Create app.py

app.py

@@ -0,0 +1,53 @@
+import streamlit as st
+from sentence_transformers import SentenceTransformer, util
+import PyPDF2
+
+# Function to extract text from the uploaded PDF
+def extract_text_from_pdf(pdf_file):
+    reader = PyPDF2.PdfReader(pdf_file)
+    text = ""
+    for page in reader.pages:
+        text += page.extract_text()
+    return text
+
+# Function to process text into sentences and embeddings
+def process_text(text):
+    sentences = [sentence.strip() for sentence in text.split("\n") if sentence.strip()]
+    model = SentenceTransformer('all-MiniLM-L6-v2')  # A lightweight transformer model
+    embeddings = model.encode(sentences, show_progress_bar=True)
+    return sentences, embeddings, model
+
+# Streamlit UI
+st.title("GitaGPT: Bhagavad Gita Chatbot")
+st.write("Upload the Bhagavad Gita PDF file and ask questions based on its teachings!")
+
+# Upload PDF file
+uploaded_file = st.file_uploader("Upload Bhagavad Gita PDF", type=["pdf"])
+
+if uploaded_file:
+    with st.spinner("Extracting text and processing..."):
+        # Step 1: Extract text
+        raw_text = extract_text_from_pdf(uploaded_file)
+
+        # Step 2: Process text to generate embeddings
+        sentences, embeddings, model = process_text(raw_text)
+    
+    st.success("PDF processed successfully! Ask your questions below.")
+    
+    # Step 3: Input for user query
+    user_query = st.text_input("Ask your question:")
+
+    if user_query:
+        with st.spinner("Finding the best answer..."):
+            # Compute embedding for the user query
+            query_embedding = model.encode(user_query)
+            # Compute similarity scores
+            scores = util.cos_sim(query_embedding, embeddings)
+            best_match_idx = scores.argmax()
+            # Fetch the best matching sentence
+            response = sentences[best_match_idx]
+        
+        st.write(f"**Answer:** {response}")
+else:
+    st.info("Please upload a PDF file to begin.")
+