Update Web_Search_tools.py

Web_Search_tools.py

@@ -0,0 +1,50 @@
+import os
+from supabase.client import Client, create_client
+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 ArxivLoader
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_community.vectorstores import SupabaseVectorStore
+from langchain.tools.retriever import create_retriever_tool
+
+
+@tool
+def wiki_search(query: str) -> str:
+    """Search Wikipedia for a query and return maximum 2 results.
+    
+    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}
+
+@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 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}
+
+@tool
+def similar_question_search(question: str) -> str:
+    """Search the vector database for similar questions and return the first results.
+    
+    Args:
+        question: the question human provided."""
+    matched_docs = vector_store.similarity_search(question, 3)
+    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 matched_docs])
+    return {"similar_questions": formatted_search_docs}