Matrix bot that generates messages based off of messages of other users using a neural network.

Go to file

array-in-a-matrix ee86f79905 correction		2022-08-16 11:28:45 -04:00
.gitignore	ignore AI related files	2022-08-15 23:38:00 -04:00
example.config.json	added retrain var	2022-08-16 03:43:59 -04:00
index.js	specify text generation in py process	2022-08-16 03:45:11 -04:00
LICENSE	Initial commit	2022-08-15 00:50:58 -04:00
package.json	dependencies	2022-08-15 17:17:45 -04:00
pnpm-lock.yaml	dependencies	2022-08-15 17:17:45 -04:00
README.md	correction	2022-08-16 11:28:45 -04:00
textgen.py	check arg passed	2022-08-16 03:46:05 -04:00

README.md

text-gen-bot

Matrix bot that generates messages based off of messages of other users using a neural network.

Usage

First install the needed libraries. Then copy example.config.json and rename it config.json. Replace the items in angled brackets with their respective values of the bot account (e.g. replace <DOMAIN.TLD> with the homeserver url like https://matrix.org or https://matrix.arrayinamatrix.xyz). An explanation of each configurable string is located in configurations section of this document. To obtain the token of an account follow the instructions here.

Once the config file has been populated with valid data, execute the index.js file (Warning: executing for the first time will be slow.).

$ node index.js
...
<some warnings show up, ignore them>
...
Client has started!
...

If you do not want to wait until the bot creates its own dataset from new messages, you can export chat history easily using Element. In this case, you will need to manually remove the time stamps from the text file.

Setup

The project is split into 2 parts index.js and textgen.py. The index.js file contains the code that interacts with the user on Matrix and sends text generated by the textgen.py file.

Install JavaSript SDK:

> pnpm add matrix-bot-sdk

Install Python module:

> pip3 install aitextgen

Configurations

Before a bot can be used the fields in the config.json file must be populated with valid information. Values in angled brackets (stared below) must be supplied before usage.

► homeserver*   ⇢     URL of the bot's homeserver.

► token*        ⇢     Account token used to sign in the bot.

► user*         ⇢     Account's User ID.

► file          ⇢     Path of file used for training the AI (.txt file only).

► prefix        ⇢     Bot listens to commands that start with this prefix.

► frequency     ⇢     How often the bot sends a message (keep high to prevent spam).

► size          ⇢     Bot starts generating messages when the number of lines in the training file is equal to this. The greater the size, the longer bot waits before messaging but might increase message quality.

► retrain       ⇢      The bot retrains itself after this many extra lines of messages are recorded in the text file.