Similar to the FirecrawlWebSearch component, we should add a TavilyWebSearch component as part of a new Tavily integration.

The first PR should not include any other component other than the TavilyWebSearch component but fully focus on search based on https://github.com/tavily-ai/tavily-python?tab=readme-ov-file#tavily-search

We'll create follow up issues for a TavilyCrawler component based on https://github.com/tavily-ai/tavily-python?tab=readme-ov-file#tavily-crawl and potentially also for https://github.com/tavily-ai/tavily-python?tab=readme-ov-file#tavily-research

If you would like to contribute, please refer to https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md#create-a-new-integration for instructions on how to easily add a new integration.

Integration tests can use an API key but the number of requests done in integration tests should be very limited and the focus should be on unit tests.

Tasks that need to be completed before closing this issue

• The code is documented with docstrings and was merged in the main branch
• There is a Github workflow running the tests for the integration nightly and at every PR
• A new label named like integration:<your integration name> has been added to the list of labels for this repository
• The labeler.yml file has been updated
• The package has been released on PyPI
• The integration has been listed in the Inventory section of this repo README
• Docs are published at https://docs.haystack.deepset.ai/
• An integration tile with a usage example has been added to https://github.com/deepset-ai/haystack-integrations
• The feature was announced through social media