langchain-python-quickstart

按官方在线快速入门在新建目录中搭建最小 LangChain Python agent：先询问用户选择模型提供商（provider:model），将密钥写入 .env，按需补充依赖，运行天气 agent（create_agent）并展示输出后停止，末尾指向进阶 skill。

热度 63.90

最近更新 2026-10-19 02:34:04

分类：开发依赖：联网浏览搜索 / 读写文件 / 代码执行 / 第三方 API / 内部调用大模型应用场景：代码生成 / API 集成 / 工作流

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add langchain-ai/langchain-skills/langchain-python-quickstart

Metadata

name: langchain-python-quickstart
description: Scaffold a minimal local LangChain agent in Python by following the official quickstart. Use when the user wants to quickly build or try a LangChain agent locally.

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

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

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

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).
Create a new directory (e.g. langchain-agent/) and do all work there — do not pollute the open project.
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.
Install the provider package needed for their model if the quickstart's base install isn't enough.
Run the example, show output, then stop. Point to langchain-fundamentals for next steps.