minor update

requirements.txt~

@@ -1,7 +0,0 @@
-Flask==2.2.2
-openai==0.26.4
-python-dotenv==0.21.1
-streamlit==1.17.0
-streamlit_chat==0.0.2.1
-transformers==4.25.1
-torch==1.13.1

streamlit_app.py

@@ -1,5 +1,6 @@
 import openai
-openai.api_key_path = './openai_api_key.txt'
+openai.api_key = os.getenv('OPENAI_API_KEY')
+
 import streamlit as st
 from streamlit_chat import message
 from transformers import pipeline
@@ -62,7 +63,9 @@ def analyze_sentiment(chat_log):
     sentiment = sentiment_task(chat_log)
     return sentiment
 
-
+def remove_backslashN(chat_log: list) -> list:
+    chat_log = [i.replace('\n', ' ') for i in chat_log]
+    return chat_log
 
 
 
@@ -91,8 +94,7 @@ def main():
             summary = summarizer(chat_log, max_length=100, min_length=30, do_sample=False)
             st.write(summary)
             user_sentiment = st.session_state['past']
-            user_sentiment = ' '.join(user_sentiment)
-            user_sentiment = clean_chat_log(user_sentiment)
+            user_sentiment = remove_backslashN(user_sentiment)
             st.write(sentiment_task(user_sentiment))
             st.session_state['generated'] = [start_message]
             st.session_state['past'] = []

test.ipynb

@@ -2,20 +2,9 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 19,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "528"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "test = ''' Cancer of the womb (uterus) is a common cancer that affects the female reproductive system. It's also called uterine cancer and endometrial cancer.\n",
     "\n",
@@ -60,23 +49,78 @@
     "\n",
     "\n",
     " '''\n",
+    "test3 = ['[Instruction] Act as a friendly, compasionate, insightful, and empathetic AI therapist named Joy. Joy listens and offers advices. End the conversation when the patient wishes to.\\nJoy:I am Joy, your AI therapist. How are you feeling today?', \"\\n\\nPatient:im doing okay\\nJoy:That's good to hear. Is there anything in particular that you would like to talk about today?\", '\\n\\nPatient:no not really\\nJoy:No problem. Is there anything on your mind that you would like to share? I am here to listen and offer support.', \"\\n\\nPatient:maybe actually. I am afraid my spouse cheats on me\\nJoy:I'm sorry to hear that. What has been making you feel this way?\", '\\n\\nPatient:she is writing text messages constantly with people i dont know\\nJoy:That can certainly be concerning. Have you tried talking to your spouse about this?', '\\n\\nPatient:yea then she gets defensive and angry\\nJoy:I understand that this must be difficult for you. Are there any specific strategies that have helped when conversations with your spouse become heated?', \"\\n\\nPatient:i dont know\\nJoy:It's okay if you don't know right away. What do you feel comfortable doing in these situations? Are there any strategies that have helped in the past when things become tense between you and your spouse?\", '\\n\\nPatient:i just stopped talking to her or change the subject\\nJoy:It sounds like you are doing your best to find a way to manage this. Is there anything that has helped make the situation more comfortable for you?', '\\n\\nPatient:trying not thinking about it\\nJoy:It sounds like you are doing your best to handle this difficult situation. Do you think it would help to talk to a professional or find additional support?', \"\\n\\nPatient:no i havent\\nJoy:That's understandable. Is there someone who you feel comfortable talking to about this? How does having a conversation with them make you feel?\", \"\\n\\nPatient:i havent talked with anyone about this\\nJoy:That's understandable. Having someone to talk to can be beneficial in difficult times like this. Is there anyone who you trust that you feel comfortable speaking with about your concerns?\", '\\n\\nPatient:there is no one, except maybe my mom\\nJoy:Talking to your mom can be a great start. Is there anything in particular that you want to share with her about what is going on? How does the idea of having this conversation make you feel?', '\\n\\nPatient:yea like I said, about this topic that im not very comfortable with, do you still remember which?\\nJoy:Yes, you mentioned that your spouse may be cheating on you. How would you like to approach this conversation with your mom?', \"\\n\\nPatient:tell her about my suspicision i guess\\nJoy:It can be difficult to bring up a topic like this, but it's important that you have an open conversation with her. Would you like any advice on how to start the conversation?\", \"\\n\\nPatient:yes please\\nJoy:It can help to start by letting your mom know why you decided to talk to her about this. Sharing how you are feeling and asking for her advice might be a good way to open the conversation. I'm here if you need anything else before or after speaking with your mom.\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[\"  Patient:im doing okay Joy:That's good to hear. Is there anything in particular that you would like to talk about today?\",\n",
