Merge branch 'Recode-Hive:main' into TheNaiveSamosa

AI_CHATBOT/README.md

@@ -0,0 +1,4 @@
+# AI_CHATBOT
+It is an Ai chatbot developed using natural language toolkit NLTK, pytorch
+I have developed this bot for a website of a photographer ,snapitize(which is also developed by me)
+Feel free to update the intents.json to make the domain  of the chatbot wider.

AI_CHATBOT/chat.py

@@ -0,0 +1,53 @@
+import random
+import json
+
+import torch
+
+from model import NeuralNet
+from nltk_utils import bag_of_words, tokenize
+
+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)
+
+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 = "Snapitizer"
+print("Let's chat! (type 'quit' to exit)")
+while True:
+    # sentence = "do you use credit cards?"
+    sentence = input("You: ")
+    if sentence == "quit":
+        break
+
+    sentence = tokenize(sentence)
+    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"]:
+                print(f"{bot_name}: {random.choice(intent['responses'])}")
+    else:
+        print(f"{bot_name}: I do not understand...")

AI_CHATBOT/intents.json

@@ -0,0 +1,157 @@
+{
+  "intents": [
+    {
+      "tag": "greeting",
+      "patterns": [
+        "Hi",
+        "Hey",
+        "How are you",
+        "Is anyone there?",
+        "Hello",
+        "Good day"
+      ],
+      "responses": [
+        "Hey :-)",
+        "Hello, thanks for visiting",
+        "Hi there, what can I do for you?",
+        "Hi there, how can I help?"
+      ]
+    },
+    {
+      "tag": "goodbye",
+      "patterns": ["Bye", "See you later", "Goodbye"],
+      "responses": [
+        "See you later, thanks for visiting",
+        "Have a nice day",
+        "Bye! Come back again soon."
+      ]
+    },
+    {
+      "tag": "thanks",
+      "patterns": ["Thanks", "Thank you", "That's helpful", "Thank's a lot!"],
+      "responses": ["Happy to help!", "Any time!", "My pleasure"]
+    },
+    {
+      "tag": "camera",
+      "patterns": [
+        "Which cameras do you have?",
+        "What kinds of equipments are there?",
+        "What is the resolution of your pictures?"
+      ],
+      "responses": [
+        "We have sony and nikon cameras",
+        "We have drones, action cameras, video cameras and many more for diffrent type of shoots"
+      ]
+    },
+    {
+      "tag": "payments",
+      "patterns": [
+        "Do you take cards?",
+        "Do you accept cheque payments?",
+        "Can I pay with Paytm?",
+        "Are you cash only?"
+      ],
+      "responses": [
+        "We accept Credit cards, debit cards, cheques and Paytm",
+        "We accept credit cards, and Paytm"
+      ]
+    },
+    {
+      "tag": "shoot time",
+      "patterns": [
+        "How long does shooting take?",
+        "When will I get my album?",
+        "How long it will take to print the album"
+      ],
+      "responses": [
+        "Shoot takes 2-4 days",
+        "processing the images and videos takes 2-4 days",
+        "Album would be ready in 1 week after the shoot"
+      ]
+    },
+    {
+      "tag": "location", 
+      "patterns": [
+        "Where are you located?",
+        "What's your address?"
+      ],
+      "responses": [
+        "We are located at New Delhi.",
+        "Our office is in Delhi, at xyzz."
+      ]
+    },
+    {
+      "tag": "services", 
+      "patterns": [
+        "What services do you offer?",
+        "Tell me about your photography services."
+      ],
+      "responses": [
+        "We offer a range of photography services including weddings, events, portraits, and more.",
+        "Our services include photography for special occasions, corporate events, and individual portraits."
+      ]
+    },
+    {
+      "tag": "packages", 
+      "patterns": [
+        "What are your photography packages?",
+        "Tell me about your pricing."
+      ],
+      "responses": [
+        "We have different packages to suit various needs. You can find detailed pricing on our website or contact us for more information."
+      ]
+    },
+    {
+      "tag": "editing", 
+      "patterns": [
+        "Do you provide photo editing services?",
+        "Can I get my photos retouched?"
+      ],
+      "responses": [
+        "Yes, we offer professional photo editing services to enhance and retouch your images."
+      ]
+    },
+    {
+      "tag": "availability", 
+      "patterns": [
+        "When are you available for a photoshoot?",
+        "What are your working hours?"
+      ],
+      "responses": [
+        "Our team is available for photoshoots during 6 from 10:00 to 00:00."
+      ]
+    },
+    {
+      "tag": "refund policy", 
+      "patterns": [
+        "What is your refund policy?",
+        "Can I get a refund if I cancel?"
+      ],
+      "responses": [
+        "Our refund policy is that we process refunds for orders cancelled before 7 days from the date of event. Please refer to our terms and conditions for more details."
+      ]
+    },
+    {
+      "tag": "reviews", 
+      "patterns": [
+        "Can I see customer reviews?",
+        "What do your clients say about your services?"
+      ],
+      "responses": [
+        "You can find customer reviews on our website or social media pages. We take pride in our positive feedback."
+      ]
+    },
+    {
+      "tag": "funny", 
+      "patterns": [
+        "Tell me a joke!",
+        "Tell me something funny!",
+        "Do you know a joke?"
+      ],
+      "responses": [
+        "What kind of candy do astronauts like? Mars bars.",
+        "What's an egg's favorite vacation spot?New Yolk City"
+      ]
+    }
+  ]
+}

AI_CHATBOT/model.py

@@ -0,0 +1,19 @@
+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

AI_CHATBOT/nltk_utils.py

@@ -0,0 +1,23 @@
+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

AI_CHATBOT/train.py

@@ -0,0 +1,108 @@
+import numpy as np
+import random
+import json
+
+import torch
+import torch.nn as nn
+from torch.utils.data import Dataset, DataLoader
+
+from nltk_utils import bag_of_words, tokenize, stem
+from model import NeuralNet
+
+with open('intents.json', '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 = ['?', '.', '!']
+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))
+
+print(len(xy), "patterns")
+print(len(tags), "tags:", tags)
+print(len(all_words), "unique stemmed words:", all_words)
+
+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)
+
+num_epochs = 1000
+batch_size = 8
+learning_rate = 0.01
+input_size = len(X_train[0])
+hidden_size = 8
+output_size = len(tags)
+print(input_size, output_size)
+
+class ChatDataset(Dataset):
+
+    def __init__(self):
+        self.n_samples = len(X_train)
+        self.x_data = X_train
+        self.y_data = y_train
+
+    def __getitem__(self, index):
+        return self.x_data[index], self.y_data[index]
+    def __len__(self):
+        return self.n_samples
+
+dataset = ChatDataset()
+train_loader = DataLoader(dataset=dataset,
+                          batch_size=batch_size,
+                          shuffle=True,
+                          num_workers=0)
+
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+model = NeuralNet(input_size, hidden_size, output_size).to(device)
+
+criterion = nn.CrossEntropyLoss()
+optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
+
+for epoch in range(num_epochs):
+    for (words, labels) in train_loader:
+        words = words.to(device)
+        labels = labels.to(dtype=torch.long).to(device)
+        outputs = model(words)
+
+        loss = criterion(outputs, labels)
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+
+    if (epoch+1) % 100 == 0:
+        print (f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f}')
+
+
+print(f'final loss: {loss.item():.4f}')
+
+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)
+
+print(f'training complete. file saved to {FILE}')