tavily-python

View on GitHub

The Tavily Python SDK allows for easy interaction with the Tavily API, offering the full range of our search, extract, crawl, map, and research functionalities directly from your Python programs. Easily integrate smart search, content extraction, and research capabilities into your applications, harnessing Tavily's powerful features.

★ 1.4K190 forksPythonMITtavily-ai

Python SDK for the Tavily API: web search, URL extraction, crawling, site mapping, and cited research, with sync and async clients. Commonly used to ground LLM/agent answers and build RAG context in one line of code.

Use Cases

Ground LLM answers with fresh web search resultsGenerate context strings for RAG pipelinesGive AI agents a web search and extract toolExtract raw content from up to 20 URLs at onceCrawl websites to collect pages matching instructionsMap a site's structure to find relevant pagesGenerate cited research reports on a topicStream research results as they are producedReturn concise Q&A answers for LLM consumptionSubmit agent feedback to improve search rankingRoute traffic through an API gateway with custom sessionsRun keyless search and extract for quick prototyping

Built With

Language: Python
Frameworks: requests · httpx · openai · pytest

tavily-python

Use Cases

Built With

Tags