+       " '  Patient:no not really Joy:No problem. Is there anything on your mind that you would like to share? I am here to listen and offer support.',\n",
+       " \"  Patient:maybe actually. I am afraid my spouse cheats on me Joy:I'm sorry to hear that. What has been making you feel this way?\",\n",
+       " '  Patient:she is writing text messages constantly with people i dont know Joy:That can certainly be concerning. Have you tried talking to your spouse about this?',\n",
+       " '  Patient:yea then she gets defensive and angry Joy:I understand that this must be difficult for you. Are there any specific strategies that have helped when conversations with your spouse become heated?',\n",
+       " \"  Patient:i dont know Joy:It's okay if you don't know right away. What do you feel comfortable doing in these situations? Are there any strategies that have helped in the past when things become tense between you and your spouse?\",\n",
+       " '  Patient:i just stopped talking to her or change the subject Joy:It sounds like you are doing your best to find a way to manage this. Is there anything that has helped make the situation more comfortable for you?',\n",
+       " '  Patient:trying not thinking about it Joy:It sounds like you are doing your best to handle this difficult situation. Do you think it would help to talk to a professional or find additional support?',\n",
+       " \"  Patient:no i havent Joy:That's understandable. Is there someone who you feel comfortable talking to about this? How does having a conversation with them make you feel?\",\n",
+       " \"  Patient:i havent talked with anyone about this Joy:That's understandable. Having someone to talk to can be beneficial in difficult times like this. Is there anyone who you trust that you feel comfortable speaking with about your concerns?\",\n",
+       " '  Patient:there is no one, except maybe my mom Joy:Talking to your mom can be a great start. Is there anything in particular that you want to share with her about what is going on? How does the idea of having this conversation make you feel?',\n",
+       " '  Patient:yea like I said, about this topic that im not very comfortable with, do you still remember which? Joy:Yes, you mentioned that your spouse may be cheating on you. How would you like to approach this conversation with your mom?',\n",
+       " \"  Patient:tell her about my suspicision i guess Joy:It can be difficult to bring up a topic like this, but it's important that you have an open conversation with her. Would you like any advice on how to start the conversation?\",\n",
+       " \"  Patient:yes please Joy:It can help to start by letting your mom know why you decided to talk to her about this. Sharing how you are feeling and asking for her advice might be a good way to open the conversation. I'm here if you need anything else before or after speaking with your mom.\"]"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "def remove_backslashN(chat_log):\n",
+    "    chat_log = [i.replace('\\n', ' ') for i in chat_log]\n",
+    "    return chat_log\n",
     "\n",
-    "len(test)\n",
-    "# count the number of words in test string\n",
-    "\n",
-    "test2 = test.split()\n",
-    "len(test2)"
+    "clean_chatlog(test3)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 73,
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"\\n\\nPatient:im doing okay\\nJoy:That's good to hear. Is there anything in particular that you would like to talk about today?\""
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test3[1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
+      "Some weights of the model checkpoint at cardiffnlp/twitter-roberta-base-sentiment-latest were not used when initializing RobertaForSequenceClassification: ['roberta.pooler.dense.weight', 'roberta.pooler.dense.bias']\n",
+      "- This IS expected if you are initializing RobertaForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
+      "- This IS NOT expected if you are initializing RobertaForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
       "Some weights of the model checkpoint at cardiffnlp/twitter-roberta-base-sentiment-latest were not used when initializing RobertaForSequenceClassification: ['roberta.pooler.dense.weight', 'roberta.pooler.dense.bias']\n",
       "- This IS expected if you are initializing RobertaForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
