<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/3f9b5c53d6c84fa89e7498a3ce7f1b99&quot; frameborder=&quot;0&quot; width=&quot;1728&quot; height=&quot;1296&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1296</height><width>1728</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1296</thumbnail_height><thumbnail_width>1728</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/3f9b5c53d6c84fa89e7498a3ce7f1b99-c87bb32bb1848660.gif</thumbnail_url><duration>279.5916</duration><title>Exploring the New Gemini Live Integration with LlamaIndex</title><description>In this video, I introduced our new Gemini Live integration and demonstrated how to use a simple script to interact with the voice agent. We imported the Gemini Live voice agent, instantiated it with default parameters, and utilized a weather tool to provide a mock weather forecast for San Francisco. During our conversation, the agent reported the weather as 16.2°C with 64% humidity and a 61% chance of precipitation. I also highlighted that the messages were empty, confirming our expectation of an audio-only interaction. I encourage you to try running the script yourself to explore the capabilities of the Gemini Live agent.</description></oembed>