评估您的 RAG 应用程序

pip install -qU datasets ragas langchain langchain-mongodb langchain-openai \
pymongo pandas tqdm matplotlib seaborn nest_asyncio

import getpass
import os
from openai import OpenAI
MONGODB_URI = getpass.getpass("Enter your MongoDB connection string:")
os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter your OpenAI API Key:")
openai_client = OpenAI()

from typing import List
def get_embeddings(docs: List[str], model: str) -> List[List[float]]:
    """Generate embeddings using the OpenAI API."""
    docs = [doc.replace("\n", " ") for doc in docs]
    response = openai_client.embeddings.create(input=docs, model=model)
    return [r.embedding for r in response.data]

from pymongo import MongoClient
from tqdm.auto import tqdm
client = MongoClient(MONGODB_URI)
DB_NAME = "ragas_evals"
db = client[DB_NAME]
batch_size = 128
EVAL_EMBEDDING_MODELS = ["text-embedding-ada-002", "text-embedding-3-small"]
for model in EVAL_EMBEDDING_MODELS:
    embedded_docs = []
    print(f"Getting embeddings for the {model} model")
    for i in tqdm(range(0, len(docs), batch_size)):
        end = min(len(docs), i + batch_size)
        batch = docs[i:end]
        batch_embeddings = get_embeddings(batch, model)
        batch_embedded_docs = [
            {"text": batch[i], "embedding": batch_embeddings[i]}
            for i in range(len(batch))
        ]
        embedded_docs.extend(batch_embedded_docs)
    collection = db[model]
    collection.delete_many({})
    collection.insert_many(embedded_docs)
    print(f"Finished inserting embeddings for the {model} model")

{
  "fields": [
    {
      "numDimensions": 1536,
      "path": "embedding",
      "similarity": "cosine",
      "type": "vector"
    }
  ]
}

from langchain_openai import OpenAIEmbeddings
from langchain_mongodb import MongoDBAtlasVectorSearch
from langchain_core.vectorstores import VectorStoreRetriever
def get_retriever(model: str, k: int) -> VectorStoreRetriever:
    """
    Get a vector store retriever for a given embedding model.
    Args:
        model (str): Embedding model to use
        k (int): Number of results to retrieve
    Returns:
        VectorStoreRetriever: A vector store retriever object
    """
    embeddings = OpenAIEmbeddings(model=model)
    vector_store = MongoDBAtlasVectorSearch.from_connection_string(
        connection_string=MONGODB_URI,
        namespace=f"{DB_NAME}.{model}",
        embedding=embeddings,
        index_name="vector_index",
        text_key="text",
    )
    retriever = vector_store.as_retriever(
        search_type="similarity", search_kwargs={"k": k}
    )
    return retriever

QUESTIONS = df["question"].to_list()
GROUND_TRUTH = df["correct_answer"].tolist()

from datasets import Dataset
from ragas import evaluate, RunConfig
from ragas.metrics import context_precision, context_recall
import nest_asyncio
# Allow nested use of asyncio (used by RAGAS)
nest_asyncio.apply()
for model in EVAL_EMBEDDING_MODELS:
    data = {"question": [], "ground_truth": [], "contexts": []}
    data["question"] = QUESTIONS
    data["ground_truth"] = GROUND_TRUTH
    retriever = get_retriever(model, 2)
    # Get relevant documents for the evaluation dataset
    for i in tqdm(range(0, len(QUESTIONS))):
        data["contexts"].append(
            [doc.page_content for doc in retriever.invoke(QUESTIONS[i])]
        )
    # RAGAS expects a Dataset object
    dataset = Dataset.from_dict(data)
    # RAGAS runtime settings to avoid hitting OpenAI rate limits
    run_config = RunConfig(max_workers=4, max_wait=180)
    result = evaluate(
        dataset=dataset,
        metrics=[context_precision, context_recall],
        run_config=run_config,
        raise_exceptions=False,
    )
    print(f"Result for the {model} model: {result}")

from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_core.runnables.base import RunnableSequence
from langchain_core.output_parsers import StrOutputParser
def get_rag_chain(retriever: VectorStoreRetriever, model: str) -> RunnableSequence:
    """
    Create a basic RAG chain.
    Args:
        retriever (VectorStoreRetriever): Vector store retriever object
        model (str): Chat completion model to use
    Returns:
        RunnableSequence: A RAG chain
    """
    # Generate context using the retriever, and pass the user question through
    retrieve = {
        "context": retriever
        | (lambda docs: "\n\n".join([d.page_content for d in docs])),
        "question": RunnablePassthrough(),
    }
    template = """Answer the question based only on the following context: \
    {context}
    Question: {question}
    """
    # Define the chat prompt
    prompt = ChatPromptTemplate.from_template(template)
    # Define the model for chat completion
    llm = ChatOpenAI(temperature=0, model=model)
    # Parse output as a string
    parse_output = StrOutputParser()
    # RAG chain
    rag_chain = retrieve | prompt | llm | parse_output
    return rag_chain

from ragas.metrics import faithfulness, answer_relevancy
for model in ["gpt-3.5-turbo-1106", "gpt-3.5-turbo"]:
    data = {"question": [], "ground_truth": [], "contexts": [], "answer": []}
    data["question"] = QUESTIONS
    data["ground_truth"] = GROUND_TRUTH
    # Use the best embedding model from the retriever evaluation
    retriever = get_retriever("text-embedding-3-small", 2)
    rag_chain = get_rag_chain(retriever, model)
    for i in tqdm(range(0, len(QUESTIONS))):
        question = QUESTIONS[i]
        data["answer"].append(rag_chain.invoke(question))
        data["contexts"].append(
            [doc.page_content for doc in retriever.invoke(question)]
        )
    # RAGAS expects a Dataset object
    dataset = Dataset.from_dict(data)
    # RAGAS runtime settings to avoid hitting OpenAI rate limits
    run_config = RunConfig(max_workers=4, max_wait=180)
    result = evaluate(
        dataset=dataset,
        metrics=[faithfulness, answer_relevancy],
        run_config=run_config,
        raise_exceptions=False,
    )
    print(f"Result for the {model} model: {result}")