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

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

Hugging Face

Models

Datasets

Spaces

Buckets new

Docs

Enterprise

Pricing

Log In

Sign Up

Back to Articles

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

Published April 27, 2026

Update on GitHub

Upvote

7

+1

yuvraj sharma

ysharma

Follow

Freddy Boulton

freddyaboulton

Follow

Abubakar Abid

abidlabs

Follow

The model

1. Document Privacy Explorer

1. Image Anonymizer

1. SmartRedact Paste

gradio.Server provides">What gradio.Server provides

Try them

Recommended reading

OpenAI released Privacy Filter on the Hub this week: an open-source personally-identifiable information (PII) detector that labels text across eight categories in a single forward pass over a 128k context. Model card. We spent a few hours building with it and landed on three apps that each reveals a different slice of what it can do.

Document Privacy Explorer: drop in a PDF or DOCX, read the document back with every PII span highlighted in place.

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.

SmartRedact Paste: paste sensitive text, share a public URL that serves the redacted version, keep a private reveal link for yourself.

All three are built on gradio.Server, which lets you pair custom HTML/JS frontends with Gradio's queueing, ZeroGPU allocation, and gradio_client SDK. In all these apps, gradio.Server plays the same backend role, and that consistency is exactly what makes it really powerful.

The model

Privacy Filter is a 1.5B-parameter model with 50M active parameters, permissively licensed under Apache 2.0. PII categories are private_person, private_address, private_email, private_phone, private_url, private_date, account_number, secret. 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.

1. Document Privacy Explorer

Try it at ysharma/OPF-Document-PII-Explorer.

User 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.

What 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.

What gr.Server does here. You could wire this up in Blocks with gr.HighlightedText and 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 lets us serve the reader view as a single HTML file and expose the model behind one queued endpoint:

import gradio as gr from fastapi.responses import HTMLResponse from gradio.data_classes import FileData

server = gr.Server()

@server.get("/", response_class=HTMLResponse) async def homepage(): return FRONTEND_HTML # reader view; see app.py

@server.api(name="analyze_document") def analyze_document(file: FileData) -> dict: text = extract_text(file["path"]) # PyMuPDF / python-docx source_text, spans = run_privacy_filter(text) # single 128k pass return { "text": source_text, "spans": spans, # [{start, end, label}, ...] "stats": compute_stats(source_text, spans), }

Note the decorator: @server.api(name="analyze_document"), not a plain @server.post. That's the piece that plugs the handler into Gradio's queue, so concurrent uploads are serialized, @spaces.GPU composes correctly on ZeroGPU, and the same endpoint is reachable from both the browser and gradio_client with no duplicated code. The browser calls it with the Gradio JS client:

1. Image Anonymizer

Try it at ysharma/OPF-Image-Anonymizer.

User 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.

What 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.

What gr.Server does here. gr.ImageEditor supports 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 frontend. gr.Server hands back pixel rectangles from one queued endpoint and lets the canvas own everything else:

@server.api(name="anonymize_screenshot") def anonymize_screenshot(image: FileData) -> dict: img = Image.open(image["path"]).convert("RGB") full_text, char_to_box = ocr_image(img) # per-word boxes + char map spans = run_privacy_filter(full_text) boxes = spans_to_pixel_boxes(spans, char_to_box) return { "image_data_url": pil_to_base64(img), "width": img.width, "height": img.height, "boxes": boxes, # [{x, y, w, h, label, text}, ...] }

The frontend invokes it with client.predict("/anonymize_screenshot", { image: handle_file(file) }), the same pattern as above. Toggles, drags, new-bar drawing, and PNG export all happen in the browser; edits never round-trip to the server.

1. SmartRedact Paste

Try it at ysharma/OPF-SmartRedact-Paste.

User problem. You want a pastebin that redacts before sharing. You paste a log line, an email, a support ticket. You get two URLs back. The public one serves the redacted version with , , placeholders, following the redaction convention from the official blog examples. The private one is gated by a token you keep and shows the original with spans highlighted.

What Privacy Filter does here. Swap each detected span with a placeholder on the stored paste. That's the entire redaction step. Multilingual text (Spanish, French, Chinese, Hindi, and others in the model-card examples) routes through the same call with no change.

