Draw a box on the document — text will be extracted automatically
No documents loaded — upload one to create a template
No document
1 / 1
Upload a document to begin
Upload target document(s)
Multiple files supported · PDF · PNG · JPG · WEBP
Run History
0
No runs yet — completed runs will appear here with download links.
Frequently Asked Questions
Everything you need to know about DocumentChimp, OCR, templates, and privacy.
Yes — DocumentChimp is 100% free with no hidden costs, subscriptions, credit limits, watermarks, or sign-ups. You can use it as often as you like for personal or commercial purposes.
No. All processing — including PDF rendering, OCR, and template matching — happens entirely inside your browser using JavaScript and WebAssembly. Your files never leave your device and are never transmitted over the network.
DocumentChimp does not save, log, or track your documents, extracted text, or templates. Everything exists only in your browser's memory for the duration of your session. Closing or refreshing the page clears everything.
A template identifier is a short string you assign to a template (for example, "INV" or "PO-2024"). When the "Use identifier matching" checkbox is enabled in the Extract Data tab, DocumentChimp checks each queued filename for a matching identifier and automatically applies the corresponding template. If no identifier matches a file, the template currently chosen in the dropdown is used as the fallback.
Yes. Click the Export button in the Templates header to export every saved template as a single JSON file. That file can later be re-imported via the Import button next to it, restoring every template at once.
Yes. Click the Import button next to the Export button in the Templates header to import one or more templates you previously downloaded. Every imported template becomes available in the dropdown, keeps its original name and identifier, and can be used for batch extraction just like one created in the app.
You can upload PDFs and common image formats including PNG, JPG/JPEG, WEBP, and BMP. Multi-page PDFs are fully supported — you can navigate between pages and draw regions on any page.
When you upload a multi-page PDF, page navigation controls appear in the toolbar. Each region you draw is tagged with the page number it belongs to. When you save a template or run batch extraction, each region is automatically extracted from the correct page.
DocumentChimp uses Tesseract.js, one of the most widely used open-source OCR engines. Accuracy depends on image resolution, contrast, and font clarity. For best results, upload high-resolution scans and draw boxes with a little padding around the text you want to capture.
Once the page and its libraries have loaded, DocumentChimp can keep working without an active internet connection. The initial page load fetches the OCR engine and PDF renderer, but everything after that runs locally.
DocumentChimp is designed from the ground up to keep your documents and data private.
No uploads, ever
Your PDFs, images, and extracted text never leave your device. There is no backend server that receives or stores your documents.
No tracking
No analytics, no fingerprinting, no third-party cookies. We don't know who you are and we don't want to.
No persistence
Documents and templates exist only in your browser's memory. Refreshing or closing the tab clears everything immediately.
Local processing
PDF rendering (PDF.js) and OCR (Tesseract.js) both run in your browser via WebAssembly. No computation happens on a remote machine.
You control exports
Templates are only shared when you explicitly download them as JSON files. No data is ever sent anywhere automatically.
Open, transparent stack
DocumentChimp is built on well-known open-source libraries. You can audit everything with your browser's developer tools.
Terms of Service
Plain-language terms for using DocumentChimp Workbench. By using this site you agree to the terms below.
Free to use
DocumentChimp is provided free of charge, as-is, and without warranty of any kind. You may use it for personal or commercial purposes.
Your responsibility
You are responsible for the documents you process and for ensuring you have the right to use them. Do not use DocumentChimp to process content you do not have permission to handle.
Acceptable use
You agree not to use DocumentChimp for unlawful purposes, to infringe intellectual property rights, or to process material that is illegal in your jurisdiction.
No liability
DocumentChimp is provided without any guarantee of accuracy, availability, or fitness for a particular purpose. We are not liable for any loss arising from its use, including OCR errors or missed extractions.
Changes to the service
Features may be added, changed, or removed at any time. These terms may be updated; continued use of the site after changes means you accept the revised terms.
Contact
Questions about these terms? Email documentchimp@gmail.com.
Guides & Tips
Practical articles about OCR template extraction, batch processing, and getting the best results from DocumentChimp.
Tutorial 5 min
Building your first OCR template
A step-by-step walkthrough for drawing regions on an invoice, naming them clearly, and saving the layout so it can be reused on dozens of similar documents. Covers the difference between the Create Template and Extract tabs, why region names matter, and how to export a template for backup.
Tutorial 4 min
Using identifiers to match templates automatically
How the template identifier works, why naming conventions in your filenames matter, and how to configure a batch of mixed invoices, receipts, and purchase orders so each document automatically finds the right template without manual selection.
Workflow 6 min
Batch-extracting hundreds of documents
Best practices for large runs: grouping files by template, using the queue in stages, monitoring progress with the run counter, and downloading results as JSON for downstream processing. Includes tips for keeping memory usage reasonable during multi-page PDF runs.
Quality 5 min
Improving OCR accuracy on scans
Why scan quality dominates OCR results, how padding around a region affects recognition, when to use higher-resolution inputs, and what to do when a region returns empty. Practical advice drawn from real invoice and receipt extraction tests.
Reference 3 min
Understanding the template JSON format
A field-by-field reference for the exported template JSON: name, identifier, pageCount, documentSize, and the region array with its coordinates. Explains how imported templates are renamed, why templates store coordinates rather than values, and how to hand-edit a template file safely.
Workflow 4 min
Handling multi-page PDFs with page-tagged regions
How regions are tagged with the page they belong to, how to draw on different pages of the same PDF, and what happens during extraction when a template spans several pages. Includes guidance on structuring templates for long documents such as contracts or statements.
Privacy 3 min
Why local processing matters for sensitive documents
An explanation of what it means for OCR and PDF rendering to run entirely in your browser, why that keeps confidential paperwork off any server, and how to verify the behavior yourself using the browser's developer tools and network panel.
Tips 2 min
Ten small tips that save time
Short, practical habits: naming regions consistently, drawing slightly larger regions than the text, using the zoom control before drawing, previewing a template against a sample file, keeping a backup of exported templates, and other quick wins gathered from daily use.
Advertisement
Save as template
Optional string to match against filenames when "Use identifier matching" is enabled.
This template contains 0 regions.
Templates store region names, page numbers, coordinates, and the identifier — not the extracted values.
Clear all documents
Are you sure you want to remove all documents?
Any templates created from these documents will also be removed.