Update app.py

app.py

@@ -1,53 +1,59 @@
 import streamlit as st
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
-import requests
 
-# Load the text file from the URL
-url = "http://llm.sumityadav.com.np/bio.txt"
-response = requests.get(url)
-text_data = response.text
+# Streamlit sidebar for file upload
+st.sidebar.title("Upload your text file")
+uploaded_file = st.sidebar.file_uploader("Choose a text file", type=["txt"])
 
-# Split the text into sentences for easier querying
-sentences = text_data.split('##')
 
-# Initialize the TF-IDF Vectorizer
-vectorizer = TfidfVectorizer().fit(sentences)
-vectors = vectorizer.transform(sentences)  # Don't convert to array, keep it sparse
-
-def get_response(user_query):
-    # Transform user query and keep the result sparse
-    user_vector = vectorizer.transform([user_query])
-    
-    # Compute cosine similarity directly with sparse matrices
-    similarities = cosine_similarity(user_vector, vectors)
+if uploaded_file:
+    # Read the text file content
+    text_data = uploaded_file.read().decode("utf-8")
     
-    # Find the index of the most similar sentence
-    closest_index = similarities.argmax()
-    return sentences[closest_index]
-
-# Streamlit chat elements
-st.title("TF-IDF Chatbot")
-
-# Chat history
-if "messages" not in st.session_state:
-    st.session_state.messages = []
-
-# Chat input box
-user_input = st.chat_input("Ask me anything")
-
-# Handle user input
-if user_input:
-    # Store the user message in the session
-    st.session_state.messages.append({"role": "user", "content": user_input})
-    
-    # Get the bot response
-    response = get_response(user_input)
-    
-    # Store the bot response in the session
-    st.session_state.messages.append({"role": "bot", "content": response})
-
-# Display the chat history
-for message in st.session_state.messages:
-    with st.chat_message(message["role"]):
-        st.write(message["content"])
+    # Split the text into sentences
+    sentences = text_data.split('\n')
+
+    # Initialize the TF-IDF Vectorizer
+    vectorizer = TfidfVectorizer().fit(sentences)
+    vectors = vectorizer.transform(sentences)  # Keep it sparse
+
+    def get_top_responses(user_query, top_n=5):
+        # Transform user query and keep the result sparse
+        user_vector = vectorizer.transform([user_query])
+        
+        # Compute cosine similarity directly with sparse matrices
+        similarities = cosine_similarity(user_vector, vectors).flatten()
+        
+        # Get indices of top N similar sentences
+        top_indices = similarities.argsort()[-top_n:][::-1]
+        
+        # Return top N most similar sentences
+        return [sentences[i] for i in top_indices]
+
+    # Streamlit chat elements
+    st.title("TF-IDF Chatbot")
+
+    # Chat history
+    if "messages" not in st.session_state:
+        st.session_state.messages = []
+
+    # Chat input box
+    user_input = st.chat_input("Ask me anything")
+
+    # Handle user input
+    if user_input:
+        # Store the user message in the session
+        st.session_state.messages.append({"role": "user", "content": user_input})
+        
+        # Get the top bot responses
+        responses = get_top_responses(user_input)
+        
+        # Store the bot responses in the session
+        for response in responses:
+            st.session_state.messages.append({"role": "bot", "content": response})
+
+    # Display the chat history
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.write(message["content"])