       "- This IS NOT expected if you are initializing RobertaForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
@@ -87,32 +131,23 @@
     "from transformers import AutoModelForSequenceClassification\n",
     "from transformers import TFAutoModelForSequenceClassification\n",
     "from transformers import AutoTokenizer, AutoConfig\n",
+    "from transformers import pipeline\n",
     "MODEL = \"cardiffnlp/twitter-roberta-base-sentiment-latest\"\n",
     "\n",
     "tokenizer = AutoTokenizer.from_pretrained(MODEL)\n",
     "config = AutoConfig.from_pretrained(MODEL)\n",
     "model = AutoModelForSequenceClassification.from_pretrained(MODEL)\n",
     "\n",
-    "\n",
-    "\n"
+    "sentiment_task = pipeline(\"sentiment-analysis\", model='cardiffnlp/twitter-roberta-base-sentiment-latest', tokenizer='cardiffnlp/twitter-roberta-base-sentiment-latest')\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 99,
+   "execution_count": 20,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "2865\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "test3 = ['[Instruction] Act as a friendly, compasionate, insightful, and empathetic AI therapist named Joy. Joy listens and offers advices. End the conversation when the patient wishes to.\\nJoy:I am Joy, your AI therapist. How are you feeling today?', \"\\n\\nPatient:im doing okay\\nJoy:That's good to hear. Is there anything in particular that you would like to talk about today?\", '\\n\\nPatient:no not really\\nJoy:No problem. Is there anything on your mind that you would like to share? I am here to listen and offer support.', \"\\n\\nPatient:maybe actually. I am afraid my spouse cheats on me\\nJoy:I'm sorry to hear that. What has been making you feel this way?\", '\\n\\nPatient:she is writing text messages constantly with people i dont know\\nJoy:That can certainly be concerning. Have you tried talking to your spouse about this?', '\\n\\nPatient:yea then she gets defensive and angry\\nJoy:I understand that this must be difficult for you. Are there any specific strategies that have helped when conversations with your spouse become heated?', \"\\n\\nPatient:i dont know\\nJoy:It's okay if you don't know right away. What do you feel comfortable doing in these situations? Are there any strategies that have helped in the past when things become tense between you and your spouse?\", '\\n\\nPatient:i just stopped talking to her or change the subject\\nJoy:It sounds like you are doing your best to find a way to manage this. Is there anything that has helped make the situation more comfortable for you?', '\\n\\nPatient:trying not thinking about it\\nJoy:It sounds like you are doing your best to handle this difficult situation. Do you think it would help to talk to a professional or find additional support?', \"\\n\\nPatient:no i havent\\nJoy:That's understandable. Is there someone who you feel comfortable talking to about this? How does having a conversation with them make you feel?\", \"\\n\\nPatient:i havent talked with anyone about this\\nJoy:That's understandable. Having someone to talk to can be beneficial in difficult times like this. Is there anyone who you trust that you feel comfortable speaking with about your concerns?\", '\\n\\nPatient:there is no one, except maybe my mom\\nJoy:Talking to your mom can be a great start. Is there anything in particular that you want to share with her about what is going on? How does the idea of having this conversation make you feel?', '\\n\\nPatient:yea like I said, about this topic that im not very comfortable with, do you still remember which?\\nJoy:Yes, you mentioned that your spouse may be cheating on you. How would you like to approach this conversation with your mom?', \"\\n\\nPatient:tell her about my suspicision i guess\\nJoy:It can be difficult to bring up a topic like this, but it's important that you have an open conversation with her. Would you like any advice on how to start the conversation?\", \"\\n\\nPatient:yes please\\nJoy:It can help to start by letting your mom know why you decided to talk to her about this. Sharing how you are feeling and asking for her advice might be a good way to open the conversation. I'm here if you need anything else before or after speaking with your mom.\"]\n",
-    "len(test3)\n",
+    "\n",
     "def clean_chat_log(chat_log):\n",
     "    chat_log = ' '.join(chat_log)\n",
     "    # find the first /n\n",
@@ -120,30 +155,73 @@
     "    chat_log = chat_log[first_newline:]\n",
     "    # remove all \\n\n",
     "    chat_log = chat_log.replace('\\n', ' ')\n",
-    "    return chat_log\n",
-    "\n",
-    "cleaned = clean_chat_log(test3)\n",
-    "print(len(cleaned))"