What gr.Server does here. This app needs two distinct GET routes for the same paste ID, one public and one token-gated, and the URL shape matters because the reveal URL is the thing you keep. gr.Server works here because it's a FastAPI app underneath — which is also why @server.api and plain @server.get can sit side by side in the same process. Note: this can also be built with gr.Blocks() by mounting custom routes with FastAPI :

Model call → queued endpoint. Hit from the browser via

client.predict("/create_paste", { text, ttl }).

@server.api(name="create_paste") def create_paste(text: str, ttl: str = "never") -> dict: source_text, spans = run_privacy_filter(text) redacted = redact(source_text, spans) # placeholders pid, reveal_token = secrets.token_urlsafe(6), secrets.token_urlsafe(22) PASTES[pid] = Paste(pid, reveal_token, source_text, redacted, spans, expires_at=_ttl(ttl)) # see app.py return { "view_path": f"/view/{pid}", "reveal_path": f"/view/{pid}?token={reveal_token}", }

View page → plain FastAPI GET. No model, no queue needed, and we

actually want the bespoke URL shape /view/{pid}?token=... that a

queued endpoint couldn't give us.

@server.get("/view/{pid}", response_class=HTMLResponse) async def view_paste(pid: str, token: str | None = None): p = _store_get(pid) # see app.py for store if p is None: return HTMLResponse(_not_found(), status_code=404) revealed = bool(token) and secrets.compare_digest(token, p.reveal_token) return HTMLResponse(_render_view(p, revealed))

A daemon thread evicts expired pastes every 30 seconds. The whole service, including storage, is about 200 lines of application code because everything lives in one process.

What gradio.Server provides

The split across all three apps is the same — anything that touches the model goes through @server.api, everything else stays on plain FastAPI routes:

App Queued compute (@server.api) Plain FastAPI routes

Document Privacy Explorer analyze_document — extract, detect, stats GET / serves the custom reader view

Image Anonymizer anonymize_screenshot — OCR, detect, spans → pixel boxes GET / + GET /examples/* serve the canvas UI and preloaded examples

SmartRedact Paste create_paste — detect, redact, mint IDs GET / compose page, GET /view/{pid}?token=... public + token-gated views, GET /api/paste/{pid} JSON lookup

@server.api gives you Gradio's queue (serialized requests, correct @spaces.GPU composition on ZeroGPU, progress events) and it's what the browser hits through @gradio/client. The same endpoint is also what gradio_client users hit from Python — one function, two SDKs, no duplicated code. Plain @server.get/@server.post are reserved for the static surfaces: HTML pages, file lookups, cheap dict reads. That's the rule of thumb from the gradio.Server intro post, and it's what makes these three apps feel consistent even though their UIs are very different.

Try them

Document Privacy Explorer

Image Anonymizer

SmartRedact Paste

Drop in a resume, a screenshot of a Slack thread, a log line with a token in it. The fun part is seeing what Privacy Filter catches (and occasionally misses) on text you actually care about.

Recommended reading

OpenAI's release post: Introducing OpenAI Privacy Filter

Model card: openai/privacy-filter on Hugging Face

Redaction examples and taxonomy on Model card

Models mentioned in this article 1

openai/privacy-filter

Token Classification • 1B • Updated 14 days ago • 155k • 1.31k

Datasets mentioned in this article 1

ai4privacy/pii-masking-300k

Viewer • Updated Apr 4 • 225k • 6.93k • 96

More Articles from our Blog

gradioserveropen-source

Any Custom Frontend with Gradio's Backend

25

April 1, 2026

gradioclaudehtml

One-Shot Any Web App with Gradio's gr.HTML

33

February 18, 2026

Community

EditPreview

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Comment

· Sign up or log in to comment

Upvote

7

Models mentioned in this article 1

openai/privacy-filter

Token Classification • 1B • Updated 14 days ago • 155k • 1.31k

Datasets mentioned in this article 1

ai4privacy/pii-masking-300k

Viewer • Updated Apr 4 • 225k • 6.93k • 96

System theme

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs