weASK / app.py
ipvikas's picture
Update app.py
2e7e616
raw
history blame
6.09 kB
import gradio as gr
import numpy as np
import nltk
nltk.download('punkt')
from nltk.stem.porter import PorterStemmer
stemmer = PorterStemmer()
def tokenize(sentence):
return nltk.word_tokenize(sentence)
def stem(word):
return stemmer.stem(word.lower())
def bag_of_words(tokenized_sentence, words):
sentence_words = [stem(word) for word in tokenized_sentence]
bag = np.zeros(len(words), dtype=np.float32)
for idx, w in enumerate(words):
if w in sentence_words:
bag[idx] = 1
return bag
########### 2 ###########
import torch
import torch.nn as nn
class NeuralNet(nn.Module):
def __init__(self, input_size, hidden_size, num_classes):
super(NeuralNet, self).__init__()
self.l1 = nn.Linear(input_size, hidden_size)
self.l2 = nn.Linear(hidden_size, hidden_size)
self.l3 = nn.Linear(hidden_size, num_classes)
self.relu = nn.ReLU()
def forward(self, x):
out = self.l1(x)
out = self.relu(out)
out = self.l2(out)
out = self.relu(out)
out = self.l3(out)
return out
########### 3 ###########
import random
import json
from torch.utils.data import Dataset, DataLoader
path = 'intents.json'
with open(path, 'r') as f:
intents = json.load(f)
all_words = []
tags = []
xy = []
for intent in intents['intents']:
tag = intent['tag']
tags.append(tag)
for pattern in intent['patterns']:
w = tokenize(pattern)
all_words.extend(w)
xy.append((w, tag))
ignore_words = ['(',')','-',':',',',"'s",'!',':',"'","''",'--','.',':','?',';''[',']','``','o','’','β€œ','”','”','[',';']
all_words = [stem(w) for w in all_words if w not in ignore_words]
all_words = sorted(set(all_words))
tags = sorted(set(tags))
X_train = []
y_train = []
for (pattern_sentence, tag) in xy:
bag = bag_of_words(pattern_sentence, all_words)
X_train.append(bag)
label = tags.index(tag)
y_train.append(label)
X_train = np.array(X_train)
y_train = np.array(y_train)
# Hyper-parameters
num_epochs = 1000
batch_size = 8
learning_rate = 0.001
input_size = len(X_train[0])
hidden_size = 8
output_size = len(tags)
class ChatDataset(Dataset):
def __init__(self):
self.n_samples = len(X_train)
self.x_data = X_train
self.y_data = y_train
# support indexing such that dataset[i] can be used to get i-th sample
def __getitem__(self, index):
return self.x_data[index], self.y_data[index]
# we can call len(dataset) to return the size
def __len__(self):
return self.n_samples
#from model import NeuralNet
dataset = ChatDataset()
train_loader = DataLoader(dataset=dataset,batch_size=batch_size,shuffle=True,num_workers=2)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = NeuralNet(input_size, hidden_size, output_size).to(device)
# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# Train the model
for epoch in range(num_epochs):
for (words, labels) in train_loader:
words = words.to(device)
labels = labels.to(dtype=torch.long).to(device)
# Forward pass
outputs = model(words)
loss = criterion(outputs, labels)
# Backward and optimize
optimizer.zero_grad()
loss.backward()
optimizer.step()
data = {
"model_state": model.state_dict(),
"input_size": input_size,
"hidden_size": hidden_size,
"output_size": output_size,
"all_words": all_words,
"tags": tags
}
FILE = "data.pth"
torch.save(data, FILE)
import random
import string # to process standard python strings
import warnings # Hide the warnings
warnings.filterwarnings('ignore')
import json
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
with open('intents.json', 'r') as json_data:
intents = json.load(json_data)
FILE = "data.pth"
data = torch.load(FILE, map_location=torch.device('cpu'))
input_size = data["input_size"]
hidden_size = data["hidden_size"]
output_size = data["output_size"]
all_words = data['all_words']
tags = data['tags']
model_state = data["model_state"]
model = NeuralNet(input_size, hidden_size, output_size).to(device)
model.load_state_dict(model_state)
model.eval()
bot_name = "WeASK"
from transformers import MBartForConditionalGeneration, MBart50Tokenizer
#model_name = "facebook/mbart-large-50-many-to-many-mmt"
#model = MBartForConditionalGeneration.from_pretrained(model_name)
#tokenizer = MBart50Tokenizer.from_pretrained(model_name)
import re, string, unicodedata
import wikipedia as wk #pip install wikipedia
from collections import defaultdict
def get_response(input_text):
#model_inputs = tokenizer(input_text, return_tensors="pt")
#generated_tokens = model.generate(**model_inputs,forced_bos_token_id=tokenizer.lang_code_to_id["en_XX"])
#translation= tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
#string2=" ".join(map(str,translation ))
sentence= tokenize(input_text)
X = bag_of_words(sentence, all_words)
X = X.reshape(1, X.shape[0])
X = torch.from_numpy(X).to(device)
output = model(X)
_, predicted = torch.max(output, dim=1)
tag = tags[predicted.item()]
probs = torch.softmax(output, dim=1)
prob = probs[0][predicted.item()]
if prob.item() > 0.75:
for intent in intents['intents']:
if tag == intent["tag"]:
return random.choice(intent['responses'])
else:
reg_ex = re.search('from wikipedia (.*)', input)#tell me about
try:
if reg_ex:
topic = reg_ex.group(1)
wiki = wk.summary(topic, sentences = 3)
return wiki
except Exception as e:
#print("No content has been found")
return "I do not understand...Please rephrase"
title = "WeASK: ChatBOT"
description = "Ask your query here"
chatbot_demo = gr.Interface(fn=get_response, inputs = 'text',outputs='text',title = title, description = description)
chatbot_demo.launch()