goai

type ContentPart interface {
	// contains filtered or unexported methods
}

type EmbedInput struct {
	// Model is the embedding model to use.
	Model model.EmbeddingModel

	// Value is the text to embed (for single embedding).
	Value string

	// Values is a list of texts to embed (for batch embedding).
	// If Value is set, it takes precedence.
	Values []string

	// Dimensions is the desired embedding dimensions (if model supports it).
	Dimensions *int

	// AbortSignal allows cancellation.
	AbortSignal context.Context

	// Headers are additional HTTP headers.
	Headers map[string]string

	// ProviderOptions are provider-specific options.
	ProviderOptions map[string]any
}

type EmbedResult struct {
	// Embedding is the generated embedding (for single value input).
	Embedding []float64

	// Embeddings contains all generated embeddings (for batch input).
	Embeddings []Embedding

	// Usage contains usage information.
	Usage EmbeddingUsage

	// Response contains response metadata.
	Response EmbeddingResponseMeta
}

type Embedding struct {
	// Values is the embedding vector.
	Values []float64

	// Index is the index of the input text this embedding corresponds to.
	Index int
}

type EmbeddingResponseMeta struct {
	// ID is the response identifier.
	ID string

	// Model is the model used for generation.
	Model string

	// Headers contains response headers.
	Headers map[string]string
}

type EmbeddingUsage struct {
	// Tokens is the total number of tokens used.
	Tokens int
}

type EventType = stream.EventType

type GenerateTextResponseMeta struct {
	// ID is the response ID from the provider.
	ID string

	// Model is the model that was used.
	Model string

	// Messages contains the conversation messages including the response.
	Messages []message.Message
}

type GenerateTextResult struct {
	// Text is the generated text from the final step.
	Text string

	// ToolCalls contains tool calls from the final step.
	ToolCalls []stream.ToolCall

	// ToolResults contains tool results from the final step.
	ToolResults []stream.ToolResultEvent

	// FinishReason indicates why the final step stopped.
	FinishReason stream.FinishReason

	// Usage contains total token usage across all steps.
	Usage stream.Usage

	// Steps contains all step results when MaxSteps > 1.
	Steps []StepResult

	// Output is the parsed result from Input.Output's ParseComplete.
	// Only populated when Input.Output was set and the final step finished
	// with FinishReasonStop. Type-assert to the expected type.
	Output any

	// Response contains additional response metadata.
	Response GenerateTextResponseMeta
}

type GeneratedImage struct {
	// Base64 is the base64-encoded image data.
	Base64 string

	// URL is the URL of the generated image (if available).
	URL string

	// MimeType is the MIME type of the image (e.g., "image/png").
	MimeType string

	// Seed is the seed used for generation (if available).
	Seed *int64

	// RevisedPrompt is the revised prompt used for generation (if available).
	RevisedPrompt string
}

type ImageInput struct {
	// Model is the image model to use.
	Model model.ImageModel

	// Prompt is the text description of the image to generate.
	Prompt string

	// N is the number of images to generate (default: 1).
	N int

	// Size is the size of the generated images (e.g., "1024x1024").
	Size string

	// AspectRatio is the aspect ratio (e.g., "16:9", "1:1").
	// Use this instead of Size for models that support aspect ratio.
	AspectRatio string

	// Seed for deterministic generation (if supported).
	Seed *int64

	// AbortSignal allows cancellation.
	AbortSignal context.Context

	// Headers are additional HTTP headers.
	Headers map[string]string

	// ProviderOptions are provider-specific options.
	ProviderOptions map[string]any
}

type ImageResponseMeta struct {
	// ID is the response identifier.
	ID string

	// Model is the model used for generation.
	Model string

	// Timestamp is the creation timestamp.
	Timestamp int64

	// Headers contains response headers.
	Headers map[string]string
}

type ImageResult struct {
	// Images contains the generated images.
	Images []GeneratedImage

	// Warnings contains any warnings from the generation process.
	Warnings []stream.Warning

	// Usage contains usage information (if available).
	Usage *ImageUsage

	// Response contains response metadata.
	Response ImageResponseMeta
}

type ImageUsage struct {
	// TotalTokens is the total number of tokens used (for models that use tokens).
	TotalTokens int

	// Steps is the number of diffusion steps (for diffusion models).
	Steps int
}

type Message = message.Message

type Part = message.Part

type RankedDocument struct {
	// Index is the original index of the document.
	Index int

	// Score is the relevance score (higher is more relevant).
	Score float64

	// Document is the document text (if ReturnDocuments was true).
	Document string
}

type ReasoningContentPart struct {
	ID              string
	Text            string
	ProviderOptions map[string]any // Contains provider-specific data like "reasoningEncryptedContent"
}

type ReasoningPart = message.ReasoningPart

type RerankInput struct {
	// Model is the reranking model to use.
	Model model.RerankingModel

	// Query is the query to rank documents against.
	Query string

	// Documents is the list of documents to rerank.
	Documents []string

	// TopN is the number of top results to return (0 means return all).
	TopN int

	// ReturnDocuments specifies whether to include document text in results.
	ReturnDocuments bool