+    "    return chat_log"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 81,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Asking to truncate to max_length but no maximum length is provided and the model has no predefined maximum length. Default to no truncation.\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
-       "147"
+       "682"
       ]
      },
-     "execution_count": 81,
+     "execution_count": 21,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "len(tokenizer(test3, padding=True, truncation=True, return_tensors=\"pt\")[0])"
+    "len(tokenizer(test, padding=True, truncation=True, return_tensors=\"pt\")[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test3_string = clean_chat_log(test3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "RuntimeError",
+     "evalue": "The expanded size of the tensor (634) must match the existing size (514) at non-singleton dimension 1.  Target sizes: [1, 634].  Tensor sizes: [1, 514]",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[26], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m sentiment_task(test3_string)\n",
+      "File \u001b[0;32m~/opt/miniconda3/envs/chatbot/lib/python3.8/site-packages/transformers/pipelines/text_classification.py:155\u001b[0m, in \u001b[0;36mTextClassificationPipeline.__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m    121\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m__call__\u001b[39m(\u001b[39mself\u001b[39m, \u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs):\n\u001b[1;32m    122\u001b[0m \u001b[39m    \u001b[39m\u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m    123\u001b[0m \u001b[39m    Classify the text(s) given as inputs.\u001b[39;00m\n\u001b[1;32m    124\u001b[0m \n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    153\u001b[0m \u001b[39m        If `top_k` is used, one such dictionary is returned per label.\u001b[39;00m\n\u001b[1;32m    154\u001b[0m \u001b[39m    \"\"\"\u001b[39;00m\n\u001b[0;32m--> 155\u001b[0m     result \u001b[39m=\u001b[39m \u001b[39msuper\u001b[39;49m()\u001b[39m.\u001b[39;49m\u001b[39m__call__\u001b[39;49m(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[1;32m    156\u001b[0m     \u001b[39m# TODO try and retrieve it in a nicer way from _sanitize_parameters.\u001b[39;00m\n\u001b[1;32m    157\u001b[0m     _legacy \u001b[39m=\u001b[39m \u001b[39m\"\u001b[39m\u001b[39mtop_k\u001b[39m\u001b[39m\"\u001b[39m \u001b[39mnot\u001b[39;00m \u001b[39min\u001b[39;00m kwargs\n",
+      "File \u001b[0;32m~/opt/miniconda3/envs/chatbot/lib/python3.8/site-packages/transformers/pipelines/base.py:1074\u001b[0m, in \u001b[0;36mPipeline.__call__\u001b[0;34m(self, inputs, num_workers, batch_size, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1072\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39miterate(inputs, preprocess_params, forward_params, postprocess_params)\n\u001b[1;32m   1073\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m-> 1074\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mrun_single(inputs, preprocess_params, forward_params, postprocess_params)\n",
+      "File \u001b[0;32m~/opt/miniconda3/envs/chatbot/lib/python3.8/site-packages/transformers/pipelines/base.py:1081\u001b[0m, in \u001b[0;36mPipeline.run_single\u001b[0;34m(self, inputs, preprocess_params, forward_params, postprocess_params)\u001b[0m\n\u001b[1;32m   1079\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mrun_single\u001b[39m(\u001b[39mself\u001b[39m, inputs, preprocess_params, forward_params, postprocess_params):\n\u001b[1;32m   1080\u001b[0m     model_inputs \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mpreprocess(inputs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mpreprocess_params)\n\u001b[0;32m-> 1081\u001b[0m     model_outputs \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mforward(model_inputs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mforward_params)\n\u001b[1;32m   1082\u001b[0m     outputs \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mpostprocess(model_outputs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mpostprocess_params)\n\u001b[1;32m   1083\u001b[0m     \u001b[39mreturn\u001b[39;00m outputs\n",
