jacobinwwey_obsidian-NotEMD/website/docs/faq.mdx

---
id: faq
title: Frequently Asked Questions
description: Common questions about Notemd installation, features, and usage
keywords: [faq, installation, LLM providers, obsidian plugin, wiki-links, concept notes, Copilot alternative, Smart Connections alternative, obsidian AI plugin comparison]
author:
  '@id': 'https://jacobinwwey.github.io/obsidian-NotEMD/#person-jacobinwwey'
concepts: [Notemd, Obsidian, LLM, wiki-links, concept notes, knowledge base, Copilot Alternative, AI Plugin Comparison]
citations:
  - title: Obsidian
    url: https://obsidian.md
  - title: Ollama
    url: https://ollama.com
faqItems:
  - question: How do I install Notemd in Obsidian?
    answer: Open Obsidian Settings, go to Community Plugins, Browse, search Notemd, Install, and Enable. Requires Obsidian 0.15.0 or later. Manual installation is also available via GitHub Releases.
  - question: What LLM providers does Notemd support?
    answer: Notemd supports 30+ providers including OpenAI, Anthropic, Google, xAI, Mistral, DeepSeek, Qwen, Ollama, LM Studio, Azure OpenAI, OpenRouter, and many China-focused providers like Qwen, Doubao, Moonshot, and GLM.
  - question: Can Notemd work with local LLMs?
    answer: Yes. Notemd works with Ollama, LM Studio, vLLM, LocalAI, and any OpenAI-compatible endpoint. All tasks work with local models including linking, concept generation, translation, research, and diagram generation.
  - question: How does Notemd differ from ChatGPT?
    answer: ChatGPT produces ephemeral chat answers. Notemd writes persistent structured results directly into your Obsidian vault as wiki-linked files, concept notes, diagrams, and translations that accumulate into a knowledge base.
  - question: How does Notemd compare to Copilot or Smart Connections?
    answer: Copilot is conversation-first for chatting about notes. Smart Connections is discovery-first for finding similar notes. Notemd is write-first, processing notes with AI and writing structured results into your vault. All three complement each other.
  - question: Which search services work with Notemd research?
    answer: Tavily (recommended, AI-optimized search, requires API key) and DuckDuckGo (experimental, no API key needed). Research results are summarized by LLM and appended to your note with source citations.
  - question: Does Notemd support Chinese or other languages?
    answer: The UI supports 21+ languages. Task output language is independently configurable, allowing mixed setups like Chinese UI with English output or vice versa.
  - question: Can I use Notemd for paper or PDF reading?
    answer: Yes. Convert PDF to Markdown using MinerU, open in Obsidian, then run Notemd tasks to add wiki-links, generate concept notes, extract text, research background, translate sections, and create Mermaid diagrams.
  - question: What diagram types can Notemd generate?
    answer: Mermaid (flowchart, sequence, class, state, ER, Gantt with syntax auto-fix), JSON Canvas (Obsidian native), Vega-Lite (data charts), HTML fallback, and explicit editable HTML/SVG figure artifacts. Draw.io XML and Drawnix JSON exporter boundaries are available for deterministic artifact testing.
  - question: Is Notemd free and open source?
    answer: Yes. MIT licensed, no paid tiers, no cloud lock-in, no telemetry. Source code on GitHub with 234+ stars. Pull requests welcome.
  - question: Can Notemd work 100% offline?
    answer: Yes with Ollama. No API key, no internet needed. All features work offline including wiki-links, concept notes, translation, and diagrams. DuckDuckGo research also works without an API key.
  - question: Is my data sent to the cloud?
    answer: With Ollama or LM Studio, no data leaves your machine. With cloud providers like OpenAI or Anthropic, your note content is sent as API input. Notemd itself collects no telemetry or user data.
---

import TLDR from '@site/src/components/TLDR';

# Frequently Asked Questions

<TLDR>
**Quick answers to the most common Notemd questions.** Covers installation (5 min setup), 30+ LLM providers support, local/cloud model options, one-click workflows, multilingual UI (21 languages), wiki-linking automation, research integration, PDF reading workflows, diagram generation, and open-source licensing. All features work offline with Ollama.
</TLDR>

---

## Installation & Setup

### How do I install Notemd in Obsidian?

Open Obsidian **Settings → Community Plugins → Browse** → search **"Notemd"** → **Install** → **Enable**.

