【AI】PythonのLangChainでRAGを実装する方法

pip install langchain langchain-openai langchain-chroma langchain-community chromadb

OPENAI_API_KEY="your_api_key"

from langchain_community.document_loaders import TextLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter

loader = TextLoader("docs/manual.txt")
documents = loader.load()

splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
chunks = splitter.split_documents(documents)

from langchain_openai import OpenAIEmbeddings
from langchain_chroma import Chroma

embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
vectorstore = Chroma.from_documents(chunks, embeddings, persist_directory="./chroma_db")

retriever = vectorstore.as_retriever(search_type="similarity", search_kwargs={"k": 4})

from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough

prompt = ChatPromptTemplate.from_template(
    "以下のコンテキストだけを根拠に質問へ回答してください。\n\nコンテキスト:\n{context}\n\n質問:\n{question}"
)

llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)

def format_docs(docs):
    return "\n\n".join(doc.page_content for doc in docs)

rag_chain = (
    {"context": retriever | format_docs, "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)

answer = rag_chain.invoke("返品ポリシーについて教えてください")
print(answer)