mirror of
https://github.com/eharris128/Obsidian-LLM-Plugin.git
synced 2026-07-22 11:30:23 +00:00
No description
edd21015c2
npm run test:e2e builds the plugin, type-checks the specs, stages a clean copy into test/plugin-dist/, and runs 13 Mocha specs against a real, sandboxed Obsidian instance (downloaded to .obsidian-cache/ on first run; ~6s wall-clock after that). No API keys or network providers needed. Coverage: plugin load + command registration + built-in skill seeding, widget open/focus-or-open/new-chat-always-fresh/per-tab input isolation, slash menu open/Escape/filtering, chat modal, chats panel, chat details panel, and the header settings toggle. Design notes (details in test/README.md): - The service copies data.json from the plugin dir into test vaults, so plugins: ["."] would leak the developer's real API keys. The staging script writes a deterministic test data.json instead (rootVaultFolder "AI" so built-in skills seed; nothing else). - Specs read the plugin id from the staged manifest at runtime rather than hardcoding it. - Specs live under test/ with their own tsconfig (root tsconfig now excludes test/); OBSIDIAN_APP_VERSION / OBSIDIAN_INSTALLER_VERSION pin the Obsidian version under test. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .claude | ||
| .github | ||
| docs | ||
| README_images | ||
| scripts | ||
| src | ||
| test | ||
| .editorconfig | ||
| .gitignore | ||
| .npmrc | ||
| bash.exe.stackdump | ||
| CLAUDE.md | ||
| esbuild.config.mjs | ||
| eslint.config.mjs | ||
| LICENSE | ||
| manifest.json | ||
| package-lock.json | ||
| package.json | ||
| README.md | ||
| SECURITY.md | ||
| SKILLS.md | ||
| styles.css | ||
| tsconfig.json | ||
| version-bump.mjs | ||
| versions.json | ||
| wdio.conf.mts | ||
| whisper-server.py | ||
Large Language Models
The Large Language Models (LLMs) Plugin gives Obsidian users access to LLMs through cloud providers (OpenAI, Anthropic, Google, and Mistral) and locally via GPT4All and Ollama. Models can be interacted with in the sidebar, main window, and a newly added, floating action button popup window.
Instructions
Installation: Download the plugin via the community plugin browser.
Using models from cloud-based providers:
- In the plugin settings menu, enter an API key from one of the supported model providers
- To interact with models, open one of the chat views using the newly added commands (see Commands section below)
Using models locally (GPT4All):
- Download GPT4All
- Download a model through GPT4All's model browser
- In the setting menu of GPT4All, toggle on the "Enable Local Server" setting
- Models downloaded via GPT4All will be selectable via the model switcher in each chat view
Using models locally (Ollama):
- Install Ollama and pull the models you want to use
- In the plugin settings, configure the Ollama host (default:
http://localhost:11434) - Click "Discover Models" to detect your locally available models
- Select an Ollama model from the model switcher in any chat view
Commands
| Command | Description |
|---|---|
| Open modal | Opens the chat modal |
| Toggle FAB | Toggles the visibility of the Floating Action Button (FAB) used to open and close the chat popup window |
| Open chat in tab | Opens the chat window in a tab |
| Open chat in sidebar | Opens the chat window in the Sidebar |
Models
Cloud-based:
| Model provider | Status |
|---|---|
| OpenAI | Supported |
| Anthropic | Supported |
| Supported | |
| Mistral | Supported |
Local:
| Model provider | Status |
|---|---|
| GPT4All | Supported |
| Ollama | Supported |
Credits
- Johnny ✨
- Ryan Mahoney
- Evan Harris