unified-ai-router 3.0.0 → 3.0.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "unified-ai-router",
-  "version": "3.0.0",
+  "version": "3.0.1",
   "description": "A unified interface for multiple LLM providers with automatic fallback. This project includes an OpenAI-compatible server and a deployable Telegram bot with a Mini App interface. It supports major providers like OpenAI, Google, Grok, and more, ensuring reliability and flexibility for your AI applications.",
   "license": "ISC",
   "author": "mlibre",
@@ -55,4 +55,4 @@
   "devDependencies": {
     "vercel": "^45.0.9"
   }
-}
+}

package/readme.md

@@ -1,31 +1,37 @@
 # Unified AI Router
 
-A unified interface for multiple LLM providers with automatic fallback. This project includes an OpenAI-compatible server and a deployable Telegram bot with a Mini App interface. It supports major providers like OpenAI, Google, Grok, and more, ensuring reliability and flexibility for your AI applications.
-
-* [🚀 Features](#-features)
-* [🛠️ Installation](#️-installation)
-* [📖 Usage](#-usage)
-  * [📚 Basic Library Usage](#-basic-library-usage)
-  * [🤖 OpenAI-Compatible Server](#-openai-compatible-server)
-  * [🧪 Testing](#-testing)
-* [🔧 Supported Providers](#-supported-providers)
-* [🔑 API Keys](#-api-keys)
-* [🔼 Vercel Deployment (Telegram Bot)](#-vercel-deployment-telegram-bot)
-  * [📋 Prerequisites](#-prerequisites)
-  * [🚀 Deployment Steps](#-deployment-steps)
-  * [📱 Enable Telegram Mini App](#-enable-telegram-mini-app)
-* [📁 Project Structure](#-project-structure)
-* [📄 License](#-license)
+Unified AI Router is a comprehensive toolkit for AI applications, featuring:
+
+- A unified interface for multiple LLM providers with automatic fallback (the core router library)
+- An OpenAI-compatible server for seamless API integration
+- A deployable Telegram bot with Mini App interface
+
+It supports major providers like OpenAI, Google, Grok, and more, ensuring reliability and flexibility.
+
+- [🚀 Features](#-features)
+- [🛠️ Installation](#️-installation)
+- [📖 Usage](#-usage)
+  - [📚 Basic Library Usage](#-basic-library-usage)
+  - [🔌 OpenAI-Compatible Server](#-openai-compatible-server)
+  - [🧪 Testing](#-testing)
+- [🔧 Supported Providers](#-supported-providers)
+- [🔑 API Keys](#-api-keys)
+- [🔼 Vercel Deployment (Telegram Bot)](#-vercel-deployment-telegram-bot)
+  - [📋 Prerequisites](#-prerequisites)
+  - [🚀 Deployment Steps](#-deployment-steps)
+  - [📱 Enable Telegram Mini App](#-enable-telegram-mini-app)
+- [📁 Project Structure](#-project-structure)
+- [📄 License](#-license)
 
 ## 🚀 Features
 
-* **Multi-Provider Support**: Works with OpenAI, Google, Grok, OpenRouter, Z.ai, Qroq, Cohere, Vercel, Cerebras, and LLM7
-* **Automatic Fallback**: If one provider fails, automatically tries the next
-* **Simple API**: Easy to use interface for all supported providers
-* **OpenAI-Compatible Server**: Drop-in replacement for OpenAI API
-* **Streaming and Non-Streaming**: Supports both streaming and non-streaming responses
-* **Tool Support**: Use tools with your LLM calls
-* **Telegram Bot**: Deployable as a Telegram bot with a Mini App interface
+- **Multi-Provider Support**: Works with OpenAI, Google, Grok, OpenRouter, Z.ai, Qroq, Cohere, Vercel, Cerebras, and LLM7
+- **Automatic Fallback**: If one provider fails, automatically tries the next
+- **Simple API**: Easy-to-use interface for all supported providers
+- **OpenAI-Compatible Server**: Drop-in replacement for the OpenAI API, enabling easy integration with existing tools and clients
+- **Streaming and Non-Streaming Support**: Handles both streaming and non-streaming responses
+- **Tool Calling**: Full support for tools in LLM interactions
+- **Telegram Bot Integration**: Deployable as a Telegram bot with an interactive Mini App interface
 
 ## 🛠️ Installation
 
@@ -76,17 +82,17 @@ const response = await llm.chatCompletion(messages, {
 console.log(response);
 ```
 
-### 🤖 OpenAI-Compatible Server
+### 🔌 OpenAI-Compatible Server
 
-The project includes an OpenAI-compatible server that can be used as a drop-in replacement for the OpenAI API.
+The OpenAI-compatible server provides a drop-in replacement for the OpenAI API. It routes requests through the unified router with fallback logic, ensuring high availability.
 
-To start the server, run:
+To start the server locally, run:
 
