From d2e711fbf21dda78a60511ff27f4dbea995d4e01 Mon Sep 17 00:00:00 2001 From: ztimson Date: Sun, 29 Mar 2026 21:50:26 -0400 Subject: [PATCH] Added wikipedia tools --- package.json | 2 +- src/tools.ts | 96 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 97 insertions(+), 1 deletion(-) diff --git a/package.json b/package.json index 4e7c18d..1217749 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "@ztimson/ai-utils", - "version": "0.8.15", + "version": "0.8.16", "description": "AI Utility library", "author": "Zak Timson", "license": "MIT", diff --git a/src/tools.ts b/src/tools.ts index b4d830f..2a702e5 100644 --- a/src/tools.ts +++ b/src/tools.ts @@ -272,3 +272,99 @@ export const WebSearchTool: AiTool = { return results; } } + +class WikipediaClient { + private ua = 'AiTools-Wikipedia/1.0'; + + private async get(url: string): Promise { + const resp = await fetch(url, {headers: {'User-Agent': this.ua}}); + return resp.json(); + } + + private api(params: Record): Promise { + const qs = new URLSearchParams({...params, format: 'json', utf8: '1'}).toString(); + return this.get(`https://en.wikipedia.org/w/api.php?${qs}`); + } + + private clean(text: string): string { + return text.replace(/\n{3,}/g, '\n\n').replace(/ {2,}/g, ' ').replace(/\[\d+\]/g, '').trim(); + } + + private truncate(text: string, max: number): string { + if(text.length <= max) return text; + const cut = text.slice(0, max); + const lastPara = cut.lastIndexOf('\n\n'); + return lastPara > max * 0.7 ? cut.slice(0, lastPara) : cut; + } + + private async searchTitles(query: string, limit = 6): Promise { + const data = await this.api({action: 'query', list: 'search', srsearch: query, srlimit: limit, srprop: 'snippet'}); + return data.query?.search || []; + } + + private async fetchExtract(title: string, intro = false): Promise { + const params: any = {action: 'query', prop: 'extracts', titles: title, explaintext: 1, redirects: 1}; + if(intro) params.exintro = 1; + const data = await this.api(params); + const page = Object.values(data.query?.pages || {})[0] as any; + return this.clean(page?.extract || ''); + } + + private pageUrl(title: string): string { + return `https://en.wikipedia.org/wiki/${encodeURIComponent(title.replace(/ /g, '_'))}`; + } + + private stripHtml(text: string): string { + return text.replace(/<[^>]+>/g, ''); + } + + async lookup(query: string, detail: 'intro' | 'full' = 'intro'): Promise { + const results = await this.searchTitles(query, 6); + if(!results.length) return `āŒ No Wikipedia articles found for "${query}"`; + + const title = results[0].title; + const url = this.pageUrl(title); + const content = await this.fetchExtract(title, detail === 'intro'); + + const text = this.truncate(content, detail === 'intro' ? 2000 : 8000); + return `## ${title}\nšŸ”— ${url}\n\n${text}`; + } + + async search(query: string): Promise { + const results = await this.searchTitles(query, 8); + if(!results.length) return `āŒ No results for "${query}"`; + + const lines = [`### Search results for "${query}"\n`]; + for(let i = 0; i < results.length; i++) { + const r = results[i]; + const snippet = this.truncate(this.stripHtml(r.snippet || ''), 150); + lines.push(`**${i + 1}. ${r.title}**\n${snippet}\n${this.pageUrl(r.title)}`); + } + return lines.join('\n\n'); + } +} + +export const WikipediaLookupTool: AiTool = { + name: 'wikipedia_lookup', + description: 'Get Wikipedia article content', + args: { + query: {type: 'string', description: 'Topic or article title', required: true}, + detail: {type: 'string', description: 'Content level: "intro" (summary, default) or "full" (complete article)', enum: ['intro', 'full'], default: 'intro'} + }, + fn: async (args: {query: string; detail?: 'intro' | 'full'}) => { + const wiki = new WikipediaClient(); + return wiki.lookup(args.query, args.detail || 'intro'); + } +}; + +export const WikipediaSearchTool: AiTool = { + name: 'wikipedia_search', + description: 'Search Wikipedia for matching articles', + args: { + query: {type: 'string', description: 'Search terms', required: true} + }, + fn: async (args: {query: string}) => { + const wiki = new WikipediaClient(); + return wiki.search(args.query); + } +};