Use the EmbedClient.V2Client class to create embeddings for text, images, audio, video, and documents. Embeddings are vector representations that enable semantic search and content understanding.

Choose a method

• To embed a query for retrieving matching content, use the embed.v_2.create method. It returns the result immediately and accepts text, images, and audio or video up to 30 seconds with Marengo 3.5.
• To embed content at scale, such as the media files you want to make searchable, use the embed.v_2.tasks.create method. It runs in the background and accepts audio, video, images, and documents.