Search...Search plugins and themes...
⌘K
Sign in
  • Get started
  • Download
  • Pricing
  • Enterprise
  • Account
  • Obsidian
  • Overview
  • Sync
  • Publish
  • Canvas
  • Mobile
  • Web Clipper
  • CLI
  • Learn
  • Help
  • Developers
  • Changelog
  • About
  • Roadmap
  • Blog
  • Resources
  • System status
  • License overview
  • Terms of service
  • Privacy policy
  • Security
  • Community
  • Plugins
  • Themes
  • Discord
  • Forum / 中文论坛
  • Merch store
  • Brand guidelines
Follow us
DiscordTwitterBlueskyThreadsMastodonYouTubeGitHub
© 2026 Obsidian

Lecture Lens

YimaYima290 downloads

Turn lecture PDFs and course materials into structured Markdown notes with LLM chat and RAG.

Add to Obsidian
  • Overview
  • Scorecard
  • Updates9

Turn lecture PDFs, slides, and screenshots into structured Obsidian notes — with BYOK AI chat, local course RAG, and source citations.

把课件 PDF、幻灯片截图变成 Obsidian 结构化笔记 — 附带 AI 聊天、课程 RAG 检索与来源引用。

Search keywords / 搜索关键词: PDF to Markdown · lecture notes · course assistant · AI chat · RAG · OCR · DeepSeek · Kimi · 课件 · PDF转笔记 · 大模型 · 课程助手 · 复习 · 识图

English · 中文 · Changelog · Community plugin page


What is Lecture Lens? / 这是什么?

English Lecture Lens is an Obsidian plugin for students and self-learners. It uses LLMs (DeepSeek, Kimi, OpenAI, Gemini, etc.) to convert lecture PDFs to Markdown, OCR slides and whiteboard photos, and answer questions in a chat sidebar — with optional local RAG over your course folder and clickable [[wiki link]] citations.
中文 Lecture Lens 是面向学生与自学者的 Obsidian 插件。接入大模型(DeepSeek、Kimi、OpenAI、Gemini 等),可 PDF 课件转 Markdown 笔记、识图/OCR 幻灯片与白板、在侧边栏 AI 聊天答疑,并可选对课程文件夹做 本地 RAG 检索,回答中带可点击的 [[双链引用]]。

Typical workflows / 典型场景

  • 📄 PDF lecture → notes — batch-convert course PDFs into structured Markdown with formulas and headings
    PDF 课件 → 笔记 — 批量将 PDF 转为含公式、标题的结构化 Markdown
  • 🖼️ Screenshot → notes — paste or attach slides; AI extracts text, LaTeX, and diagrams
    截图 → 笔记 — 粘贴或上传幻灯片,AI 提取文字、公式与图表
  • 💬 Course Q&A — chat with @ attached vault notes; streaming Markdown + math rendering
    课程问答 — @ 附加库内笔记后提问,流式 Markdown / 公式渲染
  • 🔍 RAG over your vault — index a course folder; retrieve relevant chunks and cite sources
    课程检索 — 对指定文件夹建索引,聊天时召回相关片段并标注来源

Demo

Chat & course Q&A · 聊天与课程问答

Chat and course Q&A demo

Ask in the chat sidebar with attached vault notes; replies stream as Markdown.

在聊天侧边栏结合 @ 附加笔记提问,回答流式渲染 Markdown。

Course RAG & sources · 课程 RAG 与来源引用

Course RAG demo with wiki link citations

Index a course folder, retrieve relevant note chunks, and cite sources inline with clickable [[wiki links]].

为课程文件夹建立索引,聊天时检索相关笔记片段,并在回答中用可点击的 [[wiki 链接]] 标注来源。

PDF → Markdown · PDF 转笔记

PDF to Markdown demo

Convert lecture PDFs into structured Markdown notes (single file or batch, with progress HUD).

