Skip to main content

GPT Roles

Simple PyQT chatbox that connects to a chat session with ChatGPT, along with some extra desktop integration features.

Written as an experiment with Qt and understanding the role of LLMs in virtual assistant applications.

Screenshot of GPT Roles Demo video of GPT Roles

Roleplayer

It has a "roleplaying" root prompt that attempts to make implementing more roles into ChatGPT easier. You can add "roles" to the root prompt, by default there are some roles related to commands and programming.

You can also change the root prompt to something else entirely, there's a list of some prompts that are sourced online, see features.

Command Role

Not fully implemented

- RoleGPT can request web pages or from APIs to answer your questions.
    e.g. get current prices or latest news.
- Provide basic shell commands that will be automatically be run, to find or list files etc
- Instructions to format markdown for the programming features

App Features

Programming related features:

- Run shell or python code in markdown blocks directly in the chat interface
- Edit the markdown blocks in the chat box
- Copy or save markdown blocks to a file

Additional features:

- Easily switch or add more "roles"
- Remove the roleplaying root prompt and set it as you please
- List roles from jailbreakchat.com and set them as the root prompt

Chat related features:

- TODO Shows which messages are in the current prompt chain and can be added/removed
- TODO Show alternate choices and commit to conversation

Installing/Running

From pip

Install the module and install desktop launcher integration:

pip install gptroles && ./install.sh

From source with Poetry
poetry install && poetry run main
Packaged AppImage/PyInstaller

TODO

Development installation

Use the dev.sh script.

# This only needs to be run once
./dev.sh build && ./dev.sh sysinstall && ./dev.sh install

# Then you can run with the install and dev environment matching code
./dev.sh run

Metadata

Release files for gptroles 0.1.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for gptroles 0.1.5
File Size Uploaded Provenance
gptroles-0.1.5.tar.gz 1.3 MB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for gptroles 0.1.5
File Interpreter ABI Platform
gptroles-0.1.5-py3-none-any.whl Python 3 none any Details

Total release size: 2.6 MB

Release files / gptroles-0.1.5.tar.gz

Download URL gptroles-0.1.5.tar.gz
Size 1.3 MB
Tags Source
SHA-256 checksum
How to use checksums
34b9efb250b5c81a96e55c860f2c087e694f5dc0f10163779ea9af62d0c1f44a
BLAKE2b-256 checksum
How to use checksums
1fece98eaf9147ea11a27474f65297bd56d4f930359d6133e54d5ff9d90d5a67
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/1.3.1 CPython/3.10.10 Linux/5.17.15-1-MANJARO

Release files / gptroles-0.1.5-py3-none-any.whl

Download URL gptroles-0.1.5-py3-none-any.whl
Size 1.3 MB
Tags Python 3
SHA-256 checksum
How to use checksums
c4962f1e745be840a1dc7c0d12baa5a4ddcdb70e8f556ecfe9016fba05f4a277
BLAKE2b-256 checksum
How to use checksums
8a698da184eacd365cc1de2dd386af0212d25ab29594ffb06a5d1ba004e239f4
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/1.3.1 CPython/3.10.10 Linux/5.17.15-1-MANJARO

Security for gptroles 0.1.5

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page