@aigne/openai

AIGNE OpenAI SDK for integrating with OpenAI's GPT models and API services within the AIGNE Framework.
Introduction#@aigne/openai provides a seamless integration between the AIGNE Framework and OpenAI's powerful language models and APIs. This package enables developers to easily leverage OpenAI's GPT models in their AIGNE applications, providing a consistent interface across the framework while taking advantage of OpenAI's advanced AI capabilities.
Features#OpenAI API Integration: Direct connection to OpenAI's API services using the official SDK
Chat Completions: Support for OpenAI's chat completions API with all available models
Function Calling: Built-in support for OpenAI's function calling capability
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/openai @aigne/core

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

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

Basic Usage#import { OpenAIChatModel } from "@aigne/openai";

const model = new OpenAIChatModel({
  // Provide API key directly or use environment variable OPENAI_API_KEY
  apiKey: "your-api-key", // Optional if set in env variables
  model: "gpt-4o", // Defaults to "gpt-4o-mini" if not specified
  modelOptions: {
    temperature: 0.7,
  },
});

const result = await model.invoke({
  messages: [{ role: "user", content: "Hello, who are you?" }],
});

console.log(result);
/* Output:
  {
    text: "Hello! How can I assist you today?",
    model: "gpt-4o",
    usage: {
      inputTokens: 10,
      outputTokens: 9
    }
  }
  */

Streaming Responses#import { OpenAIChatModel } from "@aigne/openai";

const model = new OpenAIChatModel({
  apiKey: "your-api-key",
  model: "gpt-4o",
});

const stream = await model.invoke(
  {
    messages: [{ role: "user", content: "Hello, who are you?" }],
  },
  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! How can I assist you today?"
console.log(json); // { model: "gpt-4o", usage: { inputTokens: 10, outputTokens: 9 } }

License#Elastic-2.0
Classes#OpenAIChatModel#Implementation of the ChatModel interface for OpenAI's API
This model provides access to OpenAI's capabilities including:
Text generation
Tool use with parallel tool calls
JSON structured output
Image understanding
Default model: 'gpt-4o-mini'
Examples#Here's how to create and use an OpenAI chat model:
const model = new OpenAIChatModel({
  // Provide API key directly or use environment variable OPENAI_API_KEY
  apiKey: "your-api-key", // Optional if set in env variables
  model: "gpt-4o", // Defaults to "gpt-4o-mini" if not specified
  modelOptions: {
    temperature: 0.7,
  },
});

const result = await model.invoke({
  messages: [{ role: "user", content: "Hello, who are you?" }],
});

console.log(result);
/* Output:
{
  text: "Hello! How can I assist you today?",
  model: "gpt-4o",
  usage: {
    inputTokens: 10,
    outputTokens: 9
  }
}
*/

Here's an example with streaming response:
const model = new OpenAIChatModel({
  apiKey: "your-api-key",
  model: "gpt-4o",
});

const stream = await model.invoke(
  {
    messages: [{ role: "user", content: "Hello, who are you?" }],
  },
  { 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! How can I assist you today?"
console.log(json); // { model: "gpt-4o", usage: { inputTokens: 10, outputTokens: 9 } }

Extends#ChatModel
Indexable#[key: symbol]: () => string | () => Promise<void>
Constructors#Constructor#new OpenAIChatModel(options?): OpenAIChatModel
Parameters#Parameter
Type
options?
OpenAIChatModelOptions
Returns#OpenAIChatModel
Overrides#ChatModel.constructor
Properties#options?#optional options: OpenAIChatModelOptions
apiKeyEnvName#protected apiKeyEnvName: string = "OPENAI_API_KEY"
apiKeyDefault#protected apiKeyDefault: undefined | string
supportsNativeStructuredOutputs#protected supportsNativeStructuredOutputs: boolean = true
supportsEndWithSystemMessage#protected supportsEndWithSystemMessage: boolean = true
supportsToolsUseWithJsonSchema#protected supportsToolsUseWithJsonSchema: boolean = true
supportsParallelToolCalls#protected supportsParallelToolCalls: boolean = true
Indicates whether the model supports parallel tool calls
Defaults to true, subclasses can override this property based on specific model capabilities
Overrides#ChatModel.supportsParallelToolCalls
supportsToolsEmptyParameters#protected supportsToolsEmptyParameters: boolean = true
supportsToolStreaming#protected supportsToolStreaming: boolean = true
supportsTemperature#protected supportsTemperature: boolean = true
Accessors#client#Get Signature#get client(): OpenAI
Returns#OpenAI
modelOptions#Get Signature#get modelOptions(): undefined | ChatModelOptions
Returns#undefined | ChatModelOptions
Methods#process()#process(input): PromiseOrValue<`AgentProcessResult`<ChatModelOutput>>
Process the input and generate a response
Parameters#Parameter
Type
Description
input
ChatModelInput
The input to process
Returns#PromiseOrValue<`AgentProcessResult`<ChatModelOutput>>
The generated response
Overrides#ChatModel.process
Interfaces#OpenAIChatModelCapabilities#Properties#Property
Type
supportsNativeStructuredOutputs
boolean
supportsEndWithSystemMessage
boolean
supportsToolsUseWithJsonSchema
boolean
supportsParallelToolCalls
boolean
supportsToolsEmptyParameters
boolean
supportsToolStreaming
boolean
supportsTemperature
boolean

OpenAIChatModelOptions#Configuration options for OpenAI Chat Model
Properties#Property
Type
Description
apiKey?
string
API key for OpenAI API If not provided, will look for OPENAI_API_KEY in environment variables
baseURL?
string
Base URL for OpenAI API Useful for proxies or alternate endpoints
model?
string
OpenAI model to use Defaults to 'gpt-4o-mini'
modelOptions?
ChatModelOptions
Additional model options to control behavior

Property	Type
`supportsNativeStructuredOutputs`	`boolean`
`supportsEndWithSystemMessage`	`boolean`
`supportsToolsUseWithJsonSchema`	`boolean`
`supportsParallelToolCalls`	`boolean`
`supportsToolsEmptyParameters`	`boolean`
`supportsToolStreaming`	`boolean`
`supportsTemperature`	`boolean`

Property	Type	Description
`apiKey?`	`string`	API key for OpenAI API If not provided, will look for OPENAI_API_KEY in environment variables
`baseURL?`	`string`	Base URL for OpenAI API Useful for proxies or alternate endpoints
`model?`	`string`	OpenAI model to use Defaults to 'gpt-4o-mini'
`modelOptions?`	`ChatModelOptions`	Additional model options to control behavior

Getting Started

How to guides

Concepts

AIGNE CLI

API Reference

Contributing

@aigne/openai

Introduction#

Features#

Installation#

Using npm#

Using yarn#

Using pnpm#

Basic Usage#

Streaming Responses#

License#

Classes#

OpenAIChatModel#

Examples#

Extends#

Indexable#

Constructors#

Constructor#

Parameters#

Returns#

Overrides#

Properties#

options?#

apiKeyEnvName#

apiKeyDefault#

supportsNativeStructuredOutputs#

supportsEndWithSystemMessage#

supportsToolsUseWithJsonSchema#

supportsParallelToolCalls#

Overrides#

supportsToolsEmptyParameters#

supportsToolStreaming#

supportsTemperature#

Accessors#

client#

Get Signature#

Returns#

modelOptions#

Get Signature#

Returns#

Methods#

process()#

Parameters#

Returns#

Overrides#

Interfaces#

OpenAIChatModelCapabilities#

Properties#

OpenAIChatModelOptions#

Properties#

@aigne/open-router

@aigne/platform-helpers