FastAPI backend service for Asset Layer, providing document analysis and deadline management functionality using LLaMA 3.1 via the Cerebrus API.
- AI-powered document content extraction
- Deadline detection and validation
- Document type classification
- Confidence scoring
- Support for multiple document types:
- BBBEE Certificates
- Environmental Authorizations
- Safety Certifications
- Document analysis endpoints
- Deadline management endpoints
- File upload handling
- FastAPI - Web framework
- LLaMA 3.1-8b - Language model (via Cerebrus API)
- PostgreSQL - Database
- pgvector - Vector storage
- Python 3.10+ - Programming language
- Python 3.10+
- PostgreSQL
- Cerebrus API key
- Create and activate virtual environment:
python -m venv env
source env/bin/activate # Linux/Mac
.\env\Scripts\activate # Windows
- Install required packages:
pip install -r requirements.txt
- Create .env file in root directory:
CEREBRUS_API_KEY=your_api_key_here
- Clone the repository:
git clone [repository-url]
cd assetlayer-mvt
- Setup Backend:
# Navigate to backend directory
cd assetlayer-backend
# Create virtual environment
python -m venv env
# Activate virtual environment
source env/bin/activate # Linux/Mac
.\env\Scripts\activate # Windows
# Install dependencies
pip install -r requirements.txt
# Create .env file and add your Cerebrus API key
echo "CEREBRUS_API_KEY=your_key_here" > .env
# Start backend server
uvicorn main:app --reload --port 8000
The Asset Layer API provides endpoints for document analysis and deadline management. All responses are in JSON format.