semantic

package
v1.2.0 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Jan 1, 2026 License: MIT Imports: 28 Imported by: 0

Documentation

Index

Constants

This section is empty.

Variables

View Source 
var (
	// ErrNotFound indicates that a chunk was not found in storage
	ErrNotFound = errors.New("chunk not found")

	// ErrStorageClosed indicates that the storage has been closed
	ErrStorageClosed = errors.New("storage is closed")
)

Functions

func FormatError 

func FormatError(err error) string

FormatError formats an error with user-friendly output

func GetChunkBuffer 

func GetChunkBuffer() *chunkBuffer

GetChunkBuffer gets a chunk buffer from the pool

func GetEmbeddingBuffer 

func GetEmbeddingBuffer(size int) *[]byte

GetEmbeddingBuffer gets a buffer from the pool, sized appropriately

func IndexPath 

func IndexPath(repoRoot string) string

IndexPath returns the default index path for a repository

func LanguageFromExtension 

func LanguageFromExtension(filename string) string

LanguageFromExtension extracts the language identifier from a filename

func PutChunkBuffer 

func PutChunkBuffer(buf *chunkBuffer)

PutChunkBuffer returns a chunk buffer to the pool

func PutEmbeddingBuffer 

func PutEmbeddingBuffer(buf *[]byte)

PutEmbeddingBuffer returns a buffer to the pool

Types

type Chunk 

type Chunk struct {
	ID        string    `json:"id"`
	FilePath  string    `json:"file_path"`
	Type      ChunkType `json:"type"`
	Name      string    `json:"name"`
	Signature string    `json:"signature,omitempty"`
	Content   string    `json:"content"`
	StartLine int       `json:"start_line"`
	EndLine   int       `json:"end_line"`
	Language  string    `json:"language"`
}

Chunk represents a semantic unit of code (function, struct, etc.)

func (*Chunk) GenerateID 

func (c *Chunk) GenerateID() string

GenerateID creates a deterministic ID for the chunk based on its content

type ChunkType 

type ChunkType int

ChunkType represents the type of code chunk 

const (
	ChunkFunction ChunkType = iota
	ChunkMethod
	ChunkStruct
	ChunkInterface
	ChunkFile
)

func ParseChunkType 

func ParseChunkType(s string) (ChunkType, error)

ParseChunkType parses a string into a ChunkType

func (ChunkType) MarshalJSON 

func (ct ChunkType) MarshalJSON() ([]byte, error)

MarshalJSON implements json.Marshaler for ChunkType

func (ChunkType) String 

func (ct ChunkType) String() string

String returns the string representation of ChunkType

func (*ChunkType) UnmarshalJSON 

func (ct *ChunkType) UnmarshalJSON(data []byte) error

UnmarshalJSON implements json.Unmarshaler for ChunkType

type Chunker 

type Chunker interface {
	// Chunk breaks source code into semantic chunks
	Chunk(path string, content []byte) ([]Chunk, error)

	// SupportedExtensions returns the file extensions this chunker handles
	SupportedExtensions() []string
}

Chunker is the interface for language-specific code chunking

type ChunkerFactory 

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

ChunkerFactory manages language-specific chunkers

func NewChunkerFactory 

func NewChunkerFactory() *ChunkerFactory

NewChunkerFactory creates a new chunker factory

func (*ChunkerFactory) GetByExtension 

func (f *ChunkerFactory) GetByExtension(filename string) (Chunker, bool)

GetByExtension returns the appropriate chunker based on filename extension

func (*ChunkerFactory) GetChunker 

func (f *ChunkerFactory) GetChunker(ext string) (Chunker, bool)

GetChunker returns a chunker for the specified language/extension

func (*ChunkerFactory) Register 

func (f *ChunkerFactory) Register(ext string, chunker Chunker)

Register adds a chunker for a specific language/extension

func (*ChunkerFactory) SupportedExtensions 

func (f *ChunkerFactory) SupportedExtensions() []string

SupportedExtensions returns all registered extensions

type CohereConfig 

type CohereConfig struct {
	APIKey    string        // Cohere API key (required)
	Model     string        // Model name (default: embed-english-v3.0)
	BaseURL   string        // Base URL (default: https://api.cohere.com)
	InputType string        // Input type: search_document, search_query, classification, clustering
	Timeout   time.Duration // Request timeout
}

