VectorNodes

A node-based pipeline builder with a high-fidelity dark-theme UI, designed for modularity and scalability.

🚀 Getting Started

Follow these steps to initialize the project locally.

1. Backend Setup (FastAPI)

# Navigate to backend directory
cd backend

# Create a virtual environment
python -m venv venv

# Activate the virtual environment
# On Linux/macOS:
source venv/bin/activate
# On Windows:
# venv\Scripts\activate

# Install dependencies
pip install fastapi uvicorn python-multipart

# Start the server with hot-reload
uvicorn main:app --reload

The API will be available at: http://localhost:8000

2. Frontend Setup (React)

# Navigate to frontend directory
cd frontend

# Install dependencies
npm install

# Start the development server
npm start

The application will open at: http://localhost:3000

---

🛠️ How it Works

1. Modular Node System: Built with a reusable BaseNode architecture that handles styling, header layout, and handle positioning.
2. Text & Variables: The Text node features dynamic resizing and real-time variable detection. Typing {{ variable_name }} instantly creates a corresponding input handle on the node.
3. 9 Integrated Nodes:
   • Data: Input, Output, Text
   • Logic: Math, Filter, Merge
   • Processing: LLM, Timer, Note
4. Pipeline Analysis: Click the 🚀 Submit Pipeline button. The backend calculates node/edge counts and verifies if the graph is a Directed Acyclic Graph (DAG).

💡 Example: Translation & Sentiment Analysis

1. Input: Add an Input node and name it customer_feedback.
2. Transform: Add a Text node with the template: Evaluate the sentiment of this text: {{ feedback }}.
3. Connect: Link the Input output to the feedback handle on the Text node.
4. Process: Add an LLM node. Connect the Text output to its Prompt handle.
5. Output: Add an Output node and connect the LLM output to it.
6. Execute: Click Submit. A report will confirm the pipeline topology and DAG status.