Ask about a PDF
Q&A and summaries generated by a local AI server you run (Ollama / LM Studio), grounded in the open document.
Chat with PDF answers questions and writes summaries using a model on YOUR machine — an Ollama or LM Studio server you connect yourself. Document excerpts are sent only to that server, never to a cloud. Without a connected server this tool explains what's missing rather than generating anything; PDFMacro's built-in on-device models search and detect, they don't generate.
Needs a live connection every time it runs — see the note beside this about where the request goes.
Document excerpts go only to the local AI server you explicitly connect (your own machine). Nothing goes to PDFMacro or any cloud service.
Typed into the workspace command bar, any of these opens this tool. They are the assistant's own routing examples, not a rewrite of them.
Also called: chat with pdf · ask the document · question the pdf · summarize pdf · summarise pdf · summary of this document · ollama · lm studio · local llm