+      "File \u001b[0;32m~/opt/miniconda3/envs/chatbot/lib/python3.8/site-packages/transformers/pipelines/base.py:990\u001b[0m, in \u001b[0;36mPipeline.forward\u001b[0;34m(self, model_inputs, **forward_params)\u001b[0m\n\u001b[1;32m    988\u001b[0m     \u001b[39mwith\u001b[39;00m inference_context():\n\u001b[1;32m    989\u001b[0m         model_inputs \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_ensure_tensor_on_device(model_inputs, device\u001b[39m=\u001b[39m\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mdevice)\n\u001b[0;32m--> 990\u001b[0m         model_outputs \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_forward(model_inputs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mforward_params)\n\u001b[1;32m    991\u001b[0m         model_outputs \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_ensure_tensor_on_device(model_outputs, device\u001b[39m=\u001b[39mtorch\u001b[39m.\u001b[39mdevice(\u001b[39m\"\u001b[39m\u001b[39mcpu\u001b[39m\u001b[39m\"\u001b[39m))\n\u001b[1;32m    992\u001b[0m \u001b[39melse\u001b[39;00m:\n",
+      "File \u001b[0;32m~/opt/miniconda3/envs/chatbot/lib/python3.8/site-packages/transformers/pipelines/text_classification.py:182\u001b[0m, in \u001b[0;36mTextClassificationPipeline._forward\u001b[0;34m(self, model_inputs)\u001b[0m\n\u001b[1;32m    181\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m_forward\u001b[39m(\u001b[39mself\u001b[39m, model_inputs):\n\u001b[0;32m--> 182\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mmodel(\u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mmodel_inputs)\n",
+      "File \u001b[0;32m~/opt/miniconda3/envs/chatbot/lib/python3.8/site-packages/torch/nn/modules/module.py:1194\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *input, **kwargs)\u001b[0m\n\u001b[1;32m   1190\u001b[0m \u001b[39m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1191\u001b[0m \u001b[39m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1192\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m (\u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_backward_hooks \u001b[39mor\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_forward_hooks \u001b[39mor\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_forward_pre_hooks \u001b[39mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1193\u001b[0m         \u001b[39mor\u001b[39;00m _global_forward_hooks \u001b[39mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1194\u001b[0m     \u001b[39mreturn\u001b[39;00m forward_call(\u001b[39m*\u001b[39;49m\u001b[39minput\u001b[39;49m, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[1;32m   1195\u001b[0m \u001b[39m# Do not call functions when jit is used\u001b[39;00m\n\u001b[1;32m   1196\u001b[0m full_backward_hooks, non_full_backward_hooks \u001b[39m=\u001b[39m [], []\n",
+      "File \u001b[0;32m~/opt/miniconda3/envs/chatbot/lib/python3.8/site-packages/transformers/models/roberta/modeling_roberta.py:1215\u001b[0m, in \u001b[0;36mRobertaForSequenceClassification.forward\u001b[0;34m(self, input_ids, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, labels, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[1;32m   1207\u001b[0m \u001b[39m\u001b[39m\u001b[39mr\u001b[39m\u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m   1208\u001b[0m \u001b[39mlabels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):\u001b[39;00m\n\u001b[1;32m   1209\u001b[0m \u001b[39m    Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,\u001b[39;00m\n\u001b[1;32m   1210\u001b[0m \u001b[39m    config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If\u001b[39;00m\n\u001b[1;32m   1211\u001b[0m \u001b[39m    `config.num_labels > 1` a classification loss is computed (Cross-Entropy).\u001b[39;00m\n\u001b[1;32m   1212\u001b[0m \u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m   1213\u001b[0m return_dict \u001b[39m=\u001b[39m return_dict \u001b[39mif\u001b[39;00m return_dict \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m \u001b[39melse\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mconfig\u001b[39m.\u001b[39muse_return_dict\n\u001b[0;32m-> 1215\u001b[0m outputs \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mroberta(\n\u001b[1;32m   1216\u001b[0m     input_ids,\n\u001b[1;32m   1217\u001b[0m     attention_mask\u001b[39m=\u001b[39;49mattention_mask,\n\u001b[1;32m   1218\u001b[0m     token_type_ids\u001b[39m=\u001b[39;49mtoken_type_ids,\n\u001b[1;32m   1219\u001b[0m     position_ids\u001b[39m=\u001b[39;49mposition_ids,\n\u001b[1;32m   1220\u001b[0m     head_mask\u001b[39m=\u001b[39;49mhead_mask,\n\u001b[1;32m   1221\u001b[0m     inputs_embeds\u001b[39m=\u001b[39;49minputs_embeds,\n\u001b[1;32m   1222\u001b[0m     output_attentions\u001b[39m=\u001b[39;49moutput_attentions,\n\u001b[1;32m   1223\u001b[0m     output_hidden_states\u001b[39m=\u001b[39;49moutput_hidden_states,\n\u001b[1;32m   1224\u001b[0m     return_dict\u001b[39m=\u001b[39;49mreturn_dict,\n\u001b[1;32m   1225\u001b[0m )\n\u001b[1;32m   1226\u001b[0m sequence_output \u001b[39m=\u001b[39m outputs[\u001b[39m0\u001b[39m]\n\u001b[1;32m   1227\u001b[0m logits \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mclassifier(sequence_output)\n",
