Add Arxiv search tool

agent.py

@@ -12,7 +12,7 @@ from langchain.tools.retriever import create_retriever_tool
 from supabase.client import Client, create_client
 
 from tools.math_tools import add, subtract, multiply, divide, modulus, power, sqrt
-from tools.search_tools import search_wikipedia, web_search
+from tools.search_tools import search_wikipedia, web_search, arxiv_search
 from tools.image_video_tools import query_image
 from tools.file_tools import analyze_excel_file, execute_python_code
 
@@ -43,7 +43,7 @@ def build_graph():
         max_retries=2,
         google_api_key=os.getenv("GOOGLE_API_KEY")  # Get API key from environment variable
         )
-    tools = [add, subtract, multiply, divide, modulus, power, sqrt, web_search, search_wikipedia, query_image, analyze_excel_file, execute_python_code]
+    tools = [add, subtract, multiply, divide, modulus, power, sqrt, web_search, arxiv_search, search_wikipedia, query_image, analyze_excel_file, execute_python_code]
 
     llm_with_tools = llm.bind_tools(tools)
 

tools/search_tools.py

@@ -1,7 +1,7 @@
 """This module contains tools for searching external sources."""
 from langchain_core.tools import tool
 from langchain_community.tools.tavily_search import TavilySearchResults
-from langchain_community.document_loaders import WikipediaLoader
+from langchain_community.document_loaders import WikipediaLoader, ArxivLoader
 
 
 @tool
@@ -44,4 +44,18 @@ def search_wikipedia(query: str) -> str:
         return docs[0].page_content
     except Exception as e:
         raise ValueError(f"Error searching Wikipedia: {str(e)}")
+    
+@tool
+def arxiv_search(query: str) -> str:
+    """Search Arxiv for a query and return maximum 3 result.
+    
+    Args:
+        query: The search query."""
+    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
+    formatted_search_docs = "\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 search_docs
+        ])
+    return {"arvix_results": formatted_search_docs}