update

README.md

@@ -1,12 +1,49 @@
 ---
-title: Gemini2
+title: Gemini 2.0 Multimodal Chatbot
 emoji: 🏆
 colorFrom: purple
 colorTo: purple
 sdk: gradio
-sdk_version: 6.5.1
+sdk_version: 6.5
 app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Gemini 2.0 Multimodal Chatbot
+
+A Gradio-based multimodal chatbot powered by Google's Gemini 2.0 Flash API. Upload images and ask questions to analyze content with advanced AI capabilities.
+
+## Features
+
+- **Multimodal Input**: Support for both text prompts and image uploads
+- **Image Analysis**: Analyze figures, graphs, and diagrams
+- **Customizable Generation**: Control temperature, token limits, sampling parameters
+- **Streaming Responses**: Real-time response generation
+
+## Setup on Hugging Face Spaces
+
+1. Create a new Space on Hugging Face with Gradio SDK
+2. Add the following secret:
+   - `GEMINI_API_KEY`: Your Google Gemini API key from [Google AI Studio](https://aistudio.google.com/apikey)
+
+3. The app will automatically use this environment variable
+
+## Running Locally
+
+```bash
+pip install -r requirements.txt
+export GEMINI_API_KEY=your_api_key_here
+python app.py
+```
+
+## Environment Variables
+
+- `GEMINI_API_KEY`: Your Google Gemini API key (required)
+
+## How to Use
+
+1. Optionally enter your API key (if not set as environment variable)
+2. Enter your question or prompt
+3. Optionally upload an image
+4. Click "Submit" to get a response
+5. Adjust generation parameters in the "Customize" section for different outputs