wikipedia_tool.py

"""Tool for the Wikipedia API."""

from typing import Optional, Type
from langchain_core.callbacks import CallbackManagerForToolRun
from langchain_core.tools import BaseTool
from pydantic import BaseModel, Field
import pandas as pd
from langchain_community.utilities.wikipedia import WikipediaAPIWrapper

class WikipediaQueryInput(BaseModel):
    """Input for the WikipediaQuery tool."""

    query: str = Field(description="query to look up on wikipedia")

class WikipediaTool(BaseTool):  # type: ignore[override, override]
    """Tool that searches the Wikipedia API."""

    name: str = "wikipedia"
    description: str = (
        "A wrapper around Wikipedia. "
        "Useful for when you need to answer general questions about "
        "people, places, companies, facts, historical events, or other subjects. "
        "Input should be a search query."
    )
    api_wrapper: WikipediaAPIWrapper

    args_schema: Type[BaseModel] = WikipediaQueryInput

    def _run(
        self,
        query: str,
        run_manager: Optional[CallbackManagerForToolRun] = None,
    ) -> str:
        """Use the Wikipedia tool."""
        pages = self.api_wrapper.load(query)

        for page in pages:
            try:
                wikitables = pd.read_html(page.metadata["source"], attrs={"class": "wikitable"})
                page.metadata["wikitable"] = "\n---\n".join(
                    f'{table}'
                    for table in wikitables
                )
            except:
                continue

        res = "\n---\n".join(
            f'{page}'
            for page in pages
        )

        return res