Grepai Chunking

This walks you through configuring how GrepAI splits your code into chunks for embedding and search. The default is 512 tokens with 50 token overlap, which works fine for most codebases, but you might want smaller chunks (384) for precise results in concise languages like Rust, or larger chunks (768) for verbose Java where you need to capture entire methods. The guide explains the tradeoffs clearly: smaller chunks give you precision but lose context, larger chunks do the opposite, and overlap prevents you from losing important code at boundaries. Worth reading if your search results feel fragmented or noisy, since tweaking these numbers and re-indexing can make a real difference.