Phase 1 · Building with LLMs · Context & retrieval
Images and documents
Send screenshots, PDFs and charts as input.
Open this lesson Create a free account
Why it matters
A lot of marketing information lives in pictures and PDFs: screenshots of ad dashboards, competitors' landing pages, charts in a report, invoices, scanned survey forms. Models that read images and documents turn those into data your code can use, without anyone retyping numbers. Sending them is just a different kind of content block in the same request you already know.
What you'll be able to do
- Send an image or a PDF to the model alongside a question
- Encode files as base64 and pick the right media type
- Estimate the tokens an image will use
- Spot good uses for vision in marketing work, and its limits
Before this lesson
Next in this phase: Embeddings