# 1. プロジェクトフォルダ作成
mkdir rag-api
cd rag-api
# 2. 仮想環境の作成と有効化
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
# 3. 必要なライブラリをインストール
pip install fastapi uvicorn[standard] langchain langchain-openai pypdf faiss-cpu sentence-transformers python-dotenv

OPENAI_API_KEY="sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"

# rag_pipeline.py
import os
from dotenv import load_dotenv
from langchain_community.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.vectorstores import FAISS
from langchain_openai import OpenAIEmbeddings, ChatOpenAI
from langchain.chains import RetrievalQA
load_dotenv()
FAISS_INDEX_PATH = "faiss_index"
def create_vector_store(pdf_path: str):
    """PDFを読み込み、ベクトルストアを作成・保存する"""
print("Loading PDF...")
loader = PyPDFLoader(pdf_path)
documents = loader.load()
print("Splitting text into chunks...")
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
chunks = text_splitter.split_documents(documents)
print("Creating embeddings and vector store...")
embeddings = OpenAIEmbeddings()
vector_store = FAISS.from_documents(chunks, embeddings)
vector_store.save_local(FAISS_INDEX_PATH)
print(f"Vector store created and saved at {FAISS_INDEX_PATH}")
def create_qa_chain():
    """ベクトルストアを読み込み、QAチェーンを作成する"""
embeddings = OpenAIEmbeddings()
if not os.path.exists(FAISS_INDEX_PATH):
raise FileNotFoundError("Vector store not found.")
vector_store = FAISS.load_local(
FAISS_INDEX_PATH, 
embeddings, 
allow_dangerous_deserialization=True # FAISSのローカル読み込みに必要
)
llm = ChatOpenAI(model_name="gpt-4o")
# LangChain Expression Language (LCEL) を使った書き方
qa_chain = RetrievalQA.from_chain_type(
llm=llm,
chain_type="stuff",
retriever=vector_store.as_retriever()
)
return qa_chain