Update README.md

README.md

@@ -1,35 +1,48 @@
+---
+title: Multimodal AI Doctor – An Agentic AI Project
+emoji: 🩺
+colorFrom: indigo
+colorTo: blue
+sdk: gradio
+sdk_version: 3.50.2
+app_file: app.py
+pinned: false
+---
+
 # Multimodal AI Doctor – An Agentic AI Project
 
-**Multimodal AI Doctor** is an **agentic multimodal assistant** built with **Gradio**, **Groq APIs**, and **ElevenLabs**.
-It combines **speech, vision, and reasoning** through a series of cooperating LLMs, simulating how a real doctor listens, observes, and responds concisely.
-The system integrates **voice input, image analysis, clinical reasoning, and voice output** into a single pipeline.
+**Multimodal AI Doctor** is an **agentic multimodal assistant** built with **Gradio**, **Groq APIs**, and **ElevenLabs**.  
+It combines **speech, vision, and reasoning** through a series of cooperating LLMs, simulating how a real doctor listens, observes, and responds concisely.  
+The system integrates **voice input, image analysis, clinical reasoning, and voice output** into a single pipeline.  
 
 ---
 
 ## Features
 
-* Record patient voice from microphone (Speech-to-Text using **Whisper Large v3** on Groq)
-* Upload an image (diagnosis/medical-related) for analysis (Vision-Language reasoning using **Llama 4 Scout** on Groq)
-* Generate a concise medical-style response (2 sentences maximum, human-like tone)
-* Convert response to voice (Text-to-Speech using **ElevenLabs** with WAV output, fallback to **gTTS** if needed)
-* Gradio-based interactive UI
+* Record patient voice from microphone (Speech-to-Text using **Whisper Large v3** on Groq)  
+* Upload an image (diagnosis/medical-related) for analysis (Vision-Language reasoning using **Llama 4 Scout** on Groq)  
+* Generate a concise medical-style response (2 sentences maximum, human-like tone)  
+* Convert response to voice (Text-to-Speech using **ElevenLabs** with WAV output, fallback to **gTTS** if needed)  
+* Gradio-based interactive UI  
 
 ---
 
 ## Project Structure
 
 ```
+
 .
 ├── app.py                    # Gradio UI + main workflow
-├── brain_of_the_doctor.py    # Image encoding + Groq multimodal analysis
-├── voice_of_the_patient.py   # Audio recording + Groq Whisper transcription
-├── voice_of_the_doctor.py    # ElevenLabs + gTTS text-to-speech
+├── brain\_of\_the\_doctor.py    # Image encoding + Groq multimodal analysis
+├── voice\_of\_the\_patient.py   # Audio recording + Groq Whisper transcription
+├── voice\_of\_the\_doctor.py    # ElevenLabs + gTTS text-to-speech
 ├── requirements.txt          # Python dependencies
 ├── .env                      # Environment variables (API keys)
-├── .gitignore                # Ignore venv, __pycache__, .env, etc.
+├── .gitignore                # Ignore venv, **pycache**, .env, etc.
 ├── images/                   # Folder for saving test/sample images
 └── README.md                 # Documentation
-```
+
+````
 
 ---
 
@@ -37,22 +50,22 @@ The system integrates **voice input, image analysis, clinical reasoning, and voi
 
 The system uses **multiple LLM agents** to process multimodal input step by step:
 
-1. **Symptom Agent** – extracts structured meaning from patient speech (via Whisper transcription).
-2. **Vision Agent** – analyzes uploaded medical images (X-ray, MRI, scan).
-3. **Reasoning Agent** – integrates speech and image findings into a medical interpretation.
-4. **Response Agent** – formats the answer in a concise, empathetic, doctor-style tone (≤ 2 sentences).
-5. **Voice Agent** – delivers the response using ElevenLabs (WAV, fallback gTTS).
+1. **Symptom Agent** – extracts structured meaning from patient speech (via Whisper transcription).  
+2. **Vision Agent** – analyzes uploaded medical images (X-ray, MRI, scan).  
+3. **Reasoning Agent** – integrates speech and image findings into a medical interpretation.  
+4. **Response Agent** – formats the answer in a concise, empathetic, doctor-style tone (≤ 2 sentences).  
+5. **Voice Agent** – delivers the response using ElevenLabs (WAV, fallback gTTS).  
 
-This makes the project an **agentic AI pipeline**, where multiple specialized models cooperate to mimic a doctor’s diagnostic process.
+This makes the project an **agentic AI pipeline**, where multiple specialized models cooperate to mimic a doctor’s diagnostic process.  
 
 ---
 
 ## Requirements
 
-* Python 3.10 or higher
-* FFmpeg installed and available in PATH (required by pydub)
-* A Groq API key (obtain from [https://console.groq.com](https://console.groq.com))
-* An ElevenLabs API key (obtain from [https://elevenlabs.io](https://elevenlabs.io))
+* Python 3.10 or higher  
+* FFmpeg installed and available in PATH (required by pydub)  
+* A Groq API key (obtain from [https://console.groq.com](https://console.groq.com))  
+* An ElevenLabs API key (obtain from [https://elevenlabs.io](https://elevenlabs.io))  
 
 ---
 
@@ -63,7 +76,7 @@ This makes the project an **agentic AI pipeline**, where multiple specialized mo
    ```bash
    git clone https://github.com/your-username/ai-doctor-2.0-voice-and-vision.git
    cd ai-doctor-2.0-voice-and-vision
-   ```
+````
 
 2. Create and activate a virtual environment:
 
@@ -99,7 +112,7 @@ This makes the project an **agentic AI pipeline**, where multiple specialized mo
 Start the Gradio app:
 
 ```bash
-python gradio_app.py
+python app.py
 ```
 
 The app will launch locally at:
@@ -158,4 +171,6 @@ For questions, issues, or collaboration, please contact:
 **Email:** [sayeem26s@gmail.com](mailto:sayeem26s@gmail.com)
 **LinkedIn:** [https://www.linkedin.com/in/s-m-shahriar-26s/](https://www.linkedin.com/in/s-m-shahriar-26s/)
 
----
+```
+
+---