Update tools.py

tools.py

@@ -1,7 +1,7 @@
 from langchain_core.tools import tool
-from langchain_community.tools.tavily_search import TavilySearchResults
 from youtube_transcript_api import YouTubeTranscriptApi
-from langchain_community.document_loaders import WikipediaLoader
+from SPARQLWrapper import SPARQLWrapper, JSON
+import jsonr
 import pandas as pd
 import whisper
 import os
@@ -129,33 +129,21 @@ def read_excel_summary(file_path: str) -> str:
     except Exception as e:
         return f"Error reading Excel file: {str(e)}"
 
-@tool
-def web_search(query: str) -> str:
-    """Search Tavily for a query and return maximum 3 results.
-    
-    Args:
-        query: The search query."""
-    search_docs = TavilySearchResults(max_results=3).invoke(query=query)
-    formatted_search_docs = "\n\n---\n\n".join(
-        [
-            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
-            for doc in search_docs
-        ])
-    return {"web_results": formatted_search_docs}
-
 @tool
 def wiki_search(query: str) -> str:
-    """Search Wikipedia for a query and return maximum 2 results.
+    """Query semantic knowledge bases using SPARQL
     
     Args:
-        query: The search query."""
-    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
-    formatted_search_docs = "\n\n---\n\n".join(
-        [
-            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
-            for doc in search_docs
-        ])
-    return {"wiki_results": formatted_search_docs}
+        query: The search query for SPARQL."""
+        try:
+            endpoint = SPARQLWrapper("https://query.wikidata.org/sparql")
+            endpoint.setQuery(query)
+            endpoint.setReturnFormat(JSON)
+
+            results = endpoint.query().convert()
+            return json.dumps(results, indent=2)
+        except Exception as e:
+            return f"Error executing SPARQL query: {str(e)}"
 
 @tool
 def transcribe_audio(file_path: str) -> str:
@@ -172,21 +160,6 @@ def transcribe_audio(file_path: str) -> str:
     except Exception as e:
         return f"Error during transcription: {str(e)}"
 
-@tool
-def arvix_search(query: str) -> str:
-    """Search Arxiv for a query and return maximum 3 result.
-        This tool allows for searching papers and articles 
-    
-    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}
-
 @tool
 def fetch_youtube_transcript(video_url: str) -> str:
     """