@promptbook/website-crawler 0.114.0-2 → 0.114.0-21

package/umd/index.umd.js

@@ -1,8 +1,8 @@
 (function (global, factory) {
-    typeof exports === 'object' && typeof module !== 'undefined' ? factory(exports, require('spacetrim'), require('@mozilla/readability'), require('jsdom'), require('crypto-js'), require('rxjs'), require('waitasecond'), require('crypto-js/enc-hex'), require('crypto-js/sha256'), require('path'), require('mime-types'), require('papaparse'), require('fs/promises'), require('showdown')) :
-    typeof define === 'function' && define.amd ? define(['exports', 'spacetrim', '@mozilla/readability', 'jsdom', 'crypto-js', 'rxjs', 'waitasecond', 'crypto-js/enc-hex', 'crypto-js/sha256', 'path', 'mime-types', 'papaparse', 'fs/promises', 'showdown'], factory) :
-    (global = typeof globalThis !== 'undefined' ? globalThis : global || self, factory(global["promptbook-website-crawler"] = {}, global.spacetrim, global.readability, global.jsdom, global.CryptoJS, global.rxjs, global.waitasecond, global.hexEncoder, global.sha256, global.path, global.mimeTypes, global.papaparse, global.promises, global.showdown));
-})(this, (function (exports, spacetrim, readability, jsdom, CryptoJS, rxjs, waitasecond, hexEncoder, sha256, path, mimeTypes, papaparse, promises, showdown) { 'use strict';
+    typeof exports === 'object' && typeof module !== 'undefined' ? factory(exports, require('spacetrim'), require('crypto-js'), require('rxjs'), require('waitasecond'), require('crypto-js/enc-hex'), require('crypto-js/sha256'), require('path'), require('mime-types'), require('papaparse'), require('fs/promises'), require('showdown')) :
+    typeof define === 'function' && define.amd ? define(['exports', 'spacetrim', 'crypto-js', 'rxjs', 'waitasecond', 'crypto-js/enc-hex', 'crypto-js/sha256', 'path', 'mime-types', 'papaparse', 'fs/promises', 'showdown'], factory) :
+    (global = typeof globalThis !== 'undefined' ? globalThis : global || self, factory(global["promptbook-website-crawler"] = {}, global.spacetrim, global.CryptoJS, global.rxjs, global.waitasecond, global.hexEncoder, global.sha256, global.path, global.mimeTypes, global.papaparse, global.promises, global.showdown));
+})(this, (function (exports, spacetrim, CryptoJS, rxjs, waitasecond, hexEncoder, sha256, path, mimeTypes, papaparse, promises, showdown) { 'use strict';
 
     function _interopDefaultLegacy (e) { return e && typeof e === 'object' && 'default' in e ? e : { 'default': e }; }
 
@@ -26,7 +26,7 @@
      * @generated
      * @see https://github.com/webgptorg/promptbook
      */
-    const PROMPTBOOK_ENGINE_VERSION = '0.114.0-2';
+    const PROMPTBOOK_ENGINE_VERSION = '0.114.0-21';
     /**
      * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
      * Note: [💞] Ignore a discrepancy between file name and entity name
@@ -1601,6 +1601,31 @@
         }
     }
 
+    /**
+     * Creates a loader which imports one module on the first call and reuses the very same module afterwards
+     *
+     * Note: [🐌] Heavy third-party dependencies are imported lazily to keep the startup of the Promptbook CLI fast.
+     *       A statically imported dependency is loaded every single time the bundle is loaded, even when the running
+     *       command never touches it. A lazily imported dependency is loaded only when the feature is really used.
