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.

Este exercício faz parte do curso

Graph RAG with LangChain and Neo4j

Instruções do exercício

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.

Exercício interativo prático

Experimente este exercício completando este código de exemplo.

# Query the graph with similarity_cypher
result = ____

# Extract and print the results
for row in result:
    print(row['____'], 'from', row['____'], 'has similarity score of ', row['____'])

Editar e executar o código

Este exercício faz parte do curso

Graph RAG with LangChain and Neo4j

AvançadoNível de habilidade

4.9+

Iniciar curso de graça

Learn how Graph RAG can improve the accuracy and reliability of RAG applications! Store information as nodes and edges in a Neo4j database, and give your LLM the ability to query it so it can retrieve entity and relational information to provide informed answers.

Exercise 1: Graphs and RAG Exercise 2: Creating nodes Exercise 3: Creating relationships Exercise 4: Saving graph documents Exercise 5: Querying a knowledge graph Exercise 6: Writing Cypher statements Exercise 7: Running Cypher statements Exercise 8: The MERGE clause Exercise 9: Text-to-Cypher Graph RAG with Neo4j Exercise 10: Building a text-to-Cypher chain Exercise 11: Text-to-Cypher retrieval chain

Text-to-Cypher applications work well in many circumstances, but we can do better than that! Discover how to construct graph databases using different graph models including lexical and domain graphs. Create Neo4j vector indexes so that you can have the best of both worlds and run graph and vector retrieval simultaneously!

Exercise 1: Lexical graphs Exercise 2: Elements of a lexical graph Exercise 3: Splitting the play into Acts Exercise 4: Creating a hierarchical lexical graph Exercise 5: Combining lexical graphs with vector search Exercise 6: Creating text chunks Exercise 7: Creating a vector index Exercise 8: Domain graphs Exercise 9: Creating a structured output Exercise 10: Requesting a structured output Exercise 11: Providing few-shot examples Exercise 12: Building a hybrid retrieval chain Exercise 13: Runnable lambdas Exercise 14: Assigning additional values to an input Exercise 15: The final link in the chain

Although Graph RAG applications are generally more reliable than vector RAG, they aren't totally infallible. In this chapter, you'll learn to evaluate your Graph RAG applications, spot incorrect or duplicate graph nodes, and integrate long-term memory so user preferences can be learned over time.

Exercise 1: Entity resolution Exercise 2: Using extracted entities Exercise 3: Graph-based entity resolution

Exercício atual

Exercise 4: Evaluating Graph RAG with RAGAS Exercise 5: Creating a Ragas evaluation Exercise 6: Evaluating context retrieval with Ragas Exercise 7: Memory graphs Exercise 8: Saving conversation memory in the graph Exercise 9: Extracting facts from conversation histories Exercise 10: Using extracted conversation facts Exercise 11: Congratulations!