Kait - Kubernetes AI Tool
Project description
Kait (Kubernetes AI Tool)
kait is an AI assisted kubernetes debugging tool which automatically troubleshoots, diagnoses, and fixes issues related to kubernetes.
kait uses autonomous AI agents built using Microsoft's AutoGen
Installation and setup
You can install kait directly using pip:
pip install kait
kait requires an OpenAI API key which is read via the environment variable KAIT_OPENAI_KEY. You can provide a list of models to use and kait will use the available model. It is recommended to use models with the capabilities of gpt-4. Larger contexts work better too e.g. 'gpt-4-1106-preview'. Your environment variable needs to point to a list of models in the following format:
[
{
"model": "gpt-4",
"api_key": "YOUR_OPENAI_API_KEY"
}
]
Usage
kait requires kubectl to be installed and authenticated against the cluster you want to use.
To run kait simply run:
kait debug <DESCRIPTION OF THE ISSUE TO DEBUG>
For a full list of options, run:
kait debug --help
Examples
A number of examples/ are provided so you can see how kait performs.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file kait-0.2.1.tar.gz.
File metadata
- Download URL: kait-0.2.1.tar.gz
- Upload date:
- Size: 7.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b815554c7f89c580ff880775f6d6f94b2fa9a63a75e1067cc8fa6d78ca8c1d2f
|
|
| MD5 |
7f10d03259aa2c685295b10427e35dc7
|
|
| BLAKE2b-256 |
0e18edec25b302a2e277438f284f591a13b6ea0a5b70afb40b1dbaf4a4cb5c37
|
File details
Details for the file kait-0.2.1-py3-none-any.whl.
File metadata
- Download URL: kait-0.2.1-py3-none-any.whl
- Upload date:
- Size: 7.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b14c1bab350c239977b132a3287f891580316460d4aa763cbf76046a49c65bcf
|
|
| MD5 |
1db3db2c8dbd77d5c1ff9ce8e37dcbdf
|
|
| BLAKE2b-256 |
dc3342aea4e8e2cdbb2c2218bae14870ce42cf602d96acca3e0e0bc9059dbcfa
|