</>
pythonadvanced

LangChain RAG Retrieval Chain

Build a full RAG pipeline with source citations using LangChain's create_retrieval_chain.

python
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_community.vectorstores import FAISS
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain.chains import create_retrieval_chain
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.documents import Document

docs = [
    Document(page_content='Python was created by Guido van Rossum.', metadata={'source': 'history.txt'}),
    Document(page_content='FastAPI is a modern Python web framework.', metadata={'source': 'frameworks.txt'}),
    Document(page_content='LangChain helps build LLM applications.', metadata={'source': 'tools.txt'}),
]

vectorstore = FAISS.from_documents(docs, OpenAIEmbeddings())
retriever   = vectorstore.as_retriever()

prompt = ChatPromptTemplate.from_template('Answer based on context:\n{context}\n\nQuestion: {input}')
llm    = ChatOpenAI(model='gpt-4o-mini')

doc_chain = create_stuff_documents_chain(llm, prompt)
rag_chain  = create_retrieval_chain(retriever, doc_chain)

result = rag_chain.invoke({'input': 'Who created Python?'})
print('Answer:', result['answer'])
print('Sources:', [d.metadata['source'] for d in result['context']])

Use Cases

  • RAG with citations
  • document Q&A
  • grounded answers

Tags

#langchain#rag#retrieval#citations

Related Snippets

Similar patterns you can reuse in the same workflow.

typescriptadvanced

LangChain RAG Chain Pipeline

Build a retrieval-augmented generation chain with LangChain using vector store retrieval and prompt templates.

Best for: Document Q&A

#langchain#rag
typescriptadvanced

RAG Pipeline Implementation

Build a retrieval-augmented generation pipeline that grounds LLM answers in your own documents.

Best for: Grounding LLM answers in private documents

#ai#rag
pythonadvanced

Build a RAG Pipeline with LangChain

Implement retrieval-augmented generation using LangChain, embeddings, and a vector store.

Best for: Knowledge base Q&A

#ai#langchain
pythonadvanced

RAG with FAISS and LangChain Python

Build a local RAG pipeline using FAISS vector store and LangChain for document Q&A.

Best for: document Q&A

#rag#faiss