@promptbook/markdown-utils 0.84.0-21 → 0.84.0-9

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (38) hide show
  1. package/README.md +5 -21
  2. package/esm/index.es.js +164 -271
  3. package/esm/index.es.js.map +1 -1
  4. package/esm/typings/src/_packages/cli.index.d.ts +0 -4
  5. package/esm/typings/src/_packages/core.index.d.ts +2 -12
  6. package/esm/typings/src/_packages/types.index.d.ts +0 -2
  7. package/esm/typings/src/_packages/utils.index.d.ts +0 -2
  8. package/esm/typings/src/_packages/wizzard.index.d.ts +0 -4
  9. package/esm/typings/src/cli/cli-commands/about.d.ts +1 -3
  10. package/esm/typings/src/cli/cli-commands/hello.d.ts +1 -3
  11. package/esm/typings/src/cli/cli-commands/list-models.d.ts +1 -3
  12. package/esm/typings/src/cli/cli-commands/make.d.ts +1 -3
  13. package/esm/typings/src/cli/cli-commands/prettify.d.ts +1 -3
  14. package/esm/typings/src/cli/cli-commands/run.d.ts +1 -3
  15. package/esm/typings/src/cli/cli-commands/runInteractiveChatbot.d.ts +1 -1
  16. package/esm/typings/src/cli/cli-commands/test-command.d.ts +1 -3
  17. package/esm/typings/src/config.d.ts +1 -27
  18. package/esm/typings/src/conversion/compilePipelineOnRemoteServer.d.ts +1 -1
  19. package/esm/typings/src/execution/FilesystemTools.d.ts +1 -1
  20. package/esm/typings/src/execution/assertsExecutionSuccessful.d.ts +1 -3
  21. package/esm/typings/src/pipeline/book-notation.d.ts +2 -3
  22. package/esm/typings/src/pipeline/prompt-notation.d.ts +5 -18
  23. package/esm/typings/src/prepare/preparePipelineOnRemoteServer.d.ts +1 -1
  24. package/esm/typings/src/remote-server/socket-types/_subtypes/PromptbookServer_Identification.d.ts +2 -5
  25. package/esm/typings/src/wizzard/wizzard.d.ts +1 -7
  26. package/package.json +14 -7
  27. package/umd/index.umd.js +165 -272
  28. package/umd/index.umd.js.map +1 -1
  29. package/esm/typings/src/_packages/deepseek.index.d.ts +0 -8
  30. package/esm/typings/src/cli/cli-commands/list-scrapers.d.ts +0 -13
  31. package/esm/typings/src/llm-providers/deepseek/DeepseekExecutionToolsOptions.d.ts +0 -9
  32. package/esm/typings/src/llm-providers/deepseek/createDeepseekExecutionTools.d.ts +0 -14
  33. package/esm/typings/src/llm-providers/deepseek/register-configuration.d.ts +0 -14
  34. package/esm/typings/src/llm-providers/deepseek/register-constructor.d.ts +0 -15
  35. package/esm/typings/src/utils/editable/edit-pipeline-string/deflatePipeline.test.d.ts +0 -1
  36. package/esm/typings/src/utils/editable/utils/isFlatPipeline.test.d.ts +0 -1
  37. package/esm/typings/src/utils/files/mimeTypeToExtension.d.ts +0 -10
  38. package/esm/typings/src/utils/files/mimeTypeToExtension.test.d.ts +0 -1
package/umd/index.umd.js CHANGED
@@ -1,15 +1,14 @@
1
1
  (function (global, factory) {
2
- typeof exports === 'object' && typeof module !== 'undefined' ? factory(exports, require('spacetrim'), require('prettier'), require('prettier/parser-html'), require('waitasecond'), require('crypto-js/enc-hex'), require('crypto-js/sha256'), require('path'), require('crypto-js'), require('mime-types'), require('papaparse')) :
3
- typeof define === 'function' && define.amd ? define(['exports', 'spacetrim', 'prettier', 'prettier/parser-html', 'waitasecond', 'crypto-js/enc-hex', 'crypto-js/sha256', 'path', 'crypto-js', 'mime-types', 'papaparse'], factory) :
4
- (global = typeof globalThis !== 'undefined' ? globalThis : global || self, factory(global["promptbook-markdown-utils"] = {}, global.spaceTrim, global.prettier, global.parserHtml, global.waitasecond, global.hexEncoder, global.sha256, global.path, global.cryptoJs, global.mimeTypes, global.papaparse));
5
- })(this, (function (exports, spaceTrim, prettier, parserHtml, waitasecond, hexEncoder, sha256, path, cryptoJs, mimeTypes, papaparse) { 'use strict';
2
+ typeof exports === 'object' && typeof module !== 'undefined' ? factory(exports, require('spacetrim'), require('prettier'), require('prettier/parser-html'), require('waitasecond'), require('path'), require('crypto-js'), require('crypto-js/enc-hex'), require('mime-types'), require('papaparse')) :
3
+ typeof define === 'function' && define.amd ? define(['exports', 'spacetrim', 'prettier', 'prettier/parser-html', 'waitasecond', 'path', 'crypto-js', 'crypto-js/enc-hex', 'mime-types', 'papaparse'], factory) :
4
+ (global = typeof globalThis !== 'undefined' ? globalThis : global || self, factory(global["promptbook-markdown-utils"] = {}, global.spaceTrim, global.prettier, global.parserHtml, global.waitasecond, global.path, global.cryptoJs, global.hexEncoder, global.mimeTypes, global.papaparse));
5
+ })(this, (function (exports, spaceTrim, prettier, parserHtml, waitasecond, path, cryptoJs, hexEncoder, mimeTypes, papaparse) { 'use strict';
6
6
 
