Glossary · Phase 1 · Building with LLMs
Multimodal
Able to work with more than text, such as images, documents or audio.
Try it now
An image is just another kind of block in the same message.
Learn it properly
Images and documents · Send screenshots, PDFs and charts as input. About 25 minutes.
Other terms from the same lesson
- base64: A way to write any file, such as an image, as plain text so it can travel inside a JSON request. It makes the data about a third bigger.
- content block: One piece of a message sent to a model, such as a stretch of text, an image or a PDF. A message can hold several.
Never trained an AI?
Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.