Skip to main content
Tavily is an AI-powered search engine that gives agents high-quality results with built-in answer synthesis.

​
Overview

Tavily is an AI-powered search engine optimized for LLMs and AI agents. It provides high-quality, relevant search results with built-in answer synthesis.

​
Installation

pip install "praisonai[tools]"

​
Environment Variables

export TAVILY_API_KEY="${TAVILY_API_KEY:?Set TAVILY_API_KEY in your shell}"
Get your API key from Tavily.

​
How It Works

​
Quick Start

1

Simple Usage

from praisonai_tools import TavilyTool

# Initialize
tavily = TavilyTool()

# Search
results = tavily.search("What is quantum computing?")
print(results)
2

With Configuration

Use the same tool with an agent — see Usage with Agent below, or pass env vars and options from the sections above.

​
Usage with Agent

from praisonaiagents import Agent
from praisonai_tools import TavilyTool

agent = Agent(
    name="Researcher",
    instructions="You are a research assistant. Use Tavily to search for information.",
    tools=[TavilyTool()]
)

response = agent.chat("Search for the latest AI news")
print(response)

​
Available Methods

​
search(query, max_results=5)

Search the web with AI-powered results. 
from praisonai_tools import TavilyTool

tavily = TavilyTool()
results = tavily.search("Python best practices", max_results=3)

# Returns:
# {
#     "query": "Python best practices",
#     "answer": "AI-generated summary...",
#     "results": [
#         {"title": "...", "url": "...", "content": "...", "score": 0.95}
#     ]
# }

​
search_context(query)

Get search context optimized for RAG applications. 
context = tavily.search_context("machine learning fundamentals")
# Returns a string with relevant context for LLM consumption

​
extract(urls)

Extract content from specific URLs. 
content = tavily.extract("https://example.com,https://another.com")
# Returns list of extracted content from each URL

​
Configuration Options

tavily = TavilyTool(
    api_key="your_key",           # Optional: defaults to TAVILY_API_KEY env var
    search_depth="advanced",       # "basic" or "advanced"
    include_answer=True,           # Include AI-generated answer
    max_tokens=6000               # Max tokens for context
)

​
Function-Based Usage

from praisonai_tools import tavily_search

# Quick search without instantiating class
results = tavily_search("latest tech news", max_results=5)

​
CLI Usage

# Set API key
export TAVILY_API_KEY=your_key

# Use with praisonai
praisonai --tools TavilyTool "Search for AI trends 2025"

​
Error Handling

from praisonai_tools import TavilyTool

tavily = TavilyTool()
results = tavily.search("my query")

if "error" in results:
    print(f"Error: {results['error']}")
else:
    print(f"Found {len(results['results'])} results")

​
Common Errors

ErrorCauseSolution
TAVILY_API_KEY not configuredMissing API keySet TAVILY_API_KEY environment variable
tavily-python not installedMissing dependencyRun pip install tavily-python
Invalid API keyWrong API keyVerify your API key at tavily.com

​
Best Practices

TavilyTool() defaults to the TAVILY_API_KEY env var. Set it in your shell or .env rather than passing api_key= inline.
search_context(query) returns text optimised for LLM consumption. Prefer it over raw search when feeding results straight into the agent.
search_depth="advanced" returns richer results at higher latency. Use "basic" for quick lookups to keep the agent responsive.

Exa Search

Neural search engine

DuckDuckGo

Privacy-focused search

Serper

Google search API