TF-IDF + LLM Reranking: How I Improved Vector Search Accuracy from 60% to 86%

TF-IDF + LLM Reranking: How I Improved Vector Search Accuracy from 60% to 86% Vector search is powerful — but it’s not perfect. When I was building a database discovery pipeline at work, our initial semantic search was only matching the right schemas about 60% of the time. That wasn’t good enough for production. Here’s exactly how I fixed it using a hybrid TF-IDF and LLM reranking approach. The Problem Our pipeline needed to match user queries to the correct database schemas from a large pool of