+     *
+     * @example
+     * const loadJsdomModule = createLazyModuleLoader(() => import('jsdom'));
+     * const { JSDOM } = await loadJsdomModule();
+     *
+     * @private internal utility of Promptbook
+     */
+    function createLazyModuleLoader(importModule) {
+        let importedModulePromise = null;
+        return function loadModule() {
+            if (importedModulePromise === null) {
+                importedModulePromise = importModule();
+            }
+            return importedModulePromise;
+        };
+    }
+    // Note: [🐌] Do not convert the lazy `import(...)` calls back to static `import` statements, it would bring back the
+    //       slow startup of the `ptbk` CLI utility
+
     var PipelineCollection = [{title:"Prepare Knowledge from Markdown",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-from-markdown.book",formfactorName:"GENERIC",parameters:[{name:"knowledgeContent",description:"Markdown document content",isInput:true,isOutput:false},{name:"knowledgePieces",description:"The knowledge JSON object",isInput:false,isOutput:true}],tasks:[{taskType:"PROMPT_TASK",name:"knowledge",title:"Knowledge",content:"You are experienced data researcher, extract the important knowledge from the document.\n\n# Rules\n\n-   Make pieces of information concise, clear, and easy to understand\n-   One piece of information should be approximately 1 paragraph\n-   Divide the paragraphs by markdown horizontal lines ---\n-   Omit irrelevant information\n-   Group redundant information\n-   Write just extracted information, nothing else\n\n# The document\n\nTake information from this document:\n\n> {knowledgeContent}",resultingParameterName:"knowledgePieces",dependentParameterNames:["knowledgeContent"]}],personas:[],preparations:[],knowledgeSources:[],knowledgePieces:[],sources:[{type:"BOOK",path:null,content:"# Prepare Knowledge from Markdown\n\n-   PIPELINE URL `https://promptbook.studio/promptbook/prepare-knowledge-from-markdown.book`\n-   INPUT PARAMETER `{knowledgeContent}` Markdown document content\n-   OUTPUT PARAMETER `{knowledgePieces}` The knowledge JSON object\n\n## Knowledge\n\n<!-- TODO: [🍆] -FORMAT JSON -->\n\n```markdown\nYou are experienced data researcher, extract the important knowledge from the document.\n\n# Rules\n\n-   Make pieces of information concise, clear, and easy to understand\n-   One piece of information should be approximately 1 paragraph\n-   Divide the paragraphs by markdown horizontal lines ---\n-   Omit irrelevant information\n-   Group redundant information\n-   Write just extracted information, nothing else\n\n# The document\n\nTake information from this document:\n\n> {knowledgeContent}\n```\n\n`-> {knowledgePieces}`\n"}],sourceFile:"./books/prepare-knowledge-from-markdown.book"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-keywords.book",formfactorName:"GENERIC",parameters:[{name:"knowledgePieceContent",description:"The content",isInput:true,isOutput:false},{name:"keywords",description:"Keywords separated by comma",isInput:false,isOutput:true}],tasks:[{taskType:"PROMPT_TASK",name:"knowledge",title:"Knowledge",content:"You are experienced data researcher, detect the important keywords in the document.\n\n# Rules\n\n-   Write just keywords separated by comma\n\n# The document\n\nTake information from this document:\n\n> {knowledgePieceContent}",resultingParameterName:"keywords",dependentParameterNames:["knowledgePieceContent"]}],personas:[],preparations:[],knowledgeSources:[],knowledgePieces:[],sources:[{type:"BOOK",path:null,content:"# Prepare Keywords\n\n-   PIPELINE URL `https://promptbook.studio/promptbook/prepare-knowledge-keywords.book`\n-   INPUT PARAMETER `{knowledgePieceContent}` The content\n-   OUTPUT PARAMETER `{keywords}` Keywords separated by comma\n\n## Knowledge\n\n<!-- TODO: [🍆] -FORMAT JSON -->\n\n```markdown\nYou are experienced data researcher, detect the important keywords in the document.