LLM Engineering

This is a collection of blog posts about RAG.

IndexFlatIP works for small corpora. For production with 100K+ vectors, you need smarter indexes. Here’s how to choose and implement them.

Picture this: You’re asking an AI about cancer treatments. It sounds super confident and gives you detailed answers. But here’s the problem — it just made up a medical study that doesn’t exist.

Product catalogs rarely match 1:1. I combine lexical and semantic similarity with thresholds to minimize false matches.

Document summarization is a critical NLP task that helps users quickly grasp key information from long documents. But how do you know if your model is actually working? This guide shows a workflow that starts with evaluation and acceptance criteria before touching models.

RAG is a design pattern, not a product. LangChain supports it out of the box. This guide shows a production-ready RAG setup in LangChain with architecture, retrieval choices, runnable code, evaluation metrics, and trade-offs from my client projects.

LightRAG is a minimal RAG toolkit that strips away heavy abstractions. Here’s a complete build with code, performance numbers versus a LangChain baseline, and when LightRAG is the right choice.

Bi-encoder retrieval is fast but imprecise. Cross-encoder reranking improves top-k precision at the cost of some latency. Here’s when and how to add it.

Want LightRAG’s lean retrieval with LangChain’s chain ecosystem? Here’s how to wrap LightRAG as a LangChain-compatible retriever.

Vector search misses keyword-heavy queries. BM25 misses semantic similarity. Combine both with hybrid search for better retrieval recall.