mcpField
L
langchain-python-quickstart

langchain-python-quickstart

github.com/langchain-aiAgent workflows1.3k5.2k installsUpdated 3d ago
Repository

About langchain-python-quickstart

A skill for developers building a first LangChain agent in Python, following the official quickstart to create a weather agent. It asks for a model provider and keeps setup and execution in a new project directory.

Key features

  1. 01Follow the official quickstart
  2. 02Create a weather agent
  3. 03Choose and configure a model provider
  4. 04Work in a separate project directory
  5. 05Run the example and show output

Use cases

  1. 01Build a first LangChain Python agent
  2. 02Choose a model provider and configure its API key
  3. 03Test the weather agent example

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/langchain-ai/langchain-skills --skill langchain-python-quickstart

After installing, type/langchain-python-quickstartin Claude Code to confirm it loaded.

Details

From the project README

LangChain Python quickstart

Follow the live docs — do not invent an alternate API from memory:

https://docs.langchain.com/oss/python/langchain/quickstart

Fetch that page (Docs MCP or HTTP) and implement what it shows (weather agent + create_agent).

Local setup constraints

Apply these on top of the quickstart (they keep setup minimal and model-agnostic):

  1. Ask which provider/model to use. Showcase that LangChain is model-agnostic. Suggested prompt:

    Which model should this agent use? Pass a provider:model string — e.g. openai:gpt-5.5, anthropic:claude-sonnet-5, google_genai:gemini-2.5-flash-lite. Default if you're unsure: anthropic:claude-sonnet-5.

    Swap the quickstart's model string for their choice (or the default).

  2. Create a new directory (e.g. langchain-agent/) and do all work there — do not pollute the open project.

  3. Only secret: the provider API key in .env (gitignored). No LangSmith / Tavily unless they ask. Prefer they edit .env themselves — don't paste keys into chat.

  4. Install the provider package needed for their model if the quickstart's base install isn't enough.

  5. Run the example, show output, then stop. Point to langchain-fundamentals for next steps.

Comments

Markdown supported