@aigne/xai
AIGNE XAI SDK for integrating with XAI language models and API services within the AIGNE Framework.
Introduction#
@aigne/xai provides a seamless integration between the AIGNE Framework and XAI's language models and API services. This package enables developers to easily leverage XAI's models in their AIGNE applications, providing a consistent interface across the framework while taking advantage of XAI's advanced AI capabilities.
Features#
- XAI API Integration: Direct connection to XAI's API services
- Chat Completions: Support for XAI'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/xai @aigne/core
Using yarn#
yarn add @aigne/xai @aigne/core
Using pnpm#
pnpm add @aigne/xai @aigne/core
Basic Usage#
import { XAIChatModel } from "@aigne/xai";
const model = new XAIChatModel({
// Provide API key directly or use environment variable XAI_API_KEY
apiKey: "your-api-key", // Optional if set in env variables
// Specify model (defaults to 'grok-2-latest')
model: "grok-2-latest",
modelOptions: {
temperature: 0.8,
},
});
const result = await model.invoke({
messages: [{ role: "user", content: "Tell me about yourself" }],
});
console.log(result);
/* Output:
{
text: "I'm Grok, an AI assistant from X.AI. I'm here to assist with a touch of humor and wit!",
model: "grok-2-latest",
usage: {
inputTokens: 6,
outputTokens: 17
}
}
*/
Streaming Responses#
import { XAIChatModel } from "@aigne/xai";
const model = new XAIChatModel({
apiKey: "your-api-key",
model: "grok-2-latest",
});
const stream = await model.invoke(
{
messages: [{ role: "user", content: "Tell me about 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: "I'm Grok, an AI assistant from X.AI. I'm here to assist with a touch of humor and wit!"
console.log(json); // { model: "grok-2-latest", usage: { inputTokens: 6, outputTokens: 17 } }
License#
Elastic-2.0
Classes#
XAIChatModel#
Implementation of the ChatModel interface for X.AI's API (Grok)
This model uses OpenAI-compatible API format to interact with X.AI models, providing access to models like Grok.
Default model: 'grok-2-latest'
Examples#
Here's how to create and use an X.AI chat model:
const model = new XAIChatModel({
// Provide API key directly or use environment variable XAI_API_KEY
apiKey: "your-api-key", // Optional if set in env variables
// Specify model (defaults to 'grok-2-latest')
model: "grok-2-latest",
modelOptions: {
temperature: 0.8,
},
});
const result = await model.invoke({
messages: [{ role: "user", content: "Tell me about yourself" }],
});
console.log(result);
/* Output:
{
text: "I'm Grok, an AI assistant from X.AI. I'm here to assist with a touch of humor and wit!",
model: "grok-2-latest",
usage: {
inputTokens: 6,
outputTokens: 17
}
}
*/
Here's an example with streaming response:
const model = new XAIChatModel({
apiKey: "your-api-key",
model: "grok-2-latest",
});
const stream = await model.invoke(
{
messages: [{ role: "user", content: "Tell me about 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: "I'm Grok, an AI assistant from X.AI. I'm here to assist with a touch of humor and wit!"
console.log(json); // { model: "grok-2-latest", usage: { inputTokens: 6, outputTokens: 17 } }
Extends#
OpenAIChatModel
Indexable#
[key: symbol]: () => string | () => Promise<void>
Constructors#
Constructor#
new XAIChatModel(
options?):XAIChatModel
Parameters#
Parameter | Type |
|---|---|
|
|
Returns#
Overrides#
OpenAIChatModel.constructor
Properties#
apiKeyEnvName#
protectedapiKeyEnvName:string="XAI_API_KEY"
Overrides#
OpenAIChatModel.apiKeyEnvName