Update app.py

app.py

@@ -7,6 +7,7 @@ from transformers import pipeline
 from langchain.llms.huggingface_pipeline import HuggingFacePipeline
 
 load_dotenv()
+
 def generate_prompts(user_input):
     prompt_template = PromptTemplate(
         input_variables=["Question"],
@@ -39,6 +40,55 @@ def answer_question(prompt):
     generated_answer = hub_chain.run(input_data)  
     return generated_answer
 
+    
+def calculate_similarity(word, other_sentences, model, threshold=0.1, upper_limit=0.80):
+    word_embedding = model.encode([word], convert_to_tensor=True)
+    sentence_embeddings = model.encode(other_sentences, convert_to_tensor=True)
+    similarities = scipy.spatial.distance.cdist(word_embedding, sentence_embeddings, "cosine")[0]
+    return [(i, 1-similarity) for i, similarity in enumerate(similarities) if threshold < 1-similarity < upper_limit]
+
+
+def highlight_words(sentence, other_sentences, model, exclude_words):
+    words = word_tokenize(sentence)
+    color_codes = ["\033[41m", "\033[42m", "\033[43m", "\033[44m", "\033[45m", "\033[46m", "\033[47m"]
+    html_color_codes = ["red", "green", "blue", "purple", "cyan", "fuchsia", "lime", "maroon", "olive", "navy", "teal", "gray", "DodgerBlue", "Tomato"]
+
+    all_matched_pairs = []
+    for i, word in enumerate(words):
+        if word.lower() not in exclude_words and word.isalnum():
+            matches = calculate_similarity(word, other_sentences, model)
+            for match_index, similarity in matches:
+                if word not in all_matched_pairs:
+                    all_matched_pairs.append((i, match_index, similarity))
+
+    
+    # Correction for variable name and HTML formatting
+    color_index = 0
+    for pair in all_matched_pairs:
+        color_code = html_color_codes[color_index % len(html_color_codes)]
+        # Correctly apply HTML span with style for coloring
+        words[pair[0]] = f"<span style='color: {color_code};'>{words[pair[0]]}</span>"
+        tokenized_other_sentence = word_tokenize(other_sentences[pair[1]])
+        tokenized_other_sentence = [f"<span style='color: {color_code};'>{word}</span>" if idx == pair[0] else word for idx, word in enumerate(tokenized_other_sentence)]
+        other_sentences[pair[1]] = ' '.join(tokenized_other_sentence)
+        color_index += 1
+
+    return ' '.join(words)
+
+
+model = SentenceTransformer('all-mpnet-base-v2')
+
+sentences = ["In a quaint little town nestled in the heart of the mountains, a small bakery famous for its artisanal breads and pastries had a line of customers stretching out the door, eagerly waiting to savor the freshly baked goods that were known far and wide for their delightful flavors.",
+
+"Within a picturesque mountain village, there stood a renowned bakery, celebrated for its handcrafted bread and sweet treats, attracting a long queue of patrons each morning, all keen to enjoy the baked delicacies that had gained widespread acclaim for their exceptional taste.",
+
+"A charming bakery, located in a small mountainous hamlet, renowned for producing exquisite handmade pastries and bread, was bustling with a crowd of eager customers lined up outside, each anticipating the chance to indulge in the famous baked items celebrated for their extraordinary deliciousness.",
+
+"In a cozy, mountain-encircled village, a beloved bakery was the center of attraction, known for its traditional baking methods and delightful pastries, drawing a consistent stream of people waiting outside, all desiring to experience the renowned flavors that made the bakery's products distinctively mouth-watering."]
+
+
+
+
 text_list = []
 
 def updateChoices(prompt):