PolarBear 🐻‍❄️

The Open-Source Hybrid Search Engine for SMEs

Features • Getting Started • Documentation • Contributing

PolarBear is a powerful, no-code, AI-enhanced search engine designed specifically for Small and Medium-sized Enterprises (SMEs). It democratizes access to advanced search technology, allowing business owners to create a professional search experience for their products, services, or inventory in minutes—completely free and open source.

Unlike complex enterprise solutions, PolarBear focuses on simplicity without compromising on power. It combines Keyword Search (Meilisearch) and Semantic Vector Search (FAISS) to deliver results that are both accurate and contextually relevant.

• 🔍 Hybrid Search: seamlessly blends keyword matching (BM25) with AI-powered semantic search (Embeddings) for superior result relevance.
• ⚡ No-Code Ingestion: Upload your data via CSV, Excel, or Google Sheets. No coding required.
• 🧠 AI-Ready: Built-in vectorization pipeline using state-of-the-art embedding models.
• 📊 Insights Dashboard: Track user behavior, top queries, zero-result searches, and conversion metrics.
• 🛍️ Product Management: Built-in catalog management to edit products and upload images directly.
• ☁️ Cloud-Native: Dockerized for easy deployment on Google Cloud Run, AWS, or your own server.
• 🔓 Open Source: 100% free to use, modify, and distribute.

• Node.js 18+
• Python 3.11+
• Docker & Docker Compose

1. Clone the Repository

   git clone https://github.com/dukesky/PolarBear.git
   cd PolarBear

2. Start Infrastructure

   cd infrastructure
   docker-compose up -d

3. Start Backend

   cd backend
   poetry install
   poetry run uvicorn app.main:app --reload --port 8000

4. Start Frontend

   cd frontend
   npm install
   npm run dev

5. Experience PolarBear

   • Upload Data: Go to http://localhost:3000/upload and upload a CSV (e.g., sample_products.csv).
   • Search: Visit http://localhost:3000/search to try the hybrid search.
   • Insights: Check http://localhost:3000/insights for analytics and product management.

Detailed walkthroughs for each development phase:

• Phase 1: Setup & MVP Core - Infrastructure and basic search.
• Phase 2: Ingestion & Indexing - CSV parsing and hybrid indexing pipeline.
• Phase 3: Search Interface - Frontend UI and search logic.
• Phase 4: Analytics - Tracking user queries and dashboard.
• Phase 5: UX & Product Mgmt - Image support, catalog editing, and advanced UX.

We welcome contributions from the community! Whether it's fixing bugs, improving documentation, or suggesting new features, your help is appreciated.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

Distributed under the MIT License. See LICENSE for more information.

Project Link: https://github.com/dukesky/PolarBear