new

model.py

@@ -0,0 +1,27 @@
+from sentence_transformers import SentenceTransformer
+import pandas as pd
+import torch
+
+# Load pre-trained model for sentence embedding
+model = SentenceTransformer('distilbert-base-nli-stsb-mean-tokens')
+
+# Load scraped courses data
+courses_df = pd.read_csv("courses_data.csv")
+
+# Encode course descriptions
+courses_df['embedding'] = courses_df['description'].apply(lambda x: model.encode(x, convert_to_tensor=True))
+
+def search_courses(query, top_k=5):
+    query_embedding = model.encode(query, convert_to_tensor=True)
+    cosine_scores = torch.nn.functional.cosine_similarity(query_embedding, torch.stack(courses_df['embedding'].tolist()))
+    top_results = torch.topk(cosine_scores, k=top_k)
+    
+    results = []
+    for idx in top_results.indices:
+        course = courses_df.iloc[idx.item()]
+        results.append({
+            'title': course['title'],
+            'description': course['description'],
+            'curriculum': course['curriculum']
+        })
+    return results