Integrating Neo4j with Generative AI

In this module, you will setup and use the Neo4j GraphRAG for Python package to:

• Create and configure a vector retrieveriFull definition for retriever (opens in a new tab)A component that searches a data source and returns the information relevant to a query. Often used to provide context for a language model..
• Perform semantic search using a vector indexiFull definition for vector index (opens in a new tab)A structure over a vector property. The database searches it to find the vectors nearest a given one, rather than comparing every vector stored..
• Build a GraphRAGiFull definition for GraphRAG (opens in a new tab)Retrieval-augmented generation whose context comes from a knowledge graph, so the model can follow the relationships between facts. pipeline that uses retrievers to give context to an LLMiGo to glossary for large language model (opens in a new tab)A model trained on text to predict the next token, and so to generate language..
• Use graph traversaliFull definition for traversal (opens in a new tab)Following relationships from one node to the next to reach other parts of a graph. in combination with vector searchiFull definition for vector search (opens in a new tab)Finding the records whose vectors lie closest to a query vector. for enhanced retrieval.
• Implement text-to-Cypher retrieval for natural language querying.

In addition, you will explore popular GenAI frameworks for integrating with Neo4j, such as LangChain and LlamaIndex.

If you are ready, let's get going!