---
id: langchain-deepseek
version: "1.1.0"
license: MIT
license_treatment: permissive
maintenance: active
---

# langchain-deepseek — An integration package connecting DeepSeek and LangChain

License: permissive · Maintenance: active · Downloads: 855.5K/mo

## What it is and what it does

This package is a LangChain integration that connects DeepSeek's language models to the LangChain ecosystem. It wraps DeepSeek's API behind LangChain's standard interfaces, allowing developers to use DeepSeek models in place of other LLM providers within LangChain applications without rewriting integration code.

The package depends on langchain-core for base abstractions and langchain-openai for shared patterns (DeepSeek's API follows OpenAI-compatible conventions). It supports Python 3.10 through 3.14 and is marked as production-stable. Use it when you want to build LangChain applications that call DeepSeek models, or when you need to swap DeepSeek in as an alternative LLM provider in an existing LangChain workflow.

Use it for:

- Build a LangChain agent or chain that uses DeepSeek as the reasoning engine instead of OpenAI or other providers.
- Migrate an existing LangChain application from one LLM provider to DeepSeek without rewriting integration logic.
- Prototype multi-model applications that compare DeepSeek output alongside other LLM providers in LangChain.
- Use DeepSeek in LangChain's retrieval-augmented generation (RAG) or document Q&A workflows.
- Deploy LangChain-based chatbots or assistants powered by DeepSeek's models.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Integrates DeepSeek language models into LangChain applications, enabling use of DeepSeek's API through the LangChain framework.

Yes. The package has low install friction, active maintenance, a permissive MIT license, no known vulnerabilities, and sits in the top 5000 PyPI packages by download volume. Install it if you are already using LangChain and want to integrate DeepSeek models; it is a straightforward drop-in provider integration.

## Install

pip install langchain-deepseek
uv add langchain-deepseek
poetry add langchain-deepseek

## Installing langchain-deepseek

Before you install: Low install friction with a pure Python wheel. Actively maintained with a recent release 72 days ago; the parent LangChain repository shows strong community engagement (144267 stars) and current development activity.

License in practice: MIT license permits free use, modification, and distribution with minimal restrictions, making it suitable for both open-source and commercial projects.

Quickstart:

pip install langchain-deepseek

from langchain_deepseek import ChatDeepSeek
from langchain_core.messages import HumanMessage

model = ChatDeepSeek(api_key="your-deepseek-key")
response = model.invoke([HumanMessage(content="Hello")])

Requires a valid DeepSeek API key and Python 3.10 or later.

Verify before relying:

- Specific DeepSeek model names and versions supported by this integration version
- Whether all DeepSeek API features are exposed or only a subset through LangChain abstractions
- Rate limiting or quota handling behavior when used with DeepSeek's API

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 855.5K/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

deepseek langchain integration, deepseek llm connector, deepseek api wrapper, langchain deepseek provider, deepseek language model integration, deepseek chat models langchain, deepseek ai integration python, llm-integration, deepseek, langchain-provider

[View on SkillFed](https://skillfed.io/packages/langchain-deepseek) · [View on PyPI](https://pypi.org/project/langchain-deepseek/)