Semantic similarity chatbots from plain-text files. Code examples released under CC0 https://creativecommons.org/choose/zero/, other text released under CC BY 4.0 https://creativecommons.org/licenses/by/4.0/

from-plain-text.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Semantic similarity chatbots from plain-text files\n",
    "\n",
    "By [Allison Parrish](http://www.decontextualize.com/)\n",
    "\n",
    "This needs copy, sorry :( :( :( But it works!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "input_file = \"gutenberg_conversations.txt\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "!pip install https://github.com/aparrish/semanticsimilaritychatbot/archive/master.zip"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from semanticsimilaritychatbot import SemanticSimilarityChatbot\n",
    "import spacy\n",
    "nlp = spacy.load('en_core_web_lg')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "chatbot = SemanticSimilarityChatbot(nlp, 300)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "lastline = None\n",
    "for line in open(input_file):\n",
    "    line = line.strip()\n",
    "    # empty lines mean \"end of conversation\"\n",
    "    if line == \"\":\n",
    "        lastline = None\n",
    "        continue\n",
    "    if lastline is not None:\n",
    "        chatbot.add_pair(lastline, line)\n",
    "    lastline = line"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "chatbot.build()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'You must not be called Tiny any more. It is an ugly name, and you are so very pretty. We will call you Maia.'"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chatbot.response_for(\"Hello there.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "!pip install flask"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "chatbot_html = \"\"\"\n",
    "<style type=\"text/css\">#log p { margin: 5px; font-family: sans-serif; }</style>\n",
    "<div id=\"log\"\n",
    "     style=\"box-sizing: border-box;\n",
    "            width: 600px;\n",
    "            height: 32em;\n",
    "            border: 1px grey solid;\n",
    "            padding: 2px;\n",
    "            overflow: scroll;\">\n",
    "</div>\n",
    "<input type=\"text\" id=\"typehere\" placeholder=\"type here!\"\n",
    "       style=\"box-sizing: border-box;\n",
    "              width: 600px;\n",
    "              margin-top: 5px;\">\n",
    "<script>\n",
    "function paraWithText(t) {\n",
    "    let tn = document.createTextNode(t);\n",
    "    let ptag = document.createElement('p');\n",
    "    ptag.appendChild(tn);\n",
    "    return ptag;\n",
    "}\n",
    "document.querySelector('#typehere').onchange = async function() {\n",
    "    let inputField = document.querySelector('#typehere');\n",
    "    let val = inputField.value;\n",
    "    inputField.value = \"\";\n",
    "    let resp = await getResp(val);\n",
    "    let objDiv = document.getElementById(\"log\");\n",
    "    objDiv.appendChild(paraWithText('😀: ' + val));\n",
    "    objDiv.appendChild(paraWithText('🤖: ' + resp));\n",
    "    objDiv.scrollTop = objDiv.scrollHeight;\n",
    "};\n",
    "async function getResp(val) {\n",
    "    let resp = await fetch(\"/response.json?sentence=\" + \n",
    "        encodeURIComponent(val));\n",
    "    let data = await resp.json();\n",
    "    return data['result'];\n",
    "}\n",
    "</script>\n",
    "\"\"\"\n",
    "from flask import Flask, request, jsonify\n",
    "app = Flask(__name__)\n",
    "@app.route(\"/response.json\")\n",
    "def response():\n",
    "    sentence = request.args['sentence']\n",
    "    return jsonify(\n",
    "        {'result': chatbot.response_for(sentence)})\n",
    "@app.route(\"/\")\n",
    "def home():\n",
    "    return chatbot_html\n",
    "app.run()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}