CohereConfig holds configuration for the Cohere embedding client

func (*CohereConfig) Validate 

func (c *CohereConfig) Validate() error

Validate checks if the config is valid

type CohereEmbedder 

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

CohereEmbedder generates embeddings using the Cohere API

func NewCohereEmbedder 

func NewCohereEmbedder(cfg CohereConfig) (*CohereEmbedder, error)

NewCohereEmbedder creates a new Cohere embedding client

func NewCohereEmbedderFromEnv 

func NewCohereEmbedderFromEnv() (*CohereEmbedder, error)

NewCohereEmbedderFromEnv creates a CohereEmbedder from environment variables

func (*CohereEmbedder) Dimensions 

func (e *CohereEmbedder) Dimensions() int

Dimensions returns the embedding dimension (0 if unknown)

func (*CohereEmbedder) Embed 

func (e *CohereEmbedder) Embed(ctx context.Context, text string) ([]float32, error)

Embed generates an embedding for a single text

func (*CohereEmbedder) EmbedBatch 

func (e *CohereEmbedder) EmbedBatch(ctx context.Context, texts []string) ([][]float32, error)

EmbedBatch generates embeddings for multiple texts

func (*CohereEmbedder) Model 

func (e *CohereEmbedder) Model() string

Model returns the model name

func (*CohereEmbedder) SetInputType 

func (e *CohereEmbedder) SetInputType(inputType string)

SetInputType allows changing the input type for different use cases Use "search_query" for queries, "search_document" for documents to be searched

type CompactEmbedding 

type CompactEmbedding struct {
	Data   []int8
	Scale  float32
	Offset float32
}

CompactEmbedding reduces precision for storage (optional memory savings) Converts float32 embeddings to int8 quantized values (-127 to 127) This reduces memory by 75% but loses some precision

func Quantize 

func Quantize(embedding []float32) *CompactEmbedding

Quantize converts a float32 embedding to a quantized form

func (*CompactEmbedding) Dequantize 

func (c *CompactEmbedding) Dequantize() []float32

Dequantize converts a quantized embedding back to float32

type Embedder 

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

Embedder generates embeddings using an OpenAI-compatible API

func NewEmbedder 

func NewEmbedder(cfg EmbedderConfig) (*Embedder, error)

NewEmbedder creates a new Embedder with the given configuration

func (*Embedder) Dimensions 

func (e *Embedder) Dimensions() int

Dimensions returns the embedding dimension (0 if unknown)

func (*Embedder) Embed 

func (e *Embedder) Embed(ctx context.Context, text string) ([]float32, error)

Embed generates an embedding for a single text

func (*Embedder) EmbedBatch 

func (e *Embedder) EmbedBatch(ctx context.Context, texts []string) ([][]float32, error)

EmbedBatch generates embeddings for multiple texts

func (*Embedder) Model 

func (e *Embedder) Model() string

Model returns the model name

type EmbedderConfig 

type EmbedderConfig struct {
	APIURL     string        // Base URL for embedding API (OpenAI-compatible)
	Model      string        // Model name (e.g., "nomic-embed-text", "mxbai-embed-large", "text-embedding-ada-002")
	APIKey     string        // API key (optional for local models)
	Timeout    time.Duration // Request timeout
	MaxRetries int           // Maximum retry attempts
}

EmbedderConfig holds configuration for the embedding client

func DefaultEmbedderConfig 

func DefaultEmbedderConfig() EmbedderConfig

DefaultEmbedderConfig returns sensible defaults

type EmbedderInterface 

type EmbedderInterface interface {
	Embed(ctx context.Context, text string) ([]float32, error)
	EmbedBatch(ctx context.Context, texts []string) ([][]float32, error)
	Dimensions() int
}

