Quick Start

Install SDK

Python

pip install omniedge

JavaScript

npm install omniedge

Initialize Client

Python

from omniedge import OmniEdge

# Initialize with API key
client = OmniEdge(api_key="sk-your-api-key-here")

JavaScript

import { OmniEdge } from 'omniedge';

// Initialize with API key
const client = new OmniEdge({
  apiKey: 'sk-your-api-key-here'
});

Make First Request

Python Example

from omniedge import OmniEdge

with OmniEdge(api_key="sk-your-api-key-here") as client:
    # Make chat request
    response = client.chat.create(
        model="openai/gpt-4o",
        messages=[
            {"role": "user", "content": "Hello, world!"}
        ]
    )

    # Print response
    print(response.choices[0].message.content)

JavaScript Example

import { OmniEdge } from 'omniedge';

const client = new OmniEdge({
  apiKey: 'sk-your-api-key-here'
});

async function main() {
    // Make chat request
    const response = await client.chat.create({
        model: "openai/gpt-4o",
        messages: [
            { role: "user", content: "Hello, world!" }
        ]
    });

    // Print response
    console.log(response.choices[0].message.content);
}

main();

Streaming Response

Python Streaming Example

from omniedge import OmniEdge

with OmniEdge(api_key="sk-your-api-key-here") as client:
    # Make streaming request
    stream = client.chat.create(
        model="openai/gpt-4o",
        messages=[
            {"role": "user", "content": "Tell me a story"}
        ],
        stream=True
    )

    # Process response chunk by chunk
    for chunk in stream:
        if chunk.choices:
            content = chunk.choices[0].delta.content
            if content:
                print(content, end='', flush=True)

JavaScript Streaming Example

import { OmniEdge } from 'omniedge';

const client = new OmniEdge({
  apiKey: 'sk-your-api-key-here'
});

async function main() {
    // Make streaming request
    const stream = await client.chat.create({
        model: "openai/gpt-4o",
        messages: [
            { role: "user", content: "Tell me a story" }
        ],
        stream: true
    });

    // Process response chunk by chunk
    for await (const chunk of stream) {
        if (chunk.choices) {
            const content = chunk.choices[0].delta.content;
            if (content) {
                process.stdout.write(content);
            }
        }
    }
}

main();

Error Handling

Python Error Handling

from omniedge import OmniEdge
from omniedge.exceptions import APIError, AuthenticationError

try:
    with OmniEdge(api_key="sk-your-api-key-here") as client:
        response = client.chat.create(
            model="openai/gpt-4o",
            messages=[{"role": "user", "content": "Hello"}]
        )
        print(response.choices[0].message.content)

except AuthenticationError:
    print("Authentication failed, please check API key")
except APIError as e:
    print(f"API Error: {e.message}")
except Exception as e:
    print(f"Unknown error: {e}")

JavaScript Error Handling

import { OmniEdge } from 'omniedge';

const client = new OmniEdge({
  apiKey: 'sk-your-api-key-here'
});

async function main() {
    try {
        const response = await client.chat.create({
            model: "openai/gpt-4o",
            messages: [{ role: "user", content: "Hello" }]
        });
        console.log(response.choices[0].message.content);

    } catch (error) {
        if (error.status === 401) {
            console.log("Authentication failed, please check API key");
        } else if (error.status >= 400 && error.status < 500) {
            console.log(`Client error: ${error.message}`);
        } else if (error.status >= 500) {
            console.log(`Server error: ${error.message}`);
        } else {
            console.log(`Unknown error: ${error.message}`);
        }
    }
}

main();

Best Practices

1. Use environment variables to store API keys
2. Enable streaming responses for long text
3. Implement retry mechanisms for temporary errors
4. Set reasonable request frequency to avoid rate limiting
5. Use async methods to improve performance

Next Steps

• View Chat API Documentation
• View Model API Documentation
• View More Example Code