Skip to main content

Tavily LogoIBM watsonx Logo

Powered by Tavily and IBM® watsonx.ai™

​
Overview

Tavily and IBM have partnered to deliver AI-enriched spreadsheets that combine Tavily’s real-time web search with IBM watsonx.ai’s advanced foundation models. This open-source solution enables users to enrich spreadsheet data with live, cited web information and powerful LLM-driven insights.

​
What is it?

With this application, you can:
  • 📊 Enrich spreadsheet cells with AI-generated content backed by live web data
  • 🧠 Entity extraction and data processing with Granite LLMs
  • 🔄 Process entire columns in batch for efficient data enhancement
  • 📑 Access source citations for all web-sourced information
  • 📂 Export your enriched data as CSV files for further use

​
How it Works

  1. Fill in spreadsheet columns with your data
  2. Enrich your spreadsheet: The app uses Tavily’s search and IBM watsonx.ai models to add live, relevant information
  3. Export as CSV for further use

​
Architecture

Architecture Diagram

​
Setup Instructions

TAVILY_API_KEY=<your API key>
WATSONX_API_KEY=<your API key>
WATSONX_PROJECT_ID=<your project id>
WATSONX_URL=<your data center url>
FOUNDATION_MODEL_ID=<watsonx.ai model id>
  • Create .env.development in ui/ directory.
VITE_API_URL=http://localhost:8000
VITE_WS_URL=ws://localhost:8000
  • Create and activate a Python 3.11 virtual environment.
python3.11 -m venv venv
source venv/bin/activate  # On Windows: .\venv\Scripts\activate
  • Install dependencies.
python3.11 -m pip install -r requirements.txt
  • Run the backend server.
python app.py
  • Build the Docker image.
docker build -t spreadsheet .
  • Run the container.
docker run -p 8000:8000 --env-file .env spreadsheet
  • Navigate to the frontend directory.
cd ui
  • Install dependencies.
npm install
  • Start the development server.
npm run dev
See full setup, usage, and contribution details in the GitHub repository.
⌘I