Writing · Piyush Kuhikar

Featured deep dive

Architecture first, vendor choices second.

Production RAG · Long-form guide

From 100,000 documents to grounded answers

A practical design for ingesting mixed PDFs, scans, images, tables, and diagrams—then retrieving them with metadata-aware BM25 and semantic search, reciprocal rank fusion, reranking, and selective GraphRAG.

RAGSystem designHybrid retrievalGraphRAG

Read the article Play the animation

100K

mixed documents enter the pipeline

1.5Mpages

2Mchunks

3retrievers

All writing

Search by title, summary, or topic.

4 posts Static HTML · no tracking

ArticleLong-form guide

From 100,000 Documents to Grounded Answers

A production-oriented RAG architecture: tiered parsing, canonical document IR, metadata and ACL filtering, BM25 plus HNSW, RRF, reranking, evaluation, and selective GraphRAG.

RAGHybrid retrievalGraphRAG

Interactive12-step animation

Inside a 100,000-document RAG knowledge base

Play, pause, and scrub through the entire production RAG pipeline—from raw mixed documents to a streamed, cited answer.

InteractiveRAGSystem design

Medium articleSystem design

The System Design Foundation Series: Scalability

The art of designing systems that grow gracefully instead of collapsing under their own success.

ScalabilityArchitectureSystems

Medium articleSystem design

The System Design Foundation Series: Latency

Why a system handling 100,000 requests per second can still deliver a terrible user experience—and why performance tuning matters at every layer.

LatencyPerformanceEngineering

About the author

Piyush Kuhikar

AI engineer and software builder focused on practical GenAI, retrieval systems, and production-grade ML workflows. I enjoy turning research ideas into robust systems, shipping measurable experiments, and writing about the engineering tradeoffs behind real-world AI products.

View GitHub Read on Medium Open projects

Ideas are useful when they survive production.