How to build a RAG chatbot with LangChain and Python?

Here is a simple RAG chatbot using LangChain:

```python
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_community.vectorstores import FAISS
from langchain.chains import RetrievalQA
from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter

# 1. Load and split documents
loader = PyPDFLoader('document.pdf')
pages = loader.load()
splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
chunks = splitter.split_documents(pages)

# 2. Create vector store
embeddings = OpenAIEmbeddings()
vectorstore = FAISS.from_documents(chunks, embeddings)

# 3. Create RAG chain
llm = ChatOpenAI(model='gpt-4o-mini')
chain = RetrievalQA.from_chain_type(llm=llm, retriever=vectorstore.as_retriever())

# 4. Ask questions
result = chain.invoke({'query': 'What is the main topic?'})
print(result['result'])
```