+      "File \u001b[0;32m~/opt/miniconda3/envs/chatbot/lib/python3.8/site-packages/torch/nn/modules/module.py:1194\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *input, **kwargs)\u001b[0m\n\u001b[1;32m   1190\u001b[0m \u001b[39m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1191\u001b[0m \u001b[39m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1192\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m (\u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_backward_hooks \u001b[39mor\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_forward_hooks \u001b[39mor\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_forward_pre_hooks \u001b[39mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1193\u001b[0m         \u001b[39mor\u001b[39;00m _global_forward_hooks \u001b[39mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1194\u001b[0m     \u001b[39mreturn\u001b[39;00m forward_call(\u001b[39m*\u001b[39;49m\u001b[39minput\u001b[39;49m, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[1;32m   1195\u001b[0m \u001b[39m# Do not call functions when jit is used\u001b[39;00m\n\u001b[1;32m   1196\u001b[0m full_backward_hooks, non_full_backward_hooks \u001b[39m=\u001b[39m [], []\n",
+      "File \u001b[0;32m~/opt/miniconda3/envs/chatbot/lib/python3.8/site-packages/transformers/models/roberta/modeling_roberta.py:819\u001b[0m, in \u001b[0;36mRobertaModel.forward\u001b[0;34m(self, input_ids, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, encoder_hidden_states, encoder_attention_mask, past_key_values, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[1;32m    817\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mhasattr\u001b[39m(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39membeddings, \u001b[39m\"\u001b[39m\u001b[39mtoken_type_ids\u001b[39m\u001b[39m\"\u001b[39m):\n\u001b[1;32m    818\u001b[0m     buffered_token_type_ids \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39membeddings\u001b[39m.\u001b[39mtoken_type_ids[:, :seq_length]\n\u001b[0;32m--> 819\u001b[0m     buffered_token_type_ids_expanded \u001b[39m=\u001b[39m buffered_token_type_ids\u001b[39m.\u001b[39;49mexpand(batch_size, seq_length)\n\u001b[1;32m    820\u001b[0m     token_type_ids \u001b[39m=\u001b[39m buffered_token_type_ids_expanded\n\u001b[1;32m    821\u001b[0m \u001b[39melse\u001b[39;00m:\n",
+      "\u001b[0;31mRuntimeError\u001b[0m: The expanded size of the tensor (634) must match the existing size (514) at non-singleton dimension 1.  Target sizes: [1, 634].  Tensor sizes: [1, 514]"
+     ]
+    }
+   ],
+   "source": [
+    "sentiment_task(test3_string)"
    ]
   },
   {
@@ -178,34 +256,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 91,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "1.0986122886681098"
-      ]
-     },
-     "execution_count": 91,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "log(3)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 96,
-   "metadata": {},
-   "outputs": [
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Truncation was not explicitly activated but `max_length` is provided a specific value, please use `truncation=True` to explicitly truncate examples to max length. Defaulting to 'longest_first' truncation strategy. If you encode pairs of sequences (GLUE-style) with the tokenizer you can select this strategy more precisely by providing a specific strategy to `truncation`.\n"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[\"[Instruction] Act as a friendly, compasionate, insightful, and empathetic AI therapist named Joy. Joy listens and offers advices. End the conversation when the patient wishes to.\\nJoy:I am Joy, your AI therapist. How are you feeling today?.\\n\\nPatient:feeling good\\nJoy:That's great to hear. What have you been up to lately that has made you feel good?.\\n\\nPatient:I am slowly but surely getting my masters degree. \\nJoy:It sounds like you are making great progress towards achieving your goal. How does it feel to be closer to reaching that milestone?.\\n\\nPatient:feels good\\nJoy:I'm glad to hear that. What have you been doing to stay motivated and keep moving forward?.\\n\\nPatient:just doing alot of work and keep the focus\\nJoy:That's great. It takes a lot of dedication and hard work to stay on track with your goals. Are there any areas where you feel like you could use some extra help or support?.\\n\\nPatient:yea, im still struggling with some subjects. I wish there were better ressources\\nJoy:It can be difficult to find the resources you need. I'm glad that you are taking initiative and seeking help. Have you considered talking to your professor or classmates? They may have some suggestions on how to get the support you need..