Tavily Python SDK

   

The Tavily Python wrapper 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.

Installing

pip install tavily-python

Tavily Search

Search lets you search the web for a given query.

Usage

Below are some code snippets that show you how to interact with our search API. The different steps and components of this code are explained in more detail in the API Methods section further down.

Getting and printing the full Search API response

from tavily import TavilyClient
Step 1. Instantiating your TavilyClient

tavily_client = TavilyClient(api_key="tvly-YOUR_API_KEY")
Step 2. Executing a simple search query

response = tavily_client.search("Who is Leo Messi?")
Step 3. That's it! You've done a Tavily Search!

print(response)

Using exact match to find specific names or phrases

from tavily import TavilyClient
client = TavilyClient(api_key="tvly-YOUR_API_KEY")
Use exact_match=True to only return results containing the exact phrase(s) inside quotes

response = client.search(
    query='"John Smith" CEO Acme Corp',
    exact_match=True
)
print(response)

This is equivalent to directly querying our REST API.

Generating context for a RAG Application

from tavily import TavilyClient
Step 1. Instantiating your TavilyClient

tavily_client = TavilyClient(api_key="tvly-YOUR_API_KEY")
Step 2. Executing a context search query

context = tavily_client.get_search_context(query="What happened during the Burning Man floods?")
Step 3. That's it! You now have a context string that you can feed directly into your RAG Application

print(context)

This is how you can generate precise and fact-based context for your RAG application in one line of code.

Getting a quick answer to a question

from tavily import TavilyClient
Step 1. Instantiating your TavilyClient

tavily_client = TavilyClient(api_key="tvly-YOUR_API_KEY")
Step 2. Executing a Q&A search query

answer = tavily_client.qna_search(query="Who is Leo Messi?")
Step 3. That's it! Your question has been answered!

print(answer)

This is how you get accurate and concise answers to questions, in one line

... [truncated — view full README on GitHub]