@promptbook/legacy-documents 0.81.0-19 → 0.81.0-21

package/esm/typings/books/index.d.ts

@@ -89,5 +89,43 @@ declare const _default: ({
         content: string;
     }[];
     sourceFile: string;
+} | {
+    title: string;
+    pipelineUrl: string;
+    formfactorName: string;
+    parameters: {
+        name: string;
+        description: string;
+        isInput: boolean;
+        isOutput: boolean;
+    }[];
+    tasks: {
+        taskType: string;
+        name: string;
+        title: string;
+        content: string;
+        resultingParameterName: string;
+        expectations: {
+            words: {
+                min: number;
+                max: number;
+            };
+            lines: {
+                min: number;
+                max: number;
+            };
+        };
+        dependentParameterNames: string[];
+    }[];
+    personas: never[];
+    preparations: never[];
+    knowledgeSources: never[];
+    knowledgePieces: never[];
+    sources: {
+        type: string;
+        path: null;
+        content: string;
+    }[];
+    sourceFile: string;
 })[];
 export default _default;

package/esm/typings/src/_packages/core.index.d.ts

@@ -10,7 +10,7 @@ import { ADMIN_GITHUB_NAME } from '../config';
 import { CLAIM } from '../config';
 import { LOGO_LIGHT_SRC } from '../config';
 import { LOGO_DARK_SRC } from '../config';
-import { DEFAULT_TITLE } from '../config';
+import { DEFAULT_BOOK_TITLE } from '../config';
 import { MAX_FILENAME_LENGTH } from '../config';
 import { DEFAULT_INTERMEDIATE_FILES_STRATEGY } from '../config';
 import { DEFAULT_MAX_PARALLEL_COUNT } from '../config';
@@ -31,8 +31,8 @@ import { DEFAULT_GET_PIPELINE_COLLECTION_FUNCTION_NAME } from '../config';
 import { ORDER_OF_PIPELINE_JSON } from '../constants';
 import { RESERVED_PARAMETER_NAMES } from '../constants';
 import { compilePipeline } from '../conversion/compilePipeline';
+import { parsePipeline } from '../conversion/parsePipeline';
 import { pipelineJsonToString } from '../conversion/pipelineJsonToString';
-import { precompilePipeline } from '../conversion/precompilePipeline';
 import { prettifyPipelineString } from '../conversion/prettify/prettifyPipelineString';
 import { extractParameterNamesFromTask } from '../conversion/utils/extractParameterNamesFromTask';
 import { validatePipeline } from '../conversion/validation/validatePipeline';
@@ -132,7 +132,7 @@ export { ADMIN_GITHUB_NAME };
 export { CLAIM };
 export { LOGO_LIGHT_SRC };
 export { LOGO_DARK_SRC };
-export { DEFAULT_TITLE };
+export { DEFAULT_BOOK_TITLE };
 export { MAX_FILENAME_LENGTH };
 export { DEFAULT_INTERMEDIATE_FILES_STRATEGY };
 export { DEFAULT_MAX_PARALLEL_COUNT };
@@ -153,8 +153,8 @@ export { DEFAULT_GET_PIPELINE_COLLECTION_FUNCTION_NAME };
 export { ORDER_OF_PIPELINE_JSON };
 export { RESERVED_PARAMETER_NAMES };
 export { compilePipeline };
+export { parsePipeline };
 export { pipelineJsonToString };
-export { precompilePipeline };
 export { prettifyPipelineString };
 export { extractParameterNamesFromTask };
 export { validatePipeline };

package/esm/typings/src/config.d.ts

@@ -58,7 +58,7 @@ export declare const LOGO_DARK_SRC: string_url_image;
  *
  * @public exported from `@promptbook/core`
  */
-export declare const DEFAULT_TITLE = "Untitled";
+export declare const DEFAULT_BOOK_TITLE = "\u2728 Untitled Book";
 /**
  * Warning message for the generated sections and files files
  *

package/esm/typings/src/conversion/compilePipeline.d.ts

@@ -5,10 +5,7 @@ import type { PrepareAndScrapeOptions } from '../prepare/PrepareAndScrapeOptions
 /**
  * Compile pipeline from string (markdown) format to JSON format
  *
- * Note: There are 3 similar functions:
- * - `compilePipeline` **(preferred)** - which propperly compiles the promptbook and use embedding for external knowledge
- * - `precompilePipeline` - use only if you need to compile promptbook synchronously and it contains NO external knowledge
- * - `preparePipeline` - just one step in the compilation process
+ * @see https://github.com/webgptorg/promptbook/discussions/196
  *
  * Note: This function does not validate logic of the pipeline only the parsing
  * Note: This function acts as compilation process

package/esm/typings/src/conversion/{precompilePipeline.d.ts → parsePipeline.d.ts}

