All projects
experiment2024

RAG Knowledge Base

Retrieval-augmented generation done properly.


An experimental RAG system exploring how chunking strategy, embedding model choice, and retrieval architecture affect answer quality on long-form technical documents.

The Problem

Most RAG tutorials produce systems that work on toy datasets but degrade on real documents. Needed to understand the actual failure modes at production content volume.

The Approach

Systematically tested chunking strategies (fixed-size, semantic, hierarchical), embedding models, and hybrid search approaches. Built an evaluation harness to measure retrieval quality independently from generation quality.

The Outcome

Documented findings on which approaches hold up at scale. Hierarchical chunking + hybrid BM25/dense retrieval consistently outperformed simpler approaches. Published internal benchmark results.


Technologies

PythonLangChainQdrantOpenAIFastAPI