event · community record
Unstructured Data in LLMs - South Bay Edition
A connected record in the developer community graph.
01
Talks & recordings
3 connected sessions
Video unavailable
Chat with Your Data Privately and Locally
How to build private, locally-running LLM applications that chat with your data using NVIDIA's tools and models without sending data to external APIs.
Video unavailable
Sparse Vectors with Milvus: Hybrid Search
How Milvus supports sparse vectors for hybrid search, combining dense semantic search with sparse keyword search for better retrieval accuracy.
Video unavailable
VoyageAI Embeddings for RAG Applications
How to use VoyageAI's domain-specific embedding models to build more accurate RAG applications with better retrieval precision.