@@ -5,7 +5,7 @@ import type { PipelineString } from '../pipeline/PipelineString';
  *
  * Note: There are 3 similar functions:
  * - `compilePipeline` **(preferred)** - which propperly compiles the promptbook and use embedding for external knowledge
- * - `precompilePipeline` - use only if you need to compile promptbook synchronously and it contains NO external knowledge
+ * - `parsePipeline` - use only if you need to compile promptbook synchronously and it contains NO external knowledge
  * - `preparePipeline` - just one step in the compilation process
  *
  * Note: This function does not validate logic of the pipeline only the parsing
@@ -16,7 +16,7 @@ import type { PipelineString } from '../pipeline/PipelineString';
  * @throws {ParseError} if the promptbook string is not valid
  * @public exported from `@promptbook/core`
  */
-export declare function precompilePipeline(pipelineString: PipelineString): PipelineJson;
+export declare function parsePipeline(pipelineString: PipelineString): PipelineJson;
 /**
  * TODO: [🧠] Maybe more things here can be refactored as high-level abstractions
  * TODO: [main] !!!! Warn if used only sync version

package/esm/typings/src/high-level-abstractions/_common/HighLevelAbstraction.d.ts

@@ -1,6 +1,6 @@
 import type { $PipelineJson } from '../../commands/_common/types/CommandParser';
 /**
- * Used in `precompilePipeline`
+ * Used in `parsePipeline`
  *
  * @private
  */

package/esm/typings/src/high-level-abstractions/index.d.ts

@@ -1,7 +1,7 @@
 /**
  * All high-level abstractions
  *
- * @private internal index of `precompilePipeline` (= used for sync) and `preparePipeline` (= used for async)
+ * @private internal index of `parsePipeline` (= used for sync) and `preparePipeline` (= used for async)
  */
 export declare const HIGH_LEVEL_ABSTRACTIONS: readonly [{
     type: "SYNC";

package/esm/typings/src/pipeline/book-notation.d.ts

@@ -1,6 +1,6 @@
 import type { PipelineString } from './PipelineString';
 /**
- * Function for notating a pipeline with a book\`...\ notation as template literal
+ * Tag function for notating a pipeline with a book\`...\ notation as template literal
  *
  * @param strings @@@
  * @param values @@@
@@ -9,7 +9,7 @@ import type { PipelineString } from './PipelineString';
  */
 export declare function book(strings: TemplateStringsArray, ...values: Array<string>): PipelineString;
 /**
- * TODO: !!!!!! Use book\`...\ notation instead of as PipelineString
+ * TODO: Use ACRY book\`...\ notation instead of as PipelineString
  * TODO: [🧠][🈴] Where is the best location for this file
  * Note: [💞] Ignore a discrepancy between file name and entity name
  */

package/esm/typings/src/prepare/isPipelinePrepared.d.ts

@@ -2,6 +2,8 @@ import type { PipelineJson } from '../pipeline/PipelineJson/PipelineJson';
 /**
  * Determine if the pipeline is fully prepared
  *
+ * @see https://github.com/webgptorg/promptbook/discussions/196
+ *
  * @public exported from `@promptbook/core`
  */
 export declare function isPipelinePrepared(pipeline: PipelineJson): boolean;

package/esm/typings/src/prepare/preparePipeline.d.ts

@@ -4,6 +4,8 @@ import type { PrepareAndScrapeOptions } from './PrepareAndScrapeOptions';
 /**
  * Prepare pipeline from string (markdown) format to JSON format
  *
+ * @see https://github.com/webgptorg/promptbook/discussions/196
+ *
  * Note: This function does not validate logic of the pipeline
  * Note: This function acts as part of compilation process
  * Note: When the pipeline is already prepared, it returns the same pipeline

package/esm/typings/src/scrapers/_common/Converter.d.ts

@@ -4,6 +4,7 @@ import type { ScraperIntermediateSource } from './ScraperIntermediateSource';
 /**
  * @@@
  *
+ * Note: [🌏] Converters are not usable in browser because they produce a files
  */
 export type Converter = {
     /**

