|
import os |
|
from typing import Dict, Any |
|
from langchain_community.tools.tavily_search import TavilySearchResults |
|
from langchain_community.document_loaders import WikipediaLoader, ArxivLoader |
|
from langchain_community.utilities.wikipedia import WikipediaAPIWrapper |
|
from langchain_core.tools import tool |
|
import logging |
|
|
|
logger = logging.getLogger(__name__) |
|
|
|
@tool |
|
def wiki_search(query: str) -> Dict[str, str]: |
|
"""Search Wikipedia for a query and return maximum 2 results. |
|
Args: |
|
query: The search query.""" |
|
try: |
|
logger.info(f"Searching Wikipedia for: {query}") |
|
search_docs = WikipediaLoader(query=query, load_max_docs=2).load() |
|
if not search_docs: |
|
logger.warning("No Wikipedia results found") |
|
return {"wiki_results": "No results found"} |
|
|
|
formatted_search_docs = "\n\n---\n\n".join( |
|
[ |
|
f'<Document source="{doc.metadata.get("source", "")}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>' |
|
for doc in search_docs |
|
]) |
|
logger.info(f"Found {len(search_docs)} Wikipedia results") |
|
return {"wiki_results": formatted_search_docs} |
|
except Exception as e: |
|
logger.error(f"Error searching Wikipedia: {str(e)}") |
|
return {"wiki_results": f"Error searching Wikipedia: {str(e)}"} |
|
|
|
@tool |
|
def web_search(query: str) -> Dict[str, str]: |
|
"""Search Tavily for a query and return maximum 3 results. |
|
Args: |
|
query: The search query.""" |
|
try: |
|
logger.info(f"Searching web for: {query}") |
|
search = TavilySearchResults(max_results=3) |
|
search_docs = search.invoke({"query": query}) |
|
|
|
if not search_docs: |
|
logger.warning("No web results found") |
|
return {"web_results": "No results found"} |
|
|
|
if isinstance(search_docs, list): |
|
formatted_search_docs = "\n\n---\n\n".join( |
|
[ |
|
f'<Document source="{doc.get("source", "")}" page="{doc.get("page", "")}"/>\n{doc.get("content", "")}\n</Document>' |
|
for doc in search_docs |
|
]) |
|
logger.info(f"Found {len(search_docs)} web results") |
|
return {"web_results": formatted_search_docs} |
|
logger.warning(f"Unexpected response format from Tavily: {type(search_docs)}") |
|
return {"web_results": f"Error: Unexpected response format from Tavily"} |
|
except Exception as e: |
|
logger.error(f"Error searching web: {str(e)}") |
|
return {"web_results": f"Error searching web: {str(e)}"} |
|
|
|
@tool |
|
def arxiv_search(query: str) -> Dict[str, str]: |
|
"""Search Arxiv for a query and return maximum 3 results. |
|
Args: |
|
query: The search query.""" |
|
try: |
|
logger.info(f"Searching Arxiv for: {query}") |
|
search_docs = ArxivLoader(query=query, load_max_docs=3).load() |
|
if not search_docs: |
|
logger.warning("No Arxiv results found") |
|
return {"arxiv_results": "No results found"} |
|
|
|
formatted_search_docs = "\n\n---\n\n".join( |
|
[ |
|
f'<Document source="{doc.metadata.get("source", "")}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>' |
|
for doc in search_docs |
|
]) |
|
logger.info(f"Found {len(search_docs)} Arxiv results") |
|
return {"arxiv_results": formatted_search_docs} |
|
except Exception as e: |
|
logger.error(f"Error searching Arxiv: {str(e)}") |
|
return {"arxiv_results": f"Error searching Arxiv: {str(e)}"} |
|
|
|
@tool |
|
def wiki_api_search(query: str) -> Dict[str, str]: |
|
"""Search Wikipedia using API wrapper for better results. |
|
Args: |
|
query: The search query.""" |
|
try: |
|
logger.info(f"Searching Wikipedia API for: {query}") |
|
wikipedia = WikipediaAPIWrapper(top_k_results=3, doc_content_chars_max=4000) |
|
results = wikipedia.run(query) |
|
|
|
if not results or results.strip() == "No good Wikipedia Search Result was found": |
|
logger.warning("No Wikipedia API results found") |
|
return {"wiki_api_results": "No results found"} |
|
|
|
logger.info(f"Found Wikipedia API results") |
|
return {"wiki_api_results": results} |
|
except Exception as e: |
|
logger.error(f"Error searching Wikipedia API: {str(e)}") |
|
return {"wiki_api_results": f"Error searching Wikipedia API: {str(e)}"} |
|
|
|
|
|
SEARCH_TOOLS = [wiki_search, web_search, arxiv_search, wiki_api_search] |
|
|
|
class SearchTools: |
|
"""Wrapper class for search tools to provide a unified interface""" |
|
|
|
def __init__(self): |
|
"""Initialize search tools""" |
|
pass |
|
|
|
def search_wikipedia(self, query: str) -> str: |
|
"""Search Wikipedia and return formatted results""" |
|
result = wiki_search(query) |
|
return result.get("wiki_results", "") |
|
|
|
def search_wikipedia_api(self, query: str) -> str: |
|
"""Search Wikipedia using API wrapper and return formatted results""" |
|
result = wiki_api_search(query) |
|
return result.get("wiki_api_results", "") |
|
|
|
def search_web(self, query: str) -> str: |
|
"""Search web and return formatted results""" |
|
result = web_search(query) |
|
return result.get("web_results", "") |
|
|
|
def search_arxiv(self, query: str) -> str: |
|
"""Search Arxiv and return formatted results""" |
|
result = arxiv_search(query) |
|
return result.get("arxiv_results", "") |