How HNSW Vector Search Actually Works
Every RAG stack leans on HNSW but treats it as a black box. Here is how the layered graph index finds nearest neighbors fast, and the knobs that matter.
Every RAG stack leans on HNSW but treats it as a black box. Here is how the layered graph index finds nearest neighbors fast, and the knobs that matter.
Retrieval puts the right chunk at rank 8, but the generator only reads the top few. How a cross-encoder reranker reorders RAG candidates, and where it fails.
How to chunk documents for a RAG pipeline: why fixed-size splitting fails, structure-aware splitting, size and overlap tradeoffs, and the failure modes.
Changed your embeddings or added a reranker? Measure it. Build a golden set and score retrieval with recall@k, MRR, and nDCG before you trust the change.
Vector search alone misses exact IDs and error codes. Here's how to combine BM25 keyword search with dense retrieval, fuse the rankings with RRF, and rerank.
How to keep a RAG index fresh without full rebuilds: detect changed files with checksums, re-embed only what changed, and handle deletions safely.
AI-powered document creation platform pairing Claude with a live .docx / .pptx / .pdf / .xlsx preview. Chat on the left, documents render live on the right, each user gets their own isolated E2B sandbox.
Secured 2nd place at the Argusa AI Challenge 2025 by building ARGRAG, a RAG system for complex enterprise document corpora with multi-modal analysis, metadata intelligence, and real-time performance.
Partnering with MIT to build an LLM-powered RAG copilot for CMS computing operations.