Create app.py

app.py

@@ -0,0 +1,62 @@
+# Step 1: Install the necessary libraries
+# (Only needed locally; Hugging Face Spaces handles dependencies via 'requirements.txt')
+# !pip install streamlit spacy numpy
+
+import streamlit as st
+import spacy
+import numpy as np
+import json
+from numpy.linalg import norm
+
+# Step 2: Load the spaCy model
+nlp = spacy.load("en_core_web_md")
+
+# Step 3: Load the FAQ data (ensure faqs.json is in the same directory)
+with open('faqs.json', 'r') as f:
+    faqs = json.load(f)
+
+# Step 4: Flatten the FAQ structure and precompute vectors
+faq_docs = []
+for category, faq_list in faqs.items():
+    for faq in faq_list:
+        question = faq['question']
+        answer = faq['answer']
+        faq_vector = nlp(question).vector  # Precompute the vector
+        faq_docs.append((question, answer, faq_vector))  # Store question, answer, and vector
+
+# Step 5: Define the function to find the most relevant FAQs
+def find_most_relevant_faq_optimized(query, faq_docs):
+    """Find the top 3 most relevant FAQs based on semantic similarity."""
+    query_vector = nlp(query).vector
+
+    # Calculate cosine similarity between query and each FAQ
+    similarities = [
+        (question, answer, np.dot(query_vector, faq_vector) / (norm(query_vector) * norm(faq_vector)))
+        for question, answer, faq_vector in faq_docs
+    ]
+
+    # Sort by similarity score (highest first)
+    similarities = sorted(similarities, key=lambda x: x[2], reverse=True)
+
+    return similarities[:3]  # Return top 3 FAQs
+
+# Step 6: Create the Streamlit UI
+st.title("Smart FAQ Search - SARAS AI Institute")
+st.markdown("### Find Answers to Your Questions Instantly")
+
+# Text input for the user query
+query = st.text_input("Enter your question here:")
+
+if query:
+    # Find the most relevant FAQs
+    top_faqs = find_most_relevant_faq_optimized(query, faq_docs)
+
+    # Display the results
+    st.markdown("### Top Relevant FAQs:")
+    for i, (question, answer, score) in enumerate(top_faqs, 1):
+        st.write(f"**{i}. {question}**")
+        st.write(f"*Answer:* {answer}")
+        st.write(f"**Similarity Score:** {score:.2f}")
+else:
+    st.write("Please enter a query to search for relevant FAQs.")
+