将课件 PDF 转为结构化 Markdown 笔记,支持单文件或批量转换与进度显示。


English

Find it in Obsidian

In Settings → Community plugins → Browse, search for:

Lecture Lens · lecture · PDF · course · RAG · DeepSeek · Kimi · AI chat · OCR · notes

Direct link: obsidian.md/plugins?id=lecture-lens

Install

Recommended — Obsidian Community Plugins

  1. Open Settings → Community plugins.
  2. If this is your first plugin, turn off Restricted mode, then return to Community plugins.
  3. Click Browse, search Lecture Lens, and click Install.
  4. Back on the Community plugins page, enable Lecture Lens.
  5. Reload Obsidian (Cmd+R on macOS, Ctrl+R on Windows/Linux).

Alternative — manual install from GitHub

Use this only if you cannot access Community plugins or need a specific release build.

  1. Download main.js, manifest.json, and styles.css from the latest GitHub release.
  2. Put all three files into:
    <your-vault>/.obsidian/plugins/lecture-lens/
    
    The folder name must be lecture-lens.
  3. Enable Lecture Lens under Settings → Community plugins, then reload Obsidian.

Features

Feature Description
PDF → Markdown Convert one or many lecture PDFs to structured notes; editable output names, progress HUD
Image / slide OCR Paste screenshots or use context menu; AI writes Markdown with LaTeX and diagrams
Chat sidebar Streaming replies, Markdown/LaTeX/Mermaid, @ vault note context, image upload (VLM)
Course RAG Local embedding index over a course folder; semantic retrieval during chat
Source citations Assistant replies link to [[Note#Section]] in your vault
Vision relay Use Kimi/OpenAI for images + DeepSeek for text in one workflow
Multi-profile LLM Save several API configs; switch provider/model in the chat panel
Sessions Chat history per vault; rename, delete, switch sessions
BYOK Your API key only — presets for OpenAI, DeepSeek, Kimi (Moonshot), Gemini, Custom
i18n English / 中文 UI (follow Obsidian or choose manually)
Mobile Works on iOS/Android (embedding/PDF may download runtime files on first use)

Quick start

  1. Settings → Lecture Lens — add an LLM profile, enter API key, click Check connection
  2. Optional: set Course folder → Rebuild index for RAG
  3. Ribbon icons — glasses = open chat; document = PDF → Markdown
  4. In chat: type @ or use chips to attach notes; ask about your course

Commands

Command Action
Open Lecture Lens chat Opens the chat sidebar
Generate PDF notes Pick PDF(s) and convert to Markdown
Rebuild RAG index Re-index the course folder
Test LLM connection Verify API key and model

Supported providers (presets)

Provider Base URL Default model
OpenAI (official) https://api.openai.com/v1 gpt-5.6-terra
DeepSeek https://api.deepseek.com deepseek-v4-pro
Kimi (Moonshot) https://api.moonshot.cn/v1 moonshot-v1-8k-vision-preview
Gemini Google OpenAI-compatible endpoint gemini-2.0-flash
Custom Your endpoint Your model

OpenAI setup: create a key in the OpenAI Platform, select OpenAI (official), paste the key, and select Test this profile. Official profiles use the Responses API with store: false; cloud embeddings continue to use /embeddings.

Vision chat: use a VLM such as GPT-5.6, gpt-4o, Kimi *-vision-*, or enable Vision relay (Kimi reads images → DeepSeek answers).

Author-tested: DeepSeek for text (chat, PDF → Markdown); Kimi for vision / image uploads.

Who is this for?

  • University / high-school students organizing lecture slides and PDFs in Obsidian
  • Self-learners building a personal knowledge base from course materials
  • Anyone who wants local-first AI (notes stay in the vault) with BYOK LLM providers

FAQ

Do I need an API key?
Yes. The plugin calls LLM APIs you configure. No bundled cloud service.

Does it upload my whole vault?
No. The current note is attached by default and can be disabled globally or toggled per message. Lecture Lens sends only the context used for that request: notes you attach, relevant RAG excerpts from the configured Course folder, extracted PDF text, and images you add. It never uploads the entire vault.

