Creating graph documents
You've been provided with a document called famous_scientists containing a paragraph of text about famous scientists from the 20th century. In this exercise, you'll transform this unstructured text data into structured graph documents using LLMs!
This exercise is part of the course
Retrieval Augmented Generation (RAG) with LangChain
Exercise instructions
- Define an OpenAI chat LLM that will produce maximally deterministic responses.
- Instantiate an LLM graph transformer for converting LangChain documents into graph documents.
- Convert the text documents (
docs) to graph documents usingllm_transformer.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Define the LLM
llm = ____(api_key="", model="gpt-4o-mini", ____)
# Instantiate the LLM graph transformer
llm_transformer = ____
# Convert the text documents to graph documents
graph_documents = ____
print(f"Derived Nodes:\n{graph_documents[0].nodes}\n")
print(f"Derived Edges:\n{graph_documents[0].relationships}")