\n\n# Rules\n\n-   Write just keywords separated by comma\n\n# The document\n\nTake information from this document:\n\n> {knowledgePieceContent}\n```\n\n`-> {keywords}`\n"}],sourceFile:"./books/prepare-knowledge-keywords.book"},{title:"Prepare Knowledge-piece Title",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-title.book",formfactorName:"GENERIC",parameters:[{name:"knowledgePieceContent",description:"The content",isInput:true,isOutput:false},{name:"title",description:"The title of the document",isInput:false,isOutput:true}],tasks:[{taskType:"PROMPT_TASK",name:"knowledge",title:"Knowledge",content:"You are experienced content creator, write best title for the document.\n\n# Rules\n\n-   Write just title, nothing else\n-   Write maximum 5 words for the title\n\n# The document\n\n> {knowledgePieceContent}",resultingParameterName:"title",expectations:{words:{min:1,max:8}},dependentParameterNames:["knowledgePieceContent"]}],personas:[],preparations:[],knowledgeSources:[],knowledgePieces:[],sources:[{type:"BOOK",path:null,content:"# Prepare Knowledge-piece Title\n\n-   PIPELINE URL `https://promptbook.studio/promptbook/prepare-knowledge-title.book`\n-   INPUT PARAMETER `{knowledgePieceContent}` The content\n-   OUTPUT PARAMETER `{title}` The title of the document\n\n## Knowledge\n\n-   EXPECT MIN 1 WORD\n-   EXPECT MAX 8 WORDS\n\n```markdown\nYou are experienced content creator, write best title for the document.\n\n# Rules\n\n-   Write just title, nothing else\n-   Write maximum 5 words for the title\n\n# The document\n\n> {knowledgePieceContent}\n```\n\n`-> {title}`\n"}],sourceFile:"./books/prepare-knowledge-title.book"},{title:"Prepare Persona",pipelineUrl:"https://promptbook.studio/promptbook/prepare-persona.book",formfactorName:"GENERIC",parameters:[{name:"availableModels",description:"List of available model names together with their descriptions as JSON",isInput:true,isOutput:false},{name:"personaDescription",description:"Description of the persona",isInput:true,isOutput:false},{name:"modelsRequirements",description:"Specific requirements for the model",isInput:false,isOutput:true}],tasks:[{taskType:"PROMPT_TASK",name:"make-model-requirements",title:"Make modelRequirements",content:"You are an experienced AI engineer, you need to find the best models for virtual assistants:\n\n## Example\n\n```json\n[\n  {\n  \"modelName\": \"gpt-4o\",\n  \"systemMessage\": \"You are experienced AI engineer and helpful assistant.\",\n  \"temperature\": 0.7\n  },\n  {\n    \"modelName\": \"claude-3-5-sonnet\",\n    \"systemMessage\": \"You are a friendly and knowledgeable chatbot.\",\n    \"temperature\": 0.5\n  }\n]\n```\n\n## Instructions\n\n-   Your output format is JSON array\n-   Sort best-fitting models first\n-   Omit any models that are not suitable\n-   Write just the JSON, no other text should be present\n-   Array contain items with following keys:\n    -   `modelName`: The name of the model to use\n    -   `systemMessage`: The system message to provide context to the model\n    -   `temperature`: The sampling temperature to use\n\n### Key `modelName`\n\nHere are the available models:\n\n```json\n{availableModels}\n```\n\n### Key `systemMessage`\n\nThe system message is used to communicate instructions or provide context to the model at the beginning of a conversation. It is displayed in a different format compared to user messages, helping the model understand its role in the conversation. The system message typically guides the model's behavior, sets the tone, or specifies desired output from the model. By utilizing the system message effectively, users can steer the model towards generating more accurate and relevant responses.\n\nFor example:\n\n> You are an experienced AI engineer and helpful assistant.\n\n> You are a friendly and knowledgeable chatbot.\n\n### Key `temperature`\n\nThe sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.