Auto Classifier
is an Obsidian plugin that helps you automatically classify tag from your notes using the ChatGPT API. The plugin can analyze your note (It can be title, frontmatter, content or selected area) and suggest relevant tag based on the input with tags in your valut. This can be used for various and specific purposes, for example, DDC classification for books, keyword recommendation, research paper categorization and so on. Save you time and improving your note organization.
-
Enter your ChatGPT API key in setting tab. You can create it at OpenAI. Check api setting by the
Test API call
button. -
This plugin consists of 4 Input Commands that you can run. By simply running these commands, it will automatically classify your note.
Classify tag from Note title
Classify tag from Note FrontMatter
Classify tag from Note Content
Classify tag from Selected Area
-
Toggle and Choose from different Tag Reference types. ChatGPT will select the appropriate tag from these references.
All tags
(default)Filtered Tags
with regular expressionManual Tags
that defined manually
-
Specify the Output Type from the response of ChatGPT.
#Tag
: at yourCurrent Cursor
orTop of Content
.[[WikiLink]]
: at yourCurrent Cursor
orTop of Content
.FrontMatter
: withkey
Title Alternative
: at the end of note's title
-
(Optional) Add
Prefix
orSuffix
for the output format. -
(Optional) Your can use your custom request for the ChatGPT API.
Custom Prompt Template
- ChatGPT will respond based on this prompt. The input coming from your Command will be replaced by
{{input}}
, and the reference tags you set will be placed in{{reference}}
.
- ChatGPT will respond based on this prompt. The input coming from your Command will be replaced by
Custom Chat Role
- You can guide ChatGPT's behabior by setting this system role
If you want use this plugin as DDC number classification, edit Custom Prompt Template
like this:
Please use Dewey Decimal Classification (DDC) to classify this content:
"""
{{input}}
"""
Answer format is JSON {reliability:0~1, output:"[ddc_number]:category"}.
Even if you are not sure, qualify the reliability and select one.
Convert the blank spaces to "_" in the output.
LCSH classification can be similar:
Please use Library of Congress Subject Headings (LCSH) to classify this content:
"""
{{input}}
"""
Answer format is JSON {reliability:0~1, output:"[First LCSH term]--[Second LCSH term]--[Third LCSH term]"}.
Even if you are not sure, qualify the reliability and select one.
Convert the blank spaces to "_" in the output.
- Search
Auto Classifier
in the Community plugin tab of the Obsidian settings. - Also, you can manually download the latest release from this repository GitHub releases and extrat the ZIP file to your Obsidian plugins folder.
If you encounter any issues while using this plugin or have any suggestions for improvement, please feel free to submit an issue on the GitHub repository. Pull requests are also welcome.
Hyeonseo Nam
MIT License