package/esm/typings/src/scrapers/_common/Scraper.d.ts

@@ -7,7 +7,6 @@ import type { string_url } from '../../types/typeAliases';
 import type { ScraperAndConverterMetadata } from './register/ScraperAndConverterMetadata';
 /**
  * @@@
- *
  */
 export type Scraper = {
     /**
@@ -53,6 +52,7 @@ export type ScraperSourceHandler = {
     asText(): Promisable<string>;
 };
 /**
+ * TODO: [🧠] Maybe split `ScraperSourceHandler` into `ScraperWebsiteSourceHandler` + `ScraperFileSourceHandler`
  * TODO: [🥽] Add ` asBlob(): Promisable<Blob>;` or asFile
  * TODO: [🐝] @@@ Annotate all
  * TODO: [🔼] Export via types

package/esm/typings/src/scrapers/_common/ScraperIntermediateSource.d.ts

@@ -9,3 +9,6 @@ export type ScraperIntermediateSource = IDestroyable & {
      */
     readonly filename: string_absolute_filename;
 };
+/**
+ * Note: [🌏] Converters can be used only in node because they uses `ScraperIntermediateSource` which  uses file system
+ */

package/esm/typings/src/scrapers/_common/register/ScraperAndConverterMetadata.d.ts

@@ -28,6 +28,8 @@ export type ScraperAndConverterMetadata = Registered & {
     readonly mimeTypes: ReadonlyArray<string_mime_type>;
     /**
      * @@@
+     *
+     * Note: [🌏] Only `MarkdownScraper` makes sense to be available in the browser, for scraping non-markdown sources in the browser use a remote server
      */
     readonly isAvilableInBrowser: boolean;
     /**

package/esm/typings/src/scrapers/pdf/PdfScraper.d.ts

@@ -37,4 +37,5 @@ export declare class PdfScraper implements Converter, Scraper {
  * TODO: [👣] Converted pdf documents can act as cached items - there is no need to run conversion each time
  * TODO: [🪂] Do it in parallel 11:11
  * Note: No need to aggregate usage here, it is done by intercepting the llmTools
+ * Note: [🟢] Code in this file should never be never released in packages that could be imported into browser environment
  */

package/esm/typings/src/scrapers/pdf/createPdfScraper.d.ts

@@ -12,7 +12,7 @@ export declare const createPdfScraper: ((tools: Pick<ExecutionTools, 'llm'>, opt
     className: string;
     mimeTypes: string[];
     documentationUrl: "https://github.com/webgptorg/promptbook/discussions/@@";
-    isAvilableInBrowser: true;
+    isAvilableInBrowser: false;
     requiredExecutables: never[];
 }>;
 /**

package/esm/typings/src/scrapers/pdf/register-metadata.d.ts

@@ -10,7 +10,7 @@ export declare const pdfScraperMetadata: import("type-fest/source/readonly-deep"
     className: string;
     mimeTypes: string[];
     documentationUrl: "https://github.com/webgptorg/promptbook/discussions/@@";
-    isAvilableInBrowser: true;
+    isAvilableInBrowser: false;
     requiredExecutables: never[];
 }>;
 /**

package/esm/typings/src/scrapers/website/createWebsiteScraper.d.ts

@@ -12,7 +12,7 @@ export declare const createWebsiteScraper: ((tools: Pick<ExecutionTools, 'llm'>,
     className: string;
     mimeTypes: string[];
     documentationUrl: "https://github.com/webgptorg/promptbook/discussions/@@";
-    isAvilableInBrowser: true; /**
+    isAvilableInBrowser: false; /**
      * TODO: [🎶] Naming "constructor" vs "creator" vs "factory"
      */
     requiredExecutables: never[];

package/esm/typings/src/scrapers/website/register-metadata.d.ts

@@ -10,7 +10,7 @@ export declare const websiteScraperMetadata: import("type-fest/source/readonly-d
     className: string;
     mimeTypes: string[];
     documentationUrl: "https://github.com/webgptorg/promptbook/discussions/@@";
-    isAvilableInBrowser: true;
+    isAvilableInBrowser: false;
     requiredExecutables: never[];
 }>;
 /**

package/esm/typings/src/utils/markdown/flattenMarkdown.d.ts

@@ -2,7 +2,7 @@ import type { string_markdown } from '../../types/typeAliases';
 /**
  * Normalizes the markdown by flattening the structure
  *
- * - It always have h1 - if there is no h1 in the markdown, it will be added "# Untitled"
+ * - It always have h1 - if there is no h1 in the markdown, it will be added `DEFAULT_BOOK_TITLE`
  * - All other headings are normalized to h2
  *
  * @public exported from `@promptbook/markdown-utils`

package/esm/typings/src/utils/organization/$sideEffect.d.ts

@@ -0,0 +1,9 @@
+import type { really_any } from './really_any';
+/**
+ * Just says that the variable is not used directlys but should be kept because the existence of the variable is important
+ *
+ * @param value any values
+ * @returns void
+ * @private within the repository
+ */
+export declare function $sideEffect(...sideEffectSubjects: ReadonlyArray<really_any>): void;

package/esm/typings/src/wizzard/wizzard.d.ts

@@ -8,36 +8,50 @@ import type { InputParameters } from '../types/typeAliases';
 import type { string_filename } from '../types/typeAliases';
 import type { string_pipeline_url } from '../types/typeAliases';
 /**
+ * Wizzard for simple usage of the Promptbook
  * Look at `wizzard` for more details
  *
+ * Note: This works only in Node.js environment and looks for the configuration, environment, tools and cache in the Node.js environment
+ *
  * @private just for single instance
  */
 declare class Wizzard {
     /**
-     * @@@!!!!!!
+     * Run the book
+     *
+     * It can be loaded from:
+     * 1) As a file ./books/write-cv.book.md
+     * 2) As a URL https://promptbook.studio/hejny/write-cv.book.md found in ./books folder recursively
+     * 2) As a URL https://promptbook.studio/hejny/write-cv.book.md fetched from the internet
+     * 3) As a string
+     *
+     * Note: This works simmilar to the `ptbk run` command
      */
-    execute(book: string_pipeline_url, inputParameters: InputParameters, onProgress?: (taskProgress: TaskProgress) => Promisable<void>): Promise<PipelineExecutorResult>;
+    execute(book: string_pipeline_url | string_filename | PipelineString, inputParameters: InputParameters, onProgress?: (taskProgress: TaskProgress) => Promisable<void>): Promise<PipelineExecutorResult>;
     private executionTools;
     /**
-     * @@@!!!
+     * Provides the tools automatically for the Node.js environment
      *
      * @param pipelineSource
      */
     getExecutionTools(): Promise<Required<Pick<ExecutionTools, 'fs' | 'fetch'>>>;
     /**
-     * TODO: Make standalone function from this exported from node and used here and in `ptbk run`
-     * @@@!!!
+     * Load book from the source
      *
-     * Strategies:
-     * 1) @@@!!!
-     * 2) @@@!!!
+     * Pipelines can be loaded from:
+     * 1) As a file ./books/write-cv.book.md
+     * 2) As a URL https://promptbook.studio/hejny/write-cv.book.md found in ./books folder recursively
+     * 2) As a URL https://promptbook.studio/hejny/write-cv.book.md fetched from the internet
+     * 3) As a string
      *
      * @param pipelineSource
      */
     getCompiledBook(pipelineSource: string_filename | string_pipeline_url | PipelineString): Promise<PipelineJson>;
 }
 /**
- * 🧙‍♂️ @@@
+ * Wizzard for simple usage of the Promptbook
+ *
+ * Note: This works only in Node.js environment and looks for the configuration, environment, tools and cache in the Node.js environment
  *
  * @singleton
  * @public exported from `@promptbook/wizzard`
@@ -45,7 +59,5 @@ declare class Wizzard {
 export declare const wizzard: Wizzard;
 export {};
 /**
- * TODO: !!!!!! Mark in jsdoc as non-pure
- * TODO: !!!!!! Add to readmes - one markdown here imported in all packages
  * Note: [🟢] Code in this file should never be never released in packages that could be imported into browser environment
  */

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@promptbook/legacy-documents",
-    "version": "0.81.0-19",
+    "version": "0.81.0-21",
     "description": "It's time for a paradigm shift. The future of software in plain English, French or Latin",
     "--note-0": "    <- [🐊]",
     "private": false,
@@ -54,7 +54,7 @@
     "module": "./esm/index.es.js",
     "typings": "./esm/typings/src/_packages/legacy-documents.index.d.ts",
     "peerDependencies": {
-        "@promptbook/core": "0.81.0-19"
+        "@promptbook/core": "0.81.0-21"
     },
     "dependencies": {
         "colors": "1.4.0",

