How do I get started with LangChain as a developer?

To get started with LangChain, install the package, set up your model provider API key, and build your first agent using the new create_agent abstraction in LangChain 1.0. The framework supports Python 3.10+ and is designed for rapid prototyping across any model provider.

1. Install LangChain
bash

2. Set Up Your Model Provider
LangChain supports any model provider with one-line changes. For OpenAI, set your API key:

bash

3. Build Your First Agent
LangChain 1.0 introduces the create_agent abstraction:

python
from langchain.agents import create_agent

weather_agent = create_agent(
model="openai:gpt-5",
tools=[get_weather],
system_prompt="Help the user by fetching the weather in their city.",
)

result = agent.invoke({"role": "user", "what's the weather in SF?"})

Language Options
LangChain is primarily a Python framework, with TypeScript support also available. For document-heavy workloads, LlamaIndex may be a better fit. For production TypeScript teams building agents with built-in Studio environments, Mastra offers a compelling alternative.

Learning Resources
LangChain Academy offers self-guided courses on building with LangChain and LangGraph. The official documentation now features a completely redesigned site alongside the 1.0 releases.

TL;DR