tavily-best-practices

Web search API for LLMs with real-time data access, content extraction, site crawling, and AI-powered research.

- Five core methods: search() for web results, extract() for URL content, crawl() for site-wide extraction, map() for URL discovery, and research() for end-to-end AI synthesis

- Supports Python and JavaScript SDKs with async clients for parallel queries and configurable search depth (ultra-fast/fast/basic/advanced)

- Crawl method accepts semantic instructions to focus extraction on specific content types; Map-then-Extract pattern available for targeted workflows

- Research method offers three model tiers (mini/pro/auto) with polling-based async execution, streaming support, and structured output schemas

- Integrates with LangChain, LlamaIndex, CrewAI, Vercel AI SDK, and other frameworks; supports Hybrid RAG patterns and project-level usage tracking

Tavily

Tavily is a search API designed for LLMs, enabling AI applications to access real-time web data.

Installation

Python:

pip install tavily-python

JavaScript:

npm install @tavily/core

See references/sdk.md for complete SDK reference.

Client Initialization