Most RAG applications like Chat with your PDF use basic vector similarity search to retrieve relevant information from the database and feed it to the LLM to generate a final response.
Vector similarity search is used to retrieve relevant information
However, basic vector search is not robust enought to handle all use case. The vector similarity search process only compares the semantic content of items based on the words and concepts they share. A RAG application based vector search will not integrate context from your data structure for advanced reasoning.
In this blog post, we'll walk you though advanced methods to build a RAG application that draws on data context to answer complex, multi-part questions. You'll learn how to use the neo4j-advanced-rag template.
You need to set up Neo4j 5.11 or later to follow along with the examples in this blog post. you can set up a local instance of the Neo4j database by downloading Neo4j application and creating a local databse instance.
from langchain.graphs import Neo4jGraph url = "neo4j+s://databases.neo4j.io" username ="neo4j" password = "" graph = Neo4jGraph( url=url, username=username, password=password )