package/umd/index.umd.js

@@ -25,7 +25,7 @@
      * @generated
      * @see https://github.com/webgptorg/promptbook
      */
-    var PROMPTBOOK_ENGINE_VERSION = '0.81.0-18';
+    var PROMPTBOOK_ENGINE_VERSION = '0.81.0-20';
     /**
      * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
      * Note: [💞] Ignore a discrepancy between file name and entity name
@@ -190,6 +190,12 @@
      * @public exported from `@promptbook/core`
      */
     var ADMIN_GITHUB_NAME = 'hejny';
+    /**
+     * When the title is not provided, the default title is used
+     *
+     * @public exported from `@promptbook/core`
+     */
+    var DEFAULT_BOOK_TITLE = "\u2728 Untitled Book";
     // <- TODO: [🧠] Better system for generator warnings - not always "code" and "by `@promptbook/cli`"
     /**
      * The maximum number of iterations for a loops
@@ -1108,7 +1114,7 @@
      * Note: [🟢] Code in this file should never be never released in packages that could be imported into browser environment
      */
 
-    var PipelineCollection = [{title:"Prepare Knowledge from Markdown",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-from-markdown.book.md",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.md`\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.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-keywords.book.md",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.md`\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.md"},{title:"Prepare Title",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-title.book.md",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-   Title should be concise and clear\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 Title\n\n-   PIPELINE URL `https://promptbook.studio/promptbook/prepare-knowledge-title.book.md`\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-   Title should be concise and clear\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.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-persona.book.md",formfactorName:"GENERIC",parameters:[{name:"availableModelNames",description:"List of available model names separated by comma (,)",isInput:true,isOutput:false},{name:"personaDescription",description:"Description of the persona",isInput:true,isOutput:false},{name:"modelRequirements",description:"Specific requirements for the model",isInput:false,isOutput:true}],tasks:[{taskType:"PROMPT_TASK",name:"make-model-requirements",title:"Make modelRequirements",content:"You are experienced AI engineer, you need to create virtual assistant.\nWrite\n\n## Example\n\n```json\n{\n\"modelName\": \"gpt-4o\",\n\"systemMessage\": \"You are experienced AI engineer and helpfull assistant.\",\n\"temperature\": 0.7\n}\n```\n\n## Instructions\n\n-   Your output format is JSON object\n-   Write just the JSON object, no other text should be present\n-   It contains the 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\nPick from the following models:\n\n-   {availableModelNames}\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:"modelRequirements",format:"JSON",dependentParameterNames:["availableModelNames","personaDescription"]}],personas:[],preparations:[],knowledgeSources:[],knowledgePieces:[],sources:[{type:"BOOK",path:null,content:"# Prepare Keywords\n\n-   PIPELINE URL `https://promptbook.studio/promptbook/prepare-persona.book.md`\n-   INPUT PARAMETER `{availableModelNames}` List of available model names separated by comma (,)\n-   INPUT PARAMETER `{personaDescription}` Description of the persona\n-   OUTPUT PARAMETER `{modelRequirements}` Specific requirements for the model\n\n## Make modelRequirements\n\n-   FORMAT JSON\n\n```markdown\nYou are experienced AI engineer, you need to create virtual assistant.\nWrite\n\n## Example\n\n\\`\\`\\`json\n{\n\"modelName\": \"gpt-4o\",\n\"systemMessage\": \"You are experienced AI engineer and helpfull assistant.\",\n\"temperature\": 0.7\n}\n\\`\\`\\`\n\n## Instructions\n\n-   Your output format is JSON object\n-   Write just the JSON object, no other text should be present\n-   It contains the 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\nPick from the following models:\n\n-   {availableModelNames}\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`-> {modelRequirements}`\n"}],sourceFile:"./books/prepare-persona.book.md"}];
