Powering AI Agents/Apps w context data from more than just default vector search

Welcome back to our meetup in April. The date is right before the GITEX AI Asia conference held at the Marina Bay Sands Convention Centre.

• 06:00 PM Registration, dinner, networking
• 06:30 PM Talk starts

Talk #1: Powering AI Agents/Apps with contextual data from more than just the default vector search

Description: Most solutions showcase vector search as the default search mechanism to power AI applications. But it is often not the most effective solution. In this demo, we will showcase different search techniques and hybrid approaches for retrieving contextual data with MongoDB.

Talk #2: Real Practical RAG, from Demo to Production - in a 10,000-person organization and an intelligence org

Moving from controlled demos to real-world deployment exposed several challenges that are easy to underestimate. In clean demos, our prompts/queries are often well-formed and datasets are neatly curated, and we test the happy paths.

But real users behave very differently. We observed clear gaps between how users express intent and how that intent is represented in the embedding space (leads to irrelevant/missed retrievals). This made retrieval design and chunking strategy critical: how documents are split, indexed, and ranked directly impacted whether the system could “understand” a query.

Additionally, as the dataset scaled with many similar or overlapping documents, retrieval became noisier - every vector is similar to a lot other vector - making it harder to consistently surface the right information.
These challenges highlight that building a production-ready RAG system is not just about ensuring our datasets and RAG method works, but also user's intent and behavior.

TBA: We will have a 2nd speaker talking about AI in real use cases in intelligence orgs either in this meetup or the next meetup. More details for the 2nd speaker are still being prepared.