Blog/#rag

#rag

6 posts

• JEPA vs LLMs: what LeCun's world models actually change for engineers

  Analysis: JEPA predicts embeddings, not tokens. My text-chunk stand-in: token-space prediction collapsed 99.4% with 10x less data, embedding-space only 45.8%.

  28 Sept 2026 · world-models · embeddings
• Do you need a vector database? Brute-force search benchmarked from 10k to 1M vectors

  Exact numpy search over 100k embeddings takes 3.5 ms on 2 vCPUs. Measured latency, memory and HNSW recall to show when an index actually pays off.

  27 Sept 2026 · vector-search · rag
• Hybrid search in Python: BM25 + vectors with Reciprocal Rank Fusion, alpha swept 0 to 1

  Tested BM25+RRF on 2,713 FastAPI doc chunks: BM25 beat vectors by 49 MRR points on identifiers; vectors beat BM25 by 24 on paraphrases. alpha=0.8 balanced both.

  27 Sept 2026 · rag · hybrid-search
• RAG chunking, measured: heading-aware chunks doubled hit@1 on the FastAPI docs

  I tested 5 chunking strategies on 151 real docs and 773 queries. Fixed-size chunks crossed section boundaries 59% of the time. Heading-aware chunks never did.

  27 Sept 2026 · rag · chunking
• The RAG production checklist: 25 checks before real users see it

  25 checks across ingestion, retrieval, generation, evaluation and operations that catch the RAG failures demos hide. Free printable PDF included.

  27 Sept 2026 · rag · production
• Stop fake citations in RAG: validate them server-side in 25 lines of Python

  LLMs will cite passage [7] when you gave them 5. A tested validator that strips invented citations and returns a grounded flag your UI can trust.

  27 Sept 2026 · rag · citations