Unstructured Data in LLMs

Topic: Connecting your unstructured data with LLMs ​We are meeting for another happy hour/discussion group about Unstructured Data and its future in machine learning and LLM apps! What we’ll do: Have some snacks and refreshments. Have a couple of talks and then unstructured networking. Tech Talk: Large Language Models ❤️ Knowledge Graphs Speaker: Michael Hunger, Head of Product Innovation, Neo4j Abstract: As you might have experienced, LLMs are powerful but not always trustworthy assistants. With a combination of a knowledge graph and vector search, you can provide the LLM with the correct, relevant context information it needs to answer your user’s questions. GraphRAG is an advanced RAG (retrieval augmented generation) that allows for higher quality and explainable responses. In this talk, we’ll explain and demonstrate the building blocks of such an approach combining vector search in Milvus with Graph search in Neo4j and show an example of code and live in action. Of course, nothing is perfect; it’s important to walk through the challenges of building such GenAI apps and how to address them.