**Requirements:**
- Obsidian 0.15.0+
- Supported on Desktop (Windows, macOS, Linux) and Mobile (iOS, Android)

**Manual installation:**
1. Download `main.js`, `styles.css`, `manifest.json` from [GitHub Releases](https://github.com/Jacobinwwey/obsidian-NotEMD/releases)
2. Place them in `<your-vault>/.obsidian/plugins/notemd/`
3. Reload Obsidian and enable the plugin

**Stats:** 4k+ downloads, 44 releases, MIT licensed.

---

## LLM Configuration

### What LLM providers does Notemd support?

Notemd supports **30+ providers**:

**Cloud providers:**
- OpenAI (GPT-4, GPT-4o, GPT-4o-mini, o1, o3)
- Anthropic (Claude Opus, Sonnet, Haiku)
- Google (Gemini Pro, Flash, Ultra)
- xAI (Grok)
- Mistral, DeepSeek, Qwen, Moonshot, GLM

**China-focused:**
- Qwen, Qwen Code, Doubao, Moonshot, Xiaomi MiMo, GLM, Z AI, MiniMax
- Huawei Cloud MaaS, Baidu Qianfan, SiliconFlow

**Local/self-hosted:**
- Ollama
- LM Studio
- Any OpenAI-compatible endpoint

**Gateways:**
- Azure OpenAI, OpenRouter, Together AI, Groq, AIHubMix
- GitHub Models, Fireworks, LiteLLM, Nebius, Cerebras
- Hugging Face, Vercel AI Gateway, Requesty

### Can Notemd work with local LLMs?

**Yes, fully supported.** Notemd works with:
- **Ollama** (native integration)
- **LM Studio** (via OpenAI-compatible endpoint)
- **vLLM, LocalAI, text-generation-webui** (via OpenAI-compatible mode)

All tasks work with local models: linking, concept generation, translation, research, and diagram generation.

**Mix & match example:**
- Ollama (local) for linking → fast, private, no cost
- OpenAI for research → high quality, web search integration
- Gemini for translation → multimodal support

### How do I configure different models for different tasks?

In **Notemd Settings**, each task has independent provider/model selectors:

| Task | Example Configuration |
|------|----------------------|
| **Linking** | DeepSeek (fast, cheap) |
| **Concept Generation** | Claude Opus (high quality) |
| **Research** | Perplexity or GPT-4o (web-grounded) |
| **Translation** | Gemini Flash (multimodal) |
| **Diagram Generation** | Ollama (local, private) |

This per-task optimization balances speed, cost, and quality.

---

## Core Features

### How does Notemd differ from ChatGPT for paper reading?

| Dimension | ChatGPT | Notemd |
|-----------|---------|--------|
| **Output location** | Chat history (ephemeral) | Obsidian vault (persistent files) |
| **Result format** | Text answer | Wiki-links, concept notes, diagrams, translations |
| **Long-term value** | Disappears after session | Accumulates into knowledge base |
| **Reusability** | Must re-query | Files stay, link, evolve |

**Use ChatGPT for:** Quick Q&A, one-off explanations
**Use Notemd for:** Building a persistent, structured knowledge base over weeks/months

### How does Notemd add wiki-links to notes?

**Process:**
1. You run "Process file (add links)" on a note
2. Notemd sends the text to your configured LLM
3. The LLM identifies key concepts in context
4. Notemd inserts `[[wiki-links]]` at each concept occurrence
5. Optionally, it auto-creates concept notes in a folder you specify

**Features:**
- Synonym suppression (avoids "transformer" vs "transformers" duplicates)
- Backlinks from concept notes to source
- Link integrity on rename/delete
- Pure extraction mode (extract concepts without modifying the original)

