1. Nauka
    2. /
  2. Kursy
    3. /
  3. Graph RAG with LangChain and Neo4j
Connected

ćwiczenie

Graph-based entity resolution

Oh no! Even with a bullet-proof prompt, few-shot examples and our fingers crossed, the LLM has still hallucinated up a character called Romeo Capulet and has assigned him a few lines in the database.

{
  "id": "romeo-capulet",
  "name": "Romeo Capulet",
  "family": "Montague"
}

Luckily, you can use the relationships in the knowledge graph to decide whether this node is likely an accidental duplicate of another named Romeo Montague.

The similarity_cypher Cypher statement uses the MEMBER_OF and INTERACTS_WITH relationships to build an arbitrary similarity score with the following properties:

Condition Cypher Points Modifier
A MEMBER_OF relationship to the same family af = bf +1
The same name property a.name = b.name +2
Percentage of characters that a and b interact with size(inCommon) / size(aInteractsWith) Multiplied by percentage of b that a interacts with

From your domain knowledge, you know that a score of 2 indicates a strong correlation.

Instrukcje

100 XP
  • Query graph with the Cypher query (similarity_cypher) to calculate similarity scores between "romeo-capulet" and the other character nodes.
  • Extract the "bId", "bFamily", and "score", in that order, from each row in results.