7
7
  function _interopDefaultLegacy (e) { return e && typeof e === 'object' && 'default' in e ? e : { 'default': e }; }
8
8
 
9
9
  var spaceTrim__default = /*#__PURE__*/_interopDefaultLegacy(spaceTrim);
10
10
  var parserHtml__default = /*#__PURE__*/_interopDefaultLegacy(parserHtml);
11
11
  var hexEncoder__default = /*#__PURE__*/_interopDefaultLegacy(hexEncoder);
12
- var sha256__default = /*#__PURE__*/_interopDefaultLegacy(sha256);
13
12
 
14
13
  // ⚠️ WARNING: This code has been generated so that any manual changes will be overwritten
15
14
  /**
@@ -25,7 +24,7 @@
25
24
  * @generated
26
25
  * @see https://github.com/webgptorg/promptbook
27
26
  */
28
- var PROMPTBOOK_ENGINE_VERSION = '0.84.0-20';
27
+ var PROMPTBOOK_ENGINE_VERSION = '0.84.0-8';
29
28
  /**
30
29
  * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
31
30
  * Note: [💞] Ignore a discrepancy between file name and entity name
@@ -363,99 +362,6 @@
363
362
 
364
363
  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- 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- 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 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.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 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.md"}];
365
364
 
366
- /**
367
- * Checks if value is valid email
368
- *
369
- * @public exported from `@promptbook/utils`
370
- */
371
- function isValidEmail(email) {
372
- if (typeof email !== 'string') {
373
- return false;
374
- }
375
- if (email.split('\n').length > 1) {
376
- return false;
377
- }
378
- return /^.+@.+\..+$/.test(email);
379
- }
380
-
381
- /**
382
- * Tests if given string is valid URL.
383
- *
384
- * Note: This does not check if the file exists only if the path is valid
385
- * @public exported from `@promptbook/utils`
386
- */
387
- function isValidFilePath(filename) {
388
- if (typeof filename !== 'string') {
389
- return false;
390
- }
391
- if (filename.split('\n').length > 1) {
392
- return false;
393
- }
394
- if (filename.split(' ').length >
395
- 5 /* <- TODO: [🧠][🈷] Make some better non-arbitrary way how to distinct filenames from informational texts */) {
396
- return false;
397
- }
398
- var filenameSlashes = filename.split('\\').join('/');
399
- // Absolute Unix path: /hello.txt
400
- if (/^(\/)/i.test(filenameSlashes)) {
401
- // console.log(filename, 'Absolute Unix path: /hello.txt');
402
- return true;
403
- }
404
- // Absolute Windows path: /hello.txt
405
- if (/^([A-Z]{1,2}:\/?)\//i.test(filenameSlashes)) {
406
- // console.log(filename, 'Absolute Windows path: /hello.txt');
407
- return true;
408
- }
409
- // Relative path: ./hello.txt
410
- if (/^(\.\.?\/)+/i.test(filenameSlashes)) {
411
- // console.log(filename, 'Relative path: ./hello.txt');
412
- return true;
413
- }
414
- // Allow paths like foo/hello
415
- if (/^[^/]+\/[^/]+/i.test(filenameSlashes)) {
416
- // console.log(filename, 'Allow paths like foo/hello');
