index

type BuildOptions struct {
	Path          string
	ReuseFromPath string
	Embedder      embed.Embedder

	// MaxChunkTokens sets the approximate maximum number of tokens (words)
	// per chunk. Sections that exceed this limit are split into smaller
	// sub-sections. Zero disables token-budget splitting.
	MaxChunkTokens int

	// ChunkOverlapTokens sets the approximate number of overlapping tokens
	// between adjacent sub-sections when a section is split. Zero disables
	// overlap.
	ChunkOverlapTokens int

	// Quantization controls the vector storage format. Supported values
	// are "float32" (default) and "int8". Int8 reduces storage by 4x at
	// the cost of minor precision loss.
	Quantization string
}

type BuildResult struct {
	Path                string
	RecordCount         int
	ChunkCount          int
	ReusedRecordCount   int
	ReusedChunkCount    int
	EmbeddedChunkCount  int
	EmbedderDimension   int
	EmbedderFingerprint string
	ContentFingerprint  string
}

type RecordQuery struct {
	Refs  []string
	Kinds []string
}

type Reranker interface {
	Rerank(ctx context.Context, query string, candidates []SearchHit) ([]SearchHit, error)
}

type SearchHit struct {
	ChunkID   int64
	Ref       string
	Kind      string
	Title     string
	SourceRef string
	Heading   string
	Content   string
	Metadata  map[string]string
	Score     float64
}

type SearchQuery struct {
	Path     string
	Text     string
	Limit    int
	Kinds    []string
	Embedder embed.Embedder
	Reranker Reranker
}

type Section struct {
	ChunkID   int64
	Ref       string
	Kind      string
	Title     string
	SourceRef string
	Heading   string
	Content   string
	Metadata  map[string]string
	Embedding []float64
}

type SectionQuery struct {
	Refs              []string
	Kinds             []string
	IncludeEmbeddings bool
}

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

type SnapshotSearchQuery struct {
	Text     string
	Limit    int
	Kinds    []string
	Embedder embed.Embedder
	Reranker Reranker
}

type Stats struct {
	Path                string
	RecordCount         int
	ChunkCount          int
	KindCounts          map[string]int
	SchemaVersion       string
	EmbedderDimension   int
	EmbedderFingerprint string
	ContentFingerprint  string
	CreatedAt           string
}

type UpdateOptions struct {
	Path     string
	Embedder embed.Embedder

	// MaxChunkTokens sets the approximate maximum number of tokens (words)
	// per chunk. It should match the chunking policy used to build the current
	// index if callers want incremental updates to remain section-compatible.
	MaxChunkTokens int

	// ChunkOverlapTokens sets the approximate number of overlapping tokens
	// between adjacent sub-sections when a section is split. It should match
	// the chunking policy used to build the current index.
	ChunkOverlapTokens int

	// Quantization, when provided, must match the existing index. Leaving it
	// empty reuses the stored quantization metadata.
	Quantization string
}

type UpdateResult struct {
	Path                string
	UpsertedCount       int
	RemovedCount        int
	RecordCount         int
	ChunkCount          int
	ReusedRecordCount   int
	ReusedChunkCount    int
	EmbeddedChunkCount  int
	EmbedderDimension   int
	EmbedderFingerprint string
	ContentFingerprint  string
}

type VectorSearchQuery struct {
	Embedding []float64
	Limit     int
	Kinds     []string
}