{"slug": "how-to-build-scalable-web-apps-with-openai-s-privacy-filter", "title": "How to build scalable web apps with OpenAI's Privacy Filter", "summary": "Three scalable web applications—a Document Privacy Explorer, an Image Anonymizer, and a SmartRedact Paste tool—all built using OpenAI's Privacy Filter model and Gradio's Server infrastructure. The Privacy Filter is a 1.5B-parameter, Apache 2.0-licensed model that detects and redacts PII categories like names, addresses, and account numbers, achieving state-of-the-art performance on the PII-Masking-300k benchmark. Gradio's Server enables these apps by pairing custom HTML/JS frontends with backend features like queueing, ZeroGPU allocation, and a client SDK, allowing for efficient single-pass processing of up to 128,000 tokens.", "body_md": "How to build scalable web apps with OpenAI's Privacy Filter\n- Document Privacy Explorer: drop in a PDF or DOCX, read the document back with every PII span highlighted in place.\n- Image Anonymizer: upload an image, get it back with redacted black bars over names, emails, and account numbers. The image is also editable on a canvas so you can make your own annotations before downloading.\n- SmartRedact Paste: paste sensitive text, share a public URL that serves the redacted version, keep a private reveal link for yourself.\nAll three are built on gradio.Server, which lets you pair custom HTML/JS frontends with Gradio's queueing, ZeroGPU allocation, and gradio_client\nSDK. In all these apps, gradio.Server\nplays the same backend role, and that consistency is exactly what makes it really powerful.\nThe model\nPrivacy Filter is a 1.5B-parameter model with 50M active parameters, permissively licensed under Apache 2.0. PII categories are private_person\n, private_address\n, private_email\n, private_phone\n, private_url\n, private_date\n, account_number\n, secret\n. Context is 128,000 tokens. Achieves state-of-the-art performance on the PII-Masking-300k benchmark. Full numbers and methodology are in the official release blog.\n1. Document Privacy Explorer\nTry it at ysharma/OPF-Document-PII-Explorer.\nUser problem. You want to read a PII-heavy document (a contract, a resume, an exported chat log) with every detected span highlighted by category, a filter in the sidebar, and a summary dashboard up top. The reading experience should feel like a normal document, not a form.\nWhat Privacy Filter does here. The whole file goes through in a single 128k-context forward pass, so there's no chunking, no stitching, and span offsets line up directly with the rendered text. BIOES decoding keeps span boundaries clean through long ambiguous runs.\nWhat gr.Server\ndoes here. You could wire this up in Blocks with gr.HighlightedText\nand a sidebar, and it would work. The reading experience we wanted (serif body, category filters that toggle CSS classes client-side instead of re-running the model, a summary dashboard that doesn't force a page re-render) was easier to hand-author than to compose. gr.Server\nlets us serve the reader view as a single HTML file and expose the model behind one queued endpoint:\nimport gradio as gr\nfrom fastapi.responses import HTMLResponse\nfrom gradio.data_classes import FileData\nserver = gr.Server()\n@server.get(\"/\", response_class=HTMLResponse)\nasync def homepage():\nreturn FRONTEND_HTML # reader view; see app.py\n@server.api(name=\"analyze_document\")\ndef analyze_document(file: FileData) -> dict:\ntext = extract_text(file[\"path\"]) # PyMuPDF / python-docx\nsource_text, spans = run_privacy_filter(text) # single 128k pass\nreturn {\n\"text\": source_text,\n\"spans\": spans, # [{start, end, label}, ...]\n\"stats\": compute_stats(source_text, spans),\n}\nNote the decorator: @server.api(name=\"analyze_document\")\n, not a plain @server.post\n. That's the piece that plugs the handler into Gradio's queue, so concurrent uploads are serialized, @spaces.GPU\ncomposes correctly on ZeroGPU, and the same endpoint is reachable from both the browser and gradio_client\nwith no duplicated code. The browser calls it with the Gradio JS client:\n\n2. Image Anonymizer\nTry it at ysharma/OPF-Image-Anonymizer.\nUser problem. You want to share an image or any screenshot (a Slack thread, a receipt, a Stripe dashboard) with black bars over the PII. You want to toggle bars on and off, drag them to reposition, or draw one by hand for anything the model missed, then export the result.\nWhat Privacy Filter does here. Tesseract runs OCR and returns per-word bounding boxes. The backend reconstructs the full text with a char-offset to box map, then runs Privacy Filter once over the whole text. Detected character spans are looked up against the word map and joined into pixel rectangles per line.\nWhat gr.Server\ndoes here. gr.ImageEditor\nsupports layered annotation and is a reasonable starting point for image redaction. The workflow we wanted (per-bar category metadata, toggle all bars in a category at once, client-side PNG export at natural resolution with no server round-trip) was cleaner to build on a custom