### What is the Notemd one-click workflow?

**One-click workflows** chain multiple actions into a **single sidebar button**.

**Default workflow:** `One-Click Extract`
```
process-current-add-links > extract-concepts-current > research-and-summarize > summarize-as-mermaid
```

**Result:** One click runs:
1. Add wiki-links to current note
2. Generate concept notes for new terms
3. Research & append background
4. Compress into a Mermaid diagram

**Custom workflows:** Define your own in Settings with the DSL format. Each workflow becomes a reusable sidebar button.

### How does Notemd compare to Copilot or Smart Connections?

These plugins solve different problems:

- **Copilot** — Conversation-first. You chat with an AI about your notes. AI answers stay in the chat panel; they don't modify your vault.
- **Smart Connections** — Discovery-first. It finds semantically similar notes using embeddings. It doesn't create or modify content.
- **Notemd** — Write-first. AI processes your notes and writes structured results (wiki-links, concept notes, research, diagrams, translations) directly into your vault as persistent files.

| What you need | Recommended plugin |
|----------------|-------------------|
| Chat with AI about notes | Copilot |
| Find similar/related notes | Smart Connections |
| Auto-insert wiki-links and build a knowledge graph | **Notemd** |
| Generate concept notes with backlinks | **Notemd** |
| Create diagrams from note content | **Notemd** |
| Research a topic and append summaries | **Notemd** |

All three can be used together — they complement rather than compete.

---

## Research & Translation

### Which search services work with Notemd research?

| Service | API Key Required | Quality | Notes |
|---------|-----------------|---------|-------|
| **Tavily** | Yes | High | Recommended, AI-optimized search |
| **DuckDuckGo** | No | Experimental | No setup, lower quality |

**How "Research & summarize" works:**
1. You select a topic or run it on current note
2. Notemd queries the search service
3. Results → LLM summarization
4. Summary appended to your note with source citations

**Result:** Persistent research trail in your vault, not browser tabs.

### Does Notemd support Chinese or other languages?

**UI languages:** 21+ supported
- English, 中文 (简体), 中文 (繁體), 日本語, 한국어
- Arabic, German, French, Spanish, Russian, Portuguese, Italian
- Hindi, Bengali, Thai, Vietnamese, Turkish, Polish, Czech, and more

**Task output language:** Independent configuration
- UI in Chinese + output in English: ✅
- UI in English + output in Chinese: ✅

**Use case:** Bilingual researchers can keep UI in native language while generating English notes for publication.

---

## PDF & Academic Workflows

### Can I use Notemd for paper/PDF reading?

**Yes.** Workflow:
1. **Convert PDF → Markdown** using [MinerU](https://github.com/opendatalab/MinerU) (recommended for academic papers)
2. Open the Markdown file in Obsidian
3. Run Notemd tasks:
   - **Add wiki-links** to key terms
   - **Generate concept notes** for unfamiliar terminology
   - **Extract original text** via custom questions (e.g., "What are the limitations?")
   - **Research background** for cited methods/datasets
   - **Translate** difficult sections
   - **Compress to Mermaid** diagram for structural understanding

**Version 1.9.1+:** Chapter structure extraction with TOC support

**Result:** Your paper reading becomes a structured, linkable knowledge artifact in your vault.

---

## Diagrams & Visualization

### What graph/diagram types can Notemd generate?

| Type | Support | Features |
|------|---------|----------|
| **Mermaid** | Full | Flowchart, sequence, class, state, ER, Gantt, syntax auto-fix, batch validation |
| **JSON Canvas** | Full | Obsidian native canvas layouts |
| **Vega-Lite** | Full | Data charts, time series, bar, scatter, customizable |
| **HTML** | Fallback | For unsupported diagram types |
| **Editable HTML/SVG** | Explicit target | Self-contained inline SVG with semantic Draw.io-style annotations |
| **Draw.io / Drawnix artifacts** | Export boundary | Deterministic XML/JSON from `SemanticFigureModel`; no editor runtime dependency |

