aggiunt tool arxiv_search

agent.py

@@ -14,7 +14,7 @@ from langchain_google_genai import ChatGoogleGenerativeAI
 
 # Local imports
 from tools import get_search_tool, get_tavily_search_tool, get_wikipedia_tool, wikipedia_search, wikipedia_search_3,\
-                  execute_python_code_from_file, download_taskid_file, analyze_excel_file, get_analyze_mp3_tool
+                  execute_python_code_from_file, download_taskid_file, analyze_excel_file, get_analyze_mp3_tool, arxiv_search
 
 # Nota: per i test in locale si usa il .env
 #       su HuggingFace invece si usano le variabili definite in Settings/"Variables and secrets"
@@ -60,7 +60,7 @@ search_tool = get_tavily_search_tool()
 #wikipedia_tool = get_wikipedia_tool()
 analyze_mp3_tool = get_analyze_mp3_tool(chat)
 
-tools = [search_tool, wikipedia_search_3, execute_python_code_from_file, download_taskid_file, analyze_excel_file, analyze_mp3_tool]
+tools = [search_tool, wikipedia_search_3, execute_python_code_from_file, download_taskid_file, analyze_excel_file, analyze_mp3_tool, arxiv_search]
 
 # Bind tools to the model
 chat_with_tools = chat.bind_tools(tools)

tools.py

@@ -10,6 +10,7 @@ from langchain_community.tools import WikipediaQueryRun
 from langchain_community.document_loaders import WikipediaLoader
 import wikipedia
 from langchain_tavily import TavilySearch
+from langchain_community.document_loaders import ArxivLoader
 from langchain_core.tools import tool
 from langchain.tools import Tool
 from langchain_core.messages import HumanMessage
@@ -255,3 +256,16 @@ def get_analyze_mp3_tool(llm):
     return analyze_mp3_file
 
 
+@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 {"arxiv_results": formatted_search_docs}