Normalize abstract input in find_synergistic_papers to improve cosine similarity calculations and handle empty inputs.

app.py

@@ -428,6 +428,16 @@ def find_synergistic_papers(abstract: str, limit=25) -> list[dict]:
     """Find papers synergistic with the given abstract using FAISS with cosine similarity"""
     global dataset
 
+    # Normalize the abstract for cosine similarity
+    abstract = abstract.replace("\n", " ")
+    # Replace multiple whitespaces with a single space
+    abstract = " ".join(abstract.split())
+    # Remove leading/trailing whitespace
+    abstract = abstract.strip()
+    # Check if the abstract is empty
+    if not abstract:
+        raise ValueError("Abstract is empty. Please provide a valid abstract.")
+
     # Generate embedding for the query abstract (normalized for cosine similarity)
     abstract_embedding = embed_text(abstract)