How to build scalable web apps with OpenAI's Privacy Filter

Summary

The article presents three web applications built around OpenAI’s open-source Privacy Filter, a PII detector that labels eight categories in one forward pass over a 128k-token context. Document Privacy Explorer extracts PDF or DOCX text and returns category-labeled spans, while Image Anonymizer combines Tesseract word boxes with character offsets to produce editable pixel redaction rectangles. SmartRedact Paste replaces detected spans with category placeholders, stores public and token-gated views, and evicts expired pastes in a daemon thread. Across the apps, gradio.Server’s @server.api routes model work through Gradio’s queue and gradio_client, while plain FastAPI routes serve custom HTML, views, and lightweight lookups. The implementations keep browser-side filtering, canvas edits, and PNG export out of server round-trips, and the paste service is about 200 lines including storage.

Takeaways

1. 1

   Privacy Filter has 1.5B parameters, 50M active parameters, an Apache 2.0 license, eight PII categories, and a 128,000-token context.

2. 2

   @server.api connects model handlers to Gradio queueing, ZeroGPU composition, progress events, and gradio_client access from both browser and Python clients.

3. 3

   Image Anonymizer maps Privacy Filter’s character spans back to OCR word boxes, joins them into pixel rectangles, and keeps bar edits and PNG export in the browser.