tavily-search

Use Tavily Search API for optimized, real-time web search results for RAG. Requires TAVILY_API_KEY.

⭐2stars🔀0forks📁View on GitHub🕐Updated Nov 26, 2025

When & Why to Use This Skill

This Claude skill integrates the Tavily Search API to deliver optimized, real-time web search results specifically tailored for Retrieval-Augmented Generation (RAG) and LLM workflows. It solves the challenge of AI hallucinations by providing clean, noise-free, and up-to-date information, ensuring that AI agents have access to the most current web data for grounded and accurate response generation.

Use Cases

  • Real-time Fact Checking: Enabling AI agents to verify claims or fetch the latest news and events that occurred after the model's knowledge cutoff.
  • RAG Pipeline Enhancement: Providing high-quality, pre-filtered context for Retrieval-Augmented Generation systems to improve the precision of complex queries.
  • Deep Market Research: Utilizing the 'advanced' search depth to perform comprehensive competitive analysis and gather detailed industry insights from multiple sources.
  • Technical Troubleshooting: Searching for specific error codes, latest API documentation, or community-driven solutions across the web to assist in debugging.
nametavily-search
descriptionUse Tavily Search API for optimized, real-time web search results for RAG. Requires TAVILY_API_KEY.

Tavily Search Skill

This skill utilizes the Tavily Search API, providing clean, real-time web search results optimized for LLMs and RAG pipelines.

Setup

  1. Dependencies: Requires tavily-python.

    pip install tavily-python python-dotenv
    
  2. API Key Configuration: Requires TAVILY_API_KEY.

    # If the script fails due to a missing key, run the following:
    echo "It seems the Tavily API key is not set up."
    read -p "Enter your Tavily API key: " TAVILY_KEY
    echo "TAVILY_API_KEY=$TAVILY_KEY" >> .env
    if [ -f .gitignore ] && ! grep -q ".env" .gitignore; then echo ".env" >> .gitignore; fi
    echo "API key saved to .env."
    

Usage

Use the scripts/tavily_search.py script.

Command

python3 scripts/tavily_search.py --query "<query>" [--max-results <N>] [--search-depth <basic|advanced>]

Parameters

  • --query (Required): The search query.
  • --search-depth (Optional): Default basic. Use advanced for intensive research (higher quality, slower).
  • --max-results (Optional): Default 10.

Example

python3 scripts/tavily_search.py --query "autonomous research agents comparison" --search-depth advanced

Output

The script outputs JSON containing a synthesized answer (if requested by the script) and a list of results (URL, title, content snippets).