AI PDF Annotator

About

AI PDF Annotator — Smart PDF Reader with AI-Powered Annotations

Read, annotate, and understand PDFs with the help of AI. Select any text or take a screenshot, ask a question, and get instant AI explanations right on your document.

🔹 Core Features:
- Text Selection Q&A — Select text in PDF, click "Ask", get AI explanation instantly
- Screenshot Q&A — Capture any area (diagrams, formulas, charts) and ask AI to explain
- Capture Pages — Render multiple pages as a single image for AI analysis
- Persistent Annotations — All Q&A pairs are saved per PDF, restored on reload
- Follow-up Questions — Continue asking within each annotation's context
- Smart Context — Only sends first + last conversation turn to save API tokens
- 4 Themes — Dark, Light, Sepia, Green

🔹 AI Providers:
- OpenAI API (GPT-4o, GPT-4.1, o4-mini)
- Claude API (Sonnet 4, Haiku 4.5)
- Ollama (local models — llama, qwen, deepseek, etc.)
- Custom endpoint (LM Studio, vLLM, or any OpenAI-compatible API)

🔹 Privacy-First:
- Your API keys are stored locally, never sent to any third-party server
- All data stays in your browser (chrome.storage)
- No analytics, no tracking, no ads
- CORS handled automatically for local AI servers — no manual configuration needed

🔹 How It Works:
1. Open any PDF (online or local file)
2. The extension automatically opens it in the built-in reader
3. Select text → click "Ask" → AI explains it in the sidebar
4. Or use Screenshot/Capture Pages for images, diagrams, formulas
5. All annotations are saved and can be revisited anytime

Bring your own API key. Supports both cloud AI (OpenAI, Claude) and fully offline local models (Ollama). Your documents and conversations never leave your device.

---

AI PDF 智能标注 — AI驱动的PDF阅读与标注工具

选中文字或截图，一键向AI提问，答案直接标注在PDF上。

主要功能：
- 选中文字提问，AI即时解释
- 截图提问，支持图表、公式、流程图
- 多页捕获，生成长图发送给AI分析
- 标注自动保存，刷新后恢复
- 每个标注独立上下文，支持追问
- 智能省token策略，节省API费用
- 4种阅读主题

支持的AI服务：OpenAI、Claude、Ollama本地模型、自定义API端点

隐私优先：API密钥本地存储，数据不出浏览器，无追踪无广告。