Update README.md

README.md

@@ -9,4 +9,38 @@ app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+# Byaldi + Qwen2VL
+
+## Overview
+
+The **Byaldi + Qwen2VL** app is an innovative tool designed for extracting text from images using advanced OCR (Optical Character Recognition) techniques and natural language processing. This application leverages the **RAGMultiModalModel** from Byaldi and the **Qwen2VL** model for generating meaningful responses based on the extracted text. 
+
+This application also takes advantage of **ZeroGPU** to run efficiently on powerful hardware, specifically the **NVIDIA A100** GPU, ensuring high-speed processing and accurate results even for large and complex image inputs.
+
+## Features
+
+- **Image Upload**: Users can upload images from which text will be extracted.
+- **Text Extraction**: Utilizes state-of-the-art models to accurately extract text from the uploaded images.
+- **Keyword Search**: Allows users to search for specific keywords within the extracted text and highlights them.
+- **High-Performance**: Runs on **ZeroGPU (NVIDIA A100)** for accelerated computation and efficient model execution.
+- **User-Friendly Interface**: Built using Gradio for an interactive user experience.
+
+## Technologies Used
+
+- **Gradio**: For creating the web interface.
+- **Byaldi RAGMultiModalModel**: For indexing and searching images.
+- **Qwen2VL**: For generating responses based on visual and textual inputs.
+- **ZeroGPU**: For efficient model inference using **NVIDIA A100**.
+- **PyTorch**: For deep learning functionalities.
+- **Pillow**: For image handling.
+
+## Getting Started
+
+### Prerequisites
+
+- Python 3.8 or later
+- Required libraries:
+  ```bash
+  pip install gradio byaldi transformers torch pillow