Struct WikipediaQuery 

pub struct WikipediaQuery {
    pub options: WikipediaQueryOptions,
    /* private fields */
}

A tool for querying Wikipedia articles

This tool searches Wikipedia and returns summaries of the top matching articles. It’s useful for answering general questions about people, places, companies, facts, historical events, and other subjects that have Wikipedia articles.

Examples

use langchain_rust::tools::{Tool, WikipediaQuery, WikipediaQueryOptions};
use serde_json::json;

#[tokio::main]
async fn main() {
    let options = WikipediaQueryOptions {
        top_k_results: 2,
        max_doc_content_length: 2000,
        lang: "en".to_string(),
    };

    let wiki = WikipediaQuery::new(options);
    let result = wiki.run(json!("LangChain")).await.unwrap();
    println!("{}", result);
}

Fields

options: WikipediaQueryOptions

Implementations

impl WikipediaQuery

pub fn new(options: WikipediaQueryOptions) -> Self

Creates a new WikipediaQuery with custom options

Arguments

• options - Configuration options for Wikipedia queries

pub fn with_lang(lang: impl Into<String>) -> Self

Creates a WikipediaQuery with a specific language

Arguments

• lang - Language code (e.g., “en”, “es”, “fr”, “de”)

pub fn with_top_k_results(self, top_k: usize) -> Self

Sets the maximum number of results to return

pub fn with_max_doc_content_length(self, max_len: usize) -> Self

Sets the maximum content length per document

pub fn with_base_url(self, base_url: impl Into<String>) -> Self

Overrides the API origin (e.g. http://127.0.0.1:1234) instead of deriving it from the configured language. Mainly useful for pointing the tool at a mock server in tests or at a self-hosted MediaWiki instance.

Trait Implementations

impl Default for WikipediaQuery

fn default() -> Self

Returns the “default value” for a type.

impl Tool for WikipediaQuery

fn name(&self) -> String

Returns the name of the tool.

fn description(&self) -> String

Provides a description of what the tool does and when to use it.

fn run<'life0, 'async_trait>( &'life0 self, input: Value, ) -> Pin<Box<dyn Future<Output = Result<String, Box<dyn Error>>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Executes the core functionality of the tool.

fn parameters(&self) -> Value

This are the parametters for OpenAi-like function call. You should return a jsnon like this one

fn call<'life0, 'life1, 'async_trait>( &'life0 self, input: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<String, Box<dyn Error>>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Processes an input string and executes the tool’s functionality, returning a Result.

fn parse_input<'life0, 'life1, 'async_trait>( &'life0 self, input: &'life1 str, ) -> Pin<Box<dyn Future<Output = Value> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Parses the input string, which could be a JSON value or a raw string, depending on the LLM model.