2026-03-21 –, Yuchengco Hall 5th Flr. Y507 (Workshop Room 1)
This hands-on workshop introduces participants to building a simple recommendation application based on the hybrid search technique, which combines semantic vector search and full-text search.
Using Django, the MongoDB family (including Full-Text and Vector Search, VoyageAI embeddings), and LangChain, we will create a web-based recommendation application that handles hybrid search, document chunking, embedding generation, and result reranking.
By the end of this two-hour session, we will have gained a strong fundamental understanding that can be applied to the recommendation system we built. A beginner's level of Python is recommended, but no prior knowledge of AI or search systems is required.
- Introduction to Hybrid Search. (10 minutes)
Short description: Why hybrid search matters - overview of lexical vs. semantic retrieval, architecture we’ll build. - Environment Setup. (20 minutes)
Short description: Configure MongoDB Atlas Vector Search; install LangChain, Gradio, VoyageAI; test API keys. - Chunking fundamentals. (20 minutes)
Short description: Techniques for document chunking; effects on embedding quality, recall vs. context window. - Embedding Generation with VoyageAI. (20 minutes)
Short description: Generate and store embeddings in MongoDB, inspect vector dimensions and index types. - Similarity functions of Vector Search (20 minutes)
Short description: Fundamentals of cosine, Euclidean, and dot product distance to perform vector search. - Building a recommendation application (25 minutes)
Short description: Build a recommendation application based on the Django framework to visualise search results using Hybrid search (Full Text Search and Vector Search). - Q&A (5 minutes)
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 APAC 2025, PyCon Lithuania 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 User Group in Thailand, which brings together over 3,000 developers.