Smart Doorbell Camera Kit - Pi 5 OCR Document Scanner & Local LLM Query
Smart Doorbell Camera Kit – Raspberry Pi 5 Document Scanner with PaddleOCR and On-Device LLM Queries
Every part needed, pre-tested for compatibility, with an AI build companion trained on this exact project. Shipped from Bengaluru in 3-5 days.
Every year thousands of invoices, GST challans, and student forms pile up needing structured data entry. This kit turns a Raspberry Pi 5 and a Pi Camera into a doorbell-style document station: place any printed form or invoice under the desk lamp, capture a sharp image, let PaddleOCR extract all text, and then query it instantly using a local large language model. No cloud, no recurring fees — all processing happens right on the Pi’s NVMe SSD, keeping your data private.
What You’ll Build
You’ll assemble a full edge AI system: a Pi 5 with a high-speed NVMe SSD over the M.2 HAT, a Pi Camera Module 3 for crisp document shots, and a desk lamp for consistent lighting. Software-wise, you’ll deploy PaddleOCR to pull text from scanned forms and invoices, then integrate a small LLM like Llama 3.2 1B or Phi-3 to answer natural language queries. By the end, you can place an invoice on your desk, click capture, and ask “What’s the vendor’s name and total amount?” — the system replies immediately.
What You’ll Learn
- Mounting and configuring an NVMe SSD on a Raspberry Pi 5 using the M.2 HAT+
- Capturing high-resolution document images with the Pi Camera Module 3 under controlled lighting
- Deploying PaddleOCR to recognize printed text from invoices, forms, and receipts
- Running a local LLM on the Pi 5 for on-device question-answering over extracted text
Kit Contents
| Component | Quantity |
|---|---|
| Raspberry Pi 5 8GB | 1 |
| Pi Camera Module 3 | 1 |
| NVMe SSD 512GB | 1 |
| Pi 5 M.2 HAT+ | 1 |
| Desk Lamp | 1 |
| USB-C PSU | 1 |
Why Buy This Kit Instead of Sourcing Parts Separately
| Factor | Sourcing Separately | Compoden Kit |
|---|---|---|
| Compatibility checks | You verify every part | Pre-tested as a system |
| Build support | Forums and scattered tutorials | AI companion trained on this exact project |
| Time to first working build | Days of debugging | Hours, with step-by-step guidance |
| Shipping coordination | Multiple sellers, multiple delays | One shipment from Bengaluru in 3-5 days |
Who This Kit Is For
This intermediate kit is ideal for B.Tech ECE/EEE students building edge AI projects, CBSE Class 12 students with the AI elective, and Smart India Hackathon teams tackling document digitization challenges. IIT, NIT, and BITS Hyderabad engineering minors that require a fully offline, deployable OCR + LLM solution will find it fits perfectly into a semester project or internship demonstration.
Built and Backed by Compoden
Every Compoden kit ships with an AI build companion trained on this exact project — accessible via a QR code on the box, with WhatsApp and email backup. We’ve spent 10 years building projects for makers, schools, and institutions across India. If a part fails because of a manufacturing defect, replace it free within 7 days.
What if I get stuck during the build?
Scan the QR code on the kit box to launch the AI companion tailored to this project. If you need a human, WhatsApp support replies within hours.
Can this read handwritten forms or Indian language invoices?
PaddleOCR supports Hindi, Marathi, Tamil, and many other Indian scripts. Handwriting recognition works well for clear block letters; cursive may need additional training data.
How fast does the local LLM answer queries?
On the Pi 5 with a 1.5B parameter model, simple queries like “what’s the total” finish in 3–5 seconds. Larger models run slower but can handle more complex reasoning.
Do I need an internet connection for the LLM?
No. The entire pipeline — image capture, OCR, and LLM — runs offline on the Pi 5. You only need internet to download the initial model weights, which the build guide covers.
Doorbell Security — PaddleOCR + local LLM on Pi 5 extracts and queries structured information from scanned forms and invoices.
What's in this kit
Shipping Information
- Prepaid Orders: ₹75 for orders up to ₹999, FREE shipping above ₹999
- COD Orders: ₹125 shipping + ₹50 COD fee = ₹175 total
- Delivery Timeline: Dispatch in 1-2 days, delivery in 2-7 days depending on location
Returns & Warranty
- 7-Day Return: Manufacturing defects only (approval required)
- Warranty: 7 days from delivery
- Non-Returnable: Batteries, consumables, cut wires, clearance items