Powerful AI Framework
HAL is an AI engine which tries to take a different approach than ALICE, Eliza, and the like, by not only having one engine doing all processing, but by having three.
Note that this is only a library, it doesn’t have any fancy interfaces pre-installed. There are two scripts, hal, which will load command- line HAL, and whal, which will load a Tkinter-based GUI for it.
|||detects keyboard spam and notify the user instead of giving an “I don’t understand” response|
|||one-word variant of matrix, designed to run after matrix.|
To install, do: pip install HAL.
After installation, run python in interactive mode and run import HAL.dbtest. If it says you don’t have full-text search, then you should install the pysqlite2 module from here. If you don’t, HAL will still function, albeit much slower.
Note that this is the raw engine, which accepts HAL file extensions to run. If you do not wish to make your own, you can use the dataset we are developing that is located here: http://github.com/HALTeam/HALdata.
To start HAL, run hal. This will search for data files in the current directory. Optionally, you can pass the directory where the dataset is as an argument to hal.
Note: The dataset is a converted AIML set, that was again converted to the new HAL engine from a previous one that only had a regex engine. Because of this, and that the entries were separated by a machine, we expect there to be a lot of bugs. Please feel free to report them on GitHub.
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size HAL-0.0.3.zip (27.3 kB)||File type Source||Python version None||Upload date||Hashes View hashes|