EmbedderInterface defines the interface for embedding generation (separate from the concrete Embedder to allow mocking)

type ErrorType 

type ErrorType int

Error types for better error handling 

const (
	ErrTypeUnknown ErrorType = iota
	ErrTypeNotFound
	ErrTypeConnection
	ErrTypeInvalidInput
	ErrTypeConfiguration
)

type GenericChunker 

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

GenericChunker implements a simple text-based chunker for unsupported file types

func NewGenericChunker 

func NewGenericChunker(maxChunkSize int) *GenericChunker

NewGenericChunker creates a new generic text chunker

func (*GenericChunker) Chunk 

func (c *GenericChunker) Chunk(path string, content []byte) ([]Chunk, error)

Chunk splits content into chunks based on paragraphs/size

func (*GenericChunker) SupportedExtensions 

func (c *GenericChunker) SupportedExtensions() []string

SupportedExtensions returns the file extensions this chunker handles

type GoChunker 

type GoChunker struct{}

GoChunker implements the Chunker interface for Go source code

func NewGoChunker 

func NewGoChunker() *GoChunker

NewGoChunker creates a new Go AST-based chunker

func (*GoChunker) Chunk 

func (c *GoChunker) Chunk(path string, content []byte) ([]Chunk, error)

Chunk parses Go source code and extracts semantic chunks

func (*GoChunker) SupportedExtensions 

func (c *GoChunker) SupportedExtensions() []string

SupportedExtensions returns the file extensions this chunker handles

type HuggingFaceConfig 

type HuggingFaceConfig struct {
	APIKey       string        // HuggingFace API key (required)
	Model        string        // Model name (default: sentence-transformers/all-MiniLM-L6-v2)
	BaseURL      string        // Base URL (default: https://api-inference.huggingface.co)
	Timeout      time.Duration // Request timeout
	WaitForModel bool          // Wait for model to load if not ready
}

HuggingFaceConfig holds configuration for the HuggingFace embedding client

func (*HuggingFaceConfig) Validate 

func (c *HuggingFaceConfig) Validate() error

Validate checks if the config is valid

type HuggingFaceEmbedder 

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

HuggingFaceEmbedder generates embeddings using the HuggingFace Inference API

func NewHuggingFaceEmbedder 

func NewHuggingFaceEmbedder(cfg HuggingFaceConfig) (*HuggingFaceEmbedder, error)

NewHuggingFaceEmbedder creates a new HuggingFace embedding client

func NewHuggingFaceEmbedderFromEnv 

func NewHuggingFaceEmbedderFromEnv() (*HuggingFaceEmbedder, error)

NewHuggingFaceEmbedderFromEnv creates a HuggingFaceEmbedder from environment variables

func (*HuggingFaceEmbedder) Dimensions 

func (e *HuggingFaceEmbedder) Dimensions() int

Dimensions returns the embedding dimension (0 if unknown)

func (*HuggingFaceEmbedder) Embed 

func (e *HuggingFaceEmbedder) Embed(ctx context.Context, text string) ([]float32, error)

Embed generates an embedding for a single text

func (*HuggingFaceEmbedder) EmbedBatch 

func (e *HuggingFaceEmbedder) EmbedBatch(ctx context.Context, texts []string) ([][]float32, error)

EmbedBatch generates embeddings for multiple texts

func (*HuggingFaceEmbedder) Model 

func (e *HuggingFaceEmbedder) Model() string

Model returns the model name

type IndexHealth 

type IndexHealth struct {
	Status        string     `json:"status"` // "healthy", "stale", "missing"
	Stats         IndexStats `json:"stats"`
	StaleFiles    int        `json:"stale_files"`
	NewFiles      int        `json:"new_files"`
	ModifiedFiles int        `json:"modified_files"`
}

IndexHealth represents the health status of the index

type IndexManager 

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

IndexManager handles indexing operations

func NewIndexManager 

func NewIndexManager(storage Storage, embedder EmbedderInterface, factory *ChunkerFactory) *IndexManager

NewIndexManager creates a new IndexManager

func (*IndexManager) Index 

func (m *IndexManager) Index(ctx context.Context, rootPath string, opts IndexOptions) (*IndexResult, error)