	// AbortSignal allows cancellation.
	AbortSignal context.Context

	// Headers are additional HTTP headers.
	Headers map[string]string

	// ProviderOptions are provider-specific options.
	ProviderOptions map[string]any
}

type RerankResponseMeta struct {
	// ID is the response identifier.
	ID string

	// Model is the model used for reranking.
	Model string

	// Headers contains response headers.
	Headers map[string]string
}

type RerankResult struct {
	// Results contains the reranked documents.
	Results []RankedDocument

	// Usage contains usage information.
	Usage RerankUsage

	// Response contains response metadata.
	Response RerankResponseMeta
}

type RerankUsage struct {
	// SearchUnits is the number of search units used.
	SearchUnits int

	// Tokens is the total number of tokens processed.
	Tokens int
}

type SpeechInput struct {
	// Model is the speech model to use.
	Model model.SpeechModel

	// Text is the text to convert to speech.
	Text string

	// Voice is the voice to use for generation.
	Voice string

	// OutputFormat is the desired output format (e.g., "mp3", "wav", "opus").
	// Default depends on the provider.
	OutputFormat string

	// Speed is the speed of the generated audio (0.25 to 4.0, 1.0 is normal).
	Speed *float64

	// AbortSignal allows cancellation.
	AbortSignal context.Context

	// Headers are additional HTTP headers.
	Headers map[string]string

	// ProviderOptions are provider-specific options.
	ProviderOptions map[string]any
}

type SpeechResponseMeta struct {
	// ID is the response identifier.
	ID string

	// Model is the model used for generation.
	Model string

	// Headers contains response headers.
	Headers map[string]string
}

type SpeechResult struct {
	// Audio is the generated audio data.
	Audio []byte

	// AudioReader provides streaming access to the audio data.
	AudioReader io.Reader

	// MimeType is the MIME type of the audio (e.g., "audio/mpeg").
	MimeType string

	// Duration is the duration of the audio in seconds (if available).
	Duration *float64

	// Warnings contains any warnings from the generation process.
	Warnings []stream.Warning

	// Usage contains usage information (if available).
	Usage *SpeechUsage

	// Response contains response metadata.
	Response SpeechResponseMeta
}

type SpeechUsage struct {
	// Characters is the number of characters processed.
	Characters int

	// Seconds is the duration of generated audio in seconds.
	Seconds float64
}

type StepResponseMeta struct {
	// Messages are the response messages generated in this step.
	Messages []message.Message
}

type StepResult struct {
	// Content contains all content parts generated in this step.
	Content []ContentPart

	// FinishReason indicates why this step ended.
	FinishReason stream.FinishReason

	// Usage contains token usage for this step.
	Usage stream.Usage

	// Response contains response metadata including messages.
	Response StepResponseMeta
}

type StopCondition func(steps []StepResult) bool

type StreamEvent = stream.Event

type StreamResult = stream.Result

type TextContentPart struct {
	Text string
}

type TextPart = message.TextPart

type ToolCallContentPart struct {
	stream.ToolCall
	Dynamic bool
}

type ToolCallPart = message.ToolCallPart

type ToolResultContentPart struct {
	stream.ToolResultEvent
	Dynamic bool
}

type ToolSet = tool.Set

type TranscribeInput struct {
	// Model is the transcription model to use.
	Model model.TranscriptionModel

	// Audio is the audio data to transcribe.
	Audio []byte

	// AudioReader provides streaming access to audio data (alternative to Audio).
	AudioReader io.Reader

	// MimeType is the MIME type of the audio (e.g., "audio/wav", "audio/mp3").
	MimeType string

	// Filename is the filename of the audio (used for format detection).
	Filename string

	// Language is the language code of the audio (e.g., "en", "es").
	// If not provided, the model will attempt to detect the language.
	Language string

	// Prompt is an optional hint for the model (can improve accuracy).
	Prompt string

	// AbortSignal allows cancellation.
	AbortSignal context.Context

	// Headers are additional HTTP headers.
	Headers map[string]string

	// ProviderOptions are provider-specific options.
	ProviderOptions map[string]any
}

type TranscriptionResponseMeta struct {
	// ID is the response identifier.
	ID string

	// Model is the model used for transcription.
	Model string

	// Headers contains response headers.
	Headers map[string]string
}

type TranscriptionResult struct {
	// Text is the transcribed text.
	Text string

	// Segments contains detailed segment information (if available).
	Segments []TranscriptionSegment

	// Language is the detected language code.
	Language string

	// Duration is the duration of the audio in seconds (if available).
	Duration *float64

	// Warnings contains any warnings from the transcription process.
	Warnings []stream.Warning

	// Usage contains usage information (if available).
	Usage *TranscriptionUsage

	// Response contains response metadata.
	Response TranscriptionResponseMeta
}

type TranscriptionSegment struct {
	// ID is the segment identifier.
	ID int

	// Text is the transcribed text for this segment.
	Text string

	// Start is the start time in seconds.
	Start float64

	// End is the end time in seconds.
	End float64

	// Confidence is the confidence score (0 to 1).
	Confidence float64

	// Words contains word-level information (if available).
	Words []TranscriptionWord
}

type TranscriptionUsage struct {
	// DurationSeconds is the duration of audio processed in seconds.
	DurationSeconds float64
}

type TranscriptionWord struct {
	// Word is the transcribed word.
	Word string

	// Start is the start time in seconds.
	Start float64

	// End is the end time in seconds.
	End float64

	// Confidence is the confidence score (0 to 1).
	Confidence float64
}