Expand description
Indexing pipeline
File scanning, parsing, and chunking for document indexing.
Re-exports§
pub use ast_chunker::chunk_semantic;pub use ast_chunker::ChunkType;pub use ast_chunker::SemanticChunk;pub use ast_chunker::SemanticChunker;
Modules§
- ast_
chunker - AST-aware semantic chunking
Structs§
- Chunk
- Document chunk
- Embed
Progress - Embedding progress
- Embed
Stats - Embedding statistics
- Scan
Options - Scan options
- Scan
Result - Scan result
Constants§
- CHUNK_
OVERLAP_ CHARS - CHUNK_
OVERLAP_ TOKENS - CHUNK_
SIZE_ CHARS - CHUNK_
SIZE_ TOKENS - Chunking configuration
Functions§
- chunk_
by_ chars - Character-based chunking (fallback)
- embed_
documents - Generate embeddings for documents with smart caching
- extract_
title - Extract title from markdown content
- handelize
- Normalize path for storage (handelize)
- scan_
files - Scan directory for files matching pattern