Installation

Tensorify is a web-based platform - no local installation required for the visual editor. However, to run exported workflows locally, you'll need Python set up on your machine.

Using Tensorify (Web)

The Tensorify visual editor runs entirely in your browser:

1. Visit app.tensorify.io
2. Sign up or log in
3. Start building workflows

No downloads or installations needed.

Local Execution Requirements

To run exported Python code locally, you'll need:

Python

Tensorify generates Python 3.10+ compatible code.

# Check your Python version
python --version

# Should output Python 3.10.x or higher

If you need to install Python, visit python.org.

pip (Package Manager)

pip comes bundled with Python. Verify it's available:

pip --version

Virtual Environment (Recommended)

We recommend using virtual environments to isolate dependencies:

# Create a virtual environment
python -m venv tensorify-env

# Activate it (macOS/Linux)
source tensorify-env/bin/activate

# Activate it (Windows)
tensorify-env\Scripts\activate

Installing Workflow Dependencies

Each exported workflow includes a requirements.txt file:

# Navigate to your workflow folder
cd my-workflow

# Install dependencies
pip install -r requirements.txt

Common Dependencies

Depending on your plugins, you might need:

| Plugin Type | Dependencies | | --------------- | ---------------------------- | | OpenAI | openai | | Anthropic | anthropic | | Data Processing | pandas, numpy | | ML/PyTorch | torch, torchvision | | Web Scraping | requests, beautifulsoup4 | | Databases | psycopg2-binary, pymongo |

GPU Support (Optional)

For ML workflows with GPU requirements:

CUDA Setup

1. Install NVIDIA drivers for your GPU
2. Install CUDA Toolkit (11.8+ recommended)
3. Install cuDNN

PyTorch with CUDA

# Install PyTorch with CUDA support
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu118

Environment Variables

Many plugins require API keys. Set them as environment variables:

# OpenAI
export OPENAI_API_KEY="sk-..."

# Anthropic
export ANTHROPIC_API_KEY="sk-ant-..."

# Or use a .env file
echo "OPENAI_API_KEY=sk-..." >> .env

Docker (Alternative)

For reproducible environments, use Docker:

FROM python:3.11-slim

WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt

COPY . .
CMD ["python", "main.py"]

Build and run:

docker build -t my-workflow .
docker run -e OPENAI_API_KEY=$OPENAI_API_KEY my-workflow

Troubleshooting

Common Issues

ModuleNotFoundError: Make sure you've installed dependencies with pip install -r requirements.txt

API Key errors: Verify environment variables are set correctly

Python version mismatch: Tensorify requires Python 3.10+

Getting Help

• Check our FAQ
• Ask in Discord
• Email [email protected]

---

Ready to build? Head to the Quick Start Guide →