rag-dev

[project]
name = "rag-dev"
version = "0.1.0"
description = "RAG development environment"
requires-python = "==3.12.*"
dependencies = [
  "torch==2.10.0",
  "torchvision==0.25.0",
  "torchaudio==2.10.0",
  "langchain==1.2.10",
  "langchain-community==0.4.1",
  "langchain-openai==1.1.10",
  "sentence-transformers==5.2.3",
  "chromadb==1.5.1",
  "faiss-cpu==1.13.2; platform_system != 'Windows'",
  "qdrant-client==1.17.0",
  "pymilvus==2.6.9",
  "milvus-lite==2.5.1",
  "rank-bm25==0.2.2",
  "ragas==0.4.3",
  "tiktoken==0.12.0",
  "openai==2.21.0",
  "ipykernel==7.2.0",
  "pytest==9.0.2",
  "ruff==0.15.2",
]

[tool.uv]
package = false

uv run python -c "import torch, langchain, chromadb, ragas; print('torch', torch.__version__); print('langchain', langchain.__version__); print('chromadb', chromadb.__version__); print('ragas', ragas.__version__)"

uv run python -c "import faiss; print('faiss', faiss.__version__)"

from langchain_community.document_loaders import TextLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_openai import OpenAIEmbeddings, ChatOpenAI
from langchain_community.vectorstores import Chroma
from langchain.chains import RetrievalQA

# 1) 문서 로드
loader = TextLoader("docs/guide.txt")
documents = loader.load()

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

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

# 4) 검색 + 생성
retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)

# 5) 질의
result = qa_chain.invoke({"query": "프로젝트 설치 방법을 알려주세요."})
print(result["result"])