RagEngine class
Unified RAG engine with simplified initialization.
Wraps SourceRagService with automatic dependency initialization.
Properties
- currentEmbeddingFingerprint → String
-
Fingerprint of the currently loaded embedding model.
Captured during initialize via a one-shot probe embed.
final
- dbPath → String
-
Path to the SQLite database.
final
- embeddingFingerprintLock → RagEmbeddingFingerprintLock?
-
Snapshot of the active embedding fingerprint lock (null when unlocked).
no setter
- hashCode → int
-
The hash code for this object.
no setterinherited
- isEmbeddingFingerprintLocked → bool
-
Whether boot detected an embedding fingerprint mismatch.
no setter
- isIndexReady → bool
-
Whether all retrieval indexes are ready for full-quality search.
no setter
-
migrationState
→ Future<
MigrationAxes> -
Read-only snapshot of all on-device data migration axes.
no setter
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
- service → SourceRagService
-
Access to the underlying SourceRagService for advanced operations.
no setter
- vocabSize → int
-
Vocabulary size of the loaded tokenizer.
final
-
warmupFuture
→ Future<
void> -
Completes when the latest index warmup/rebuild task has finished.
no setter
Methods
-
addDocument(
String content, {String? metadata, String? name, String? filePath, ChunkingStrategy? strategy, Duration? chunkDelay, void onProgress(int done, int total)?, String? collectionId}) → Future< SourceAddResult> - Add a document with automatic chunking and embedding.
-
addDocumentFromFile(
String filePath, {String? metadata, String? name, ChunkingStrategy? strategy, Duration? chunkDelay, void onProgress(int done, int total)?, String? collectionId}) → Future< SourceAddResult> - Add a document from a file path using a Rust-side ingest fast path.
-
addDocumentUtf8(
Uint8List bytes, {String? metadata, String? name, ChunkingStrategy? strategy, Duration? chunkDelay, void onProgress(int done, int total)?, String? collectionId}) → Future< SourceAddResult> - Add a UTF-8 document payload while reducing input-side Dart String materialization.
-
assembleContext(
{required SearchHandle searchHandle, int tokenBudget = 2000, ContextStrategy strategy = ContextStrategy.relevanceFirst, String separator = '\n\n---\n\n', bool singleSourceMode = false, String? collectionId}) → Future< AssembledContextV2> -
clearAllData(
) → Future< void> - Clear all data (database and index files) and reset the engine.
-
clearAndRestart(
{required ClearAndRestartConfirmation confirm}) → Future< void> - Resolve an embeddingFingerprintLock by discarding every on-device embedding (chunks table) and rotating the fingerprint baseline.
-
collectionWarmupFuture(
String collectionId) → Future< void> - Completes when a specific collection warmup/rebuild task has finished.
-
deriveContextBudgetForPromptV2(
{required int fullPromptBudget, required String query, String? systemInstruction, bool useStrictMode = true, int safetyMarginTokens = 0, int? fixedPromptOverheadTokens, String? collectionId}) → Future< int> -
formatPrompt(
String query, RagSearchResult result) → String - Format search results as an LLM prompt.
-
getAdjacentChunks(
{required int sourceId, required int minIndex, required int maxIndex}) → Future< List< ChunkSearchResult> > - Get adjacent chunks around a given chunk range.
-
getChunkExcerpts(
{required SearchHandle searchHandle, required List< int> chunkIds, required int maxBytes, String? collectionId}) → Future<List< ChunkExcerptResult> > -
getSourceChunkCount(
int sourceId) → Future< int> - Get the number of chunks for a specific source.
-
getSourceChunks(
int sourceId) → Future< List< String> > - Get all chunk texts for a specific source.
-
getSourceDocument(
int sourceId) → Future< String?> - Get the original source document content by ID.
-
getStats(
{String? collectionId}) → Future< SourceStats> - Get statistics about stored sources and chunks.
-
hydrateChunks(
{required SearchHandle searchHandle, required List< int> chunkIds, String? collectionId}) → Future<List< ChunkSearchResult> > -
isCollectionIndexReady(
String collectionId) → bool - Whether a specific collection index is ready for full-quality search.
-
listSources(
{String? collectionId}) → Future< List< SourceEntry> > - Get a list of all stored sources.
-
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
rebuildIndex(
{bool force = false, String? collectionId}) → Future< void> - Rebuild the HNSW index after adding documents.
-
reembedAll(
{void onProgress(RagReembedProgress progress)?, int batchSize = 32}) → Future< void> - Resolve an embeddingFingerprintLock by re-embedding every chunk with the currently loaded model.
-
reembedRemaining(
) → Future< int> - Up-to-date count of chunks still tagged with a non-current fingerprint.
-
regenerateAllEmbeddings(
{void onProgress(int done, int total)?, String? collectionId}) → Future< void> - Regenerate embeddings for all existing chunks.
-
removeSource(
int sourceId, {String? collectionId}) → Future< void> - Remove a source and all its chunks from the database.
-
saveIndex(
{String? collectionId}) → Future< void> - Save the HNSW index marker to disk.
-
search(
String query, {int topK = 10, int tokenBudget = 2000, ContextStrategy strategy = ContextStrategy.relevanceFirst, int adjacentChunks = 0, bool singleSourceMode = false, List< int> ? sourceIds, String? collectionId}) → Future<RagSearchResult> - Search for relevant chunks and assemble context for LLM.
-
searchHybrid(
String query, {int topK = 10, double vectorWeight = kDefaultVectorWeight, double bm25Weight = kDefaultBm25Weight, List< int> ? sourceIds, String? collectionId}) → Future<List< HybridSearchResult> > - Hybrid search combining vector and keyword (BM25) search.
-
searchHybridWithContext(
String query, {int topK = 10, int tokenBudget = 2000, ContextStrategy strategy = ContextStrategy.relevanceFirst, double vectorWeight = kDefaultVectorWeight, double bm25Weight = kDefaultBm25Weight, List< int> ? sourceIds, int adjacentChunks = 0, bool singleSourceMode = false, SearchHydrationMode hydrationMode = SearchHydrationMode.full, int previewMaxBytes = 512, String? collectionId}) → Future<RagSearchResult> - Hybrid search with context assembly for LLM.
-
searchMeta(
String query, {int topK = 10, double vectorWeight = kDefaultVectorWeight, double bm25Weight = kDefaultBm25Weight, List< int> ? sourceIds, int adjacentChunks = 0, String? collectionId}) → Future<SearchMetaResult> - Additive metadata-first low-level search lane.
-
toString(
) → String -
A string representation of this object.
inherited
-
tryLoadCachedIndex(
{String? collectionId}) → Future< bool> - Try to load a cached HNSW index from disk.
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited