Beyond Basic RAG: Boosting Accuracy with Hybrid Search and Fusion Algorithms.
Speaker
Piti Champeethong
I've been working with databases and software development for 20 years. Currently, I'm a MongoDB senior consulting engineer based in Singapore. I've previously spoken at conferences such as PyCon Lithuania 2025, PyCon APAC 2025, PyCon SG 2025, PyCon Thailand 2025, and Global Azure Thailand 2025. I’m also part of the community leader team for the MongoDB and PyLanna (the Python) User Group in Thailand, which brings together over 3,000 developers.
Abstract
Retrieval-Augmented Generation (RAG) often produces incorrect results when relying solely on vector-based similarity. While vector search is strong, it fails on exact keywords, acronyms, and domain-specific terms. This talk shows how to build high-accuracy RAG pipelines with Hybrid Search and Re-ranking using LangChain, combining vector and full-text retrieval and applying cross-encoder scoring to deliver more relevant context and reduce hallucinations.
Description
The outline course is as follows:
- Evolution of the recommender system (2 minutes)
- Introduction to Hybrid Search. (5 minutes) Short description: Why hybrid search matters - overview of keyword vs. semantic retrieval.
- Introduction to the Fusion algorithm (5 minutes) Short description: Why the fusion algorithm matters - overview of Reciprocal Rank Fusion (RRF) vs Relative Score Fusion (RSF)
- Proposed RAG pipeline (5 minutes) Short description: Overview of key components and core snippet of fusion algorithm.
- Key takeaway (3 minutes)
- Q&A (5 minutes)