About us
The SurrealDB Bengaluru User Group is a community-led meetup for developers, students, and professionals who want to learn, share, and connect over SurrealDB.
What do SurrealDB User Groups do?
Our events are run locally by community organizers, with support from the SurrealDB team. Meetups typically feature technical talks, demos, and open discussions, followed by networking (and often some swag). Whether you’re just discovering SurrealDB or already building with it, you’ll find a welcoming space to explore ideas and meet others who share your interest in multi-model databases.
Want to get involved?
🗣️ Speak at a future meetup → Share your project, demo, or lessons learned with the group.
🤝 Partner with us → If you can provide a venue or would like to co-host a meetup, we’d love to hear from you.
🌍 Start a SurrealDB User Group in your city → Reach out to events@surrealdb.com and we’ll help you get started.
What is SurrealDB?
SurrealDB is a multi-model, cloud-native database that combines document, graph, and vector search into a single system. It’s designed for modern AI-native applications, from semantic search and knowledge graphs to real-time analytics and RAG pipelines.
Upcoming events
1
- Network event
Prompt engineering for agentic retrieval (Text-to-SurQL)
·OnlineOnline23 attendees from 7 groups## Please note - to reserve a spot for this webinar you must register at: https://sdb.li/4g8WJvD
Most text-to-SQL agents fail for the same boring reason: someone pasted a schema into a system prompt months ago, a field was renamed since, and the model has been confidently writing queries against a database that no longer exists. No runbook fixes that, because documentation always rots at exactly the speed your schema changes. This session takes a different approach. Instead of maintaining the prompt as a document, we generate it as a query. SurrealDB can describe its own live structure, carry notes written specifically for the model inside its DDL, and assemble the finished prompt server side.
In this session you'll learn:
- How to generate a schema block for your prompt from live database state, so it can never drift
- Writing schema comments for a third audience: not the engine, not your colleagues, but the model
- Grounding low-cardinality values in real data to stop the most common class of hallucination
- Retrieving few-shot examples by meaning with vector search instead of hardcoding them
- Why graph traversals are an easier generation target than JOINs, and what that removes
- Enforcing safety with read-only roles, query plan checks, and timeouts rather than regex filters
- Closing the loop so accepted queries improve the next generation4 attendees from this group
Past events
7
