Chatbot-specific answers

Question

I'm creating a chatbot that asks questions and answers questions, but for now it doesn't have a specific function of answering specific questions that it asks itself. I think you can solve this in the lists themselves

import string
import re
import random

    class eliza:
      def __init__(self):
        self.keys = list(map(lambda x:re.compile(x[0], re.IGNORECASE),gPats))
        self.values = list(map(lambda x:x[1],gPats))
    
      #----------------------------------------------------------------------
      # translate: take a string, replace any words found in dict.keys()
      #  with the corresponding dict.values()
      #----------------------------------------------------------------------
      def translate(self,str,dict):
        words = str.lower().split()
        keys = dict.keys();
        for i in range(0,len(words)):
          if words[i] in keys:
            words[i] = dict[words[i]]
        return ' '.join(words)
    
      #----------------------------------------------------------------------
      #  respond: take a string, a set of regexps, and a corresponding
      #    set of response lists; find a match, and return a randomly
      #    chosen response from the corresponding list.
      #----------------------------------------------------------------------
      def respond(self,str):
        # find a match among keys
        for i in range(0, len(self.keys)):
          match = self.keys[i].match(str)
          if match:
            # found a match ... stuff with corresponding value
            # chosen randomly from among the available options
            resp = random.choice(self.values[i])
            # we've got a response... stuff in reflected text where indicated
            pos = resp.find('%')
            while pos > -1:
              num = int(resp[pos+1:pos+2])
              resp = resp[:pos] + \
                self.translate(match.group(num),gReflections) + \
                resp[pos+2:]
              pos = resp.find('%')
            # fix munged punctuation at the end
            if resp[-2:] == '?.': resp = resp[:-2] + '.'
            if resp[-2:] == '??': resp = resp[:-2] + '?'
            return resp
    
    #----------------------------------------------------------------------
    # gReflections, a translation table used to convert things you say
    #    into things the computer says back, e.g. "I am" --> "you are"
    #----------------------------------------------------------------------
    gReflections = {
      "am"   : "are",
      "was"  : "were",
      "i"    : "you",
      "i'd"  : "you would",
      "i've"  : "you have",
      "i'll"  : "you will",
      "my"  : "your",
      "are"  : "am",
      "you've": "I have",
      "you'll": "I will",
      "your"  : "my",
      "yours"  : "mine",
      "you"  : "me",
      "me"  : "you"
    }
    
    #----------------------------------------------------------------------
    # gPats, the main response table.  Each element of the list is a
    #  two-element list; the first is a regexp, and the second is a
    #  list of possible responses, with group-macros labelled as
    #  %1, %2, etc.
    #----------------------------------------------------------------------
    gPats = [
      [r'I need (.*)',
      [  "Why do you need %1?",
        "Would it really help you to get %1?",
        "Are you sure you need %1?"]],
]

I'd like to make the chatbot give a specific answer if it's only after it asks itself a specific question. For example:

User: hello

Bot: Hello! What is your favorite color?

User: Red.

Bot: Interesting, I also like red.

I thought about doing something like this, but it doesn't work:

     [r'Hello (.*)',
          [  "Hello! What is your favorite color?",
[r'%1', 
["Interesting, I also like %1.]]]]
    ]

Answer 1

This might not be an answer your looking for but the usual way to implement such a chatbot is in a "Call-Response"-manner.

That means the user sends a text to the chatbot and the chatbot tries to categorize the sentence (and its Intent) and by categorizing tries to answer with a tag-correlating (and predefined) answer-sentence. This already would suggest the usage of a small neural network combined with usual chatbot libraries for tokenizing and lemmatizing sentences(creating the word-base of all words). I can recommend some tutorials on that matter (for example tec with tims https://www.techwithtim.net/tutorials/ai-chatbot/part-1/).

What you try implies using such a framework plus memorizing some states for later usage plus temporary session-knowledge about what has been talked to the same user-id and then chain answers together for a somewhat seamless talk with detailed and variable information-exchange.

For your 'chatbot ask questions first part', this is harder to do. You would need to build somewhat of a behavior tree which your chatbot follows. This tree would dictate questions to ask if some actions where made by the user like "If last question was 'Whats your name' + Answer of user => next message to user should be 'What is your favorite color'". This is in generall possible but would require quite some overhead to post here in a single run. I hope that helped.