@retrivora-ai/rag-engine

Retrivora AI is a plug-and-play AI engine 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 (v1.0.0)

| Category | Options | |---|---| | Vector DBs | Pinecone, pgVector (PostgreSQL), MongoDB Atlas, ChromaDB, Qdrant, Milvus, Weaviate, Redis | | LLM Providers | OpenAI, Anthropic Claude, Google Gemini, Ollama, LiteLLM, Universal REST | | Integrations | LangChain (Agentic orchestration), LlamaIndex (Semantic chunking) | | Document Ingestion | Universal support for PDF, DOCX, CSV, JSON, MD, TXT | | Architecture | Modular & Pluggable registry-based system with static health checks & validators | | RAG Patterns | Simple, Hybrid, Graph-based, and Agentic workflows |

🚀 How it Works

Retrivora AI acts as a universal bridge between your data and your users. It normalizes different AI providers and Vector databases into a single interface using a registry-based architecture.

1. Ingest: Upload or send documents to the /api/upload endpoint. They are parsed and chunked using LlamaIndex strategies if configured.
2. Retrieve: Queries are processed via the QueryProcessor to extract semantic hints and filter criteria.
3. Generate: Context is retrieved and processed through a Pipeline (or LangChainAgent) to produce grounded, streaming responses.

📦 Installation

npm install @retrivora-ai/rag-engine

🛠️ Pluggable Architecture

Starting with v1.0.0, the engine uses a modular registry for all providers. Every provider now exposes:

• Static Validators: getValidator() for deep configuration schema checks.
• Static Health Checkers: getHealthChecker() for real-time connectivity and capability validation.

This decoupling allows you to add custom providers without modifying the core engine logic.

NPM Package Usage

1. Embed the ChatWidget

import { ConfigProvider, ChatWidget } from '@retrivora-ai/rag-engine';

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

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

// src/app/api/upload/route.ts
import { createUploadHandler, getRagConfig } from '@retrivora-ai/rag-engine/server';
export const POST = createUploadHandler(getRagConfig());

3. Use Pipeline programmatically

import { Pipeline, getRagConfig } from '@retrivora-ai/rag-engine/server';

const config = getRagConfig();
const pipeline = new Pipeline(config);

// Ingest documents
await pipeline.ingest([{ docId: 'readme', content: 'Your document text here' }]);

// Ask questions
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, milvus, qdrant, weaviate | | LLM_PROVIDER | openai, anthropic, gemini, ollama | | EMBEDDING_PROVIDER | openai, ollama, google-gemini | | RAG_ARCHITECTURE | simple, hybrid, graph, agentic |

License

MIT