@langchain/deepseek

This package contains the LangChain.js integrations for DeepSeek.

Installation

npm install @langchain/deepseek @langchain/core
Copy

Chat models

This package adds support for DeepSeek's chat model inference.

Set the necessary environment variable (or pass it in via the constructor):

export DEEPSEEK_API_KEY=
Copy

import { ChatDeepSeek } from "@langchain/deepseek";
import { HumanMessage } from "@langchain/core/messages";

const model = new ChatDeepSeek({
  apiKey: process.env.DEEPSEEK_API_KEY, // Default value.
  model: "<model_name>",
});

const res = await model.invoke([
  {
    role: "user",
    content: message,
  },
]);
Copy

Development

To develop the @langchain/deepseek package, you'll need to follow these instructions:

Install dependencies

yarn install
Copy

Build the package

yarn build
Copy

Or from the repo root:

yarn build --filter=@langchain/deepseek
Copy

Run tests

Test files should live within a tests/ file in the src/ folder. Unit tests should end in .test.ts and integration tests should end in .int.test.ts:

$ yarn test
$ yarn test:int
Copy

Lint & Format

Run the linter & formatter to ensure your code is up to standard:

yarn lint && yarn format
Copy

Adding new entrypoints

If you add a new file to be exported, either import & re-export from src/index.ts, or add it to the entrypoints field in the config variable located inside langchain.config.js and run yarn build to generate the new entrypoint.