Update README.md
Browse files
README.md
CHANGED
|
@@ -11,3 +11,22 @@ short_description: IT IS OCR+GEMINI PIPELINE FOR AUTOMATIC FORMFILLING
|
|
| 11 |
---
|
| 12 |
|
| 13 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
| 14 |
+
# 🧠 AutoFill Form Extractor
|
| 15 |
+
|
| 16 |
+
This app extracts structured information from documents (like PAN Card forms) using:
|
| 17 |
+
- **OCR (pytesseract)** for text extraction
|
| 18 |
+
- **Gemini 1.5 Flash** for intelligent field parsing
|
| 19 |
+
|
| 20 |
+
## 🚀 How to Use
|
| 21 |
+
1. Upload a PDF document (e.g., PAN Card)
|
| 22 |
+
2. Select the form type
|
| 23 |
+
3. View the extracted JSON output
|
| 24 |
+
|
| 25 |
+
## 🧩 Tech Stack
|
| 26 |
+
- Python + Gradio
|
| 27 |
+
- Google Gemini API
|
| 28 |
+
- Tesseract OCR
|
| 29 |
+
- pdf2image
|
| 30 |
+
|
| 31 |
+
## 🔒 Environment Variable
|
| 32 |
+
Set your Gemini API key in Hugging Face Space → Settings → Variables and Secrets:
|