@aigne/gemini

AIGNE Gemini SDK for integrating with Google's Gemini AI models within the AIGNE Framework.
Introduction#@aigne/gemini provides a seamless integration between the AIGNE Framework and Google's Gemini language models and API. This package enables developers to easily leverage Gemini's advanced AI capabilities in their AIGNE applications, providing a consistent interface across the framework while taking advantage of Google's state-of-the-art multimodal models.
Features#Google Gemini API Integration: Direct connection to Google's Gemini API services
Chat Completions: Support for Gemini's chat completions API with all available models
Multimodal Support: Built-in support for handling both text and image inputs
Function Calling: 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/gemini @aigne/core

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

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

Basic Usage#import { GeminiChatModel } from "@aigne/gemini";

const model = new GeminiChatModel({
  // Provide API key directly or use environment variable GOOGLE_API_KEY
  apiKey: "your-api-key", // Optional if set in env variables
  // Specify Gemini model version (defaults to 'gemini-1.5-pro' if not specified)
  model: "gemini-1.5-flash",
  modelOptions: {
    temperature: 0.7,
  },
});

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

console.log(result);
/* Output:
  {
    text: "Hello from Gemini! I'm Google's helpful AI assistant. How can I assist you today?",
    model: "gemini-1.5-flash"
  }
  */

Streaming Responses#import { GeminiChatModel } from "@aigne/gemini";

const model = new GeminiChatModel({
  apiKey: "your-api-key",
  model: "gemini-1.5-flash",
});

const stream = await model.invoke(
  {
    messages: [{ role: "user", content: "Hi there, 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 from Gemini! I'm Google's helpful AI assistant. How can I assist you today?"
console.log(json); // { model: "gemini-1.5-flash" }

License#Elastic-2.0
Classes#GeminiChatModel#Implementation of the ChatModel interface for Google's Gemini API
This model uses OpenAI-compatible API format to interact with Google's Gemini models, providing access to models like Gemini 1.5 and Gemini 2.0.
Examples#Here's how to create and use a Gemini chat model:
const model = new GeminiChatModel({
  // Provide API key directly or use environment variable GOOGLE_API_KEY
  apiKey: "your-api-key", // Optional if set in env variables
  // Specify Gemini model version (defaults to 'gemini-1.5-pro' if not specified)
  model: "gemini-1.5-flash",
  modelOptions: {
    temperature: 0.7,
  },
});

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

console.log(result);
/* Output:
{
  text: "Hello from Gemini! I'm Google's helpful AI assistant. How can I assist you today?",
  model: "gemini-1.5-flash"
}
*/

Here's an example with streaming response:
const model = new GeminiChatModel({
  apiKey: "your-api-key",
  model: "gemini-1.5-flash",
});

const stream = await model.invoke(
  {
    messages: [{ role: "user", content: "Hi there, 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 from Gemini! I'm Google's helpful AI assistant. How can I assist you today?"
console.log(json); // { model: "gemini-1.5-flash" }

Extends#OpenAIChatModel
Indexable#[key: symbol]: () => string | () => Promise<void>
Constructors#Constructor#new GeminiChatModel(options?): GeminiChatModel
Parameters#Parameter
Type
options?
OpenAIChatModelOptions
Returns#GeminiChatModel
Overrides#OpenAIChatModel.constructor
Properties#apiKeyEnvName#protected apiKeyEnvName: string = "GEMINI_API_KEY"
Overrides#OpenAIChatModel.apiKeyEnvName
supportsEndWithSystemMessage#protected supportsEndWithSystemMessage: boolean = false
Overrides#OpenAIChatModel.supportsEndWithSystemMessage
supportsToolsUseWithJsonSchema#protected supportsToolsUseWithJsonSchema: boolean = false
Overrides#OpenAIChatModel.supportsToolsUseWithJsonSchema
supportsParallelToolCalls#protected supportsParallelToolCalls: boolean = false
Overrides#OpenAIChatModel.supportsParallelToolCalls
supportsToolStreaming#protected supportsToolStreaming: boolean = false
Overrides#OpenAIChatModel.supportsToolStreaming
Getting Started

How to guides

Concepts

AIGNE CLI

API Reference

Contributing

@aigne/gemini

Introduction#

Features#

Installation#

Using npm#

Using yarn#

Using pnpm#

Basic Usage#

Streaming Responses#

License#

Classes#

GeminiChatModel#

Examples#

Extends#

Indexable#

Constructors#

Constructor#

Parameters#

Returns#

Overrides#

Properties#

apiKeyEnvName#

Overrides#

supportsEndWithSystemMessage#

Overrides#

supportsToolsUseWithJsonSchema#

Overrides#

supportsParallelToolCalls#

Overrides#

supportsToolStreaming#

Overrides#

@aigne/deepseek

@aigne/ollama
