Lab 6 — The Same RAG, with LangChain¶

⏱️ ~30 min

Rebuild Lab 4 using LangChain. Notice how much boilerplate disappears. Uses OpenAI for embeddings + chat.

Requires an OpenAI API key — these labs use OpenAI embeddings / function-calling specifically. (Labs 1–3 work with OpenAI or Anthropic.)

In [ ]:

# Tip: pin these to exact versions in real projects — these frameworks ship breaking changes often.
!pip install -q langchain langchain-openai langchain-chroma
import os, getpass
if not os.environ.get("OPENAI_API_KEY"):
    os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API key: ")

# Tip: pin these to exact versions in real projects — these frameworks ship breaking changes often. !pip install -q langchain langchain-openai langchain-chroma import os, getpass if not os.environ.get("OPENAI_API_KEY"): os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API key: ")

1. Same documents as Lab 4¶

In [ ]:

documents = [
    "The Helios API rate limit is 100 requests per minute per API key.",
    "Helios refunds are processed within 5 business days to the original payment method.",
    "The Helios SDK supports Python 3.9 and above; Python 3.8 reached end of life.",
    "To rotate a Helios API key, go to Settings > Security > Rotate Key. Old keys expire in 24h.",
    "Helios stores data in the EU (Frankfurt) region by default for all new accounts.",
]

documents = [ "The Helios API rate limit is 100 requests per minute per API key.", "Helios refunds are processed within 5 business days to the original payment method.", "The Helios SDK supports Python 3.9 and above; Python 3.8 reached end of life.", "To rotate a Helios API key, go to Settings > Security > Rotate Key. Old keys expire in 24h.", "Helios stores data in the EU (Frankfurt) region by default for all new accounts.", ]

2. Build the vector store in 3 lines¶

In [ ]:

from langchain_openai import OpenAIEmbeddings
from langchain_chroma import Chroma
vectorstore = Chroma.from_texts(documents, embedding=OpenAIEmbeddings(model="text-embedding-3-small"))
retriever = vectorstore.as_retriever(search_kwargs={"k": 2})

from langchain_openai import OpenAIEmbeddings from langchain_chroma import Chroma vectorstore = Chroma.from_texts(documents, embedding=OpenAIEmbeddings(model="text-embedding-3-small")) retriever = vectorstore.as_retriever(search_kwargs={"k": 2})

3. Wire retriever → prompt → model with LCEL¶

In [ ]:

from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_core.output_parsers import StrOutputParser

prompt = ChatPromptTemplate.from_template(
    "Answer ONLY from the context. If absent, say you don't know.\n\n"
    "Context:\n{context}\n\nQuestion: {question}")

def format_docs(docs):
    return "\n".join(f"- {d.page_content}" for d in docs)

chain = (
    {"context": retriever | format_docs, "question": RunnablePassthrough()}
    | prompt | ChatOpenAI(model="gpt-4o-mini", temperature=0) | StrOutputParser()
)

from langchain_openai import ChatOpenAI from langchain_core.prompts import ChatPromptTemplate from langchain_core.runnables import RunnablePassthrough from langchain_core.output_parsers import StrOutputParser prompt = ChatPromptTemplate.from_template( "Answer ONLY from the context. If absent, say you don't know.\n\n" "Context:\n{context}\n\nQuestion: {question}") def format_docs(docs): return "\n".join(f"- {d.page_content}" for d in docs) chain = ( {"context": retriever | format_docs, "question": RunnablePassthrough()} | prompt | ChatOpenAI(model="gpt-4o-mini", temperature=0) | StrOutputParser() )

In [ ]:

print(chain.invoke("How long until my old API key stops working after I rotate it?"))
print(chain.invoke("What is the Helios phone support number?"))

print(chain.invoke("How long until my old API key stops working after I rotate it?")) print(chain.invoke("What is the Helios phone support number?"))

Takeaway: Lab 4's manual embed/store/retrieve/augment loop is now a few composable lines. The framework owns the plumbing; you own the prompt and the data.

✅ Did it work?¶

• The first chain.invoke answered the key-rotation question from the Helios docs (old keys expire in 24h).
• The second chain.invoke declined the phone-support question — same grounding behavior as Lab 4, far less code.