Skip to main content

A PKM web app integrated with LLMs

Project description

MetaList

PyPI PyPI - Python Version Runs on Linux | MacOS | Windows

What is MetaList?

MetaList is a personal knowledge management web application, tightly integrated with large language models.

⚠️ MetaList is currently in Development: Expect breaking changes and bugs

Features

  • Chat feature: LLM integration (currently only OpenAI API)
  • Chart.js integration for LLM-generated visualizations
  • Hierarchical, collapsable note structure
  • Reordering notes in one context survives to other search contexts; notes maintain a total order
  • Quick, responsive searching (tags, full-text, or combo of both)
  • Search suggestions
  • Tagging
  • Tag suggestions (uses a Jaccard index)
  • Tags can imply other tags
  • Tag implication rules are also notes; they can themselves be tagged and searched
  • Nested subitems in notes inherit tags from their parents
  • Markdown/LaTeX support
  • Infinite undo/redo
  • Infinite scrolling

Chat Feature

Search filters notes down to a relevant subset (a "search context"), which has the nice effect of acting as a form of human-guided retrieval augmented generation. The chat feature is fully integrated with the underlying notes. Mousing over a reference in the chat will highlight the referenced note, if it is within view, and clicking on the reference will navigate to and select the note, even opening up collapsed items in the note hierarchy so that all the relevant info becomes visible.

Some Examples

Recommendations based on a list of favorite movies, with interactive back-references:

Visualizing data from MetaList items:

Installation

It is recommended that you create a Python virtual environment before installing MetaList.

python3 -m venv venv
source venv/bin/activate

Then, install MetaList using pip:

pip install metalist

Usage

From the installation directory, run:

metalist

Navigate to http://127.0.0.0:8080/

Read the cheatsheet.

Roadmap

  • Chat integration with other models
  • Menus / Settings
  • Reminders
  • Passwords / encryption at rest
  • Import data from browser bookmarks
  • Import data from other PKM apps
  • Export notes to JSON, Markdown, HTML, PDF
  • File handling
  • Access to local file system
  • Multi-user
  • Mobile friendly
  • More unit/integration testing

License

MetaList is licensed under the MIT license. See LICENSE for more information.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

MetaList-0.1.11.tar.gz (273.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

MetaList-0.1.11-py3-none-any.whl (296.6 kB view details)

Uploaded Python 3

File details

Details for the file MetaList-0.1.11.tar.gz.

File metadata

  • Download URL: MetaList-0.1.11.tar.gz
  • Upload date:
  • Size: 273.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.4.2 requests/2.31.0 setuptools/45.2.0 requests-toolbelt/0.8.0 tqdm/4.66.1 CPython/3.8.10

File hashes

Hashes for MetaList-0.1.11.tar.gz
Algorithm Hash digest
SHA256 97ea3fd023d962f59bfd69c221e410ca1a38ce1350471158532b9b44227fa213
MD5 1df3e2738e3f992d7eedb27dd156f569
BLAKE2b-256 9fd2e74d566fa15e39cc37fac92e1a4bfdef28dcdd7edbe83323e824fef071ca

See more details on using hashes here.

File details

Details for the file MetaList-0.1.11-py3-none-any.whl.

File metadata

  • Download URL: MetaList-0.1.11-py3-none-any.whl
  • Upload date:
  • Size: 296.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.4.2 requests/2.31.0 setuptools/45.2.0 requests-toolbelt/0.8.0 tqdm/4.66.1 CPython/3.8.10

File hashes

Hashes for MetaList-0.1.11-py3-none-any.whl
Algorithm Hash digest
SHA256 71b38e2fe8ce83cf290f8b24425872f4edc99d2f7b3e002f20ff63521d3eb7fb
MD5 737f42a9685db150b4b404204bf50d14
BLAKE2b-256 c73f8894116675ee50d3e1d69b59f0c982bb5120057ca7f5083229a6b73a246b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page