[lu.ma/_ai registration required] DSPy and GraphRAG: Making GenAI Real
[lu.ma/_ai registration required] DSPy and GraphRAG: Making GenAI Real was a developer community event.
Talks & recordings
4 connected sessions
DSPy: Prompt Optimization for LM Programs
DSPy is the library for Programming—not Prompting—LMs. This talk introduces LM Programs as composable calls to LLMs that can be rigorously tested and optimized, and demonstrates MIPROv2, a high-performing prompt optimization algorithm.
Graphs and AI: Making GraphRAG Real
GraphRAG is one of the most promising architectures for enterprise AI. A review of technical and community efforts required to make GenAI ready for production, focusing on recent advances in GraphRAG with LangChain and LlamaIndex integrations.
Improving RAG with Knowledge Graph and Milvus
Techniques of Knowledge Engineering that improve RAG quality: offline extracting knowledge graphs and implementing comprehensive retrieval by storing and searching knowledge embeddings in Milvus.
Vectors and Graphs: Better Together
How graph databases and vector databases can work in tandem in agentic ways to deliver unique analysis of complex, interconnected data sets.
Connections
5 relationships