Does PDF conversion work offline?
No. PDF → Markdown and chat require your configured LLM API. Local RAG embeddings run on-device after the selected model weights and runtime files are downloaded once; download size varies by model.

Windows / community plugin install issues?
Version 1.1.3+ auto-downloads missing ONNX/PDF worker files. First use needs network access.

Security & privacy

  • Local-first storage — chat history, RAG indexes, and model caches stay under .obsidian/lecture-lens/; plugin settings stay in Obsidian's plugin data file
  • Controlled context — the open note may be attached by default; you can disable it, remove it per message, and limit RAG to one course folder
  • Local vault access — file pickers, @ attachments, and RAG enumerate vault paths locally; file lists are never sent to a provider
  • Clipboard access — the plugin reads only images pasted into chat and writes only when you select Copy on a response
  • API keys — encrypted with Electron safeStorage on desktop when available; otherwise stored in the local plugin data file
  • OpenAI response storage — official OpenAI profiles send store: false on Responses API requests
  • No telemetry — Lecture Lens does not send analytics, vault names, or usage events

Automated review notes

  • Vault enumeration is used only for local PDF/note pickers and the course-folder RAG index; the resulting file list is never transmitted.
  • Clipboard access is limited to images the user pastes into chat and the explicit Copy action on a response.
  • Dynamic-code signatures come from the bundled Transformers.js/ONNX Web worker runtime. Lecture Lens uses its browser/WASM path and does not download or execute remote JavaScript.
  • The declarative settings API is currently an Obsidian 1.13 insider feature. Lecture Lens retains its existing settings UI while supporting Obsidian 1.8.7 and later; a complete dual-mode migration is planned rather than exposing an incomplete searchable settings page.
Network destination When it is used Data sent
Your configured LLM / embedding endpoint Chat, vision, PDF notes, or cloud embeddings API key and only the prompt/context required for that request
Your configured Hugging Face mirror Downloading a local embedding model Public model-file requests only; no note content
jsDelivr A required PDF.js or ONNX runtime file is missing Public runtime-file requests only; no note content

Development

git clone https://github.com/Yima-Gu/obsidian-lecture-lens.git lecture-lens
cd lecture-lens
npm ci
npm run dev

Copy or build into <vault>/.obsidian/plugins/lecture-lens/, enable the plugin, and reload. Run npm run check before opening a pull request. See AGENTS.md for contributor conventions.


中文

在 Obsidian 里怎么找到

打开 设置 → 第三方插件 → 浏览,搜索:

Lecture Lens · lecture · PDF · 课件 · 笔记 · RAG · DeepSeek · Kimi · 大模型 · AI · OCR · 课程

插件页:obsidian.md/plugins?id=lecture-lens

安装

推荐 — Obsidian 社区插件

  1. 打开 设置 → 第三方插件。
  2. 若是首次安装插件,先关闭 受限模式,再回到第三方插件页面。
  3. 点击 浏览,搜索 Lecture Lens,点击 安装。
  4. 返回第三方插件列表,启用 Lecture Lens。
  5. 重载 Obsidian(macOS:Cmd+R;Windows / Linux:Ctrl+R)。

备选 — 从 GitHub 手动安装

仅在无法使用社区插件、或需要指定版本时使用。

  1. 从 最新版 GitHub Release 下载 main.js、manifest.json 和 styles.css。
  2. 将这三个文件放入:
    <你的库>/.obsidian/plugins/lecture-lens/
    
