AI engineering glossary · Agents tools MCP
What is langChain?
LangChain: An open-source framework of building blocks for applications that use language models, including prompt templates, model wrappers, retrievers, tool interfaces and chains. It speeds up prototyping by providing ready-made integrations.
LangChain: an example
A team uses LangChain to connect a model to a vector store and a calculator tool in a few lines.
LangChain in Python
A short example you can run (Python 3.11). The output below is what it really prints.
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnableLambda
from langchain_core.output_parsers import StrOutputParser
prompt = ChatPromptTemplate.from_messages([
("system", "You answer in one short sentence."),
("human", "What is {topic}?"),
])
# A stand-in for a chat model so this runs without an API key; swap in ChatOpenAI(), ChatAnthropic() etc.
fake_llm = RunnableLambda(lambda p: f"[model saw {len(p.to_messages())} messages] {p.to_messages()[-1].content}")
chain = prompt | fake_llm | StrOutputParser()
print(chain.invoke({"topic": "RAG"}))Output
[model saw 2 messages] What is RAG?
Related terms
More Agents tools MCP terms
- LangGraph
- Least privilege for agents
- LlamaIndex
- Long-term memory
- Max iterations
- MCP authorization
- MCP capability negotiation
- MCP client
Where you learn it
LangChain is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.