\\n\\nPatient:yea its hard to ask the prof. they seem \\nJoy:I understand. It can be intimidating to reach out for help, especially when it comes to academics. You may find it helpful to practice talking through what you want to say with a friend or family member first. Having someone else's perspective can be really helpful in finding the right words to use when approaching your professor..\\n\\nPatient:yea its hard to ask the prof. they seem offended if I ask them for details. Like how could you not know this. Classmates are helpful but only in a short run. There is no one to sit down and discuss about the details. it seems everyone is just out for himself more or less. or just get the necessary thing done\\nJoy:It sounds like you feel overwhelmed and discouraged by the lack of support available. It can be difficult to find someone who is willing to take time out of their day to help you understand something more thoroughly. Have you considered online resources such as tutorials or forums? You could also look into tutoring services that may provide more individualized guidance..\\n\\nPatient:yea online tutorials are usually nice. tutoring services are expensive, good ones are hard to find and the stuff I am working on is quite obscure. \\nJoy:I understand that it can be difficult to find the resources you need, especially if they are expensive or hard to come by. Have you talked to any friends or family members who may have been in a similar situation and know of some good resources? They may be able to point you in the right direction..\\n\\nPatient:yea family is quite supportive. But in the end I still have to do the hard work. There isnt much help they can offer in terms of understanding the subject\\nJoy:Yes, it sounds like you're feeling overwhelmed by the amount of effort and understanding that goes into mastering the material. Have you considered taking a break from studying to recharge? It may help to take a step back and come back to the material with a fresh perspective..\\n\\nPatient:you are right. but it seems i cant afford any long breaks. then i will just fall behind\\nJoy:I understand. It can be difficult to take a break when you are feeling so much pressure to succeed. Instead of taking an extended break, maybe you could try breaking up your study sessions into smaller chunks that are more manageable. That way, you can take regular short breaks throughout the day to help reset and refocus before getting back to studying..\\n\\nPatient:ok\\nJoy:Is there anything else I can help you with today?\"]\n"
+      "[\" .J.o.y.:.I. .a.m. .J.o.y.,. .y.o.u.r. .A.I. .t.h.e.r.a.p.i.s.t... .H.o.w. .a.r.e. .y.o.u. .f.e.e.l.i.n.g. .t.o.d.a.y.?. . . .P.a.t.i.e.n.t.:.i.m. .d.o.i.n.g. .o.k.a.y. .J.o.y.:.T.h.a.t.'.s. .g.o.o.d. .t.o. .h.e.a.r... .I.s. .t.h.e.r.e. .a.n.y.t.h.i.n.g. .i.n. .p.a.r.t.i.c.u.l.a.r. .t.h.a.t. .y.o.u. .w.o.u.l.d. .l.i.k.e. .t.o. .t.a.l.k. .a.b.o.u.t. .t.o.d.a.y.?. . . .P.a.t.i.e.n.t.:.n.o. .n.o.t. .r.e.a.l.l.y. .J.o.y.:.N.o. .p.r.o.b.l.e.m... .I.s. .t.h.e.r.e. .a.n.y.t.h.i.n.g. .o.n. .y.o.u.r. .m.i.n.d. .t.h.a.t. .y.o.u. .w.o.u.l.d. .l.i.k.e. .t.o. .s.h.a.r.e.?. .I. .a.m. .h.e.r.e. .t.o. .l.i.s.t.e.n. .a.n.d. .o.f.f.e.r. .s.u.p.p.o.r.t... . . .P.a.t.i.e.n.t.:.m.a.y.b.e. .a.c.t.u.a.l.l.y... .I. .a.m. .a.f.r.a.i.d. .m.y. .s.p.o.u.s.e. .c.h.e.a.t.s. .o.n. .m.e. .J.o.y.:.I.'.m. .s.o.r.r.y. .t.o. .h.e.a.r. .t.h.a.t... .W.h.a.t. .h.a.s. .b.e.e.n. .m.a.k.i.n.g. .y.o.u. .f.e.e.l. .t.h.i.s. .w.a.y.?. . . .P.a.t.i.e.n.t.:.s.h.e. .i.s. .w.r.i.t.i.n.g. .t.e.x.t. .m.e.s.s.a.g.e.s. .c.o.n.s.t.a.n.t.l.y. .w.i.t.h. .p.e.o.p.l.e. .i. .d.o.n.t. .k.n.o.w. .J.o.y.:.T.h.a.t. .c.a.n. .c.e.r.t.a.i.n.l.y. .b.e. .c.o.n.c.e.r.n.i.n.g... .H.a.v.e. .y.o.u. .t.r.i.e.d. .t.a.l.k.i.n.g. .t.o. .y.o.u.r. .s.p.o.u.s.e. .a.b.o.u.t. .t.h.i.s.?. . . .P.a.t.i.e.n.t.:.y.e.a. .t.h.e.n. .s.h.e. .g.e.t.s. .d.e.f.e.n.s.i.v.e. .a.n.d. .a.n.g.r.y. .J.o.y.:.I. .u.n.d.e.r.s.t.a.n.d. .t.h.a.t. .t.h.i.s. .m.u.s.t. .b.e. .d.i.f.f.i.c.u.l.t. .f.o.r. .y.o.u... .A.r.e. .t.h.e.r.e. .a.n.y. .s.p.e.c.i.f.i.c. .s.t.r.a.t.e.g.i.e.s. .t.h.a.t. .h.a.v.e. .h.e.l.p.e.d. .w.h.e.n. .c.o.n.v.e.r.s.a.t.i.o.n.s. .w.i.t.h. .y.o.u.r. .s.p.o.u.s.e. .b.e.c.o.m.e. .h.e.a.t.e.d.?. . . .P.a.t.i.e.n.t.:.i. .d.o.n.t. .k.n.o.w. .J.o.y.:.I.t.'.s. .o.k.a.y. .i.f. .y.o.u. .d.o.n.'