    文件夹名必须为 lecture-lens。
  3. 在 设置 → 第三方插件 中启用 Lecture Lens,然后重载 Obsidian。

功能一览

功能 说明
PDF 转 Markdown 单个或批量转换课件 PDF;可编辑输出文件名,带进度面板
课件 / 截图 OCR 粘贴截图或右键分析;AI 生成含 LaTeX、图表的 Markdown
聊天侧边栏 流式回复,Markdown / 公式 / Mermaid;@ 附加笔记;可上传图片(需 VLM)
课程 RAG 对课程文件夹做本地向量索引,聊天时语义检索相关片段
来源引用 回答中插入可点击的 [[笔记#章节]] 双链
识图中继 Kimi/OpenAI 识图 + DeepSeek 文字回答,一条工作流搞定
多 API 配置 保存多套密钥与模型,聊天面板内切换
会话管理 按库保存聊天记录;重命名、删除、切换会话
自带 Key 仅使用你配置的 API;预设 DeepSeek、Kimi(月之暗面)、OpenAI、Gemini、自定义
中英界面 可跟随 Obsidian 语言或手动切换
移动端 支持 iOS / Android(首次使用嵌入/PDF 功能可能需下载运行时文件)

快速上手

  1. 设置 → Lecture Lens — 添加 LLM 配置、填写 API Key、点击 检查连接
  2. 可选:设置 课程文件夹 → 重建索引 启用 RAG
  3. 功能区图标 — 眼镜 = 打开聊天;文档 = PDF 转笔记
  4. 聊天中用 @ 或芯片附加笔记,向 AI 提问课程内容

命令

命令 作用
打开 Lecture Lens 聊天 打开聊天侧边栏
生成 PDF 笔记 选择 PDF 并转为 Markdown
重建 RAG 索引 重新索引课程文件夹
测试 LLM 连接 验证 API Key 与模型

支持的 API 提供商(预设)

提供商 Base URL 默认模型
OpenAI(官方) https://api.openai.com/v1 gpt-5.6-terra
DeepSeek https://api.deepseek.com deepseek-v4-pro
Kimi(月之暗面) https://api.moonshot.cn/v1 moonshot-v1-8k-vision-preview
Gemini Google OpenAI 兼容端点 gemini-2.0-flash
自定义 你的接口地址 你的模型名

OpenAI 配置: 在 OpenAI Platform 创建密钥,选择 OpenAI(官方),粘贴密钥后点击 测试此配置。官方配置使用 Responses API,并发送 store: false;云端嵌入仍调用 /embeddings。

识图聊天: 需 VLM(如 GPT-5.6、gpt-4o、Kimi *-vision-*),或开启 识图中继(Kimi 读图 → DeepSeek 回答)。

作者实测: DeepSeek 适合文字任务(聊天、PDF 转笔记);Kimi 适合识图 / 多模态上传。

适合谁用?

  • 在 Obsidian 里整理 课件 PDF、幻灯片 的大学生 / 高中生
  • 把网课、自学材料沉淀为 个人知识库 的自学者
  • 希望 笔记留在本地、自行配置 大模型 API 的用户

常见问题

需要 API Key 吗?
需要。插件只调用你配置的大模型接口,不提供内置云服务。

会上传整个库吗?
不会。默认会附加当前打开的笔记,你可以在设置中关闭,或在每次发送前移除。Lecture Lens 只发送本次请求需要的上下文:你附加的笔记、设定的 课程文件夹 中命中的 RAG 片段、PDF 提取文本,以及你主动添加的图片;不会上传整个库。

PDF 转换能离线吗?
不能。PDF 转笔记和聊天需调用你配置的 LLM API。本地 RAG 嵌入会在设备上运行,但首次需下载所选模型权重和运行时文件,大小因模型而异。

Windows / 社区插件安装后报错?
1.1.3 起会自动下载缺失的 ONNX / PDF 运行时文件,首次使用需联网。

安全说明

  • 本地优先存储 — 聊天记录、RAG 索引与模型缓存保存在 .obsidian/lecture-lens/;插件设置保存在 Obsidian 的插件数据文件中
  • 上下文可控 — 默认可附加当前笔记;你可全局关闭、逐条移除,并将 RAG 限定在一个课程文件夹内
  • 本地库访问 — 文件选择器、@ 附件和 RAG 只在本地枚举库内路径;不会把文件列表发送给服务商
  • 剪贴板访问 — 仅在你向聊天框粘贴图片时读取,并仅在你选择回复上的 复制 时写入文本
  • API 密钥 — 桌面版在可用时使用 Electron safeStorage 加密,否则保存在本地插件数据文件中
  • OpenAI 响应存储 — OpenAI 官方配置的 Responses API 请求会发送 store: false
  • 无遥测 — 不发送分析事件、库名称或使用统计

