Fix

agent.py

@@ -24,28 +24,34 @@ from langchain.schema import Document
 
 @tool
 def multiply(a: int, b: int) -> int:
+    """Multiply two integers and return the result."""
     return a * b
 
 @tool
 def add(a: int, b: int) -> int:
+    """Add two integers and return the result."""
     return a + b
 
 @tool
 def subtract(a: int, b: int) -> int:
+    """Subtract second integer from the first and return the result."""
     return a - b
 
 @tool
 def divide(a: int, b: int) -> float:
+    """Divide first integer by second and return the result as a float."""
     if b == 0:
         raise ValueError("Cannot divide by zero.")
     return a / b
 
 @tool
 def modulus(a: int, b: int) -> int:
+    """Return the remainder when first integer is divided by second."""
     return a % b
 
 @tool
 def wiki_search(query: str) -> str:
+    """Search Wikipedia for the given query and return formatted documents."""
     search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
     formatted = "\n\n---\n\n".join(
         [
@@ -57,6 +63,7 @@ def wiki_search(query: str) -> str:
 
 @tool
 def web_search(query: str) -> str:
+    """Search the web using Tavily API for the given query."""
     search_docs = TavilySearchResults(max_results=3).invoke(query=query)
     formatted = "\n\n---\n\n".join(
         [
@@ -68,6 +75,7 @@ def web_search(query: str) -> str:
 
 @tool
 def arvix_search(query: str) -> str:
+    """Search Arxiv for academic papers related to the query."""
     search_docs = ArxivLoader(query=query, load_max_docs=3).load()
     formatted = "\n\n---\n\n".join(
         [
@@ -77,6 +85,19 @@ def arvix_search(query: str) -> str:
     )
     return {"arvix_results": formatted}
 
+@tool
+def similar_question_search(query: str) -> str:
+    """Find and return top 3 most similar past questions from vector store."""
+    matched_docs = vector_store.similarity_search(query, 3)
+    formatted = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
+            for doc in matched_docs
+        ]
+    )
+    return {"similar_questions": formatted}
+
+
 # ---- Embedding & Vector Store ----
 
 embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")