Index builds or rebuilds the semantic index for a directory

func (*IndexManager) Status 

func (m *IndexManager) Status(ctx context.Context) (*IndexStats, error)

Status returns index statistics

func (*IndexManager) Update 

func (m *IndexManager) Update(ctx context.Context, rootPath string, opts UpdateOptions) (*UpdateResult, error)

Update performs incremental index update

type IndexOptions 

type IndexOptions struct {
	Includes []string // Glob patterns to include (e.g., "*.go")
	Excludes []string // Directory/pattern names to exclude (e.g., "vendor", "node_modules")
	Force    bool     // Re-index all files even if unchanged
}

IndexOptions configures indexing behavior

type IndexResult 

type IndexResult struct {
	FilesProcessed int
	FilesSkipped   int
	ChunksCreated  int
	Errors         []string
}

IndexResult contains statistics from an indexing operation

type IndexStats 

type IndexStats struct {
	FilesIndexed   int    `json:"files_indexed"`
	ChunksTotal    int    `json:"chunks_total"`
	EmbeddingModel string `json:"embedding_model"`
	IndexSizeBytes int64  `json:"index_size_bytes"`
	LastUpdated    string `json:"last_updated"`
}

IndexStats holds statistics about the semantic index

type JSChunker 

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

JSChunker implements the Chunker interface for JavaScript/TypeScript

func NewJSChunker 

func NewJSChunker() *JSChunker

NewJSChunker creates a new JavaScript/TypeScript chunker

func (*JSChunker) Chunk 

func (c *JSChunker) Chunk(path string, content []byte) ([]Chunk, error)

Chunk parses JavaScript/TypeScript source code and extracts semantic chunks

func (*JSChunker) SupportedExtensions 

func (c *JSChunker) SupportedExtensions() []string

SupportedExtensions returns the file extensions this chunker handles

type ListOptions 

type ListOptions struct {
	Limit    int    // Maximum number of chunks to return (0 = no limit)
	Offset   int    // Number of chunks to skip
	FilePath string // Filter by file path
	Type     string // Filter by chunk type
	Language string // Filter by language
}

ListOptions configures how chunks are listed

type MemoryStats 

type MemoryStats struct {
	ChunksInMemory   int
	EmbeddingBytes   int64
	EstimatedTotalMB float64
}

MemoryStats holds memory usage statistics

func EstimateMemory 

func EstimateMemory(chunks int, embeddingDim int) MemoryStats

EstimateMemory estimates memory usage for a set of chunks

type OfflineEmbedder 

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

OfflineEmbedder wraps an embedder with offline mode support

func NewOfflineEmbedder 

func NewOfflineEmbedder(embedder EmbedderInterface, dimensions int) *OfflineEmbedder

NewOfflineEmbedder creates an embedder with offline fallback support

func (*OfflineEmbedder) Dimensions 

func (o *OfflineEmbedder) Dimensions() int

Dimensions returns the embedding dimensions

func (*OfflineEmbedder) Embed 

func (o *OfflineEmbedder) Embed(ctx context.Context, text string) ([]float32, error)

Embed tries to use the embedder, falls back to keyword embedding if unavailable

func (*OfflineEmbedder) EmbedBatch 

func (o *OfflineEmbedder) EmbedBatch(ctx context.Context, texts []string) ([][]float32, error)

EmbedBatch tries to use the embedder batch, falls back if unavailable

func (*OfflineEmbedder) IsOffline 

func (o *OfflineEmbedder) IsOffline() bool

IsOffline returns true if operating in offline mode

type OfflineMode 

type OfflineMode int

OfflineMode represents the current offline mode state 

const (
	// OnlineMode indicates the embedder is working normally
	OnlineMode OfflineMode = iota
	// OfflineFallback indicates we're using keyword fallback
	OfflineFallback
)

type OfflineSearcher 

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

OfflineSearcher provides search capabilities with offline fallback

func NewOfflineSearcher 

func NewOfflineSearcher(storage Storage, embedder *OfflineEmbedder) *OfflineSearcher

