Terminal-AI
A zero-shot AI assistant in the terminal, backended by the GROQ AI, for blazing fast responses. The free API key from GROQ can be obtained here
Installation
To install protai, simply run the following command in your terminal:
pip install --upgrade protai
Usage
To use this application, simply run the following command in your terminal:
protai <query>
For example:
[!Note] On first run you will be prompted to enter your free Groq AI API key. You can get one at the Groq AI website.
[!IMPORTANT] You need to have a valid Groq AI API key to use this application.
The application uses the following models:
-
Instant Mode:
llama-3.3-70b-versatilefor fast, zero-shot inference. -
Interactive Mode:
openai/gpt-oss-120bfor multi-turn, zero-shot inference.
Development
To develop for this application, clone the repository and install dependencies using the provided scripts:
git clone https://github.com/protik09/terminal-ai.git
cd terminal-ai
./activate_venv.sh
or
git clone https://github.com/protik09/terminal-ai.git
cd terminal-ai
.\activate_venv.ps1
To generate the wheel and upload to PyPI, we use the following command:
python setup.py upload
[!IMPORTANT] Only the current maintainer has access to the PyPI repository API key. If you wish to contribute, please fork the repository and submit a pull request.
Key Files & Structure
protai/protai.py: CLI entry, argument parsing, main logic, reply formatting, error handling.protai/auth.py: API key storage, retrieval, validation, user prompts (usesprompt-toolkit).protai/mygroq.py: GROQ API wrapper (usesrequestsandorjson).protai/texteffects.py: Terminal output formatting.protai/ismarkdown.py: Markdown detection for replies.protai/__init__.pyandVERSION: Version management.
Prerequisites
- Python 3.9 or later 🐍
- Groq AI API key (available at Groq AI website)
[!NOTE]
- Python 3.9 or later 🐍
- Groq AI API key (available at Groq AI website)
Program Flow Chart
Contributing
Contributions are welcome! If you'd like to contribute to this application, please fork the repository and submit a pull request.
[!WARNING] WSL2 is not supported for development. Please use a native Linux or Windows environment. There are issues with keyring access in WSL2.
License
This application is licensed under the MIT License. See LICENSE for details.
Metadata
Release files for protai 1.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| protai-1.1.1.tar.gz | 19.7 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| protai-1.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 34.6 kB
Release files / protai-1.1.1.tar.gz
| Download URL | protai-1.1.1.tar.gz |
|---|---|
| Size | 19.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0323185621b79a83e05c99fe3b706b23f615a368dd712e08970417caf6b3cb3f
|
|
BLAKE2b-256 checksum How to use checksums |
6d99a01438f4467c448d71c76d75f1e649dbcea93746a44fa856cf812004adca
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.7
|
Release files / protai-1.1.1-py3-none-any.whl
| Download URL | protai-1.1.1-py3-none-any.whl |
|---|---|
| Size | 14.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
bc46e452d91cc5f72595d4c90eda71760a8a677c9aaa8d5102fe1ce1acfaf68f
|
|
BLAKE2b-256 checksum How to use checksums |
00643c58418fa790e3a0eb2b635d461e8790b3d9484e3cfc60d4a059c720d9c0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.7
|