Large Language Models are incredible at handling general questions, but they lack the context of your specific data. This session provides a technical foundation for retrieval-augmented generation (RAG) and moves into a practical build. Watch as we demonstrate how to create a RAG-based chatbot using MongoDB and open-source LLMs.
Key Takeaways:
- Master RAG foundations including chunking, embedding, and semantic search
- Build a RAG system from the ground up using MongoDB
- Use MongoDB as a unified operational store, vector store, and memory provider
- Integration techniques for connecting open-source LLMs to your data
Mastering RAG is a critical step in modern application development. View this session on-demand to gain the practical skills required to build context-aware applications that leverage your proprietary data securely and efficiently.
After you’ve watched the session, be sure to take our RAG With MongoDB skills check and earn a skill badge.
