Update README.md

README.md

@@ -1,59 +1,45 @@
+---
+title: AGI Telecom POC
+emoji: 📡
+colorFrom: blue
+colorTo: indigo
+sdk: docker
+sdk_version: "latest"
+app_file: app.py
+pinned: false
+---
+
 # AGI Telecom POC
 
 This Hugging Face Space demonstrates an AGI-powered telecom interface that enables voice and text interaction through telecommunication channels (WebRTC/SIP).
 
 ## Overview
 
-This proof-of-concept showcases how AI assistants can be delivered through telecom infrastructure with:
-
+This proof-of-concept showcases:
 - Multimodal communication (voice + text)
-- Agentic intelligence (reasoning, memory)
-- Telecom-enabled delivery
-
-## Demo Usage
+- Agentic intelligence (reasoning, memory, response)
+- Telecom-enabled delivery (SIP/WebRTC)
 
-This space provides two ways to interact with the system:
+The system is powered by:
+- Meta-Llama-3.1-8B-Instruct through Hugging Face Inference Endpoints
+- Whisper for speech-to-text conversion
+- Edge TTS for natural-sounding speech synthesis
 
-1. **Gradio Interface**: A simplified interface that demonstrates core functionality
-   - Upload audio or use text input
-   - Get transcriptions, agent responses, and speech synthesis
-   - Manage conversation sessions
-
-2. **API Endpoints**: Direct API access for more advanced integration
-   - `/api/transcribe` - Convert audio to text
-   - `/api/query` - Process text with agent
-   - `/api/speak` - Convert text to speech
-   - `/api/session` - Create new conversation sessions
-
-## Architecture
+## Using the Interface
 
-The system follows this processing flow:
+This demo provides two ways to interact with the system:
 
-```
-[User Voice Input] → [Speech-to-Text] → [Agent Reasoning] → [Text-to-Speech Output] → [Telecom Network Delivery]
-```
+1. **Web Interface**: A user-friendly chat interface with voice capabilities
+   - Type messages or use voice input
+   - See real-time visualizations of audio
+   - Experience AI responses via text and speech
 
-## Local Development
+2. **API Endpoints**: Direct access for integration
+   - `/query` - Process text with agent
+   - `/transcribe` - Convert audio to text
+   - `/speak` - Convert text to speech
+   - `/complete_flow` - End-to-end processing
 
-To run this project locally:
-
-1. Clone the repository
-2. Install dependencies: `pip install -r requirements.txt`
-3. Run the app: `python app.py`
-4. Open http://localhost:8000 in your browser
-
-## Notes
-
-- This demo uses simplified mock implementations
-- For production use, you would replace the mock functions with:
-  - Whisper for speech-to-text
-  - A proper LLM (like LLAMA, Mistral) for reasoning
-  - A high-quality TTS engine
-  - Full WebRTC/SIP implementation
-
-## Future Extensions
+## Architecture
 
-- Full SIP integration
-- Mesh networking with fallback intelligence
-- Enhanced multi-agent collaboration
-- Advanced contextual reasoning
+The system follows this processing flow: