Skip to main content

keep and reuse your thoughts

Project description

Rethink

Unittest License Package version Supported Python versions

English | 简体中文

Rethink represents rethinking and is an AI (Large Language Model, LLM) based personal knowledge and cognitive growth assistant tool. Rethink will assist your knowledge and cognitive growth in the following two aspects:

  1. Going beyond note-taking software, it automatically recommends and links existing knowledge and cognition when recording, building a more solid knowledge network;

internal link

  1. AI knowledge expansion based on the LLM, allowing your cognition to continuously iterate and extend.

AI recommend

Main Features of Rethink

  1. Personal Cognitive Growth Tool: Record and extend your thinking, assisting you in efficient growth;
  2. AI Recommendation: AI knowledge expansion based on the large language model LLM, allowing your cognition to continuously iterate and extend;
  3. Bidirectional Linking: Use @ linking or automatic recommendation to other notes;
  4. Markdown Syntax: Seamless support for Markdown syntax;
  5. Local Storage: Rethink highly values data security and provides a local deployment solution. In addition, there is an online version at https://rethink.run/r/login for synchronization between multiple platforms;
  6. History Version Tracking: Supports history version tracking, making it easy to view and restore historical versions;

Installation and deployment methods:

Deploy using Docker containerization

Pull the image:

docker pull morvanzhou/rethink

Run the container:

To ensure data security, you should mount the local path to the container.

docker run \
 -p 8080:8080 \
 -v /your/data/path:/.data \
 morvanzhou/rethink

Now you can access http://127.0.0.1:8080 in your browser to use the service.

If you want to customize other ports, in addition to modifying the first half of the -p parameter, you also need to add an environment variable API_URL to redirect the API address in the frontend service: Make sure the port number in API_URL is consistent with the first half of the -p parameter (port 8001 in the following example).

docker run \
 -e API_URL=http://127.0.0.1:8081 \
 -p 8081:8080 \
 -v /your/data/path:/.data \
 morvanzhou/rethink

If you want to use Rethink authentication, you can add the environment variable APP_PASSWORD:

docker run \
 -e APP_PASSWORD=12345678 \
 -p 8080:8080 \
 -v /your/data/path:/.data \
 morvanzhou/rethink

All configurable environment variables:

  • API_URL: API address in the frontend service, default is http://127.0.0.1:8080
  • APP_PASSWORD: Authentication password, default is None
  • APP_LANGUAGE: Language, default is English, optional values: zh, en

Deploy using Python

Install via pip

The second way to install and use Rethink is through pip installation. Then start the service directly with Python.

Initial installation:

pip install retk

Update:

pip install -U retk

Configure with Python

Use the retk.run() method to quickly start

Star History

Star History Chart

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

retk-0.3.1.tar.gz (2.0 MB view details)

Uploaded Source

Built Distribution

retk-0.3.1-py3-none-any.whl (2.1 MB view details)

Uploaded Python 3

File details

Details for the file retk-0.3.1.tar.gz.

File metadata

  • Download URL: retk-0.3.1.tar.gz
  • Upload date:
  • Size: 2.0 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.9.21

File hashes

Hashes for retk-0.3.1.tar.gz
Algorithm Hash digest
SHA256 c83693329119cdc2294c8c67480b845c7a7916bb890107afbe5875c18fd49ff3
MD5 b88a8bcfcb9416ad6b8665a10543add6
BLAKE2b-256 a96dfadd0a56ffd072306ea3e123bc16628d8d7b127d49c3840f5036eb5bfa79

See more details on using hashes here.

File details

Details for the file retk-0.3.1-py3-none-any.whl.

File metadata

  • Download URL: retk-0.3.1-py3-none-any.whl
  • Upload date:
  • Size: 2.1 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.9.21

File hashes

Hashes for retk-0.3.1-py3-none-any.whl
Algorithm Hash digest
SHA256 fa529ace6ff9654f83362fc371e832895cb1a25b5051e61f615af64708f138d7
MD5 6768d2027b27252529a6742bc8542a7e
BLAKE2b-256 43efbf22bb7f1e494d5a0b304fe15494249408a80ce7a723766d22d11ab43fbb

See more details on using hashes here.

Supported by

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