Update pages/Comparision.py

pages/Comparision.py

@@ -5,62 +5,77 @@ from transformers import pipeline
 from rake_nltk import Rake
 from nltk.corpus import stopwords
 from fuzzywuzzy import fuzz
+import openai
+import os
+from dotenv import load_dotenv
 
-# Ensure NLTK resources are downloaded
-nltk.download('punkt', quiet=True)
-nltk.download('stopwords', quiet=True)
+# Load environment variables for Llama 3
+load_dotenv()
 
-st.title("Exploring Torch, Transformers, Rake, and Others analyzing Text")
+# Title of the app
+st.title("Sentiment Analysis Comparison: Transformers vs Llama 3")
 
-# Define the options for the dropdown menu, Selecting a remote txt file already created to analyze the text
-options = ['None','Apprecitation Letter', 'Regret Letter', 'Kindness Tale', 'Lost Melody Tale', 'Twitter Example 1', 'Twitter Example 2']
+# Define the options for the dropdown menu, selecting a remote txt file already created to analyze the text
+options = ['None', 'Appreciation Letter', 'Regret Letter', 'Kindness Tale', 'Lost Melody Tale', 'Twitter Example 1', 'Twitter Example 2']
 
 # Create a dropdown menu to select options
 selected_option = st.selectbox("Select a preset option", options)
 
 # Define URLs for different options
-url_option1 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Appreciation_Letter.txt"
-url_option2 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Regret_Letter.txt"
-url_option3 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Kindness_Tale.txt"
-url_option4 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Lost_Melody_Tale.txt"
-url_option5 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Twitter_Example_1.txt"
-url_option6 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Twitter_Example_2.txt"
+urls = {
+    'Appreciation Letter': "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Appreciation_Letter.txt",
+    'Regret Letter': "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Regret_Letter.txt",
+    'Kindness Tale': "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Kindness_Tale.txt",
+    'Lost Melody Tale': "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Lost_Melody_Tale.txt",
+    'Twitter Example 1': "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Twitter_Example_1.txt",
+    'Twitter Example 2': "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Twitter_Example_2.txt"
+}
 
 # Function to fetch text content based on selected option
 def fetch_text_content(selected_option):
-    if selected_option == 'Apprecitation Letter':
-        return requests.get(url_option1).text
-    elif selected_option == 'Regret Letter':
-        return requests.get(url_option2).text
-    elif selected_option == 'Kindness Tale':
-        return requests.get(url_option3).text
-    elif selected_option == 'Lost Melody Tale':
-        return requests.get(url_option4).text
-    elif selected_option == 'Twitter Example 1':
-        return requests.get(url_option5).text
-    elif selected_option == 'Twitter Example 2':
-        return requests.get(url_option6).text
-    else:
-        return ""
+    return requests.get(urls[selected_option]).text if selected_option in urls else ""
 
 # Fetch text content based on selected option
-jd = fetch_text_content(selected_option)
+text = fetch_text_content(selected_option)
 
-# Initialize pipeline for sentiment analysis
+# Display text content in a text area
+text = st.text_area('Enter the text to analyze', text)
+
+# Download NLTK resources
+nltk.download('punkt')
+nltk.download('stopwords')
+
+# Initialize sentiment, summarization, and keyword extraction pipelines for Transformers
 pipe_sent = pipeline('sentiment-analysis')
-# Initialize pipeline for summarization
 pipe_summ = pipeline("summarization", model="facebook/bart-large-cnn")
 