**Mermaid auto-fix:** Deep debug mode repairs:
- Broken arrows (`-->`, `-.->`, `==>`)
- Invalid labels, comments
- Subgraph syntax errors
- Shape notation (`[`, `(`, `{`, `((`)
- Pipe characters in labels
- Note attachments

**Workflow:**
1. Run "Summarize as Mermaid diagram" on a note
2. Preview in modal
3. Export as SVG or PNG
4. Or save as `.mmd` file in vault

---

## Open Source & Community

### Is Notemd free and open source?

**Yes.**
- **License:** MIT (permissive, commercial use OK)
- **Source code:** https://github.com/Jacobinwwey/obsidian-NotEMD
- **No paid tiers, no cloud lock-in, no telemetry**
- **Community:** 234+ GitHub stars, active Discord

**You own:**
- Your data (stays in your vault)
- Your workflows (customize prompts, models, chains)
- Your privacy (local LLM support)

**Contribute:** Pull requests welcome. See [CONTRIBUTING.md](https://github.com/Jacobinwwey/obsidian-NotEMD/blob/main/CONTRIBUTING.md)

---

## Troubleshooting

### My LLM calls are failing. What should I check?

1. **API key valid?** Check Settings → Provider Configuration
2. **Model name correct?** Use "获取模型列表" (Get Model List) button in settings
3. **Network accessible?** Some providers require VPN
4. **Rate limits?** Check provider dashboard
5. **Diagnostics:** Run "Connection Test" in settings for detailed error logs

### Notemd is slow. How can I speed it up?

1. **Use faster models:** DeepSeek, Gemini Flash, GPT-4o-mini
2. **Reduce chunk size:** Settings → Smart Chunking → lower word count
3. **Parallel processing:** Settings → Batch Processing → increase concurrency
4. **Local models:** Ollama for tasks that don't need web search

### Can Notemd work 100% offline?

**Yes, with Ollama.** No API key, no internet, no data leaves your machine:

1. Install [Ollama](https://ollama.com) and run `ollama serve`
2. In Notemd settings, select **Ollama** as your provider
3. Pull a model: `ollama pull llama3` (or qwen2.5, gemma2, etc.)
4. All features work: wiki-links, concept notes, translation, diagrams

**DuckDuckGo research** also works without an API key (experimental quality).

With cloud providers (OpenAI, Anthropic, Google, DeepSeek, etc.), your note content is sent as API input. Check each provider's privacy policy for data handling details.

### Is my data sent to the cloud?

**It depends on your provider:**

| Provider type | Data sent to cloud? | Notes |
|--------------|---------------------|-------|
| **Ollama (local)** | No | Everything stays on your machine |
| **LMStudio (local)** | No | Same as Ollama |
| **DeepSeek, OpenAI, etc.** | Yes | Note content sent as API input for processing |
| **OpenRouter, AIHubMix** | Yes | Gateway that routes to cloud providers |

Notemd itself collects **no telemetry, no analytics, no user data**. The plugin is fully open source (MIT). The only data that leaves your machine is what you explicitly send to your configured LLM provider.

### Which Obsidian AI plugin is best for research?

Depends on your research workflow:

| Need | Plugin | Why |
|------|--------|-----|
| Find related papers/notes | Smart Connections | Semantic similarity discovery |
| Chat about your sources | Copilot | Conversation with vault context |
| Auto-link concepts + generate notes | **Notemd** | AI identifies concepts, inserts links, creates notes |
| Web research + summarize into notes | **Notemd** | Tavily/DuckDuckGo search → LLM summary → appended to note |
| Generate diagrams from research | **Notemd** | Mermaid/Canvas/Vega-Lite from note content |

**Recommended combo:** Smart Connections (discovery) + Notemd (structuring) + Copilot (discussion).

---

## Getting Help

- **Documentation:** https://jacobinwwey.github.io/obsidian-NotEMD/
- **GitHub Issues:** https://github.com/Jacobinwwey/obsidian-NotEMD/issues
- **Discord:** https://discord.gg/qnGgsQ9W
- **Sponsor:** https://github.com/sponsors/Jacobinwwey