Evaluating Graph RAG with RAGAS

Graph RAG with LangChain and Neo4j

Adam Cowley

Manager, Developer Education at Neo4j

Text-to-Cypher

 

The results are injected into the prompt ready to be sent to the LLM

 

The review is posted by a Person with the screen name @emileifrem

Graph RAG with LangChain and Neo4j

Evaluating Graph RAG

 

  1. Evaluating end-to-end generating using time
  2. Evaluating token usage and costs with tiktoken
  3. Evaluating output quality with ragas
    • Context precision
    • Noise sensitivity

 

performance_tradeoffs.jpg

1 Image generated with GPT-4o
Graph RAG with LangChain and Neo4j

Noise Sensitivity

  • Measures amount of irrelevant information in retrieved documents
  • Higher in vector search alone
  • Returns a score based on relevant information
from ragas.metrics import NoiseSensitivity


metric = NoiseSensitivity(
    llm=evaluator_llm, 
    mode="irrelevant"
)
1 https://docs.ragas.io/en/stable/concepts/metrics/available_metrics/noise_sensitivity/
Graph RAG with LangChain and Neo4j

Context Precision

  • Measures the proportion of relevant chunks in retrieved documents
  • Higher score means retrieved information is more relevant
from ragas.metrics import LLMContextPrecisionWithReference


metric = LLMContextPrecisionWithReference(
    llm=evaluator_llm, 
)
1 https://docs.ragas.io/en/stable/concepts/metrics/available_metrics/context_precision/#llm-based-context-precision
Graph RAG with LangChain and Neo4j

Context Precision

  • Measures the proportion of relevant chunks in retrieved documents
  • Higher score means retrieved information is more relevant
from ragas.metrics import LLMContextPrecisionWithoutReference


metric = LLMContextPrecisionWithoutReference(
    llm=evaluator_llm, 
)
Graph RAG with LangChain and Neo4j

Text-to-Cypher result structure

cypher_result = {

    "user_input": "Who is Romeo's love?",

    "response": "Romeo loves Juliet",

    "retrieved_contexts": [
        {
            "source": "Romeo",
            "target": "Juliet",
            "relationship": "LOVES",
            "sentiment": 0.9837
        },
    ]

}
Graph RAG with LangChain and Neo4j

Text-to-Cypher result structure

cypher_result = {
    "user_input": "Who is Romeo's love?",
    "response": "Romeo loves Juliet",
    "retrieved_contexts": [
        json.dumps({
            "source": "Romeo",
            "target": "Juliet",
            "relationship": "LOVES",
            "sentiment": 0.9837
        }),
    ]
}
Graph RAG with LangChain and Neo4j

Vector-only result structure

vector_result = { 
    "user_input": "Who is Romeo's love?",
    "response": "Romeo loves Juliet",
    "retrieved_contexts": [

        "But, soft! what light through yonder window breaks?..."
        "O, she doth teach the forches to burn bright!"

    ]
}
Graph RAG with LangChain and Neo4j

Hybrid result structure

hybrid_result = {
    "user_input": "Who is Romeo's love?",
    "response": "Romeo loves Juliet",

    "retrieved_contexts": [

        json.dumps({
            "page_content": "But, soft! what light through yonder window breaks? ...",

            "metadata": {

              "act": 2, "scene": 2, "spoken_to": "Juliet"

            }

        }),

        # ...

    ]
}
Graph RAG with LangChain and Neo4j

Creating an evaluation dataset

cypher_result = {
    "user_input": "Who is Romeo's love?",
    "retrieved_contexts": [
        json.dumps({
            "source": "Romeo",
            "target": "Juliet",
            "relationship": "LOVES",
            "sentiment": 0.9837
        }),
    ]
}


cypher_dataset = EvaluationDataset.from_list([cypher_result])
Graph RAG with LangChain and Neo4j

Choosing an LLM for evaluation

from langchain_openai import ChatOpenAI

# Choose an LLM to perform the evaluation
llm = ChatOpenAI(
    model="gpt-4o-mini",
    temperature=0
)


# Wrap in LangchainLLMWrapper
from ragas.llms import LangchainLLMWrapper
evaluator_llm = LangchainLLMWrapper(llm)
Graph RAG with LangChain and Neo4j

Evaluating responses

from ragas import evaluate, EvaluationDataset
from ragas.metrics import LLMContextPrecisionWithoutReference, NoiseSensitivity

cypher_scores = evaluate(

    dataset=cypher_dataset,

    metrics=[

        LLMContextPrecisionWithoutReference(llm=evaluator_llm),

        NoiseSensitivity(llm=evaluator_llm, mode="irrelevant")

    ]

)

{'llm_context_precision_without_reference': 1.0000,
'noise_sensitivity(mode=irrelevant)': 0.0000}
Graph RAG with LangChain and Neo4j

Let's practice!

Graph RAG with LangChain and Neo4j

Preparing Video For Download...