search

type Chunker interface {
	Chunk(ctx context.Context, doc *Document) []*DocumentChunk
}

type CodeDocument struct {
	*Document
	FilePath string       `json:"file_path"`
	Language string       `json:"language"`
	Symbols  []CodeSymbol `json:"symbols,omitempty"`
}

type CodeIndex struct {
	*SemanticIndex
	// contains filtered or unexported fields
}

type CodeSymbol struct {
	Name      string `json:"name"`
	Kind      string `json:"kind"` // "function", "class", "method", etc.
	StartLine int    `json:"start_line"`
	EndLine   int    `json:"end_line"`
	Signature string `json:"signature,omitempty"`
}

type Document struct {
	ID        string           `json:"id"`
	Content   string           `json:"content"`
	Metadata  map[string]any   `json:"metadata,omitempty"`
	Embedding Embedding        `json:"embedding,omitempty"`
	Chunks    []*DocumentChunk `json:"chunks,omitempty"`
}

type DocumentChunk struct {
	ID         string    `json:"id"`
	DocumentID string    `json:"document_id"`
	Content    string    `json:"content"`
	StartPos   int       `json:"start_pos"`
	EndPos     int       `json:"end_pos"`
	Embedding  Embedding `json:"embedding,omitempty"`
}

type Embedding []float64

type EmbeddingProvider interface {
	// Embed generates an embedding for the given text.
	Embed(ctx context.Context, text string) (Embedding, error)

	// EmbedBatch generates embeddings for multiple texts.
	EmbedBatch(ctx context.Context, texts []string) ([]Embedding, error)

	// Dimension returns the embedding dimension.
	Dimension() int
}

type FixedSizeChunker struct {
	Size      int
	Overlap   int
	MaxChunks int // Maximum chunks per document (0 = unlimited)
}

type IndexConfig struct {
	ChunkSize    int
	ChunkOverlap int
	MaxChunks    int
}

type IndexOption func(*SemanticIndex)

type SearchOptions struct {
	// Offset skips the first N results (for pagination).
	Offset int
	// Limit caps the number of returned results.
	// If zero, uses the topK parameter as limit.
	Limit int
}

type SearchResponse struct {
	Results    []*SearchResult `json:"results"`
	TotalCount int             `json:"total_count"`
	Offset     int             `json:"offset"`
	Limit      int             `json:"limit"`
}

type SearchResult struct {
	Document   *Document      `json:"document"`
	Chunk      *DocumentChunk `json:"chunk,omitempty"`
	Score      float64        `json:"score"`
	Highlights []string       `json:"highlights,omitempty"`
}

type SemanticIndex struct {
	// contains filtered or unexported fields
}

type SentenceChunker struct {
	MaxSentences int
	Overlap      int
	MaxChunks    int // Maximum chunks per document (0 = unlimited)
}