feat(rag): mmap embeddings + on-demand metadata - peak 320MB RSS

↗ view on GitHub · Davemaina1 · 2026-05-14 · 3ec32238

Downloads corpus files to /tmp, memory-maps the embeddings (zero RAM cost),
and reads metadata only for the top-K results on each query. Drops BM25
(150MB overhead) - semantic-only search is good enough for testing phase.

Removes chromadb and rank-bm25 dependencies entirely.
Measured peak RSS: 320MB (well within Render's 512MB free tier).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Repository Davemaina1/iroh_
Author Davemaina1 <dmain7015@gmail.com>
Authored
Parents 0b5251e8
Stats 2 files changed , +174 , -268
Part of RAG Python sidecar - memory-engineered for 512MB free tier

Capture this commit into my fork

Download a Markdown prompt that tells Claude how to port this exact commit into your working tree. Run it via claude -p < capture-commit-3ec32238.md from inside the repo you want the change in.

⬇ Download capture-commit-3ec32238.md