@generalcompute/sdk

OpenAI-compatible Node.js SDK for the GeneralCompute API. A drop-in replacement for OpenAI's SDK with the same API surface.

Installation

``bash
npm install @generalcompute/sdk
`

Quick Start

`typescript
import GeneralCompute from "@generalcompute/sdk";

const client = new GeneralCompute({
apiKey: process.env.GENERALCOMPUTE_API_KEY,
});

const completion = await client.chat.completions.create({
model: "llama3.1-8b",
messages: [{ role: "user", content: "Hello!" }],
});

console.log(completion.choices[0].message.content);
`

API Key Setup

You can provide your API key in two ways:

1. Environment variable (recommended):

`bash
export GENERALCOMPUTE_API_KEY=gc_your_api_key_here
`

2. Constructor option:

`typescript
const client = new GeneralCompute({
apiKey: "gc_your_api_key_here",
});
`

Usage Examples

$3

`typescript
import GeneralCompute from "@generalcompute/sdk";

const client = new GeneralCompute({
apiKey: process.env.GENERALCOMPUTE_API_KEY,
});

const response = await client.chat.completions.create({
model: "llama3.1-8b",
messages: [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "What is the capital of France?" },
],
temperature: 0.7,
max_tokens: 100,
});

console.log(response.choices[0].message.content);
`

$3

`typescript
const stream = await client.chat.completions.create({
model: "llama3.1-8b",
messages: [{ role: "user", content: "Write a short poem about TypeScript" }],
stream: true,
});

for await (const chunk of stream) {
const content = chunk.choices[0]?.delta?.content;
if (content) {
process.stdout.write(content);
}
}
`

$3

`typescript
const models = await client.models.list();

console.log("Available models:");
models.data.forEach((model) => {
console.log(- ${model.id} (owned by ${model.owned_by}));
});
`

$3

`typescript
import GeneralCompute, { AuthenticationError, RateLimitError } from "@generalcompute/sdk";

const client = new GeneralCompute({
apiKey: process.env.GENERALCOMPUTE_API_KEY,
});

try {
const response = await client.chat.completions.create({
model: "llama3.1-8b",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);
} catch (error) {
if (error instanceof AuthenticationError) {
console.error("Invalid API key");
} else if (error instanceof RateLimitError) {
console.error("Rate limit exceeded. Please try again later.");
} else {
console.error("An error occurred:", error);
}
}
`

Migration from OpenAI

Switching from OpenAI's SDK to GeneralCompute is simple:

$3

`typescript
import OpenAI from "openai";

const client = new OpenAI({
apiKey: process.env.OPENAI_API_KEY,
});

const completion = await client.chat.completions.create({
model: "gpt-4",
messages: [{ role: "user", content: "Hello!" }],
});
`

$3

`typescript
import GeneralCompute from "@generalcompute/sdk";

const client = new GeneralCompute({
apiKey: process.env.GENERALCOMPUTE_API_KEY, // Changed
});

const completion = await client.chat.completions.create({
model: "llama3.1-70b", // Changed
messages: [{ role: "user", content: "Hello!" }],
});
`

What changed:

1. ✏️ Import: openai → @generalcompute/sdk
2. ✏️ API key: OPENAI_API_KEY → GENERALCOMPUTE_API_KEY
3. ✏️ Model name: gpt-4 → llama3.1-70b (or your chosen model)

What stayed the same:

- ✅ Method name: client.chat.completions.create()
- ✅ Parameters: messages, temperature, stream, etc.
- ✅ Response format: Same structure and types
- ✅ Error handling: Same error classes
- ✅ Streaming: Same async iteration pattern

Model Compatibility

| OpenAI Model | GeneralCompute Equivalent | Notes |
| ------------- | ------------------------- | ------------------------------------ |
| gpt-4 | llama3.1-70b | High capability, similar performance |
| gpt-3.5-turbo | llama3.1-8b | Fast, cost-effective |
| gpt-4-turbo | llama3.3-70b | Latest generation |

Discover all available models:

`typescript
const models = await client.models.list();
console.log(models.data.map((m) => m.id));
`

API Reference

$3

`typescript
interface GeneralComputeOptions {
apiKey?: string; // API key (or use GENERALCOMPUTE_API_KEY env var)
baseURL?: string; // Custom base URL (default: https://api.generalcompute.com/v1)
timeout?: number; // Request timeout in ms (default: 60000)
maxRetries?: number; // Max retry attempts (default: 2)
defaultHeaders?: Record; // Additional headers
}
`

$3

`typescript
client.chat.completions.create(params);
`

Parameters:

- model (string, required): Model ID to use
- messages (array, required): Array of chat messages
- temperature (number, optional): Sampling temperature (0-2)
- max_tokens (number, optional): Maximum tokens to generate
- stream (boolean, optional): Enable streaming responses
- top_p (number, optional): Nucleus sampling (0-1)
- stop (string | string[], optional): Stop sequences
- presence_penalty (number, optional): Presence penalty (-2 to 2)
- frequency_penalty (number, optional): Frequency penalty (-2 to 2)

Returns:

- Non-streaming: Promise
- Streaming: Promise>

$3

`typescript
client.models.list();
`

Returns: Promise

$3

All errors extend APIError:

- AuthenticationError (401): Invalid or missing API key
- RateLimitError (429): Rate limit exceeded
- BadRequestError (400): Invalid request parameters
- NotFoundError (404): Resource not found
- InternalServerError (500+): Server errors

Advanced Usage

$3

`typescript
const client = new GeneralCompute({
apiKey: "your-api-key",
baseURL: "https://custom-endpoint.example.com/v1",
});
`

$3

`typescript
const client = new GeneralCompute({
apiKey: "your-api-key",
timeout: 120000, // 2 minutes
});
`

$3

`typescript
const client = new GeneralCompute({
apiKey: "your-api-key",
defaultHeaders: {
"X-Custom-Header": "value",
},
});
`

TypeScript Support

The SDK is written in TypeScript and provides full type definitions out of the box:

`typescript
import GeneralCompute, {
ChatMessage,
ChatCompletionResponse,
ChatCompletionChunk,
} from "@generalcompute/sdk";

const messages: ChatMessage[] = [{ role: "user", content: "Hello!" }];

const response: ChatCompletionResponse = await client.chat.completions.create({
model: "llama3.1-8b",
messages,
});
``

Contributing

Contributions are welcome! Please see our GitHub repository for details.

License

MIT

Support

For support, please contact support@generalcompute.ai or visit our documentation.