Langchain 学习03 RAG基础

最新推荐文章于 2025-04-05 22:22:50 发布

leichangqing

最新推荐文章于 2025-04-05 22:22:50 发布

阅读量463

点赞数 7

分类专栏： Langchain 文章标签： langchain

本文链接：https://blog.youkuaiyun.com/leichangqing/article/details/136546105

版权

Langchain 专栏收录该内容

6 篇文章

订阅专栏

本文介绍了如何使用AzureOpenAIAPI和RAG(Retrieval-AugmentedGeneration)方法，结合DocArray进行文档检索，并在聊天场景中处理用户问题，实现实时、基于上下文的信息查找和生成答案。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

RAG基础

# Requires:
# pip install langchain docarray tiktoken

import os
from dotenv import load_dotenv, find_dotenv
_ = load_dotenv(find_dotenv())  # 读取本地 .env 文件，里面定义了 OPENAI_API_KEY

#############
api_key = os.environ['AZURE_OPENAI_API_KEY']
azure_endpoint = os.environ['AZURE_OPENAI_ENDPOINT']
api_version = os.environ['AZURE_OPENAPI_VERSION']
model="gpt-35-turbo"
deployment_name="gpt-35-turbo"
############

from langchain_community.vectorstores import DocArrayInMemorySearch
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnableParallel, RunnablePassthrough
from langchain_openai.chat_models import AzureChatOpenAI
from langchain_openai.embeddings import AzureOpenAIEmbeddings

## retrieve relevant documents to the search and include them as part of the context.
vectorstore = DocArrayInMemorySearch.from_texts(
    ["harrison worked at kensho", "bears like to eat honey"],
    embedding=AzureOpenAIEmbeddings(),
)
retriever = vectorstore.as_retriever()
## if no vector, the code as following:
# retriever.invoke("where did harrison work?")

template = """Answer the question based only on the following context:
{context}

Question: {question}
"""
prompt = ChatPromptTemplate.from_template(template)
model = AzureChatOpenAI(
    model=model,
    deployment_name=deployment_name,
    api_key=api_key,
    azure_endpoint=azure_endpoint,
    api_version=api_version,
)
output_parser = StrOutputParser()
##  create a RunnableParallel object with two entries. The first entry, context will include the document results fetched by the retriever.
## The second entry, question will contain the user’s original question. To pass on the question, we use RunnablePassthrough to copy this entry.
## using the retriever for document search, and RunnablePassthrough to pass the user’s question
setup_and_retrieval = RunnableParallel(
    {"context": retriever, "question": RunnablePassthrough()}
)
chain = setup_and_retrieval | prompt | model | output_parser

print(chain.invoke("where did harrison work?"))