NewOfflineSearcher creates a searcher with offline support

func (*OfflineSearcher) IsOffline 

func (s *OfflineSearcher) IsOffline() bool

IsOffline returns true if the searcher is operating in offline mode

func (*OfflineSearcher) Search 

func (s *OfflineSearcher) Search(ctx context.Context, query string, opts SearchOptions) ([]SearchResult, error)

Search performs semantic or keyword-based search

type OpenRouterConfig 

type OpenRouterConfig struct {
	APIKey     string        // OpenRouter API key (required)
	Model      string        // Model name (default: mistralai/codestral-embed-2505)
	BaseURL    string        // Base URL (default: https://openrouter.ai)
	Timeout    time.Duration // Request timeout
	MaxRetries int           // Maximum retry attempts for rate limiting
}

OpenRouterConfig holds configuration for the OpenRouter embedding client

func (*OpenRouterConfig) Validate 

func (c *OpenRouterConfig) Validate() error

Validate checks if the config is valid

type OpenRouterEmbedder 

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

OpenRouterEmbedder generates embeddings using the OpenRouter API

func NewOpenRouterEmbedder 

func NewOpenRouterEmbedder(cfg OpenRouterConfig) (*OpenRouterEmbedder, error)

NewOpenRouterEmbedder creates a new OpenRouter embedding client

func NewOpenRouterEmbedderFromEnv 

func NewOpenRouterEmbedderFromEnv() (*OpenRouterEmbedder, error)

NewOpenRouterEmbedderFromEnv creates an OpenRouterEmbedder from environment variables

func (*OpenRouterEmbedder) Dimensions 

func (e *OpenRouterEmbedder) Dimensions() int

Dimensions returns the embedding dimension (0 if unknown)

func (*OpenRouterEmbedder) Embed 

func (e *OpenRouterEmbedder) Embed(ctx context.Context, text string) ([]float32, error)

Embed generates an embedding for a single text

func (*OpenRouterEmbedder) EmbedBatch 

func (e *OpenRouterEmbedder) EmbedBatch(ctx context.Context, texts []string) ([][]float32, error)

EmbedBatch generates embeddings for multiple texts

func (*OpenRouterEmbedder) Model 

func (e *OpenRouterEmbedder) Model() string

Model returns the model name

type PHPChunker 

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

PHPChunker implements the Chunker interface for PHP

func NewPHPChunker 

func NewPHPChunker() *PHPChunker

NewPHPChunker creates a new PHP chunker

func (*PHPChunker) Chunk 

func (c *PHPChunker) Chunk(path string, content []byte) ([]Chunk, error)

Chunk parses PHP source code and extracts semantic chunks

func (*PHPChunker) SupportedExtensions 

func (c *PHPChunker) SupportedExtensions() []string

SupportedExtensions returns the file extensions this chunker handles

type PythonChunker 

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

PythonChunker implements the Chunker interface for Python

func NewPythonChunker 

func NewPythonChunker() *PythonChunker

NewPythonChunker creates a new Python chunker

func (*PythonChunker) Chunk 

func (c *PythonChunker) Chunk(path string, content []byte) ([]Chunk, error)

Chunk parses Python source code and extracts semantic chunks

func (*PythonChunker) SupportedExtensions 

func (c *PythonChunker) SupportedExtensions() []string

SupportedExtensions returns the file extensions this chunker handles

type QdrantConfig 

type QdrantConfig struct {
	APIKey         string
	URL            string // Full URL like https://abc123.qdrant.io:6334
	CollectionName string
	EmbeddingDim   int
}

QdrantConfig holds configuration for Qdrant storage

func (*QdrantConfig) Validate 

func (c *QdrantConfig) Validate() error

Validate checks if the config is valid

type QdrantStorage 

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

QdrantStorage implements the Storage interface using Qdrant cloud

func NewQdrantStorage 

func NewQdrantStorage(config QdrantConfig) (*QdrantStorage, error)

NewQdrantStorage creates a new Qdrant-based storage

func NewQdrantStorageFromEnv 

func NewQdrantStorageFromEnv(embeddingDim int) (*QdrantStorage, error)

