code-chunking

AST-aware chunking for source code RAG. Covers tree-sitter, LangChain Language splitter, LlamaIndex CodeSplitter, preserving function/class boundaries, keeping docstrings with implementations, and code-specific embeddings (voyage-code-2, CodeBERT). USE WHEN: user mentions "code chunking", "tree-sitter", "code splitter", "AST chunking", "code embedding", "v…

Independent GitHub snapshot · Automated classification · Original documentation governs