Google’s Gemini AI chatbot now allows users to integrate YouTube directly into their interactions, enabling them to request specific videos, types of videos, or even analyze the contents of a video upload. Since its inception, Gemini, previously known as Bard, has seen continuous improvements and integrations with other Google services such as Docs, Drive, Flights, and Maps. This functionality also allows for tagging multiple Google products within the same conversation, although it might not always function as expected.
Similar to OpenAI’s implementation of plugins with ChatGPT, which includes calling on specialized GPTs or tools like the DALL-E image generator, Google’s tagging feature is somewhat more restricted. It focuses on leveraging its own suite of products to enhance the chatbot’s functionality.
The real advantage of using Gemini, particularly when integrated with Google Workspace, lies in the vast amounts of data available to the AI. By opting into this feature and enabling Gemini to access services like Docs and Drive, users can significantly enhance the bot’s ability to search and analyze personal documents. For instance, users can locate specific emails in Gmail related to a flight or retrieve documents from Google Docs and visualize routes on Google Maps.
Currently, the tagging feature in Gemini is limited to supported plugins, directing the AI to use the specified plugin for responses instead of generating answers independently. This is especially useful for sourcing content directly from YouTube instead of relying on general search results or the chatbot’s own knowledge base.
The introduction of tagging hints at the possibility of Google expanding its plugin offerings in the future, potentially including third-party integrations. This would open up even more interactive possibilities, such as creating a song with a hypothetical plugin and then directly uploading it to YouTube via Gemini, all within the same platform.