\n\nYou can pick a value between 0 and 2. For example:\n\n-   `0.1`: Low temperature, extremely conservative and deterministic\n-   `0.5`: Medium temperature, balanced between conservative and creative\n-   `1.0`: High temperature, creative and bit random\n-   `1.5`: Very high temperature, extremely creative and often chaotic and unpredictable\n-   `2.0`: Maximum temperature, completely random and unpredictable, for some extreme creative use cases\n\n# The assistant\n\nTake this description of the persona:\n\n> {personaDescription}",resultingParameterName:"modelsRequirements",format:"JSON",dependentParameterNames:["availableModels","personaDescription"]}],personas:[],preparations:[],knowledgeSources:[],knowledgePieces:[],sources:[{type:"BOOK",path:null,content:"# Prepare Persona\n\n-   PIPELINE URL `https://promptbook.studio/promptbook/prepare-persona.book`\n-   INPUT PARAMETER `{availableModels}` List of available model names together with their descriptions as JSON\n-   INPUT PARAMETER `{personaDescription}` Description of the persona\n-   OUTPUT PARAMETER `{modelsRequirements}` Specific requirements for the model\n\n## Make modelRequirements\n\n-   FORMAT JSON\n\n```markdown\nYou are an experienced AI engineer, you need to find the best models for virtual assistants:\n\n## Example\n\n\\`\\`\\`json\n[\n  {\n  \"modelName\": \"gpt-4o\",\n  \"systemMessage\": \"You are experienced AI engineer and helpful assistant.\",\n  \"temperature\": 0.7\n  },\n  {\n    \"modelName\": \"claude-3-5-sonnet\",\n    \"systemMessage\": \"You are a friendly and knowledgeable chatbot.\",\n    \"temperature\": 0.5\n  }\n]\n\\`\\`\\`\n\n## Instructions\n\n-   Your output format is JSON array\n-   Sort best-fitting models first\n-   Omit any models that are not suitable\n-   Write just the JSON, no other text should be present\n-   Array contain items with following keys:\n    -   `modelName`: The name of the model to use\n    -   `systemMessage`: The system message to provide context to the model\n    -   `temperature`: The sampling temperature to use\n\n### Key `modelName`\n\nHere are the available models:\n\n\\`\\`\\`json\n{availableModels}\n\\`\\`\\`\n\n### Key `systemMessage`\n\nThe system message is used to communicate instructions or provide context to the model at the beginning of a conversation. It is displayed in a different format compared to user messages, helping the model understand its role in the conversation. The system message typically guides the model's behavior, sets the tone, or specifies desired output from the model. By utilizing the system message effectively, users can steer the model towards generating more accurate and relevant responses.\n\nFor example:\n\n> You are an experienced AI engineer and helpful assistant.\n\n> You are a friendly and knowledgeable chatbot.\n\n### Key `temperature`\n\nThe sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.\n\nYou can pick a value between 0 and 2. For example:\n\n-   `0.1`: Low temperature, extremely conservative and deterministic\n-   `0.5`: Medium temperature, balanced between conservative and creative\n-   `1.0`: High temperature, creative and bit random\n-   `1.5`: Very high temperature, extremely creative and often chaotic and unpredictable\n-   `2.0`: Maximum temperature, completely random and unpredictable, for some extreme creative use cases\n\n# The assistant\n\nTake this description of the persona:\n\n> {personaDescription}\n```\n\n`-> {modelsRequirements}`\n"}],sourceFile:"./books/prepare-persona.book"},{title:"Prepare Title",pipelineUrl:"https://promptbook.studio/promptbook/prepare-title.book",formfactorName:"GENERIC",parameters:[{name:"book",description:"The book to prepare the title for",isInput:true,isOutput:false},{name:"title",description:"Best title for the book",isInput:false,isOutput:true}],tasks:[{taskType:"PROMPT_TASK",name:"make-title",title:"Make title",content:"Make best title for given text which describes the workflow:\n\n## Rules\n\n-   Write just title, nothing else\n-   Title should be concise and clear - Write maximum ideally 2 