SurrealDB San Francisco

Agents and copilots need more than search - they need persistent, structured memory.

In this on-demand session, learn how to use SurrealDB as a long-term memory layer for LLM apps, combining graph and vector data to power richer context and better decisions.

Retrieval-Augmented Generation (RAG) is reshaping the future of AI — and in financial services, it unlocks even greater potential.
In this on-demand session you'll learn how Graph-based RAG pipelines can power faster, more accurate insights using SurrealDB. You’ll see how real-time querying and graph visualisation of financial networks enable smarter, more transparent AI systems.

🖥️ Accessing this webinar
Please note you will need to register at the event page to join this online event:

Multi-model RAG with SurrealDB & Langchain

In the rapidly evolving field of AI, most of the time is spent optimising. You are either maximising your accuracy, or minimising your latency. Join our live SurrealDB webinar where we'll be showing some LangChain components, testing some prompt engineering tricks, and identifying specific use-case challenges.

We’ll walk through an experiment: a chatbot answering questions over chat-style conversations, showing when vector retrieval wins, when lightweight graphs help, and how to handle tricky bits like time awareness.

In this session, you’ll learn how to:

• Set up SurrealDB as both a graph and vector store—one connection, one system
• Use LangChain to ingest documents
• Use LLMs to infer keywords
• Tune retrieval (k, thresholds) and compare vector-only, graph-only, and intersected results

Agenda

• Welcome & introductions – 10 minutes
• Multi-model RAG with SurrealDB & Langchain – 40 minutes
• Q&A – 10 minutes

Most RAG tutorials start with a heavy framework like LangChain. In this on-demand session, we’ll show you how to go leaner and faster — building production-ready RAG applications using just Python, SurrealDB, and Streamlit.

You’ll learn how to:

• Build the fundamentals in pure Python before reaching for a framework
• Manage multi-model data with SurrealDB
• Add a front end for your RAG app using Streamlit