NewQdrantStorageFromEnv creates a QdrantStorage from environment variables Env vars: QDRANT_API_KEY, QDRANT_API_URL, QDRANT_COLLECTION (optional, default: llm_semantic)

func (*QdrantStorage) Close 

func (s *QdrantStorage) Close() error

func (*QdrantStorage) Create 

func (s *QdrantStorage) Create(ctx context.Context, chunk Chunk, embedding []float32) error

func (*QdrantStorage) Delete 

func (s *QdrantStorage) Delete(ctx context.Context, id string) error

func (*QdrantStorage) DeleteByFilePath 

func (s *QdrantStorage) DeleteByFilePath(ctx context.Context, filePath string) (int, error)

func (*QdrantStorage) DeleteCollection 

func (s *QdrantStorage) DeleteCollection() error

DeleteCollection removes the collection (used for testing cleanup)

func (*QdrantStorage) List 

func (s *QdrantStorage) List(ctx context.Context, opts ListOptions) ([]Chunk, error)

func (*QdrantStorage) Read 

func (s *QdrantStorage) Read(ctx context.Context, id string) (*Chunk, error)

func (*QdrantStorage) Search 

func (s *QdrantStorage) Search(ctx context.Context, queryEmbedding []float32, opts SearchOptions) ([]SearchResult, error)

func (*QdrantStorage) Stats 

func (s *QdrantStorage) Stats(ctx context.Context) (*IndexStats, error)

func (*QdrantStorage) Update 

func (s *QdrantStorage) Update(ctx context.Context, chunk Chunk, embedding []float32) error

type SQLiteStorage 

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

SQLiteStorage implements the Storage interface using SQLite

func NewSQLiteStorage 

func NewSQLiteStorage(dbPath string, embeddingDim int) (*SQLiteStorage, error)

NewSQLiteStorage creates a new SQLite-based storage

func (*SQLiteStorage) Close 

func (s *SQLiteStorage) Close() error

func (*SQLiteStorage) Create 

func (s *SQLiteStorage) Create(ctx context.Context, chunk Chunk, embedding []float32) error

func (*SQLiteStorage) Delete 

func (s *SQLiteStorage) Delete(ctx context.Context, id string) error

func (*SQLiteStorage) DeleteByFilePath 

func (s *SQLiteStorage) DeleteByFilePath(ctx context.Context, filePath string) (int, error)

func (*SQLiteStorage) List 

func (s *SQLiteStorage) List(ctx context.Context, opts ListOptions) ([]Chunk, error)

func (*SQLiteStorage) Read 

func (s *SQLiteStorage) Read(ctx context.Context, id string) (*Chunk, error)

func (*SQLiteStorage) Search 

func (s *SQLiteStorage) Search(ctx context.Context, queryEmbedding []float32, opts SearchOptions) ([]SearchResult, error)

func (*SQLiteStorage) Stats 

func (s *SQLiteStorage) Stats(ctx context.Context) (*IndexStats, error)

func (*SQLiteStorage) Update 

func (s *SQLiteStorage) Update(ctx context.Context, chunk Chunk, embedding []float32) error

type SearchOptions 

type SearchOptions struct {
	TopK       int     // Maximum number of results to return
	Threshold  float32 // Minimum similarity score (0.0 - 1.0)
	Type       string  // Filter by chunk type
	PathFilter string  // Filter by file path pattern (glob)
}

SearchOptions configures how vector search is performed

type SearchResult 

type SearchResult struct {
	Chunk     Chunk     `json:"chunk"`
	Score     float32   `json:"score"`
	Embedding []float32 `json:"-"` // Not included in JSON output
}

SearchResult represents a chunk with its similarity score

func (SearchResult) MinimalJSON 

func (sr SearchResult) MinimalJSON() string

MinimalJSON returns a compact JSON representation for --min output

type Searcher 

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

Searcher orchestrates semantic search across the index

func NewSearcher 

func NewSearcher(storage Storage, embedder EmbedderInterface) *Searcher

NewSearcher creates a new Searcher with the given storage and embedder

func (*Searcher) Search 

func (s *Searcher) Search(ctx context.Context, query string, opts SearchOptions) ([]SearchResult, error)

