Update app.py

app.py

@@ -1,28 +1,50 @@
-# Step 1: Install the necessary libraries
-# (Only needed locally; Hugging Face Spaces handles dependencies via 'requirements.txt')
-# !pip install streamlit spacy numpy
-
+# Step 1: Install necessary libraries (Handled by Hugging Face via 'requirements.txt')
 import streamlit as st
 import spacy
+from spacy.cli import download  # To download the model programmatically
 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 2: Download the spaCy model if not already installed
+try:
+    nlp = spacy.load("en_core_web_md")
+except OSError:
+    st.warning("Downloading spaCy model 'en_core_web_md'. This may take a few minutes...")
+    download("en_core_web_md")
+    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 3: Hardcode the FAQ data within the code
+faqs = {
+    'Admissions': [
+        {
+            'question': 'What is the process for admission into Saras AI Institute?',
+            'answer': 'The admission process involves submitting the online application form, followed by a pre-enrollment assessment.'
+        },
+        {
+            'question': 'Is there an application fee for applying to Saras AI Institute?',
+            'answer': 'There is no application fee for applying to any program at Saras.'
+        }
+    ],
+    'Curriculum and Faculty': [
+        {
+            'question': 'What is the curriculum like at Saras AI Institute?',
+            'answer': 'The curriculum prepares students for roles like AI/ML Engineer, Data Scientist, and Gen AI Engineer.'
+        },
+        {
+            'question': 'Do you also conduct LIVE sessions?',
+            'answer': 'Yes, live sessions are conducted regularly to provide interactive learning and Q&A.'
+        }
+    ]
+}
 
-# Step 4: Flatten the FAQ structure and precompute vectors
+# Step 4: Precompute vectors for FAQ questions
 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
+        faq_vector = nlp(question).vector  # Precompute vector
+        faq_docs.append((question, answer, faq_vector))
 
 # Step 5: Define the function to find the most relevant FAQs
 def find_most_relevant_faq_optimized(query, faq_docs):
@@ -59,4 +81,3 @@ if query:
         st.write(f"**Similarity Score:** {score:.2f}")
 else:
     st.write("Please enter a query to search for relevant FAQs.")
-