# Chat with a PDF — Ask Questions, Get Answers With Page Numbers > Ask questions about any PDF and get answers with the page each one came from. The model runs in your browser — the file is never uploaded. Chat with PDF reads a PDF in your browser, splits it into passages, indexes them with a sentence-embedding model, and answers your questions from the passages closest to what you asked — showing each passage and its page number beside the answer. The whole pipeline, retrieval and answering alike, runs on your own device, so the file is never uploaded and no API key or account is needed. It answers questions whose answer is stated in the document, and says it cannot find it rather than guessing when it is not. **URL:** https://convertto.tech/t/chat-with-pdf **Category:** On-Device AI (https://convertto.tech/c/local-ai-tools) **Privacy:** Runs entirely in the browser; no upload **Cost:** Free, no sign-up **Last updated:** 2026-08-01 ## Key facts - **Accepts:** PDF with a text layer. Scanned pages need OCR first - **Citations:** Every answer shows the passages and page numbers it came from - **Uploads:** None — parsing, indexing and answering all happen in your browser - **Cost:** Free, with no API key, account or per-question charge - **Privacy:** Runs entirely in your browser — nothing is uploaded ## How to use 1. Select your pdf file — the file stays on your device and is never uploaded. 2. Enter or paste your question. 3. Choose the answer model. 4. Press Run, then download the result when it is ready. ## FAQ ### Why does it say my PDF has no text? Because it is a scan — a photograph of pages rather than a document. There is nothing to read and no amount of indexing will help. Run it through the PDF OCR tool first to add a text layer, then chat with the result. ### Can it tell me which page an answer came from? Yes, and it always does. Passages keep their page number through splitting and indexing, so every answer arrives with the page and the exact text it was drawn from. A local model of this size is wrong often enough that an answer you cannot check is not worth much. ### How large a PDF can it handle? A few hundred pages is realistic on a laptop. Indexing time grows with length — it is roughly linear, at a second or two per ten pages once the model is loaded — and it all happens once, before the first question. Very long documents are better split first. ### Is my document uploaded anywhere? No. The file is read, split, indexed and answered entirely inside this browser tab. The only thing downloaded is the model itself, from Hugging Face, and that happens once and is then cached. Nothing about your document goes the other way — which is the point of using this rather than a service on a contract, a payslip or a medical letter. ### How does it answer questions about a document too long for the model to read? The document is split into passages and each one is turned into a vector that captures its meaning. Your question is turned into a vector the same way, the closest few passages are found by comparing them, and only those passages are given to the answer model. This is the same retrieval-augmented approach the hosted services use; the difference is that here the retrieval and the answering both happen on your device. ### How accurate is it? It is a model between 65 and 400 megabytes, which is one to four orders of magnitude smaller than a hosted assistant. It is good at pulling out a fact that is stated plainly in one place and much weaker at questions requiring several parts of the document to be combined, or at anything needing judgement. That is exactly why the passages behind every answer are shown with it — the answer is a shortcut to the right paragraph, not a substitute for reading it. ### What happens if the document does not contain the answer? It says so rather than inventing one. Two separate checks make that possible: if no passage is even topically close to the question, the question is never put to the model at all, and when the extractive model is used its confidence is thresholded, because that model always returns its best guess and only its low confidence distinguishes a guess from an answer. ### Do I need an API key or an account? Neither. There is no key to obtain, no sign-up, no quota and no per-question cost. The trade is that the models are small enough to run on your own hardware, and answer quality reflects that. ### Does it work offline? After the first run, yes. The model is cached by the browser, so a second visit works with no network at all. The first visit has to download it. ## Sources - [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://arxiv.org/abs/2005.11401) — arXiv - [transformers.js — running Hugging Face models in the browser](https://huggingface.co/docs/transformers.js) — Hugging Face ## Related tools - [Add Page Numbers to PDF](https://convertto.tech/t/add-page-numbers-pdf): Number the pages of a PDF with a custom start, position and format. - [Chat with Any Document](https://convertto.tech/t/chat-with-document): Ask questions about a PDF, Word file, spreadsheet, CSV, Markdown or text file and get answers with the passage each came from. - [Chat with Word Document](https://convertto.tech/t/chat-with-word): Ask questions about a Word document and get answers with the heading each came from. Runs on your device — nothing is uploaded. - [Merge PDF](https://convertto.tech/t/merge-pdf): Combine several PDF files into one document, in your browser and without uploading. - [PDF to BMP Converter](https://convertto.tech/t/pdf-to-bmp): Convert PDF pages into uncompressed 24-bit BMP bitmaps. - [PDF to CSV Converter](https://convertto.tech/t/pdf-to-csv): Extract PDF tables into properly quoted CSV, one row per table row. - [PDF to DOCX Converter](https://convertto.tech/t/pdf-to-docx): Export PDF document content into 100% editable Microsoft Word DOCX format. - [PDF to Ebook Converter](https://convertto.tech/t/pdf-to-ebook): Turn a PDF into a reflowable ebook you can read comfortably on a phone or e-reader. - [Chat with Excel & CSV](https://convertto.tech/t/chat-with-excel): Ask questions about a spreadsheet in plain English and get answers with the sheet and row they came from. Runs entirely in your browser.