Refactor find_synergistic_papers to use DatasetManager for accessing the training dataset

app.py

@@ -368,8 +368,11 @@ def find_synergistic_papers(abstract: str, limit=25) -> list[dict]:
     # Generate embedding for the query abstract (normalized for cosine similarity)
     abstract_embedding = embed_text(abstract)
 
+    # Access the dataset's train split from the DatasetManager instance
+    train_dataset = dataset.dataset["train"]
+
     # Search for similar papers using FAISS with inner product (cosine similarity for normalized vectors)
-    scores, examples = dataset["train"].get_nearest_examples("embedding", abstract_embedding, k=limit)
+    scores, examples = train_dataset.get_nearest_examples("embedding", abstract_embedding, k=limit)
 
     papers = []
     for i in range(len(scores)):