TraumaAI

An artificial intelligence-based system for assistance in diagnosis and processing of trauma data. TraumaAI provides an API for interaction with a chat system, storage and analysis of medical data related to traumatology.

Core Technologies

FastAPI - Modern high-performance web framework for building APIs
MongoDB - NoSQL database for data storage
OpenAI - Integration with artificial intelligence models for medical data analysis
Python 3.12 - Programming language
Docker - Application containerization
FAISS - Library for vector search (used for finding similar medical cases)
PyJWT/jose - User authentication and authorization
Uvicorn - ASGI server for running FastAPI

Local Installation and Setup

Prerequisites

Python 3.12 or higher
MongoDB
OpenAI API key

Windows

Clone the repository:
```
git clone <repository-url>
cd TraumaAI
```

Create and activate a virtual environment:

python -m venv .venv
.venv\Scripts\activate

Install dependencies:
```
pip install -r requirements.txt
```
Create a .env file based on .env.example:
```
copy .env.example .env
```
Then edit the .env file, adding your values for MongoDB URL and OpenAI API key.
Run the application:
```
uvicorn main:app --reload
```

macOS / Ubuntu

Clone the repository:
```
git clone <repository-url>
cd TraumaAI
```

Create and activate a virtual environment:

python3 -m venv .venv
source .venv/bin/activate

Install dependencies:
```
pip install -r requirements.txt
```
Create a .env file based on .env.example:
```
cp .env.example .env
```
Then edit the .env file, adding your values for MongoDB URL and OpenAI API key.
Run the application:
```
uvicorn main:app --reload
```

Running with Docker

Build the Docker image:
```
docker build -t traumaai .
```

Run the container:

docker run -p 7860:7860 --env-file .env traumaai

API Access

After startup, the API will be available at: http://localhost:7860

API documentation is available at:

http://localhost:7860/docs - Swagger UI
http://localhost:7860/redoc - ReDoc