 ```bash
 npm start
 ```
 
-The server will be available at `http://localhost:3000/v1/chat/completions`.
+The server listens at `http://localhost:3000/v1/chat/completions` and supports standard OpenAI endpoints like `/v1/chat/completions`.
 
 ### 🧪 Testing
 
@@ -108,32 +114,32 @@ node tests/tools.js
 
 ## 🔧 Supported Providers
 
-* OpenAI
-* Google Gemini
-* Grok
-* OpenRouter
-* Z.ai
-* Qroq
-* Cohere
-* Vercel
-* Cerebras
-* LLM7
+- OpenAI
+- Google Gemini
+- Grok
+- OpenRouter
+- Z.ai
+- Qroq
+- Cohere
+- Vercel
+- Cerebras
+- LLM7
 
 ## 🔑 API Keys
 
 Get your API keys from the following providers:
 
-* **OpenAI**: [platform.openai.com/api-keys](https://platform.openai.com/api-keys)
-* **Google Gemini**: [aistudio.google.com/app/apikey](https://aistudio.google.com/app/apikey)
-* **Grok**: [console.x.ai](https://console.x.ai/)
-* **OpenRouter**: [openrouter.ai/keys](https://openrouter.ai/keys)
-* **Z.ai**: [api.z.ai](https://api.z.ai)
-* **Qroq**: [console.groq.com/keys](https://console.groq.com/keys)
-* **Cohere**: [dashboard.cohere.com/api-keys](https://dashboard.cohere.com/api-keys)
-* **Vercel**: [vercel.com/docs/ai/ai-gateway](https://vercel.com/masoud-ghorbanzadehs-projects/~/ai/api-keys)
-* **Cerebras**: [cloud.cerebras.ai](https://cloud.cerebras.ai)
-* **LLM7**: [token.llm7.io](https://token.llm7.io/)
-  * Seems like it does not support tool calling
+- **OpenAI**: [platform.openai.com/api-keys](https://platform.openai.com/api-keys)
+- **Google Gemini**: [aistudio.google.com/app/apikey](https://aistudio.google.com/app/apikey)
+- **Grok**: [console.x.ai](https://console.x.ai/)
+- **OpenRouter**: [openrouter.ai/keys](https://openrouter.ai/keys)
+- **Z.ai**: [api.z.ai](https://api.z.ai)
+- **Qroq**: [console.groq.com/keys](https://console.groq.com/keys)
+- **Cohere**: [dashboard.cohere.com/api-keys](https://dashboard.cohere.com/api-keys)
+- **Vercel AI Gateway**: [vercel.com/docs/ai/ai-gateway](https://vercel.com/docs/ai-gateway)
+- **Cerebras**: [cloud.cerebras.ai](https://cloud.cerebras.ai)
+- **LLM7**: [token.llm7.io](https://token.llm7.io/)
+  - Seems like it does not support tool calling
 
 ## 🔼 Vercel Deployment (Telegram Bot)
 
@@ -141,9 +147,9 @@ This section describes how to deploy the AIRouter as a Telegram bot using Vercel
 
 ### 📋 Prerequisites
 
-* A Telegram Bot Token (@BotFather)
-* API keys for various AI providers
-* Vercel account
+- A Telegram Bot Token (@BotFather)
+- API keys for various AI providers
+- Vercel account
 
 ### 🚀 Deployment Steps
 
@@ -196,16 +202,16 @@ curl "https://ai-router-flame.vercel.app/api?register_webhook=true"
 After deploying the bot, you need to configure the Telegram Mini App and menu button:
 
 1. **Configure Mini App:**
-   * Go to [@BotFather](https://t.me/botfather)
-   * Send `/mybots` and select your bot
-   * Go to `Bot Settings` → `Configure Mini App`
-   * Set the Mini App URL to: `https://ai-router-flame.vercel.app`
+   - Go to [@BotFather](https://t.me/botfather)
+   - Send `/mybots` and select your bot
+   - Go to `Bot Settings` → `Configure Mini App`
+   - Set the Mini App URL to: `https://ai-router-flame.vercel.app`
 
 2. **Configure Menu Button:**
-   * Go to [@BotFather](https://t.me/botfather)
-   * Send `/mybots` and select your bot
-   * Go to `Bot Settings` → `Menu Button`
-   * Ensure the URL shown is: `https://ai-router-flame.vercel.app`
+   - Go to [@BotFather](https://t.me/botfather)
+   - Send `/mybots` and select your bot
+   - Go to `Bot Settings` → `Menu Button`
+   - Ensure the URL shown is: `https://ai-router-flame.vercel.app`
 
 Once configured, users can access the Mini App by sending `/start` or `/app` to your bot, or through the menu button.
 
@@ -213,17 +219,17 @@ An example of a deployed bot is accessible on Telegram: [https://t.me/freePulseA
 
 ## 📁 Project Structure
 
-* `main.js` - The core AIRouter library.
-* `provider.js` - A list of supported AI providers.
-* `openai-compatible-server/index.js` - An OpenAI-compatible server.
-* `tests/` - A suite of tests for the library and server.
-* `bruno/` - A Bruno collection for API testing.
-* `vercel-project/` - A Vercel project for deploying a Telegram bot.
-  * `api/index.js` - Main webhook handler for the Telegram bot.
-  * `api/search.js` - A search proxy for the Telegram bot.
-  * `public/` - The frontend for the Telegram Mini App.
-  * `src/config.js` - Configuration for the Telegram bot.
-  * `src/telegram.js` - Telegram client implementation.
+- `main.js` - Core AIRouter library implementing the unified interface and fallback logic
+- `provider.js` - Configuration for supported AI providers
+- `openai-compatible-server/index.js` - OpenAI-compatible API server
+- `tests/` - Comprehensive tests for the library, server, and tools
+- `bruno/` - Bruno API collection for testing endpoints
+- `vercel-project/` - Ready-to-deploy Vercel setup for the Telegram bot
+  - `api/index.js` - Telegram webhook handler
+  - `api/search.js` - Search proxy endpoint
+  - `public/` - Mini App frontend (HTML, CSS, JS)
+  - `src/config.js` - Bot configuration
+  - `src/telegram.js` - Telegram API integration
 
 ## 📄 License