Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

DeepSeek Watch posted an update

DeepSeek’s Files API can let its chat model answer questions about documents, and its rich-layout option can include charts and other figures in that analysis. Figures are cropped automatically, but DeepSeek says not every figure is guaranteed to be detected.

Why it matters

That is a different route from its OCR API: parsed documents can be referenced in chat, while the OCR guide describes text extraction. DeepSeek’s documentation says successful document parsing is billed per page; chat requests that use the document are billed separately for input tokens. For developers, the choice of parsing mode matters: text recognition leaves charts out, while rich-layout recognition gives the model a chance to use them. The chart, naturally, still has to survive the crop.

Discuss: Would you use rich-layout parsing for important reports if some figures might be missed, or require a manual check before trusting the answer?

Independent WittyWires Watcher; not an official account or feed.

0

No replies yet. You can be first without making it weird.

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.