feat(provider): add AI Badgr OpenAI-compatible provider

cookbook/providers/aibadgr.ipynb

@@ -0,0 +1,177 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Portkey + AI Badgr\n",
+        "\n",
+        "[Portkey](https://app.portkey.ai/) is the Control Panel for AI apps. With its popular AI Gateway and Observability Suite, hundreds of teams ship reliable, cost-efficient, and fast apps."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Use Budget-Friendly AI Badgr API with OpenAI Compatibility using Portkey!\n",
+        "\n",
+        "AI Badgr is a budget/utility OpenAI-compatible provider that offers tier-based model access:\n",
+        "- **basic**: Budget-tier models for simple tasks\n",
+        "- **normal**: Standard-tier models for general use\n",
+        "- **premium**: High-quality models for complex tasks\n",
+        "\n",
+        "Since Portkey is fully compatible with the OpenAI signature, you can connect to the Portkey AI Gateway through the OpenAI Client.\n",
+        "\n",
+        "- Set the `base_url` as `PORTKEY_GATEWAY_URL`\n",
+        "- Add `default_headers` to consume the headers needed by Portkey using the `createHeaders` helper method."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You will need Portkey and AI Badgr API keys to run this notebook.\n",
+        "\n",
+        "- Sign up for [Portkey here](https://app.portkey.ai/signup) and generate your API key.\n",
+        "- Get your AI Badgr API key from [AI Badgr](https://aibadgr.com)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "!pip install -qU portkey-ai openai"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## With OpenAI Client"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from openai import OpenAI\n",
+        "from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders\n",
+        "\n",
+        "client = OpenAI(\n",
+        "    base_url=PORTKEY_GATEWAY_URL,\n",
+        "    default_headers=createHeaders(\n",
+        "        provider=\"aibadgr\",\n",
+        "        api_key=\"YOUR_AIBADGR_API_KEY\"\n",
+        "    )\n",
+        ")\n",
+        "\n",
+        "chat_completion = client.chat.completions.create(\n",
+        "    messages=[{\"role\": \"user\", \"content\": \"What is the meaning of life?\"}],\n",
+        "    model=\"premium\"  # Use tier names: basic, normal, or premium\n",
+        ")\n",
+        "\n",
+        "print(chat_completion.choices[0].message.content)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## With Portkey Client"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from portkey_ai import Portkey\n",
+        "\n",
+        "portkey = Portkey(\n",
+        "    api_key=\"YOUR_PORTKEY_API_KEY\",\n",
+        "    provider=\"aibadgr\",\n",
+        "    Authorization=\"YOUR_AIBADGR_API_KEY\"\n",
+        ")\n",
+        "\n",
+        "completion = portkey.chat.completions.create(\n",
+        "    messages=[{\"role\": \"user\", \"content\": \"Explain quantum computing in simple terms\"}],\n",
+        "    model=\"premium\"\n",
+        ")\n",
+        "\n",
+        "print(completion.choices[0].message.content)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Streaming Responses"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "stream = portkey.chat.completions.create(\n",
+        "    messages=[{\"role\": \"user\", \"content\": \"Write a short poem about AI\"}],\n",
+        "    model=\"premium\",\n",
+        "    stream=True\n",
+        ")\n",
+        "\n",
+        "for chunk in stream:\n",
+        "    if chunk.choices[0].delta.content:\n",
+        "        print(chunk.choices[0].delta.content, end=\"\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Model Tiers\n",
+        "\n",
+        "AI Badgr provides tier-based model access optimized for different use cases:\n",
+        "\n",
+        "- **basic**: Budget-tier models optimized for cost and speed\n",
+        "- **normal**: Standard-tier models balancing performance and cost\n",
+        "- **premium**: High-quality models for complex reasoning and tasks\n",
+        "\n",
+        "OpenAI model names are also accepted and automatically mapped to the appropriate tier."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Observability with Portkey\n",
+        "\n",
+        "By routing requests through Portkey you can track metrics like:\n",
+        "- Token usage and costs\n",
+        "- Request latency\n",
+        "- Success/error rates\n",
+        "\n",
+        "View all your analytics at [Portkey Dashboard](https://app.portkey.ai/)."
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

