File size: 2,654 Bytes
8ca4128
 
 
 
 
 
 
 
 
 
 
 
232248c
 
 
 
 
 
 
 
8ca4128
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8124efd
 
 
6611fe9
8124efd
8ca4128
 
6611fe9
8124efd
8ca4128
 
 
 
 
 
 
 
 
 
 
 
8124efd
8ca4128
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
import gradio as gr

import nltk

nltk.download('popular')
from nltk.stem import WordNetLemmatizer

lemmatizer = WordNetLemmatizer()
import pickle
import numpy as np

from tensorflow.keras.models import load_model

model = load_model('model.h5')
import json
import random

intents = json.loads(open('data.json').read())
words = pickle.load(open('texts.pkl', 'rb'))
classes = pickle.load(open('labels.pkl', 'rb'))


def clean_up_sentence(sentence):
    # tokenize the pattern - split words into array
    sentence_words = nltk.word_tokenize(sentence)
    # stem each word - create short form for word
    sentence_words = [lemmatizer.lemmatize(word.lower()) for word in sentence_words]
    return sentence_words


# return bag of words array: 0 or 1 for each word in the bag that exists in the sentence

def bow(sentence, words, show_details=True):
    # tokenize the pattern
    sentence_words = clean_up_sentence(sentence)
    # bag of words - matrix of N words, vocabulary matrix
    bag = [0] * len(words)
    for s in sentence_words:
        for i, w in enumerate(words):
            if w == s:
                # assign 1 if current word is in the vocabulary position
                bag[i] = 1
                if show_details:
                    print("found in bag: %s" % w)
    return (np.array(bag))


def predict_class(sentence, model):
    # filter out predictions below a threshold
    p = bow(sentence, words, show_details=False)
    res = model.predict(np.array([p]))[0]
    ERROR_THRESHOLD = 0.25
    results = [[i, r] for i, r in enumerate(res) if r > ERROR_THRESHOLD]
    # sort by strength of probability
    results.sort(key=lambda x: x[1], reverse=True)
    return_list = []
    for r in results:
        return_list.append({"intent": classes[r[0]], "probability": str(r[1])})
    return return_list


def getResponse(ints, intents_json):
    tag = ints[0]['intent']
    list_of_intents = intents_json['intents']
    for i in list_of_intents:
        if (i['tag'] == tag):
            result = random.choice(i['responses'])
            break
    return result


def chatbot_response(msg, history):
    history = history or []
    s = list(sum(history, ()))
    s.append(msg)
    inp = ' '.join(s)
    ints = predict_class(msg, model)
    res = getResponse(ints, intents)
    history.append((msg, res))
    return history, history


prompt = "Ask anything ..."

block = gr.Blocks()


with block:
    chatbot = gr.Chatbot()
    message = gr.Textbox(placeholder=prompt)
    state = gr.State()
    submit = gr.Button("SEND")
    submit.click(chatbot_response, inputs=[message, state], outputs=[chatbot, state])

block.launch(debug = True)