# Chat with a Spreadsheet — Ask Questions About Excel or CSV Data > Ask questions about a spreadsheet in plain English and get answers with the sheet and row they came from. Runs entirely in your browser. Chat with Excel & CSV reads a spreadsheet in your browser and turns each row into a passage with its column headers attached, so "Region: North; Revenue: 41200" is what gets indexed rather than a bare list of values. Questions are answered from the rows closest in meaning to what you asked, each cited by sheet and row number. It is built for looking things up and reading rows back in plain English, not for aggregation — it will find the row describing a figure, but it will not sum a column. **URL:** https://convertto.tech/t/chat-with-excel **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:** XLSX, XLS, CSV and TSV, with the first row treated as headers - **Citations:** Sheet name and row number - **Good at:** Finding and reading back specific rows - **Not built for:** Sums, averages and other aggregation across many rows - **Privacy:** Runs entirely in your browser — nothing is uploaded - **Cost:** Free, unlimited, no sign-up ## How to use 1. Select your excel & csv 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 ### Can it total a column or work out an average? No, and it will not pretend to. Only the handful of rows closest to your question are given to the model, so any total it produced would be over a fraction of the data and would look exactly like a real one. Use a spreadsheet formula for arithmetic; use this for finding the rows that matter and reading them back in plain English. ### Why does it need a header row? Each row is indexed with its column names attached, so the passage reads "Region: North; Revenue: 41200" rather than "North; 41200". Without headers a number carries no indication of what it measures, and neither retrieval nor the answer model can recover it. ### How many rows can it handle? Several thousand is workable, though indexing time grows with the row count and it all happens up front. Very large exports are better filtered down to the columns and rows you care about first — retrieval quality improves too, because there is less near-identical text to choose between. ### 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 - [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. - [ASCII Table Formatter](https://convertto.tech/t/ascii-table-formatter): Turn CSV or tab-separated text into an aligned plain-text, Markdown or box-drawing table. - [Chat with PDF](https://convertto.tech/t/chat-with-pdf): 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. - [CSV Analyser](https://convertto.tech/t/csv-analyser): Profile a CSV: column types, missing values, ranges, distinct counts and outliers. - [CSV Column Extractor](https://convertto.tech/t/csv-column-extractor): Pull selected columns out of a CSV by name or position, and reorder them. - [CSV Duplicate Remover](https://convertto.tech/t/csv-deduplicator): Remove duplicate rows from a CSV, matching on every column or just a key you choose. - [CSV Merger & Joiner](https://convertto.tech/t/csv-merger): Join two CSV files on a shared key, or stack them, with inner, left and outer joins.