Upload 2 files

app.py

@@ -0,0 +1,65 @@
+import streamlit as st
+import faiss
+import numpy as np
+from sentence_transformers import SentenceTransformer
+
+# Sample course data (replace with real course data)
+courses = [
+    {'title': 'Data Science for Beginners', 'description': 'Learn the basics of data science, including data analysis and machine learning.', 'curriculum': 'Introduction to Data Science, Data Cleaning, Data Visualization, Supervised Learning'},
+    {'title': 'Advanced Machine Learning', 'description': 'Deep dive into advanced machine learning algorithms, including reinforcement learning and neural networks.', 'curriculum': 'Reinforcement Learning, Neural Networks, Deep Learning, Hyperparameter Tuning'},
+    {'title': 'Data Visualization with Python', 'description': 'Master data visualization techniques using Python libraries like Matplotlib and Seaborn.', 'curriculum': 'Data Visualization Basics, Seaborn, Matplotlib, Plotly'}
+]
+
+# Initialize the model and FAISS index (similar to what we did earlier)
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+# Create a list of course descriptions and generate embeddings
+course_descriptions = [course['description'] for course in courses]
+embeddings = model.encode(course_descriptions, convert_to_tensor=True)
+
+# Initialize FAISS index
+embedding_matrix = embeddings.cpu().detach().numpy()
+index = faiss.IndexFlatL2(embedding_matrix.shape[1])  # L2 distance index
+index.add(embedding_matrix)
+
+# Function to search courses based on user query
+def search_courses(query, top_k=3):
+    query_embedding = model.encode([query], convert_to_tensor=True).cpu().detach().numpy()
+    D, I = index.search(query_embedding, top_k)
+
+    results = []
+    for idx in I[0]:  # I[0] contains the indices of the most similar courses
+        course = courses[idx]
+        results.append({
+            'title': course['title'],
+            'description': course['description'],
+            'curriculum': course['curriculum']
+        })
+    
+    return results
+
+# Streamlit UI
+
+st.title("Smart Search for Free Courses")
+
+st.markdown("""
+    Enter a keyword or phrase, and we'll find the most relevant courses for you.
+    You can search for things like 'machine learning', 'data science', or 'Python'.
+""")
+
+# User input
+query = st.text_input("Enter your query:")
+
+if query:
+    st.subheader(f"Search Results for: '{query}'")
+    results = search_courses(query)
+
+    if results:
+        for idx, result in enumerate(results, 1):
+            st.write(f"**Result {idx}:**")
+            st.write(f"**Title:** {result['title']}")
+            st.write(f"**Description:** {result['description']}")
+            st.write(f"**Curriculum:** {result['curriculum']}")
+            st.write("-" * 50)
+    else:
+        st.write("No results found!")

requirements.txt

@@ -0,0 +1,4 @@
+streamlit
+numpy
+faiss-cpu
+sentence-transformers