@abhinav1201/rag-ai-accelerator

A plug-and-play AI accelerator for RAG chat experiences that can be embedded into Next.js apps or used as a standalone demo app. Bring your own vector database, LLM, embeddings, and UI branding.

✨ Features

| Category | Options | |---|---| | Vector DBs | Pinecone, pgVector (PostgreSQL), MongoDB Atlas, ChromaDB, Qdrant, universal REST adapters | | LLM Providers | OpenAI, Anthropic Claude, Google Gemini, Ollama, LiteLLM, universal REST adapters | | Document Ingestion | Universal support for PDF, DOCX, CSV, JSON, MD, TXT | | UI | Full-page ChatWindow + floating ChatWidget, fully branded & responsive | | RAG | Configurable chunk size/overlap, top-K retrieval, score threshold, namespaced multi-tenancy |

🚀 How it Works

The AI Accelerator acts as a universal bridge between your data and your users. It normalizes different AI providers and Vector databases into a single interface.

1. Ingest: Upload or send documents to the /api/upload endpoint. They are automatically parsed, chunked, and embedded.
2. Retrieve: When a user asks a question, the system converts it to a vector and searches your configured database.
3. Generate: The retrieved context is combined with the user query and sent to your configured LLM (OpenAI, Claude, etc.) to generate a grounded response.

📦 How to Install

To integrate the AI Accelerator into your existing Next.js project, simply run:

npm install @abhinav1201/rag-ai-accelerator

Alternatively, if you want to run the standalone demo application:

git clone https://github.com/abhinav1201/ai-accelerator
cd ai-accelerator
npm install
cp .env.example .env.local
# Fill in your API keys in .env.local
npm run dev

NPM Package Usage

1. Embed the ChatWidget

Wrap your application in the ConfigProvider and add the ChatWidget.

import { ConfigProvider, ChatWidget } from '@abhinav1201/rag-ai-accelerator';

export default function Layout({ children }) {
  return (
    <ConfigProvider
      config={{
        projectId: 'my-project',
        ui: {
          title: 'Support Bot',
          primaryColor: '#6366f1',
          accentColor: '#8b5cf6',
          welcomeMessage: 'Hi! How can I help you today?',
        },
      }}
    >
      {children}
      <ChatWidget position="bottom-right" />
    </ConfigProvider>
  );
}

2. Mount the API routes

Create standard Next.js route handlers and plug in the library's factories.

// src/app/api/chat/route.ts
import { createChatHandler, getRagConfig } from '@abhinav1201/rag-ai-accelerator/server';
export const POST = createChatHandler(getRagConfig());

// src/app/api/upload/route.ts (Handles PDF, DOCX, etc.)
import { createUploadHandler, getRagConfig } from '@abhinav1201/rag-ai-accelerator/server';
export const POST = createUploadHandler(getRagConfig());

3. Use RAGPipeline programmatically

import { RAGPipeline } from '@abhinav1201/rag-ai-accelerator/server';

const pipeline = new RAGPipeline(config);
await pipeline.ingest([{ docId: 'readme', content: 'Your document text here' }]);
const { reply, sources } = await pipeline.ask('What is the refund policy?');

Configuration Reference

The library is entirely dynamic. You can switch between providers simply by updating your environment variables.

| Variable | Description | |---|---| | RAG_PROJECT_ID | Project namespace for data isolation | | VECTOR_DB_PROVIDER | pinecone, pgvector, mongodb, or universal_rest | | VECTOR_UNIVERSAL_PROFILE | pinecone-rest, mongodb-atlas, chromadb, qdrant | | LLM_PROVIDER | openai, anthropic, ollama, or universal_rest | | LLM_UNIVERSAL_PROFILE | openai-compatible, litellm, anthropic-claude, google-gemini | | EMBEDDING_PROVIDER | openai, ollama, or rest |

Architecture

User Query
   |
   v
[embed query]  <-- EmbeddingProvider (OpenAI / Ollama / Custom)
   |
   v
[vector search]  <-- IVectorDB (Pinecone / pgVector / MongoDB / Chroma / REST)
   |
   v
[build context]
   |
   v
[LLM chat]  <-- ILLMProvider (OpenAI / Anthropic / Gemini / LiteLLM)
   |
   v
ChatResponse { reply, sources[] }

License

MIT - GSPANN Technologies