push config

README.md

@@ -1,124 +1,10 @@
-# QuickCare Text - MediScope AI
-
-A FastAPI service for medical chat using BioMistral-7B model with **conversational AI support** and **session management**.
-
-## 🚀 Quick Start
-
-### 1. Install Dependencies
-
-```bash
-pip install -r requirements.txt
-```
-
-### 2. Run the Server
-
-```bash
-uvicorn app:app --host 0.0.0.0 --port 8000 --reload
-```
-
-The server will start on `http://127.0.0.1:8000`
-
-**Note:** On first run, the BioMistral-7B model (~14GB) will be downloaded from Hugging Face. This may take several minutes.
-
-### 3. Test the API
-
-#### Start a new conversation:
-```bash
-curl -X POST "http://127.0.0.1:8000/chat" \
-     -H "Content-Type: application/json" \
-     -d '{"prompt": "I have a rash on my arm that itches for 3 days"}'
-```
-
-**Response:**
-```json
-{
-  "response": "It sounds like you may have a mild skin irritation...",
-  "session_id": "550e8400-e29b-41d4-a716-446655440000"
-}
-```
-
-#### Continue the conversation (use the session_id from previous response):
-```bash
-curl -X POST "http://127.0.0.1:8000/chat" \
-     -H "Content-Type: application/json" \
-     -d '{
-       "prompt": "What should I do about it?",
-       "session_id": "550e8400-e29b-41d4-a716-446655440000"
-     }'
-```
-
-#### Clear a session:
-```bash
-curl -X DELETE "http://127.0.0.1:8000/chat/550e8400-e29b-41d4-a716-446655440000"
-```
-
-## 📁 Project Structure
-
-```
-.
-├── app.py                    # FastAPI application with session management
-├── model/
-│   ├── __init__.py
-│   └── biomistral_service.py # BioMistral model with conversation history
-├── requirements.txt          # Python dependencies
-└── README.md                 # This file
-```
-
-## 🔧 API Endpoints
-
-### `GET /`
-Health check and API information.
-
-### `GET /health`
-Health check endpoint.
-
-### `POST /chat`
-Chat endpoint with conversation support.
-
-**Request Body:**
-```json
-{
-  "prompt": "Your medical question or symptom description",
-  "session_id": "optional-session-id"  // If omitted, a new session is created
-}
-```
-
-**Response:**
-```json
-{
-  "response": "AI-generated medical advice/explanation",
-  "session_id": "session-id-for-continuing-conversation"
-}
-```
-
-### `DELETE /chat/{session_id}`
-Clear conversation history for a specific session.
-
-## 💬 Conversation Features
-
-- **Session Management**: Each conversation has a unique `session_id`
-- **Multi-turn Conversations**: Maintain context across multiple messages
-- **Automatic Session Creation**: New sessions are created automatically if `session_id` is not provided
-- **Conversation History**: Full conversation history is maintained per session
-
-## 🧠 Model Information
-
-- **Model:** BioMistral/BioMistral-7B
-- **Source:** Hugging Face
-- **Purpose:** Medical chat, reasoning, and education
-- **Capabilities:** Multi-turn medical conversations, symptom analysis, medical education
-
-## ⚠️ Important Notes
-
-- This is an **educational tool** and should not replace professional medical consultation
-- Always encourage users to consult healthcare professionals for serious conditions
-- The model is loaded into memory on startup, which may take time and require significant RAM/VRAM
-- Sessions are stored in memory (not persisted). Restarting the server will clear all sessions
-- For production use, consider implementing persistent storage, caching, rate limiting, and proper error handling
-
-## 🔜 Next Steps
-
-- Add `/analyze-image` endpoint (BiomedCLIP)
-- Add `/analyze-text` endpoint (ClinicalBERT)
-- Fuse all endpoints into `/triage` endpoint
-- Add persistent session storage (Redis/Database)
+---
+title: QuickCare Text
+emoji: 🚀
+colorFrom: green
+colorTo: indigo
+sdk: docker
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference