From the course: GraphRAG Essential Training
Unlock this course with a free trial
Join today to access over 25,500 courses taught by industry experts.
Enhancing your knowledge graph with richer data - Neo4j Tutorial
From the course: GraphRAG Essential Training
Enhancing your knowledge graph with richer data
- [Instructor] So far, we've created a pretty basic knowledge graph using content from the web. While that's a great starting point, chances are in your Graph RAG applications, you'll want to add many other sources of data. After all, your graph is only as good as the data you put into it. So let's talk about ways to bring in other data sources. For this video, I'm going to show you how to bring in PDF files. For demonstration purposes, I have this small PDF file about skiing that I'm going to use. You should see if you can find a PDF or two about your subject. It's helpful to find PDFs about subtopics that your graph might be lacking to provide additional information. I'm going to load it in using a built-in LangChain tool for importing PDF files and extracting the text from them called PyPDFLoader. When I do that, I get back a list of LangChain documents. In LangChain, a document is a class that represents a chunk of content, typically from a file or external source, and it's used…
Contents
-
-
-
-
-
-
(Locked)
Creating a GraphRAG pipeline with LangChain to query your data3m 45s
-
(Locked)
Enhancing your knowledge graph with richer data4m 35s
-
(Locked)
Using knowledge graphs in a GraphRAG pipeline3m 18s
-
(Locked)
Comparing the GraphRAG results to a traditional vector-based RAG1m 48s
-
(Locked)
Evaluating your GraphRAG pipeline2m 58s
-
(Locked)
Challenge: Evaluate your GraphRAG application1m 17s
-
(Locked)
Solution: Evaluate your GraphRAG application5m 33s
-
(Locked)
-
-