Create app.py

app.py

@@ -0,0 +1,50 @@
+import json
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+import numpy as np
+import gradio as gr
+
+# Load the SentenceTransformer model
+model = SentenceTransformer('sentence-transformers/all-mpnet-base-v2')
+
+# Load the embeddings from the JSON file
+with open('/content/drive/My Drive/final_data_with_embeddings.json', 'r') as f:
+    data = json.load(f)
+
+# Function to perform the search
+def search_courses(user_query):
+    query_embedding = model.encode(user_query)  # Get the embedding for user query
+    similarity_scores = []  # Array to store similarity scores
+
+    # Compare the user query embedding with each stored embedding
+    for dets in data:
+        embed = np.array(dets['embedding'])
+        similarity = cosine_similarity([query_embedding], [embed])
+        similarity_scores.append((similarity[0][0], dets))
+
+    # Sort the similarity scores in descending order
+    similarity_scores.sort(key=lambda x: x[0], reverse=True)
+
+    # Get the top 4 courses
+    top_4_dets = [item[1] for item in similarity_scores[:4]]
+
+    results = []
+    for i,det in enumerate(top_4_dets,1):
+        course_info = f"{i}. " \
+                      f"**Category**: {det['Course Category']}\n\n" \
+                      f"**Course Name**: {det['Course Name']}\n\n" \
+                      f"**Course URL**: {det['Course Url']}\n\n" \
+                      f"**Description**: {det['Course Description']}\n\n"
+        results.append(course_info)
+
+    return "\n\n\n".join(results)
+
+# Create the Gradio interface
+iface = gr.Interface(fn=search_courses,
+                     inputs="text",
+                     outputs="markdown",
+                     title="Course Search with Sentence Transformers",
+                     description="Enter a query to find the top 4 most similar courses.")
+
+# Launch the Gradio app
+iface.launch()