@aigne/deepseek

AIGNE Deepseek SDK for integrating with Deepseek AI models within the AIGNE Framework.
Introduction#@aigne/deepseek provides a seamless integration between the AIGNE Framework and Deepseek's powerful language models and API. This package enables developers to easily leverage Deepseek's AI models in their AIGNE applications, providing a consistent interface across the framework while taking advantage of Deepseek's advanced AI capabilities.
Features#Deepseek API Integration: Direct connection to Deepseek's API services
Chat Completions: Support for Deepseek's chat completions API with all available models
Function Calling: Built-in support for function calling capabilities
Streaming Responses: Support for streaming responses for more responsive applications
Type-Safe: Comprehensive TypeScript typings for all APIs and models
Consistent Interface: Compatible with the AIGNE Framework's model interface
Error Handling: Robust error handling and retry mechanisms
Full Configuration: Extensive configuration options for fine-tuning behavior
Installation#Using npm#npm install @aigne/deepseek @aigne/core

Using yarn#yarn add @aigne/deepseek @aigne/core

Using pnpm#pnpm add @aigne/deepseek @aigne/core

Basic Usage#import { DeepSeekChatModel } from "@aigne/deepseek";

const model = new DeepSeekChatModel({
  // Provide API key directly or use environment variable DEEPSEEK_API_KEY
  apiKey: "your-api-key", // Optional if set in env variables
  // Specify model version (defaults to 'deepseek-chat')
  model: "deepseek-chat",
  modelOptions: {
    temperature: 0.7,
  },
});

const result = await model.invoke({
  messages: [{ role: "user", content: "Introduce yourself" }],
});

console.log(result);
/* Output:
  {
    text: "Hello! I'm an AI assistant powered by DeepSeek's language model.",
    model: "deepseek-chat",
    usage: {
      inputTokens: 7,
      outputTokens: 12
    }
  }
  */

Streaming Responses#import { DeepSeekChatModel } from "@aigne/deepseek";

const model = new DeepSeekChatModel({
  apiKey: "your-api-key",
  model: "deepseek-chat",
});

const stream = await model.invoke(
  {
    messages: [{ role: "user", content: "Introduce yourself" }],
  },
  undefined,
  { streaming: true },
);

let fullText = "";
const json = {};

for await (const chunk of stream) {
  const text = chunk.delta.text?.text;
  if (text) fullText += text;
  if (chunk.delta.json) Object.assign(json, chunk.delta.json);
}

console.log(fullText); // Output: "Hello! I'm an AI assistant powered by DeepSeek's language model."
console.log(json); // { model: "deepseek-chat", usage: { inputTokens: 7, outputTokens: 12 } }

License#Elastic-2.0
Classes#DeepSeekChatModel#Implementation of the ChatModel interface for DeepSeek's API
This model uses OpenAI-compatible API format to interact with DeepSeek's models, but with specific configuration and capabilities for DeepSeek.
Default model: 'deepseek-chat'
Examples#Here's how to create and use a DeepSeek chat model:
const model = new DeepSeekChatModel({
  // Provide API key directly or use environment variable DEEPSEEK_API_KEY
  apiKey: "your-api-key", // Optional if set in env variables
  // Specify model version (defaults to 'deepseek-chat')
  model: "deepseek-chat",
  modelOptions: {
    temperature: 0.7,
  },
});

const result = await model.invoke({
  messages: [{ role: "user", content: "Introduce yourself" }],
});

console.log(result);
/* Output:
{
  text: "Hello! I'm an AI assistant powered by DeepSeek's language model.",
  model: "deepseek-chat",
  usage: {
    inputTokens: 7,
    outputTokens: 12
  }
}
*/

Here's an example with streaming response:
const model = new DeepSeekChatModel({
  apiKey: "your-api-key",
  model: "deepseek-chat",
});

const stream = await model.invoke(
  {
    messages: [{ role: "user", content: "Introduce yourself" }],
  },
  { streaming: true },
);

let fullText = "";
const json = {};

for await (const chunk of stream) {
  const text = chunk.delta.text?.text;
  if (text) fullText += text;
  if (chunk.delta.json) Object.assign(json, chunk.delta.json);
}

console.log(fullText); // Output: "Hello! I'm an AI assistant powered by DeepSeek's language model."
console.log(json); // { model: "deepseek-chat", usage: { inputTokens: 7, outputTokens: 12 } }

Extends#OpenAIChatModel
Indexable#[key: symbol]: () => string | () => Promise<void>
Constructors#Constructor#new DeepSeekChatModel(options?): DeepSeekChatModel
Parameters#Parameter
Type
options?
OpenAIChatModelOptions
Returns#DeepSeekChatModel
Overrides#OpenAIChatModel.constructor
Properties#apiKeyEnvName#protected apiKeyEnvName: string = "DEEPSEEK_API_KEY"
Overrides#OpenAIChatModel.apiKeyEnvName
supportsNativeStructuredOutputs#protected supportsNativeStructuredOutputs: boolean = false
Overrides#OpenAIChatModel.supportsNativeStructuredOutputs
supportsToolsEmptyParameters#protected supportsToolsEmptyParameters: boolean = false
Overrides#OpenAIChatModel.supportsToolsEmptyParameters
Getting Started

How to guides

Concepts

AIGNE CLI

API Reference

Contributing

@aigne/deepseek

Introduction#

Features#

Installation#

Using npm#

Using yarn#

Using pnpm#

Basic Usage#

Streaming Responses#

License#

Classes#

DeepSeekChatModel#

Examples#

Extends#

Indexable#

Constructors#

Constructor#

Parameters#

Returns#

Overrides#

Properties#

apiKeyEnvName#

Overrides#

supportsNativeStructuredOutputs#

Overrides#

supportsToolsEmptyParameters#

Overrides#

memory

@aigne/gemini
