@Logan M Couple of quick questions for you. I looked for an example of combining neo4 and
KnowledgeGraphIndex with
HierarchicalNodeParser to extract hierarchical nodes from markdown documents containing headers, tables, etc. I couldn't find an example, and after some trial and error, I was unable to achieve this.
- Does hierarchical node processor extract nodes based on headers and other document structure?
- Is there a way to accomplish the above, or something like it?
I'm going off the recommendation that since I have legal-like structured documents, that extracting nodes and keeping the structure I can get the better than average results from a Q&A RAG app. I also, am assuming I can use neo4j since it is an established knowledge graph for better performance than simply storing the nodes on disk and querying from there.