Search performs semantic search using the query text

func (*Searcher) SearchMultiple 

func (s *Searcher) SearchMultiple(ctx context.Context, queries []string, opts SearchOptions) ([]SearchResult, error)

SearchMultiple performs search with multiple query terms and combines results

type SemanticError 

type SemanticError struct {
	Type    ErrorType
	Message string
	Cause   error
	Hint    string
}

SemanticError provides structured error information

func ErrChunkingFailure 

func ErrChunkingFailure(filePath string, cause error) *SemanticError

ErrChunkingFailure creates an error for code chunking failures

func ErrConnectionFailed 

func ErrConnectionFailed(cause error) *SemanticError

ErrConnectionFailed creates an error for API connection failures

func ErrEmbeddingFailure 

func ErrEmbeddingFailure(cause error) *SemanticError

ErrEmbeddingFailure creates an error for embedding generation failures

func ErrIndexNotFound 

func ErrIndexNotFound() *SemanticError

ErrIndexNotFound creates an error for when the index doesn't exist

func ErrInvalidPath 

func ErrInvalidPath(path string, cause error) *SemanticError

ErrInvalidPath creates an error for invalid file paths

func ErrInvalidQuery 

func ErrInvalidQuery(query string) *SemanticError

ErrInvalidQuery creates an error for invalid search queries

func ErrStorageFailure 

func ErrStorageFailure(operation string, cause error) *SemanticError

ErrStorageFailure creates an error for storage-related issues

func (*SemanticError) Error 

func (e *SemanticError) Error() string

func (*SemanticError) FormatWithHint 

func (e *SemanticError) FormatWithHint() string

FormatWithHint returns the error message with hint if available

func (*SemanticError) Unwrap 

func (e *SemanticError) Unwrap() error

func (*SemanticError) WithHint 

func (e *SemanticError) WithHint(hint string) *SemanticError

WithHint adds a helpful hint to the error

type Storage 

type Storage interface {
	// Create stores a new chunk with its embedding
	Create(ctx context.Context, chunk Chunk, embedding []float32) error

	// Read retrieves a chunk by its ID
	Read(ctx context.Context, id string) (*Chunk, error)

	// Update replaces an existing chunk and its embedding
	Update(ctx context.Context, chunk Chunk, embedding []float32) error

	// Delete removes a chunk by its ID
	Delete(ctx context.Context, id string) error

	// DeleteByFilePath removes all chunks for a given file path
	DeleteByFilePath(ctx context.Context, filePath string) (int, error)

	// List retrieves chunks based on filter options
	List(ctx context.Context, opts ListOptions) ([]Chunk, error)

	// Search finds chunks similar to the query embedding
	Search(ctx context.Context, queryEmbedding []float32, opts SearchOptions) ([]SearchResult, error)

	// Stats returns statistics about the stored index
	Stats(ctx context.Context) (*IndexStats, error)

	// Close releases any resources held by the storage
	Close() error
}

Storage defines the interface for persisting and querying chunks with embeddings

type StreamingChunkProcessor 

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

StreamingChunkProcessor processes chunks without loading all into memory

func NewStreamingChunkProcessor 

func NewStreamingChunkProcessor(batchSize int, processor func([]Chunk) error) *StreamingChunkProcessor

NewStreamingChunkProcessor creates a new streaming processor

func (*StreamingChunkProcessor) Process 

func (p *StreamingChunkProcessor) Process(chunks <-chan Chunk) error

Process processes chunks in batches

type UpdateOptions 

type UpdateOptions struct {
	Includes []string // Glob patterns to include
	Excludes []string // Patterns to exclude
}

UpdateOptions configures incremental update behavior

type UpdateResult 

type UpdateResult struct {
	FilesUpdated  int
	FilesRemoved  int
	ChunksCreated int
	ChunksRemoved int
}

UpdateResult contains statistics from an update operation

Source Files

View all Source files

Directories

Path Synopsis

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.