+    var PipelineCollection = [{title:"Prepare Knowledge from Markdown",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-from-markdown.book.md",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.md`\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.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-keywords.book.md",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.md`\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.md"},{title:"Prepare Knowledge-piece Title",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-title.book.md",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-   Title should be concise and clear - Write maximum ideally 2 words, maximum 5 words\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.md`\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-   Title should be concise and clear - Write maximum ideally 2 words, maximum 5 words\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.md"},{title:"Prepare Persona",pipelineUrl:"https://promptbook.studio/promptbook/prepare-persona.book.md",formfactorName:"GENERIC",parameters:[{name:"availableModelNames",description:"List of available model names separated by comma (,)",isInput:true,isOutput:false},{name:"personaDescription",description:"Description of the persona",isInput:true,isOutput:false},{name:"modelRequirements",description:"Specific requirements for the model",isInput:false,isOutput:true}],tasks:[{taskType:"PROMPT_TASK",name:"make-model-requirements",title:"Make modelRequirements",content:"You are experienced AI engineer, you need to create virtual assistant.\nWrite\n\n## Example\n\n```json\n{\n\"modelName\": \"gpt-4o\",\n\"systemMessage\": \"You are experienced AI engineer and helpfull assistant.\",\n\"temperature\": 0.7\n}\n```\n\n## Instructions\n\n-   Your output format is JSON object\n-   Write just the JSON object, no other text should be present\n-   It contains the 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\nPick from the following models:\n\n-   {availableModelNames}\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:"modelRequirements",format:"JSON",dependentParameterNames:["availableModelNames","personaDescription"]}],personas:[],preparations:[],knowledgeSources:[],knowledgePieces:[],sources:[{type:"BOOK",path:null,content:"# Prepare Persona\n\n-   PIPELINE URL `https://promptbook.studio/promptbook/prepare-persona.book.md`\n-   INPUT PARAMETER `{availableModelNames}` List of available model names separated by comma (,)\n-   INPUT PARAMETER `{personaDescription}` Description of the persona\n-   OUTPUT PARAMETER `{modelRequirements}` Specific requirements for the model\n\n## Make modelRequirements\n\n-   FORMAT JSON\n\n```markdown\nYou are experienced AI engineer, you need to create virtual assistant.\nWrite\n\n## Example\n\n\\`\\`\\`json\n{\n\"modelName\": \"gpt-4o\",\n\"systemMessage\": \"You are experienced AI engineer and helpfull assistant.\",\n\"temperature\": 0.7\n}\n\\`\\`\\`\n\n## Instructions\n\n-   Your output format is JSON object\n-   Write just the JSON object, no other text should be present\n-   It contains the 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\nPick from the following models:\n\n-   {availableModelNames}\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`-> {modelRequirements}`\n"}],sourceFile:"./books/prepare-persona.book.md"},{title:"Prepare Title",pipelineUrl:"https://promptbook.studio/promptbook/prepare-title.book.md",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 task:\n\n> {book}\n\n## Rules\n\n-   Write just title, nothing else\n-   Title should be concise and clear\n-   Title starts with emoticon",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.md`\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 task:\n\n> {book}\n\n## Rules\n\n-   Write just title, nothing else\n-   Title should be concise and clear\n-   Title starts with emoticon\n```\n\n`-> {title}`\n"}],sourceFile:"./books/prepare-title.book.md"}];
 
