Example Eval - LlamaIndex

from llama_index.core import VectorStoreIndex, Document
from llama_index.llms.openai import OpenAI

docs = [Document(text="Our refund policy allows returns within 30 days.")]
index = VectorStoreIndex.from_documents(docs)
engine = index.as_query_engine(llm=OpenAI(model="gpt-4o-mini"))

def llamaindex_agent(case):
    response = engine.query(case.query)
    return {"output": str(response), "metadata": {"framework": "llamaindex"}}

report = (
    client.evaluations
    .run(dataset_id="...", subject={"kind": "custom_agent", "displayName": "LlamaIndex RAG", "framework": "llamaindex"})
    .execute(llamaindex_agent)
    .finalize()
    .analyze()
)