Skip to main content

Crate trueno_rag

Crate trueno_rag 

Source
Expand description

trueno-rag has moved to aprender-rag.

This crate re-exports aprender-rag for backward compatibility. New code should depend on aprender-rag directly.

Modules§

chunk
Document chunking strategies for RAG pipelines
embed
Embedding generation for RAG pipelines
error
Error types for Trueno-RAG
fusion
Score fusion strategies for hybrid retrieval
index
Indexing for RAG pipelines (BM25 sparse index and vector store)
loader
Document loading abstraction for pluggable file format support.
media
Media types for subtitle and transcript support.
metrics
Retrieval evaluation metrics
pipeline
RAG Pipeline implementation with context assembly
preprocess
Query preprocessing strategies for improved retrieval.
rerank
Reranking module for RAG pipelines
retrieve
Retrieval module for RAG pipelines
sqlite
SQLite+FTS5 persistent storage backend for RAG indices.

Structs§

AggregatedMetrics
Aggregated metrics across multiple queries
BM25Index
BM25 index implementation
Chunk
A chunk of text from a document
ChunkId
Unique chunk identifier
ChunkMetadata
Metadata associated with a chunk
ContextAssembler
Assembles retrieved chunks into a coherent context
Document
A document to be indexed
DocumentId
Document identifier
EmbeddingConfig
Configuration for embedding generation
FixedSizeChunker
Fixed-size chunker implementation
HybridRetriever
Hybrid retriever combining dense and sparse retrieval
LoaderRegistry
Registry that dispatches file loading to the appropriate DocumentLoader.
ParagraphChunker
Paragraph-based chunker
RagPipeline
Complete RAG pipeline
RecursiveChunker
Recursive chunker implementation
RetrievalMetrics
Retrieval metrics for evaluation
RetrievalResult
Result of a retrieval operation
SemanticChunker
Semantic chunker that groups sentences by embedding similarity
SentenceChunker
Sentence-based chunker
SqliteIndex
SQLite-backed sparse index using FTS5 for BM25 search.
SqliteStore
Combined document store + BM25 index backed by SQLite.
StructuralChunker
Structural chunker that respects document structure (headers, sections)
SubtitleCue
A single timed text cue from a subtitle file.
SubtitleLoader
Loads subtitle files and produces Documents with timestamp metadata.
SubtitleTrack
Parsed subtitle file.
TextLoader
Loads plain text and Markdown files.
TimestampChunker
Timestamp-aware chunker for subtitle/transcript content.
VectorStore
Vector store for dense retrieval

Enums§

ChunkingStrategy
Chunking strategy configuration
Error
Error types for RAG pipeline operations
FusionStrategy
Strategy for fusing dense and sparse retrieval results
PoolingStrategy
Pooling strategy for token embeddings
SubtitleFormat
Subtitle file format.

Traits§

Chunker
Trait for document chunkers
DocumentLoader
Abstraction for loading files of any format into Documents.
Embedder
Trait for embedding generation
Reranker
Trait for reranking retrieved results
SparseIndex
Sparse index trait for lexical retrieval

Functions§

parse_subtitles
Parse SRT or VTT from a string, auto-detecting format.

Type Aliases§

Result
Result type for Trueno-RAG operations