     /**
      * Prettify the html code
@@ -2513,11 +2519,16 @@
     /**
      * Determine if the pipeline is fully prepared
      *
+     * @see https://github.com/webgptorg/promptbook/discussions/196
+     *
      * @public exported from `@promptbook/core`
      */
     function isPipelinePrepared(pipeline) {
         // Note: Ignoring `pipeline.preparations` @@@
         // Note: Ignoring `pipeline.knowledgePieces` @@@
+        if (pipeline.title === undefined || pipeline.title === '' || pipeline.title === DEFAULT_BOOK_TITLE) {
+            return false;
+        }
         if (!pipeline.personas.every(function (persona) { return persona.modelRequirements !== undefined; })) {
             return false;
         }
@@ -3838,7 +3849,7 @@
                                                                 partialPieces = __spreadArray([], __read(partialPiecesUnchecked), false);
                                                                 return [2 /*return*/, "break"];
                                                             }
-                                                            console.warn(spaceTrim__default["default"](function (block) { return "\n                        Cannot scrape knowledge from source despite the scraper `".concat(scraper.metadata.className, "` supports the mime type \"").concat(sourceHandler.mimeType, "\".\n                        \n                        The source:\n                        > ").concat(block(knowledgeSource.sourceContent
+                                                            console.warn(spaceTrim__default["default"](function (block) { return "\n                        Cannot scrape knowledge from source despite the scraper `".concat(scraper.metadata.className, "` supports the mime type \"").concat(sourceHandler.mimeType, "\".\n\n                        The source:\n                        ").concat(block(knowledgeSource.sourceContent
                                                                 .split('\n')
                                                                 .map(function (line) { return "> ".concat(line); })
                                                                 .join('\n')), "\n\n                        ").concat(block($registeredScrapersMessage(scrapers)), "\n\n\n                    "); }));
@@ -3876,7 +3887,7 @@
                                             return [7 /*endfinally*/];
                                         case 9:
                                             if (partialPieces === null) {
-                                                throw new KnowledgeScrapeError(spaceTrim__default["default"](function (block) { return "\n                        Cannot scrape knowledge\n                        \n                        The source:\n                        > ".concat(block(knowledgeSource.sourceContent
+                                                throw new KnowledgeScrapeError(spaceTrim__default["default"](function (block) { return "\n                        Cannot scrape knowledge\n\n                        The source:\n                        > ".concat(block(knowledgeSource.sourceContent
                                                     .split('\n')
                                                     .map(function (line) { return "> ".concat(line); })
                                                     .join('\n')), "\n\n                        No scraper found for the mime type \"").concat(sourceHandler.mimeType, "\"\n\n                        ").concat(block($registeredScrapersMessage(scrapers)), "\n\n\n                    "); }));
@@ -3977,6 +3988,8 @@
     /**
      * Prepare pipeline from string (markdown) format to JSON format
      *
+     * @see https://github.com/webgptorg/promptbook/discussions/196
+     *
      * Note: This function does not validate logic of the pipeline
      * Note: This function acts as part of compilation process
      * Note: When the pipeline is already prepared, it returns the same pipeline
@@ -3989,16 +4002,17 @@
             <- TODO: [🧠][🪑] `promptbookVersion` */
             knowledgeSources /*
             <- TODO: [🧊] `knowledgePieces` */, personas /*
-            <- TODO: [🧊] `preparations` */, _llms, llmTools, llmToolsWithUsage, currentPreparation, preparations, preparedPersonas, knowledgeSourcesPrepared, partialknowledgePiecesPrepared, knowledgePiecesPrepared, tasksPrepared /* TODO: parameters: parametersPrepared*/;
+            <- TODO: [🧊] `preparations` */, sources, _llms, llmTools, llmToolsWithUsage, currentPreparation, preparations, title, collection, prepareTitleExecutor, _c, result, outputParameters, titleRaw, preparedPersonas, knowledgeSourcesPrepared, partialknowledgePiecesPrepared, knowledgePiecesPrepared, tasksPrepared /* TODO: parameters: parametersPrepared*/;
+            var _d;
             var _this = this;
-            return __generator(this, function (_c) {
-                switch (_c.label) {
+            return __generator(this, function (_e) {
+                switch (_e.label) {
                     case 0:
                         if (isPipelinePrepared(pipeline)) {
                             return [2 /*return*/, pipeline];
                         }
                         rootDirname = options.rootDirname, _a = options.maxParallelCount, maxParallelCount = _a === void 0 ? DEFAULT_MAX_PARALLEL_COUNT : _a, _b = options.isVerbose, isVerbose = _b === void 0 ? DEFAULT_IS_VERBOSE : _b;
-                        parameters = pipeline.parameters, tasks = pipeline.tasks, knowledgeSources = pipeline.knowledgeSources, personas = pipeline.personas;
+                        parameters = pipeline.parameters, tasks = pipeline.tasks, knowledgeSources = pipeline.knowledgeSources, personas = pipeline.personas, sources = pipeline.sources;
                         if (tools === undefined || tools.llm === undefined) {
                             throw new MissingToolsError('LLM tools are required for preparing the pipeline');
                         }
@@ -4016,6 +4030,40 @@
                             // <- TODO: [🧊]
                             currentPreparation,
                         ];
+                        title = pipeline.title;
+                        if (!(title === undefined || title === '' || title === DEFAULT_BOOK_TITLE)) return [3 /*break*/, 3];
