" yaml:"reasoning_effort"`
Metadata map[string]string `json:"metadata" yaml:"metadata"`
}
type ModelsDataResponse struct {
Object string `json:"object"`
Data []OpenAIModel `json:"data"`
}