Package Exports
- @agentick/openai
- @agentick/openai/dist/index.js
This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@agentick/openai) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.
Readme
@agentick/openai
Native OpenAI adapter for Agentick.
Installation
pnpm add @agentick/openaiUsage
Factory Pattern (Recommended)
import { openai } from '@agentick/openai';
import { createApp } from '@agentick/core';
const model = openai({ model: 'gpt-4o' });
// Use with createApp
const app = createApp(MyAgent, { model });
const session = await app.session();
await session.run({ messages: [{ role: 'user', content: [{ type: 'text', text: 'Hello!' }] }] });
// Or use as JSX component
function MyAgent() {
return (
<model temperature={0.9}>
<System>You are helpful.</System>
<Timeline />
</model>
);
}
// Or call directly
const result = await model.generate({
messages: [{ role: 'user', content: 'Hello!' }],
});JSX Component Pattern
import { OpenAIModel } from '@agentick/openai';
function MyAgent() {
return (
<OpenAIModel
model="gpt-4o"
temperature={0.7}
maxTokens={4096}
>
<System>You are helpful.</System>
<Timeline />
</OpenAIModel>
);
}Azure OpenAI
const model = openai({
apiKey: process.env.AZURE_OPENAI_KEY,
baseURL: 'https://your-resource.openai.azure.com',
model: 'gpt-4o',
});Configuration
| Option | Type | Description |
|---|---|---|
model |
string |
Model name (e.g., gpt-4o) |
apiKey |
string? |
OpenAI API key (env: OPENAI_API_KEY) |
baseURL |
string? |
Custom API endpoint |
organization |
string? |
OpenAI organization ID |
temperature |
number? |
Sampling temperature (0-2) |
maxTokens |
number? |
Maximum tokens to generate |
Exports
openai(config)- Factory function returningModelClasscreateOpenAIModel(config)- Same asopenai()OpenAIModel- JSX component for declarative usage