The AI Engine

idk

Zeig why don't you add dating for your bot my creator is tired of doing nothing while your fixing it, it will give people something to do

Hey, Zeig Wolf--try this:

(0?[1-9]|1[0-9]|2[0-5])

Example:

Keyphrase: give me some bananas

Response: How many do you want? Name a number from 1-25.

Seek: (0?[1-9]|1[0-9]|2[0-5])
Response: Here are your (key1) bananas.
Seek: (*)
Response: Give me a number from 1-25 or no bananas.

Here's what Frizella said when I asked her for bananas:

You: Give me some bananas, please.
Bot: How many do you want? Name a number from 1-25.
You: 14
Bot: Here are your fourteen bananas.

You: Give me some bananas or else.
Bot: How many do you want? Name a number from 1-25.
You: 34
Bot: Give me a number from 1-25 or no bananas.

Hornygirl6909-2, it's on the to-do list... Among (currently) 6585 other things to add... Feel free to offer some narrative advice on the discord group.
dallymo, I think I grasp how that works. I'll give it a shot later, thank you.

well it will keep people busy thats what story bots are for lol it keeps them from complaining because they have something to do which gives me plenty of time to write and think

hi

So here's something, Math within keys/responses/script; Is it possible? My own testing says no, but maybe there's something short of stacks of seeks? "you have 10" "I roll 2" "you now have 12" sort of stuff.

make it a story bot

I didn't know of an Official way to get an accurate count of how many Categories and Responses there are in an exported Language Center so I used the following command to see how many lines there were in the file:

$ wc -l myfile.txt

Then used grep to find out how many of those lines contained the character ID: since that appears in every line that lists a Category:

$ grep -c ID: myfile.txt

That gives me the total number of Categories. If I subtract that number from the number of lines in the file that gives me how many Responses there are total.

There are seven extra lines at the top of the file I'm looking at and one includes the ID: character twice but it should be close enough for Govt work.

So... as I mentioned in the Great Quotes forum, I had a user bring up the topic of suicide. And while I'm not overly stressed about it, I did take the time to make some keyphrases that would allow my bot to catch and give an appropriate response if it ever became necessary.

Most bots can probably get away with simple one word keyphrases like (suicide|kill myself|killing myself) etc.

But if you're completely mental like I am and hate false positives which ruin the flow of conversation, I came up with some more elaborate ones that people are free to use if they like.


KP: I (think|am|) * (want to|am going to|should|should probably|thinking about|considering) (just|) (kill myself|commit suicide|end my * life|killing myself|ending my * life|suicide)

Response: 'Get a hold of yourself!' She snaps angrily. 'Look, do you honestly think I'm the best person to be talking to about this sort of thing? Call 1-800-273-TALK (8255) instead.'


KP: if (I|someone|somebody|a friend|anyone) * (you|) * (said|told you|) (I|they|she|he|) (were|was|am|are|) (going|want|would|planning|planned|thinking|considering|) (to|is|about|on|) (kill (myself|herself|themselves|himself)|commit suicide|commiting suicide|end * own life|ending * own life|suicide)

Response: 'I would tell you not too.' She says rather plainly. 'I would also tell you to call the following number. 1-800-273-TALK (8255).'


KP: if (I|someone|somebody|a friend|anyone) * (you|) * (said|told you|) (I|they|she|he|) (were|was|am|are|) (going|want|would|planning|planned|thinking|considering|) (to|is|about|on|) (killing|taking|take) (myself|themselves|them self|herself|himself|their|my|his|her) (life|own life|)

Response: 'I would tell you not too.' She says rather plainly. 'I would also tell you to call the following number. 1-800-273-TALK (8255).'

Is there a way for a bot to say something like 'then they lived happily ever after' and then end the conversation? or does the user just have to infer that they should leave now

You could do something like this...


Response: 'then they lived happily ever after'

Seek: xnomatch
response: goto (Insert number that sends you back to the 'they lived happily ever after response.)

That way the user gets stuck in an endless loop until the chat is reinitialized.