Update app.py

app.py

@@ -174,17 +174,32 @@ def python_fuzzy_match(user_query, top_k=5):
     return docs
 
 def extract_main_entity(question):
+    import re
+    quoted = re.findall(r"['\"]([^'\"]+)['\"]", question)
+    if quoted:
+        return quoted[0].lower()
+    email = re.findall(r"\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b", question)
+    if email:
+        return email[0].lower().split('@')[0]
     tokens = re.findall(r"\b([A-Za-z0-9]+)\b", question)
-    keywords = [t.lower() for t in tokens if t.lower() not in {"how", "much", "did", "spend", "was", "the", "is", "in", "on", "for", "a", "an", "of", "to", "with"}]
-    return keywords[0] if keywords else None
+    stopwords = {"how", "much", "did", "spend", "was", "the", "is", "in", "on", "for", "a", "an", "of", "to", "with"}
+    keywords = [t.lower() for t in tokens if t.lower() not in stopwords]
+    if not keywords:
+        return ""
+    return max(keywords, key=len)
 
 def filter_records_by_entity(records, entity):
+    if not entity:
+        return records
     matches = []
     for doc in records:
-        if entity and entity in doc.page_content.lower():
+        if entity in doc.page_content.lower():
+            matches.append(doc)
+        elif any(entity in v.lower() for v in doc.page_content.split(';')):
             matches.append(doc)
     return matches if matches else records
 
+
 def hybrid_query(user_query, top_k=5):
     vector_docs = query_vector_db(user_query, top_k=top_k)
     fuzzy_docs = python_fuzzy_match(user_query, top_k=top_k)