构建 LLM 应用与 AI Agent 的开源框架,统一模型、向量库与工具接口,支持 Python 与 JS/TS。

langchain-xai==1.4.0
发布于
18 小时前
149,657
星标
809
下载
同步于
26 分钟前

最新版本

langchain-mistralai==1.2.0 2026年11月15日 22:38
下载慢?可在上方随时切换镜像源 如何校验 SHA256

langchain_mistralai-1.2.0.tar.gz

135 KB ·压缩包 ·SHA256 59b1729f1b…
下载

langchain_mistralai-1.2.0-py3-none-any.whl

23 KB ·文件 ·SHA256 47af938357…
下载
下载或用起来遇到问题?
下载速度慢或中断
在下载区右上角切换镜像源(ghfast / gh-proxy / moeyy),源文件不变,只是换条线路。
Windows 提示“未知发布者”
多数开源项目没有购买代码签名证书,SmartScreen 会拦一下。核对 SHA256 与仓库来源后,点“更多信息 → 仍要运行”。
macOS 提示“已损坏,无法打开”
在终端执行 xattr -cr /Applications/应用名.app 去掉隔离属性;仅对可信来源这么做。
安装包架构怎么选
Apple 芯片选 arm64,Intel Mac 选 x64;Windows 绝大多数选 x64,ARM 设备选 arm64;Linux 优先 AppImage。
怎么确认文件没被篡改
下载后本地计算 SHA256,与安装包右侧的校验值逐位比对,不一致就不要运行。

项目说明

The agent engineering platform.

PyPI - License PyPI - Downloads Version Twitter / X


LangChain is a framework for building agents and LLM-powered applications. It helps you chain together interoperable components and third-party integrations to simplify AI application development — all while future-proofing decisions as the underlying technology evolves.

[!TIP]
Just getting started? Check out Deep Agents — a higher-level package built on LangChain for agents that have built-in capabilities for common usage patterns such as planning, subagents, file system usage, and more.

Quickstart

uv add langchain
from langchain.chat_models import init_chat_model

model = init_chat_model("openai:gpt-5.5")
result = model.invoke("Hello, world!")

If you're looking for more advanced customization or agent orchestration, check out LangGraph, our framework for building controllable agent workflows.

For an equivalent JS/TS library, check out LangChain.js.

[!TIP]
For developing, debugging, and deploying AI agents and LLM applications, see LangSmith.

LangChain ecosystem

While the LangChain framework can be used standalone, it also integrates seamlessly with any LangChain product, giving developers a full suite of tools when building LLM applications.

  • Deep Agents — Build agents that can plan, use subagents, and leverage file systems for complex tasks
  • LangGraph — Build agents that can reliably handle complex tasks with our low-level agent orchestration framework
  • Integrations — Chat & embedding models, tools & toolkits, and more
  • LangSmith — Agent evals, observability, and debugging for LLM apps
  • LangSmith Deployment — Deploy and scale agents with a purpose-built platform for long-running, stateful workflows

Why use LangChain?

LangChain helps developers build applications powered by LLMs through a standard interface for models, embeddings, vector stores, and more.

  • Real-time data augmentation — Easily connect LLMs to diverse data sources and external/internal systems, drawing from LangChain's vast library of integrations with model providers, tools, vector stores, retrievers, and more
  • Model interoperability — Swap models in and out as your engineering team experiments to find the best choice for your application's needs. As the industry frontier evolves, adapt quickly — LangChain's abstractions keep you moving without losing momentum
  • Rapid prototyping — Quickly build and iterate on LLM applications with LangChain's modular, component-based architecture. Test different approaches and workflows without rebuilding from scratch, accelerating your development cycle
  • Production-ready features — Deploy reliable applications with built-in support for monitoring, evaluation, and debugging through integrations like LangSmith. Scale with confidence using battle-tested patterns and best practices
  • Vibrant community and ecosystem — Leverage a rich ecosystem of integrations, templates, and community-contributed components. Benefit from continuous improvements and stay up-to-date with the latest AI developments through an active open-source community
  • Flexible abstraction layers — Work at the level of abstraction that suits your needs — from high-level chains for quick starts to low-level components for fine-grained control. LangChain grows with your application's complexity

Resources

历史版本

共 30 个版本
langchain-mistralai==1.2.0 2026.11.15 2 个文件
langchain_mistralai-1.2.0.tar.gz 135 KB
langchain_mistralai-1.2.0-py3-none-any.whl 23 KB
langchain-groq==1.2.0 2026.11.15 2 个文件
langchain_groq-1.2.0.tar.gz 188 KB
langchain_groq-1.2.0-py3-none-any.whl 21 KB
langchain-xai==1.4.0 2026.11.15 2 个文件
langchain_xai-1.4.0.tar.gz 182 KB
langchain_xai-1.4.0-py3-none-any.whl 13 KB
langchain-deepseek==1.2.0 2026.11.15 2 个文件
langchain_deepseek-1.2.0.tar.gz 138 KB
langchain_deepseek-1.2.0-py3-none-any.whl 12 KB
langchain-core==1.8.1 2026.11.15 2 个文件
langchain_core-1.8.1.tar.gz 995 KB
langchain_core-1.8.1-py3-none-any.whl 574 KB
langchain-openai==1.8.0 2026.11.13 2 个文件
langchain_openai-1.8.0.tar.gz 3.2 MB
langchain_openai-1.8.0-py3-none-any.whl 151 KB
langchain-typesafe==0.1.0 2026.11.11 2 个文件
langchain_typesafe-0.1.0.tar.gz 169 KB
langchain_typesafe-0.1.0-py3-none-any.whl 20 KB
langchain==1.5.0 2026.11.11 2 个文件
langchain-1.5.0.tar.gz 705 KB
langchain-1.5.0-py3-none-any.whl 173 KB
langchain-core==1.8.0 2026.11.11 2 个文件
langchain_core-1.8.0.tar.gz 993 KB
langchain_core-1.8.0-py3-none-any.whl 573 KB
langchain==1.4.10 2026.11.10 2 个文件
langchain-1.4.10.tar.gz 754 KB
langchain-1.4.10-py3-none-any.whl 167 KB
langchain-core==1.7.7 2026.11.10 2 个文件
langchain_core-1.7.7.tar.gz 1018 KB
langchain_core-1.7.7-py3-none-any.whl 567 KB
langchain-fireworks==1.7.3 2026.11.09 2 个文件
langchain_fireworks-1.7.3.tar.gz 250 KB
langchain_fireworks-1.7.3-py3-none-any.whl 35 KB