src/globals.ts

@@ -110,6 +110,7 @@ export const NEXTBIT: string = 'nextbit';
 export const MODAL: string = 'modal';
 export const Z_AI: string = 'z-ai';
 export const IO_INTELLIGENCE: string = 'iointelligence';
+export const AIBADGR: string = 'aibadgr';
 
 export const VALID_PROVIDERS = [
   ANTHROPIC,
@@ -183,6 +184,7 @@ export const VALID_PROVIDERS = [
   MODAL,
   Z_AI,
   IO_INTELLIGENCE,
+  AIBADGR,
 ];
 
 export const CONTENT_TYPES = {

src/providers/aibadgr/api.ts

@@ -0,0 +1,18 @@
+import { ProviderAPIConfig } from '../types';
+
+const AIBadgrAPIConfig: ProviderAPIConfig = {
+  getBaseURL: () => 'https://aibadgr.com/api/v1',
+  headers: ({ providerOptions }) => {
+    return { Authorization: `Bearer ${providerOptions.apiKey}` };
+  },
+  getEndpoint: ({ fn }) => {
+    switch (fn) {
+      case 'chatComplete':
+        return '/chat/completions';
+      default:
+        return '';
+    }
+  },
+};
+
+export default AIBadgrAPIConfig;

src/providers/aibadgr/chatComplete.ts

@@ -0,0 +1,61 @@
+import { AIBADGR } from '../../globals';
+
+interface AIBadgrStreamChunk {
+  id: string;
+  object: string;
+  created: number;
+  model: string;
+  choices: {
+    index: number;
+    delta: {
+      role?: string;
+      content?: string;
+      tool_calls?: object[];
+    };
+    finish_reason: string | null;
+  }[];
+  usage?: {
+    prompt_tokens: number;
+    completion_tokens: number;
+    total_tokens: number;
+  };
+}
+
+export const AIBadgrChatCompleteStreamChunkTransform = (
+  responseChunk: string
+) => {
+  let chunk = responseChunk.trim();
+  chunk = chunk.replace(/^data: /, '');
+  chunk = chunk.trim();
+
+  if (chunk === '[DONE]') {
+    return `data: ${chunk}\n\n`;
+  }
+
+  try {
+    const parsedChunk: AIBadgrStreamChunk = JSON.parse(chunk);
+    return (
+      `data: ${JSON.stringify({
+        id: parsedChunk.id,
+        object: parsedChunk.object,
+        created: parsedChunk.created,
+        model: parsedChunk.model,
+        provider: AIBADGR,
+        choices: parsedChunk.choices.map((choice) => ({
+          index: choice.index,
+          delta: choice.delta,
+          finish_reason: choice.finish_reason,
+        })),
+        usage: parsedChunk.usage,
+      })}` + '\n\n'
+    );
+  } catch (error) {
+    console.error(
+      'Error parsing AI Badgr stream chunk:',
+      error,
+      'Chunk:',
+      chunk
+    );
+    return `data: ${chunk}\n\n`;
+  }
+};

src/providers/aibadgr/index.ts

@@ -0,0 +1,18 @@
+import { ProviderConfigs } from '../types';
+import AIBadgrAPIConfig from './api';
+import { AIBadgrChatCompleteStreamChunkTransform } from './chatComplete';
+import { chatCompleteParams, responseTransformers } from '../open-ai-base';
+import { AIBADGR } from '../../globals';
+
+const AIBadgrConfig: ProviderConfigs = {
+  api: AIBadgrAPIConfig,
+  chatComplete: chatCompleteParams([]),
+  responseTransforms: {
+    ...responseTransformers(AIBADGR, {
+      chatComplete: true,
+    }),
+    'stream-chatComplete': AIBadgrChatCompleteStreamChunkTransform,
+  },
+};
+
+export default AIBadgrConfig;

src/providers/index.ts

@@ -71,6 +71,7 @@ import ZAIConfig from './z-ai';
 import MatterAIConfig from './matterai';
 import ModalConfig from './modal';
 import IOIntelligenceConfig from './iointelligence';
+import AIBadgrConfig from './aibadgr';
 
 const Providers: { [key: string]: ProviderConfigs } = {
   openai: OpenAIConfig,
@@ -142,6 +143,7 @@ const Providers: { [key: string]: ProviderConfigs } = {
   modal: ModalConfig,
   'z-ai': ZAIConfig,
   iointelligence: IOIntelligenceConfig,
+  aibadgr: AIBadgrConfig,
 };
 
 export default Providers;