tavily-search

LLM-optimized web search returns content snippets and relevance scores by querying the web and structuring the output for direct use in language model pipelines. This approach provides fast, accurate information gathering.

Yes, you can filter web search results by domain and time range. The search functionality includes domain filtering and time-range constraints to narrow results to specific sources or recent publication dates.

Tavily search supports optional JSON output for easy downstream processing. This structured format allows you to parse search results, snippets, and relevance scores programmatically without extracting raw text.

To run a Tavily web search query, you need the tvly command-line tool available on your system PATH. This executable processes your search string and applies depth, time-range, and domain filters.

Use LLM-optimized search for article discovery when you need relevance scores and content snippets formatted for language model pipelines. It is suited for information gathering, article discovery, and recent news lookup across topics.

Yes, you can query recent news across topics using domain filtering and depth controls. The search applies time-range and domain filters to recent-news queries, returning LLM-optimized results with relevance scores.