from copy import deepcopy from typing import List, Dict, Optional, Any from flows.base_flows import AtomicFlow from flows.utils import logging from .wikipediaAPI import WikipediaAPIWrapper log = logging.get_logger(__name__) class WikiSearchAtomicFlow(AtomicFlow): REQUIRED_KEYS_CONFIG = ["lang", "top_k_results", "doc_content_chars_max"] REQUIRED_KEYS_CONSTRUCTOR = [] SUPPORTS_CACHING: bool = True api_wrapper: WikipediaAPIWrapper def __init__(self, **kwargs): super().__init__(**kwargs) def run(self, input_data: Dict[str, Any]) -> Dict[str, Any]: # ~~~ Process input ~~~ term = input_data.get("search_term", None) api_wrapper = WikipediaAPIWrapper( lang=self.flow_config["lang"], top_k_results=self.flow_config["top_k_results"], doc_content_chars_max=self.flow_config["doc_content_chars_max"] ) # ~~~ Call ~~~ if page_content := api_wrapper._fetch_page(term): search_response = {"wiki_content": page_content, "relevant_pages": None} else: page_titles = api_wrapper.search_page_titles(term) search_response = {"wiki_content": None, "relevant_pages": f"Could not find [{term}]. similar: {page_titles}"} # Log the update to the flow messages list observation = search_response["wiki_content"] if search_response["wiki_content"] else search_response["relevant_pages"] return {"wiki_content": observation}