PrivyPDF

Overview

Understand and chat with your PDFs—privately.

PrivyPDF is a local-first macOS app that turns your PDFs into a searchable, question-answerable knowledge base. All processing runs on your Mac. Your documents and embeddings stay in your App Sandbox; no data is sent to the cloud. Think of it as your local knowledge asset entry and a PDF-dedicated copilot.

Features

• Import — Add PDFs via Import or drag-and-drop
• Parse & Index — Extract text and build a local vector index using your own Ollama server
• Ask — Type questions in natural language and get answers with source citations; responses stream in as they’re generated
• Jump — Tap a citation to jump to the exact page (and region) in the PDF preview
• Export — Export document text as Markdown or JSON for use elsewhere

Assistant replies support Markdown (bold, lists, code, and more). Resize the Documents or Q&A panels to focus on the PDF preview.

Advantages

PrivyPDF stores PDFs, extracted text, and indexes only in the app sandbox. AI runs through your own Ollama server, the app does not ship model weights, and document Q&A does not require an account, telemetry, or external document-processing service.

Benefits

Find answers in long PDFs faster, verify claims through citations, jump back to source pages, and preserve private document workflows for contracts, research, technical manuals, and internal knowledge.

Requirements

• macOS 14.6 or later
• Ollama — Installed and running locally, with at least one embedding model (e.g. qwen3-embedding:0.6b or nomic-embed-text) and one chat model (e.g. qwen2.5:7b-instruct). Configure the base URL and models in PrivyPDF → Settings. Download at ollama.ai

Who it's for

• Developers and engineers who want to query technical docs offline
• Researchers and knowledge workers who need citations and local control
• Enterprise knowledge workers and anyone who values privacy and wants a PDF copilot that never uploads their data