Add get_diseases_related_to_clinical_trials

utils.py

@@ -150,6 +150,28 @@ def get_diseases_related_to_a_textual_description(
 
     return [{"uri": row[0], "distance": row[1]} for row in data]
 
+def get_diseases_related_to_clinical_trials(
+    diseases: List[str], encoder
+) -> List[str]:
+    # Embed the diseases using sentence-transformers
+    diseases_string = ", ".join(diseases)
+    disease_embedding = get_embedding(diseases_string, encoder)
+    print(f"Size of the embedding: {len(disease_embedding)}")
+    string_representation = str(disease_embedding.tolist())[1:-1]
+    print(f"String representation: {string_representation}")
+
+    with engine.connect() as conn:
+        with conn.begin():
+            sql = f"""
+                    SELECT TOP 5 d.uri, VECTOR_COSINE(d.embedding, TO_VECTOR('{string_representation}', DOUBLE)) AS distance
+                    FROM Test.ClinicalTrials d
+                    ORDER BY distance DESC
+                """
+            result = conn.execute(text(sql))
+            data = result.fetchall()
+
+    return [{"uri": row[0], "distance": row[1]} for row in data]
+
 
 if __name__ == "__main__":
     username = "demo"