langchain-rag

LangChain RAG Builder

Quick Decision: Which Vector Store?

RAG Pipeline Quick Start

from langchain_community.document_loaders import WebBaseLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_core.vectorstores import InMemoryVectorStore
from langchain_openai import OpenAIEmbeddings, ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough

# 1. Load documents
loader = WebBaseLoader("https://example.com/docs")
docs = loader.load()

# 2. Split into chunks
splitter = RecursiveCharacterTextSplitter(
    chunk_size=1000,      # Characters per chunk
    chunk_overlap=200,    # Overlap between chunks
    add_start_index=True, # Track position in original doc
)
chunks = splitter.split_documents(docs)

# 3. Create vector store with embeddings
embeddings = OpenAIEmbeddings()
vectorstore = InMemoryVectorStore.from_documents(chunks, embeddings)

# 4. Create retriever
retriever = vectorstore.as_retriever(search_kwargs={"k": 4})

# 5. Build RAG chain
prompt = ChatPromptTemplate.from_template("""
Answer based only on the context. If unsure, say "I don't know."

Context: {context}
Question: {question}
""")

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

llm = ChatOpenAI(model="gpt-4o")

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

# 6. Query
answer = rag_chain.invoke("What is this document about?")