i am setting up my rag evaluation pipeline, here is my code ```python import osfrom d

python 
import os
from dotenv import load_dotenv
import nest_asyncio

load_dotenv()
nest_asyncio.apply()

from llama_index.core.evaluation import RetrieverEvaluator

Settings.embed_model = OpenAIEmbedding(model="text-embedding-ada-002", embed_batch_size=10)
llm = OpenAI(model="gpt-4o")

client = qdrant_client.QdrantClient(
    url=os.getenv("QDRANT_URI"), api_key=os.getenv("QDRANT_API_KEY")
)
vector_store = QdrantVectorStore(client=client, collection_name="mlofo-loan-officer-july")
index = VectorStoreIndex.from_vector_store(vector_store=vector_store)

qa_dataset = EmbeddingQAFinetuneDataset.from_json("pg_eval_dataset.json")


metrics = ["mrr", "hit_rate"]

retriever_evaluator = RetrieverEvaluator.from_metric_names(
    metrics, retriever=index.as_retriever(similarity_top_k=2)
)

sample_id, sample_query = list(qa_dataset.queries.items())[0]
sample_expected = qa_dataset.relevant_docs[sample_id]

eval_result = retriever_evaluator.evaluate(sample_query, sample_expected)
print(eval_result)

nodes = vector_store.get_nodes()

qa_dataset = generate_question_context_pairs(
    nodes, llm=llm, num_questions_per_chunk=2
)