n8n Search Engine

A semantic search engine for CSV data using sentence transformers and FAISS for fast similarity search.

🚀 Features..

• Semantic Search: Uses sentence transformers to understand the meaning behind your queries
• Fast Search: FAISS indexing for lightning-fast similarity search
• CLI Interface: Command-line tool for quick searches
• Web Interface: Beautiful Streamlit web app with interactive features
• Easy Setup: Simple installation and setup process

Screenshots

Landing Page

Search

Workflow Paste

🛠️ Setup Instructions

1. Install Python Dependencies

First, create a virtual environment (recommended):

# Create virtual environment
python -m venv venv

# Activate it
# On Windows:
venv\Scripts\activate
# On Mac/Linux:
source venv/bin/activate

Install the required packages:

pip install -r requirements.txt

2. Prepare Your Data

Place your CSV file in the data/ folder as workflows.csv. Make sure it has at least these columns:

• workflow: Name or identifier for each item
• description: Text description to search through

3. Build the Search Index

Navigate to the src/ folder and run:

cd src
python build_index.py

This will:

• Load CSV data
• Generate semantic embeddings for all descriptions
• Build a FAISS index for fast searching
• Save everything to the embeddings/ folder

🔍 Usage

Command Line Interface

For quick searches from the terminal:

cd src
python search.py

Then enter your search queries interactively. Examples:

• "email automation"
• "data scraping"
• "notifications"
• "file backup"

Web Interface (Recommended)

For a beautiful web interface with more features:

cd src
streamlit run app.py

This will open a web browser with:

• Interactive search box
• Similarity scores
• Example queries
• Downloadable results
• Dataset statistics

📝 License

This project is open source and available under the MIT License.

🤝 Contributing

Feel free to submit issues, feature requests, or pull requests to improve this search engine!