← All insightsAutomation

Automating LangChain from scratch

CodeWizard Academy · 2 September 2025 · 3 min read · Intermediate

Anything you do to LangChain twice should be automated. This walks the path from a manual install to a repeatable, pipeline-driven setup.

1. Install it reproducibly

bash
pip install langchain langchain-openai langchain-community
export OPENAI_API_KEY=...   # keep keys in a secret manager

2. Describe the desired state

A tiny RAG chain over local documents.

python
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_community.vectorstores import FAISS

vs = FAISS.from_texts(docs, OpenAIEmbeddings())
retriever = vs.as_retriever(search_kwargs={'k': 4})
llm = ChatOpenAI(model='gpt-4o-mini', temperature=0)

def answer(q):
    ctx = '\n'.join(d.page_content for d in retriever.invoke(q))
    return llm.invoke(f'Use only this context:\n{ctx}\n\nQ: {q}').content

3. Run it from CI

Run evals against a golden set in CI with LangSmith.

yaml
- run: |
    pip install langsmith
    python evals/run.py   # scores answers vs a labelled dataset, fails under threshold

Want senior help putting LangChain to work - or a team bootcamp on it? CodeWizard runs Israel's largest DevOps community and embeds named senior engineers with a transparent hours log. Book a free consult or explore the Academy.

Like where this is going?

Get hands-on help from the engineers who write these posts.

Book a free consult