LangChain map_reduce处理CSV失效及高成本问题求助

问题情况 #

我尝试用LangChain搭配ChatGPT提取CSV文件中的信息：

• 使用少量数据并采用stuff模式时，运行完全正常；
• 使用完整CSV文件并采用map_reduce模式时，多数查询（如统计德国车手数量、查找使用14号的车手、出生日期最早的车手等）无法得到正确结果，且调用成本极高（达8美元）。

代码示例 #

queries = ["Tell me the name of every driver who is German","how many german drivers are?",  "which driver uses the number 14?", "which driver has the oldest birthdate?"]

import os

from dotenv import load_dotenv, find_dotenv
load_dotenv(find_dotenv()) # 读取本地.env文件

from langchain.document_loaders import CSVLoader
from langchain.callbacks import get_openai_callback
from langchain.chains import RetrievalQA
from langchain.llms import OpenAI
from langchain.vectorstores import Chroma

files = ['drivers.csv','drivers_full.csv']

for file in files:
    print("=====================================")
    print(file)
    print("=====================================")
    with get_openai_callback() as cb:

        loader = CSVLoader(file_path=file,encoding='utf-8')
        docs = loader.load()

        from langchain.embeddings.openai import OpenAIEmbeddings

        embeddings = OpenAIEmbeddings()

        # 创建向量存储用作索引
        db = Chroma.from_documents(docs, embeddings)
        # 将索引暴露为检索器接口
        retriever = db.as_retriever(search_type="similarity", search_kwargs={"k":1000, "score_threshold":"0.2"})

        for query in queries:
            qa_stuff = RetrievalQA.from_chain_type(
                llm=OpenAI(temperature=0,batch_size=20), 
                chain_type="map_reduce", 
                retriever=retriever,
                verbose=True
            )

            print(query)
            result = qa_stuff.run(query)

            print(result)
            
        print(cb)

内容的提问来源于stack exchange，提问作者Pablo Castilla