Setting Up

Generating an API Key

To use the HareProxy API, you need to have an Discord account and generate an API key. Follow these steps:

Go to the Discord Channel Chat (I.E 🤖・commands).
Use the discord command /key to generate a new key.
If you already have a existing key, Enter /key to view it.

Bot is not responsive? Ping @yongdong for help.

Configure Base URL

Depending on your environment and application, you will set the base URL differently. Below is the main API endpoint that you can use to access the services:

https://api.hareproxy.io.vn/proxy

Unified Endpoint

https://unified.hareproxy.io.vn/v1

Available Endpoints

The API supports multiple endpoints for various AI services:

OpenAI: https://api.hareproxy.io.vn/proxy/openai
OpenAI Image: https://api.hareproxy.io.vn/proxy/openai-image
Google AI: https://api.hareproxy.io.vn/proxy/google-ai
Mistral AI: https://api.hareproxy.io.vn/proxy/mistral-ai
Azure: https://api.hareproxy.io.vn/proxy/azure/openai
Anthropic Claude: https://api.hareproxy.io.vn/proxy/anthropic

Making Your First API Call

Based on your environment, you will call our API differently. Below are two common ways to call our API using two popular programming languages: Python and NodeJS

Example in Python

Here's an example of how to use the OpenAI library in Python for chat completion with our API: Remember to replace "YOUR_API_KEY" with the actual API key you obtained using the /key command in both examples.

import openai

openai.api_key = "YOUR_API_KEY"
openai.api_base = "https://api.hareproxy.io.vn/proxy/<provider>/<llm-service>/v1" # Example: https://api.hareproxy.io.vn/proxy/azure/openai/v1

response = openai.ChatCompletion.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

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

Example in Node.js

Here's an example of how to use the OpenAI library in Node.js for chat completion with our API:

const { Configuration, OpenAIApi } = require("openai");

const configuration = new Configuration({
  apiKey: "YOUR_API_KEY",
  basePath: "https://api.hareproxy.io.vn/proxy/<provider>/<llm-service>/v1",
});

const openai = new OpenAIApi(configuration);

async function chatCompletion() {
  try {
    const response = await openai.createChatCompletion({
      model: "gpt-4o",
      messages: [
        { role: "system", content: "You are a helpful assistant." },
        { role: "user", content: "Hello, how are you?" },
      ],
    });

    console.log(response.data.choices[0].message.content);
  } catch (error) {
    console.error("Error:", error);
  }
}

chatCompletion();

Remember to replace "YOUR_API_KEY" with the actual API key you obtained using the /key command in both examples.

To run the Node.js example, make sure you have the OpenAI package installed:

npm install openai

Previous🤖Introduction NextAvailable Models

Last updated 9 days ago

import openai openai.api_key = "YOUR_API_KEY" openai.api_base = "https://api.hareproxy.io.vn/proxy/<provider>/<llm-service>/v1" # Example: https://api.hareproxy.io.vn/proxy/azure/openai/v1 response = openai.ChatCompletion.create( model="gpt-4o", messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello, how are you?"} ] ) print(response.choices[0].message.content)

const { Configuration, OpenAIApi } = require("openai"); const configuration = new Configuration({ apiKey: "YOUR_API_KEY", basePath: "https://api.hareproxy.io.vn/proxy/<provider>/<llm-service>/v1", }); const openai = new OpenAIApi(configuration); async function chatCompletion() { try { const response = await openai.createChatCompletion({ model: "gpt-4o", messages: [ { role: "system", content: "You are a helpful assistant." }, { role: "user", content: "Hello, how are you?" }, ], }); console.log(response.data.choices[0].message.content); } catch (error) { console.error("Error:", error); } } chatCompletion();