LangChain vs LlamaIndex 比較

# LangChain — RAGパイプライン(Python)
from langchain_anthropic import ChatAnthropic
from langchain_community.vectorstores import Chroma
from langchain_openai import OpenAIEmbeddings
from langchain.chains import RetrievalQA

# ベクトルストアを作成
embeddings = OpenAIEmbeddings()
vectorstore = Chroma.from_documents(documents, embeddings)

# RAGチェーン
llm = ChatAnthropic(model="claude-opus-4-7")
qa_chain = RetrievalQA.from_chain_type(
    llm=llm,
    retriever=vectorstore.as_retriever(search_kwargs={"k": 5}),
    return_source_documents=True
)

result = qa_chain.invoke({"query": "Şirket politikası nedir?"})
print(result["result"])
print("Kaynaklar:", [doc.metadata for doc in result["source_documents"]])

# LlamaIndex — ドキュメントベースの質問応答システム
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.llms.anthropic import Anthropic
from llama_index.core import Settings

# LLMを設定
Settings.llm = Anthropic(model="claude-opus-4-7")

# ドキュメントを読み込みインデックス化
documents = SimpleDirectoryReader("./docs").load_data()
index = VectorStoreIndex.from_documents(documents)

# クエリエンジン
query_engine = index.as_query_engine(
    similarity_top_k=5,
    response_mode="tree_summarize"
)

response = query_engine.query(
    "KVKK kapsamında kullanıcı hakları nelerdir?"
)
print(response)
print("Kaynak düğümler:", response.source_nodes)