+                        collection = createCollectionFromJson.apply(void 0, __spreadArray([], __read(PipelineCollection), false));
+                        _c = createPipelineExecutor;
+                        _d = {};
+                        return [4 /*yield*/, collection.getPipelineByUrl('https://promptbook.studio/promptbook/prepare-title.book.md')];
+                    case 1:
+                        prepareTitleExecutor = _c.apply(void 0, [(_d.pipeline = _e.sent(),
+                                _d.tools = tools,
+                                _d)]);
+                        return [4 /*yield*/, prepareTitleExecutor({
+                                book: sources
+                                    .map(function (_a) {
+                                    var content = _a.content;
+                                    return content;
+                                })
+                                    .join('\n\n')
+                                    // TODO: !!!!!!! Parameters in parameters - DO NOT ALLOW, ESCAPE:
+                                    .split('{')
+                                    .join('[')
+                                    .split('}')
+                                    .join(']'),
+                            })];
+                    case 2:
+                        result = _e.sent();
+                        assertsExecutionSuccessful(result);
+                        outputParameters = result.outputParameters;
+                        titleRaw = outputParameters.title;
+                        if (isVerbose) {
+                            console.info("The title is \"".concat(titleRaw, "\""));
+                        }
+                        title = titleRaw || DEFAULT_BOOK_TITLE;
+                        _e.label = 3;
+                    case 3:
                         preparedPersonas = new Array(personas.length);
                         return [4 /*yield*/, forEachAsync(personas, { maxParallelCount: maxParallelCount /* <- TODO: [🪂] When there are subtasks, this maximul limit can be broken */ }, function (persona, index) { return __awaiter(_this, void 0, void 0, function () {
                                 var modelRequirements, preparedPersona;
@@ -4034,12 +4082,12 @@
                                     }
                                 });
                             }); })];
-                    case 1:
-                        _c.sent();
+                    case 4:
+                        _e.sent();
                         knowledgeSourcesPrepared = knowledgeSources.map(function (source) { return (__assign(__assign({}, source), { preparationIds: [/* TODO: [🧊] -> */ currentPreparation.id] })); });
                         return [4 /*yield*/, prepareKnowledgePieces(knowledgeSources /* <- TODO: [🧊] {knowledgeSources, knowledgePieces} */, __assign(__assign({}, tools), { llm: llmToolsWithUsage }), __assign(__assign({}, options), { rootDirname: rootDirname, maxParallelCount: maxParallelCount /* <- TODO:  [🪂] */, isVerbose: isVerbose }))];
-                    case 2:
-                        partialknowledgePiecesPrepared = _c.sent();
+                    case 5:
+                        partialknowledgePiecesPrepared = _e.sent();
                         knowledgePiecesPrepared = partialknowledgePiecesPrepared.map(function (piece) { return (__assign(__assign({}, piece), { preparationIds: [/* TODO: [🧊] -> */ currentPreparation.id] })); });
                         return [4 /*yield*/, prepareTasks({
                                 parameters: parameters,
@@ -4050,8 +4098,8 @@
                                 maxParallelCount: maxParallelCount /* <- TODO:  [🪂] */,
                                 isVerbose: isVerbose,
                             })];
-                    case 3:
-                        tasksPrepared = (_c.sent()).tasksPrepared;
+                    case 6:
+                        tasksPrepared = (_e.sent()).tasksPrepared;
                         // ----- /Tasks preparation -----
                         // TODO: [😂] Use here all `AsyncHighLevelAbstraction`
                         // Note: Count total usage
@@ -4062,7 +4110,7 @@
                                 order: ORDER_OF_PIPELINE_JSON,
                                 value: __assign(__assign({}, pipeline), { 
                                     // <- TODO: Probbably deeply clone the pipeline because `$exportJson` freezes the subobjects
-                                    knowledgeSources: knowledgeSourcesPrepared, knowledgePieces: knowledgePiecesPrepared, tasks: __spreadArray([], __read(tasksPrepared), false), 
+                                    title: title, knowledgeSources: knowledgeSourcesPrepared, knowledgePieces: knowledgePiecesPrepared, tasks: __spreadArray([], __read(tasksPrepared), false), 
                                     // <- TODO: [🪓] Here should be no need for spreading new array, just ` tasks: tasksPrepared`
                                     personas: preparedPersonas, preparations: __spreadArray([], __read(preparations), false) }),
                             })];
@@ -6117,6 +6165,7 @@
         mimeTypes: ['text/markdown', 'text/plain'],
         documentationUrl: 'https://github.com/webgptorg/promptbook/discussions/@@',
         isAvilableInBrowser: true,
+        // <- Note: [🌏] This is the only scraper which makes sense to be available in the browser, for scraping non-markdown sources in the browser use a remote server
         requiredExecutables: [],
     }); /* <- Note: [🤛] */
     /**
@@ -6315,6 +6364,7 @@
         mimeTypes: ['application/vnd.openxmlformats-officedocument.wordprocessingml.document'],
         documentationUrl: 'https://github.com/webgptorg/promptbook/discussions/@@',
         isAvilableInBrowser: false,
+        // <- Note: [🌏] Only `MarkdownScraper` makes sense to be available in the browser, for scraping non-markdown sources in the browser use a remote server
         requiredExecutables: ['Pandoc'],
     }); /* <- Note: [🤛] */
     /**
@@ -6479,6 +6529,7 @@
         mimeTypes: ['application/msword', 'text/rtf'],
         documentationUrl: 'https://github.com/webgptorg/promptbook/discussions/@@',
         isAvilableInBrowser: false,
+        // <- Note: [🌏] Only `MarkdownScraper` makes sense to be available in the browser, for scraping non-markdown sources in the browser use a remote server
         requiredExecutables: [
             'Pandoc',
             'LibreOffice',