langgraph-python-quickstart

1# LangGraph Python quickstart
2 
3Follow the live docs — do not invent an alternate API from memory:
4 
5**https://docs.langchain.com/oss/python/langgraph/quickstart**
6 
7Fetch that page (Docs MCP or HTTP) and implement what it shows (calculator / math agent with the Graph API). Prefer the Graph API path over the Functional API unless the user asks otherwise. Skip IPython graph visualization.
8 
9## Local setup constraints
10 
11Apply these on top of the quickstart (they keep setup minimal and model-agnostic):
12 
131. **Ask** which provider/model to use. Showcase that LangGraph works with any LangChain chat model. Suggested prompt:
14 
15   > 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`**.
16 
17   The docs often hardcode Anthropic — replace with `init_chat_model("<MODEL>")` (or equivalent) using their choice. If using Claude Sonnet 5+, omit `temperature` / `top_p` / `top_k` (unsupported).
18 
192. Create a **new** directory (e.g. `langgraph-agent/`) and do all work there — do not pollute the open project.
20 
213. 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.
22 
234. Install packages from the quickstart plus the provider package for their model.
24…