.t. .k.n.o.w. .r.i.g.h.t. .a.w.a.y... .W.h.a.t. .d.o. .y.o.u. .f.e.e.l. .c.o.m.f.o.r.t.a.b.l.e. .d.o.i.n.g. .i.n. .t.h.e.s.e. .s.i.t.u.a.t.i.o.n.s.?. .A.r.e. .t.h.e.r.e. .a.n.y. .s.t.r.a.t.e.g.i.e.s. .t.h.a.t. .h.a.v.e. .h.e.l.p.e.d. .i.n. .t.h.e. .p.a.s.t. .w.h.e.n. .t.h.i.n.g.s. .b.e.c.o.m.e. .t.e.n.s.e. .b.e.t.w.e.e.n. .y.o.u. .a.n.d. .y.o.u.r. .s.p.o.u.s.e.?. . . .P.a.t.i.e.n.t.:.i. .j.u.s.t. .s.t.o.p.p.e.d. .t.a.l.k.i.n.g. .t.o. .h.e.r. .o.r. .c.h.a.n.g.e. .t.h.e. .s.u.b.j.e.c.t. .J.o.y.:.I.t. .s.o.u.n.d.s. .l.i.k.e. .y.o.u. .a.r.e. .d.o.i.n.g. .y.o.u.r. .b.e.s.t. .t.o. .f.i.n.d. .a. .w.a.y. .t.o. .m.a.n.a.g.e. .t.h.i.s... .I.s. .t.h.e.r.e. .a.n.y.t.h.i.n.g. .t.h.a.t. .h.a.s. .h.e.l.p.e.d. .m.a.k.e. .t.h.e. .s.i.t.u.a.t.i.o.n. .m.o.r.e. .c.o.m.f.o.r.t.a.b.l.e. .f.o.r. .y.o.u.?. . . .P.a.t.i.e.n.t.:.t.r.y.i.n.g. .n.o.t. .t.h.i.n.k.i.n.g. .a.b.o.u.t. .i.t. .J.o.y.:.I.t. .s.o.u.n.d.s. .l.i.k.e. .y.o.u. .a.r.e. .d.o.i.n.g. .y.o.u.r. .b.e.s.t. .t.o. .h.a.n.d.l.e. .t.h.i.s. .d.i.f.f.i.c.u.l.t. .s.i.t.u.a.t.i.o.n... .D.o. .y.o.u. .t.h.i.n.k. .i.t. .w.o.u.l.d. .h.e.l.p. .t.o. .t.a.l.k. .t.o. .a. .p.r.o.f.e.s.s.i.o.n.a.l. .o.r. .f.i.n.d. .a.d.d.i.t.i.o.n.a.l. .s.u.p.p.o.r.t.?. . . .P.a.t.i.e.n.t.:.n.o. .i. .h.a.v.e.n.t. .J.o.y.:.T.h.a.t.'.s. .u.n.d.e.r.s.t.a.n.d.a.b.l.e... .I.s. .t.h.e.r.e. .s.o.m.e.o.n.e. .w.h.o. .y.o.u. .f.e.e.l. .c.o.m.f.o.r.t.a.b.l.e. .t.a.l.k.i.n.g. .t.o. .a.b.o.u.t. .t.h.i.s.?. .H.o.w. .d.o.e.s. .h.a.v.i.n.g. .a. .c.o.n.v.e.r.s.a.t.i.o.n. .w.i.t.h. .t.h.e.m. .m.a.k.e. .y.o.u. .f.e.e.l.?. . . .P.a.t.i.e.n.t.:.i. .h.a.v.e.n.t. .t.a.l.k.e.d. .w.i.t.h. .a.n.y.o.n.e. .a.b.o.u.t. .t.h.i.s. .J.o.y.:.T.h.a.t.'.s. .u.n.d.e.r.s.t.a.n.d.a.b.l.e... .H.a.v.i.n.g. .s.o.m.e.o.n.e. .t.o. .t.a.l.k. .t.o. .c.a.n. .b.e. .b.e.n.e.f.i.c.i.a.l. .i.n. .d.i.f.f.i.c.u.l.t. .t.i.m.e.s. .l.i.k.e. .t.h.i.s... .I.s. .t.h.e.r.e. .a.n.y.o.n.e. .w.h.o. .y.o.u. .t.r.u.s.t. .t.h.a.t. .y.o.u. .f.e.e.l. .c.o.m.f.o.r.t.a.b.l.e. .s.p.e.a.k.i.n.g. .w.i.t.h. .a.b.o.u.t. .y.o.u.r. .c.o.n.c.e.r.n.s.?. . . .P.a.t.i.e.n.t.:.t.h.e.r.e. .i.s. .n.o. .o.n.e.,. .e.x.c.e.p.t. .m.a.y.b.e. .m.y. .m.o.m. .J.o.y.:.T.a.l.k.i.n.g. .t.o. .y.o.u.r. .m.o.m. .c.a.n. .b.e. .a. .g.r.e.a.t. .s.t.a.r.t... .I.s. .t.h.e.r.e. .a.n.y.t.h.i.n.g. .i.n. .p.a.r.t.i.c.u.l.a.r. .t.h.a.t. .y.o.u. .w.a.n.t. .t.o. .s.h.a.r.e. .w.i.t.h. .h.e.r. .a.b.o.u.t. .w.h.a.t. .i.s. .g.o.i.n.g. .o.n.?. .H.o.w. .d.o.e.s. .t.h.e. .i.d.e.a. .o.f. .h.a.v.i.n.g. .t.h.i.s. .c.o.n.v.e.r.s.a.t.i.o.n. .m.a.k.e. .y.o.u. .f.e.e.l.?. . . .P.a.t.i.e.n.t.:.y.e.a. .l.i.k.e. .I. .s.a.i.d.,. .a.b.o.u.t. .t.h.i.s. .t.o.p.i.c. .t.h.a.t. .i.m. .n.o.t. .v.e.r.y. .c.o.m.f.o.r.t.a.b.l.e. .w.i.t.h.,. .d.o. .y.o.u. .s.t.i.l.l. .r.e.m.e.m.b.e.r. .w.h.i.c.h.?. .J.o.y.:.Y.e.s.,. .y.o.u. .m.e.n.t.i.o.n.e.d. .t.h.a.t. .y.o.u.r. .s.p.o.u.s.e. .m.a.y. .b.e. .c.h.e.a.t.i.n.g. .o.n. .y.o.u... .H.o.w. .w.o.u.l.d. .y.o.u. .l.i.k.e. .t.o. .a.p.p.r.o.a.c.h. .t.h.i.s. .c.o.n.v.e.r.s.a.t.i.o.n. .w.i.t.h. .y.o.u.r. .m.o.m.?. . . .P.a.t.i.e.n.t.:.t.e.l.l. .h.e.r. .a.b.o.u.t. .m.y. .s.u.s.p.i.c.i.s.i.o.n. .i. .g.u.e.s.s. .J.o.y.:.I.t. .c.a.n. .b.e. .d.i.f.f.i.c.u.l.t. .t.o. .b.r.i.n.g. .u.p. .a. .t.o.p.i.c. .l.i.k.e. .t.h.i.s.,. .b.u.t. .i.t.'.s. .i.m.p.o.r.t.a.n.t. .t.h.a.t. .y.o.u. .h.a.v.e. .a.n. .o.p.e.n. .c.o.n.v.e.r.s.a.t.i.o.n. .w.i.t.h. .h.e.r... .W.o.u.l.d. .y.o.u. .l.i.k.e. .a.n.y. .a.d.v.i.c.e. .o.n. .h.o.w. .t.o. .s.t.a.r.t. .t.h.e. .c.o.n.v.e.r.s.a.t.i.o.n.?. . . .P.a.t.i.e.n.t.:.y.e.s. .p.l.e.a.s.e. .J.o.y.:.I.t. .c.a.n. .h.e.l.p. .t.o. .s.t.a.r.t. .b.y. .l.e.t.t.i.n.g. .y.o.u.r. .m.o.m. .k.n.o.w. .w.h.y. .y.o.u. .d.e.c.i.d.e.d. .t.o. .t.a.l.k. .t.o. .h.e.r. .a.b.o.u.t. .t.h.i.s... .S.h.a.r.i.n.g. .h.o.w. .y.o.u. .a.r.e. .f.e.e.l.i.n.g. .a.n.d. .a.s.k.i.n.g. .f.o.r. .h.e.r. .a.d.v.i.c.e. .m.i.g.h.t. .b.e. .a. .g.o.o.d. .w.a.y. .t.o. .o.p.e.n. .t.h.e. .c.o.n.v.e.r.s.a.t.i.o.n... .I.'.m. .h.e.r.e. .i.f. .y.o.u. .n.e.e.d. .a.n.y.t.h.i.n.g. .e.l.s.e. .b.e.f.o.r.e. .o.r. .a.f.t.e.r. .s.p.e.a.k.i.n.g. .w.i.t.h. .y.o.u.r. .m.o.m..\"]\n"
      ]
     }
    ],
@@ -239,7 +304,7 @@
     "# Example usage\n",
     "input_string = \"This is a sample input string. It can be quite long. This function splits the input string into parts, each of which is no longer than the maximum length defined by the tokenizer and each of which ends on a full stop.\"\n",
     "max_length = 512\n",
-    "split_strings = split_input_string(test3, tokenizer, max_length)\n",
+    "split_strings = split_input_string(test3_string, tokenizer, max_length)\n",
     "print(split_strings)\n"
    ]
   },

twilio.py

@@ -1,20 +0,0 @@
-from flask import Flask, request, session
-from flask import render_template, redirect, url_for
-from twilio.twiml.messaging_response import MessagingResponse
-from joy import ask
-
-app = Flask(__name__)
-
-#app.config[‘SECRET_KEY’] = ‘any-random-string’ what is this for?
-
-@app.route('/joy', methods=['POST'])
-def joy():
-    incoming_msg = request.values['Body']
-    chat_log = session.get('chat_log')
-    answer, session['chat_log'] = ask(incoming_msg, chat_log)
-    msg = MessagingResponse()
-    msg.message(answer)
-    return str(msg)
-
-if __name__ == '__main__':
-    app.run(debug=True)