unified-ai-router 3.1.1 → 3.1.4

package/.env.example

@@ -9,4 +9,5 @@ VERCEL_AI_GATEWAY_API_KEY=API_KEY
 COHERE_API_KEY=API_KEY
 CEREBRAS_API_KEY=API_KEY
 LLM7_API_KEY=API_KEY
-SEARX_URL=https://searx.perennialte.ch
+SEARX_URL=https://searx.perennialte.ch
+PORT=3000

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "unified-ai-router",
-  "version": "3.1.1",
+  "version": "3.1.4",
   "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",

package/readme.md

@@ -4,7 +4,6 @@ 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.
 
@@ -13,6 +12,7 @@ It supports major providers like OpenAI, Google, Grok, and more, ensuring reliab
 - [📖 Usage](#-usage)
   - [📚 Basic Library Usage](#-basic-library-usage)
   - [🔌 OpenAI-Compatible Server](#-openai-compatible-server)
+    - [Setup](#setup)
   - [🧪 Testing](#-testing)
 - [🔧 Supported Providers](#-supported-providers)
 - [🔑 API Keys](#-api-keys)
@@ -31,15 +31,14 @@ It supports major providers like OpenAI, Google, Grok, and more, ensuring reliab
 - **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
 
 ```bash
 npm i unified-ai-router
 # OR
-git clone https://github.com/mlibre/AIRouter
-cd AIRouter
+git clone https://github.com/mlibre/Unified-AI-Router
+cd Unified-AI-Router
 npm i
 ```
 
@@ -87,16 +86,14 @@ console.log(response);
 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.  
 The server uses the provider configurations defined in [provider.js](provider.js) file, and requires API keys set in a `.env` file.
 
-#### Setup
+1. Configure your providers in `provider.js`. Add new provider or modify existing ones with the appropriate `name`, `apiKey` (referencing the corresponding env variable), `model`, and `apiUrl` for the providers you want to use.
 
-1. Copy the example environment file:
+2. Copy the example environment file:
 
    ```bash
    cp .env.example .env
    ```
 
-2. Configure your providers in `provider.js`. Add new provider or modify existing ones with the appropriate `name`, `apiKey` (referencing the corresponding env variable), `model`, and `apiUrl` for the providers you want to use.
-
 3. Edit `.env` and add your API keys for the desired providers (see [🔑 API Keys](#-api-keys) for sources).
 
 To start the server locally, run:
@@ -105,7 +102,13 @@ To start the server locally, run:
 npm start
 ```
 
-The server listens at `http://localhost:3000/v1/chat/completions` and supports standard OpenAI endpoints like `/v1/chat/completions`.
+The server listens at `http://localhost:3000/` and supports the following OpenAI-compatible endpoints:
+
+- `POST /v1/chat/completions` - Chat completions (streaming and non-streaming)
+- `POST /chat/completions` - Chat completions (streaming and non-streaming)
+- `GET /v1/models` - List available models
+- `GET /models` - List available models
+- `GET /health` - Health check
 
 ### 🧪 Testing
 
@@ -137,6 +140,7 @@ node tests/tools.js
 - Vercel
 - Cerebras
 - LLM7
+- Any Other OpenAI Compatible Server
 
 ## 🔑 API Keys
 
@@ -152,7 +156,6 @@ Get your API keys from the following providers:
 - **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)
 
@@ -214,19 +217,14 @@ 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`
+**Configure Mini 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` → `Configure Mini App`
+- Set the Mini App URL to: `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.
+Once configured, users can access the Mini App by sending `/start` or `/app` to your bot.
 
 An example of a deployed bot is accessible on Telegram: [https://t.me/freePulseAIbot](https://t.me/freePulseAIbot)