words, maximum 5 words\n-   Title starts with emoticon\n-   Title should not mention the input and output of the workflow but the main purpose of the workflow\n    _For example, not \"✍ Convert Knowledge-piece to title\" but \"✍ Title\"_\n\n## The workflow\n\n> {book}",resultingParameterName:"title",expectations:{words:{min:1,max:8},lines:{min:1,max:1}},dependentParameterNames:["book"]}],personas:[],preparations:[],knowledgeSources:[],knowledgePieces:[],sources:[{type:"BOOK",path:null,content:"# Prepare Title\n\n-   PIPELINE URL `https://promptbook.studio/promptbook/prepare-title.book`\n-   INPUT PARAMETER `{book}` The book to prepare the title for\n-   OUTPUT PARAMETER `{title}` Best title for the book\n\n## Make title\n\n-   EXPECT MIN 1 Word\n-   EXPECT MAX 8 Words\n-   EXPECT EXACTLY 1 Line\n\n```markdown\nMake best title for given text which describes the workflow:\n\n## Rules\n\n-   Write just title, nothing else\n-   Title should be concise and clear - Write maximum ideally 2 words, maximum 5 words\n-   Title starts with emoticon\n-   Title should not mention the input and output of the workflow but the main purpose of the workflow\n    _For example, not \"✍ Convert Knowledge-piece to title\" but \"✍ Title\"_\n\n## The workflow\n\n> {book}\n```\n\n`-> {title}`\n"}],sourceFile:"./books/prepare-title.book"}];
 
     /**
@@ -8497,7 +8522,23 @@
         });
     }
 
-    // TODO: [🏳‍🌈] Finally take pick of .json vs .ts
+    /**
+     * Loads `jsdom` on demand
+     *
+     * Note: [🐌] `jsdom` is by far the heaviest dependency of Promptbook, loading it eagerly would slow down every single
+     *       run of the `ptbk` CLI utility even when no website is scraped
+     *
+     * @private internal utility of `WebsiteScraper`
+     */
+    const loadJsdomModule = createLazyModuleLoader(() => import('jsdom'));
+    /**
+     * Loads `@mozilla/readability` on demand
+     *
+     * Note: [🐌] Loaded lazily to keep the startup of the `ptbk` CLI utility fast
+     *
+     * @private internal utility of `WebsiteScraper`
+     */
+    const loadReadabilityModule = createLazyModuleLoader(() => import('@mozilla/readability'));
     /**
      * Scraper for websites
      *
@@ -8533,14 +8574,15 @@
             if (this.tools.fs === undefined) {
                 throw new EnvironmentMismatchError('Can not scrape websites without filesystem tools');
             }
-            const jsdom$1 = new jsdom.JSDOM(await source.asText(), {
+            const [{ JSDOM }, { Readability }] = await Promise.all([loadJsdomModule(), loadReadabilityModule()]);
+            const jsdom = new JSDOM(await source.asText(), {
                 url: source.url,
             });
-            const reader = new readability.Readability(jsdom$1.window.document);
+            const reader = new Readability(jsdom.window.document);
             const article = reader.parse();
             // console.log(article);
             // await forTime(10000);
-            let html = (article === null || article === void 0 ? void 0 : article.content) || (article === null || article === void 0 ? void 0 : article.textContent) || jsdom$1.window.document.body.innerHTML;
+            let html = (article === null || article === void 0 ? void 0 : article.content) || (article === null || article === void 0 ? void 0 : article.textContent) || jsdom.window.document.body.innerHTML;
             // Note: Unwrap html such as it is convertable by `markdownConverter`
             for (let i = 0; i < 2; i++) {
                 html = html.replace(/<div\s*(?:id="readability-page-\d+"\s+class="page")?>(.*)<\/div>/is, '$1');
@@ -8573,7 +8615,7 @@
                     throw error;
                 }
             }
-            const markdown = this.showdownConverter.makeMarkdown(html, jsdom$1.window.document);
+            const markdown = this.showdownConverter.makeMarkdown(html, jsdom.window.document);
             return { ...cacheFilehandler, markdown };
         }
         /**