自动审核提示说明

  • 库文件枚举 仅用于本地 PDF / 笔记选择器与课程文件夹 RAG 索引;文件列表不会被传输。
  • 剪贴板访问 仅用于用户粘贴到聊天框的图片,以及回复上的显式 复制 操作。
  • 动态代码特征 来自随插件打包的 Transformers.js / ONNX Web Worker 运行时;Lecture Lens 只使用浏览器 / WASM 路径,不下载或执行远程 JavaScript。
  • 声明式设置 API 目前属于 Obsidian 1.13 Insider 功能。Lecture Lens 仍支持 Obsidian 1.8.7 及以上版本,因此会在完整完成双模式迁移后再启用设置搜索,避免先提供不完整的设置页。
网络目标 使用时机 发送内容
你配置的 LLM / 嵌入接口 聊天、识图、PDF 笔记或云端嵌入 API 密钥及该次请求所需的提示词与上下文
你配置的 Hugging Face 镜像 下载本地嵌入模型 仅请求公开模型文件;不发送笔记内容
jsDelivr 缺少 PDF.js 或 ONNX 运行时文件 仅请求公开运行时文件;不发送笔记内容

开发

git clone https://github.com/Yima-Gu/obsidian-lecture-lens.git lecture-lens
cd lecture-lens
npm ci
npm run dev

构建产物放入 <你的库>/.obsidian/plugins/lecture-lens/ 后启用并重载。提交 PR 前请运行 npm run check;贡献规范见 AGENTS.md。


License

MIT — see LICENSE.

HealthExcellent
ReviewSatisfactory
About
Convert lecture slides and whiteboard photos into structured Markdown notes using vision-capable LLMs that extract text, LaTeX, and diagrams. Index course folders for RAG-powered, context-aware chat; analyze images singly or in batch and ask questions tied to your course materials.
AIOCRImages
Details
Current version
1.1.8
Last updated
7 days ago
Created
7 months ago
Updates
9 releases
Downloads
290
Compatible with
Obsidian 1.8.7+
Platforms
Desktop, Mobile
License
MIT
Report bugRequest featureReport plugin
Sponsor
Support
Author
YimaYimayima-gu
GitHubyima-gu
  1. Community
  2. Plugins
  3. AI
  4. Lecture Lens

Related plugins

AI Image OCR

Extracts text from images using AI Vision models.

Tars

Text generation based on tag suggestions, using Claude, OpenAI, Ollama, Kimi, Doubao, Qwen, Zhipu, DeepSeek, QianFan & more.

Smart Connections

Find related notes and excerpts while writing. Your AI link building copilot displays relevant content in graph + list view. A local embedding model powers semantic search. Zero setup. No API key.

Claudian

Embeds Claude Code/Codex and other local Agents as AI collaborators in your vault.

Copilot

Your AI Copilot: Chat with Your Second Brain, Learn Faster, Work Smarter.

Fast Note Sync

Real-time sync of your vaults across server, mobile, and web; shareable with anyone; supports REST and MCP integrations to build your personal AI knowledge base.

Agent Client

Chat with Claude Code, Codex, Gemini CLI, and more via the Agent Client Protocol — right from your vault.

Ink

Handwriting and drawing directly between paragraphs using a digital pen, stylus, or Apple pencil.

Text Generator

Generate text content using GPT-3 (OpenAI).

Smart Composer

AI chat with note context, smart writing assistance, and one-click edits for your vault.