agent.pydevelopmentLangchainv1.0

LangChain: RAG Document Agent

Load a directory of docs, embed them, and expose a Q&A agent. Answers questions with citations.

Setup time: ~15 min

Model: GPT-4o

Cost: ~$0.10/day

Last updated: Mar 8, 2026

byFullVibeAIcontributor

Template

agent.py

# Install: pip install langchain langchain-openai langchain-community chromadb

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

# --- Config ---
DOCS_DIR = "./docs"          # point at your docs directory
CHROMA_DIR = "./chroma_db"   # where embeddings are stored
OPENAI_API_KEY = os.environ["OPENAI_API_KEY"]

# --- Load and chunk documents ---
loader = DirectoryLoader(DOCS_DIR, glob="**/*.md", loader_cls=TextLoader)
docs = loader.load()

splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
chunks = splitter.split_documents(docs)

# --- Embed and store ---
embeddings = OpenAIEmbeddings()
vectorstore = Chroma.from_documents(chunks, embeddings, persist_directory=CHROMA_DIR)
retriever = vectorstore.as_retriever(search_kwargs={"k": 4})

# --- Build QA chain ---
prompt = PromptTemplate(
    template="""Answer the question using only the context below.
If the answer is not in the context, say "I don't know."
Cite the source file for each fact.

Context: {context}
Question: {question}
Answer:""",
    input_variables=["context", "question"],
)

llm = ChatOpenAI(model="gpt-4o", temperature=0)
qa_chain = RetrievalQA.from_chain_type(
    llm=llm,
    retriever=retriever,
    chain_type_kwargs={"prompt": prompt},
    return_source_documents=True,
)

# --- Run ---
if __name__ == "__main__":
    while True:
        query = input("Ask a question (or 'quit'): ")
        if query.lower() == "quit":
            break
        result = qa_chain.invoke({"query": query})
        print("\nAnswer:", result["result"])
        print("Sources:", [d.metadata["source"] for d in result["source_documents"]])
        print()

Setup

1
Copy the agent.py content above.
2
Create a Python virtual environment and install dependencies.
3
Set your OPENAI_API_KEY environment variable.
4
Run: python agent.py

Run with LangChain

This is a Python script using LangChain. Set up a virtual environment and install dependencies.

# 1. Create a virtual environment
python -m venv venv && source venv/bin/activate

# 2. Install dependencies
pip install langchain langchain-openai langchain-community chromadb

# 3. Set your API key
export OPENAI_API_KEY="sk-..."

# 4. Save the agent.py from above and run it
python agent.py