-# Function to extract keywords and remove duplicates
+# Llama 3 initialization
+llama_api_key = os.getenv('HFSecret')
+llama_base_url = "https://api-inference.huggingface.co/v1"
+llama_repo_id = "meta-llama/Meta-Llama-3-8B-Instruct"
+
+# Function to use Llama 3 for sentiment analysis, summarization, and keyword extraction
+def analyze_with_llama(text):
+    headers = {
+        "Authorization": f"Bearer {llama_api_key}"
+    }
+    data = {
+        "inputs": text,
+        "parameters": {
+            "max_new_tokens": 200
+        }
+    }
+    # Perform the request
+    response = requests.post(f"{llama_base_url}/models/{llama_repo_id}", headers=headers, json=data)
+    return response.json()
+
+# Function to extract keywords using RAKE and remove duplicates
 def extract_keywords(text):
     r = Rake()
     r.extract_keywords_from_text(text)
     phrases_with_scores = r.get_ranked_phrases_with_scores()
     stop_words = set(stopwords.words('english'))
-    keywords = []
-    for score, phrase in phrases_with_scores:
-        if phrase.lower() not in stop_words:
-            keywords.append((score, phrase))
+    keywords = [(score, phrase) for score, phrase in phrases_with_scores if phrase.lower() not in stop_words]
     keywords.sort(key=lambda x: x[0], reverse=True)
     unique_keywords = []
     seen_phrases = set()
@@ -75,28 +90,56 @@ def extract_keywords(text):
             seen_phrases.add(phrase)
     return unique_keywords[:10]
 
-# Display text content in a text area
-text = st.text_area('Enter the text to analyze', jd)
+# Create two columns
+col1, col2 = st.columns(2)
 
-# Run analysis when button is pressed
-if st.button("Start Analysis"):
-    with st.spinner("Analyzing Sentiment"):
-        with st.expander("Sentiment Analysis - ✅ Completed", expanded=False):
+# Transformer-based analysis in the first column
+with col1:
+    st.header("Transformer-based Analysis")
+    if st.button("Analyze with Transformers"):
+        with st.spinner("Analyzing with Transformers..."):
+            # Sentiment analysis
             out_sentiment = pipe_sent(text)
             sentiment_score = out_sentiment[0]['score']
             sentiment_label = out_sentiment[0]['label']
             sentiment_emoji = '😊' if sentiment_label == 'POSITIVE' else '😞'
             sentiment_text = f"Sentiment Score: {sentiment_score}, Sentiment Label: {sentiment_label.capitalize()} {sentiment_emoji}"
-            st.write(sentiment_text)
-
-    with st.spinner("Summarizing - This may take a while"):
-        with st.expander("Summarization - ✅ Completed", expanded=False):        
+            
+            with st.expander("Sentiment Analysis (Transformers)"):
+                st.write(sentiment_text)
+            
+            # Summarization
             out_summ = pipe_summ(text)
             summarized_text = out_summ[0]['summary_text']
-            st.write(summarized_text)
-
-    with st.spinner("Extracting Keywords"):
-        with st.expander("Keywords Extraction - ✅ Completed", expanded=False):
+            
+            with st.expander("Summarization (Transformers)"):
+                st.write(summarized_text)
+            
+            # Keyword extraction
             keywords = extract_keywords(text)
             keyword_list = [keyword[1] for keyword in keywords]
-            st.write(keyword_list)
+            
+            with st.expander("Keywords (Transformers)"):
+                st.write(keyword_list)
+
+# Llama 3-based analysis in the second column
+with col2:
+    st.header("Llama 3-based Analysis")
+    if st.button("Analyze with Llama 3"):
+        with st.spinner("Analyzing with Llama 3..."):
+            llama_response = analyze_with_llama(text)
+            
+            if llama_response:
+                # Assuming the response returns in the same format, adjust if needed
+                sentiment_text = llama_response.get('sentiment_analysis', 'No sentiment detected')
+                summarized_text = llama_response.get('summarization', 'No summary available')
+                keywords = llama_response.get('keywords', 'No keywords available')
+                
+                with st.expander("Sentiment Analysis (Llama 3)"):
+                    st.write(sentiment_text)
+                
+                with st.expander("Summarization (Llama 3)"):
+                    st.write(summarized_text)
+                
+                with st.expander("Keywords (Llama 3)"):
+                    st.write(keywords)