skills.rest
BEIRUX
BEIRUXOFFICIAL
Explore all skills by this author →
GitHub

tavily-best-practices

Integrate Tavily Search, Extract, Crawl, Map, and Research APIs into agent workflows.

Updated Apr 3, 2026
Search Tags:#research#rag#integrations#web-search#crawl#tavily#content-extraction
One-click install
npx skills add https://github.com/BEIRUX/agent-skills --skill tavily-best-practices-beirux
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tavily-best-practices
Source: https://github.com/BEIRUX/agent-skills/tree/main/tavily-best-practices
Command: npx skills add https://github.com/BEIRUX/agent-skills --skill tavily-best-practices-beirux

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Reduce the friction and risk of integrating live web search and site extraction into AI agents by providing clear, production-grade patterns, parameter guidance, and integration examples for Tavily's Search, Extract, Crawl, Map, and Research APIs.

Core Features & Use Cases

  • SDK guidance: Concrete initialization and async usage for Python and JavaScript clients to ensure reliable API access and credential management.
  • Extraction & crawling patterns: Best practices for Map-then-Extract, chunks_per_source/instructions usage, depth/breadth tuning, and rate-limit/error handling for site-wide extraction and RAG pipelines.
  • Integrations: Examples and recommendations for LangChain, LlamaIndex, Vercel AI SDK, OpenAI/Anthropic tool calling, and no-code platforms to embed Tavily into agentic workflows.
  • Use Case: Build a research pipeline that maps a docs site, filters API pages, extracts key sections into chunks, and ingests them into a vector store for retrieval-augmented generation.

Quick Start

Initialize a Tavily client with your TAVILY_API_KEY and run a focused search or map call using an appropriate search_depth or max_depth to discover and extract the URLs you need.

Frequently Asked Questions about tavily-best-practices

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I integrate web search and content extraction into an AI agent workflow?▼

Web search and content extraction integration requires initializing the Tavily SDK with an API key and applying Map-then-Extract workflows to discover URLs and retrieve focused content chunks for agentic systems.

What is the best way to crawl a documentation site for a RAG pipeline?▼

Crawling a documentation site for RAG pipelines involves mapping the site to filter API pages, extracting key sections into chunks using chunks_per_source, and ingesting them into a vector store for retrieval-augmented generation.

How do I tune search_depth and max_depth parameters for web extraction?▼

Tuning search_depth and max_depth parameters controls the depth and breadth of web extraction, allowing you to balance result comprehensiveness against API rate limits and response latency in production integrations.

Does Tavily work with LangChain and LlamaIndex for autonomous agents?▼

Tavily integrates with LangChain, LlamaIndex, Vercel AI SDK, and OpenAI/Anthropic tool calling through integration adapters, enabling autonomous agents to perform live web search and site extraction within existing frameworks.

How do I handle rate limits and errors during site-wide crawling?▼

Handling rate limits and errors during site-wide crawling requires implementing async patterns and error-handling logic specified in integration adapters to ensure reliable extraction across large documentation sets.

Can I use async patterns for parallel URL discovery and content extraction?▼

Async patterns for parallel URL discovery and content extraction are supported through the Python and JavaScript SDK clients, enabling reliable concurrent API access and credential management for production workloads.

Related Skills

Explore More Software Engineering Skills→
JuanMS20JuanMS20

github-auth

Configure GitHub authentication for Hermes Agent using git, gh CLI, or SSH credentials.

Community
Intermediate
adeboldadebold

AgentDB Vector Search

Perform vector-based semantic search against an AgentDB index.

Community
Advanced
tavily-aitavily-ai
1

tavily-best-practices

Document Tavily search, extract, crawl, map, and research APIs.

Official
Intermediate
dotlab-hqdotlab-hq

tanstack-ai

Generates streaming, tool-calling AI responses across multiple providers with React hooks.

Official
Advanced