417
- return true;
418
- }
419
- // Allow paths like hello.book
420
- if (/^[^/]+\.[^/]+$/i.test(filenameSlashes)) {
421
- // console.log(filename, 'Allow paths like hello.book');
422
- return true;
423
- }
424
- return false;
425
- }
426
- /**
427
- * TODO: [🍏] Implement for MacOs
428
- */
429
-
430
- /**
431
- * Tests if given string is valid URL.
432
- *
433
- * Note: Dataurl are considered perfectly valid.
434
- * Note: There are two simmilar functions:
435
- * - `isValidUrl` which tests any URL
436
- * - `isValidPipelineUrl` *(this one)* which tests just promptbook URL
437
- *
438
- * @public exported from `@promptbook/utils`
439
- */
440
- function isValidUrl(url) {
441
- if (typeof url !== 'string') {
442
- return false;
443
- }
444
- try {
445
- if (url.startsWith('blob:')) {
446
- url = url.replace(/^blob:/, '');
447
- }
448
- var urlObject = new URL(url /* because fail is handled */);
449
- if (!['http:', 'https:', 'data:'].includes(urlObject.protocol)) {
450
- return false;
451
- }
452
- return true;
453
- }
454
- catch (error) {
455
- return false;
456
- }
457
- }
458
-
459
365
  /**
460
366
  * Function `validatePipelineString` will validate the if the string is a valid pipeline string
461
367
  * It does not check if the string is fully logically correct, but if it is a string that can be a pipeline string or the string looks completely different.
@@ -469,15 +375,6 @@
469
375
  if (isValidJsonString(pipelineString)) {
470
376
  throw new ParseError('Expected a book, but got a JSON string');
471
377
  }
472
- else if (isValidUrl(pipelineString)) {
473
- throw new ParseError("Expected a book, but got just the URL \"".concat(pipelineString, "\""));
474
- }
475
- else if (isValidFilePath(pipelineString)) {
476
- throw new ParseError("Expected a book, but got just the file path \"".concat(pipelineString, "\""));
477
- }
478
- else if (isValidEmail(pipelineString)) {
479
- throw new ParseError("Expected a book, but got just the email \"".concat(pipelineString, "\""));
480
- }
481
378
  // <- TODO: Implement the validation + add tests when the pipeline logic considered as invalid
482
379
  return pipelineString;
483
380
  }
@@ -778,12 +675,6 @@
778
675
  * @public exported from `@promptbook/core`
779
676
  */
780
677
  var DEFAULT_BOOK_TITLE = "\u2728 Untitled Book";
781
- /**
782
- * Maximum file size limit
783
- *
784
- * @public exported from `@promptbook/core`
785
- */
786
- var DEFAULT_MAX_FILE_SIZE = 100 * 1024 * 1024; // 100MB
787
678
  // <- TODO: [🧠] Better system for generator warnings - not always "code" and "by `@promptbook/cli`"
788
679
  /**
789
680
  * The maximum number of iterations for a loops
@@ -817,12 +708,6 @@
817
708
  * @private within the repository - too low-level in comparison with other `MAX_...`
818
709
  */
819
710
  var IMMEDIATE_TIME = 10;
820
- /**
821
- * The maximum length of the (generated) filename
822
- *
823
- * @public exported from `@promptbook/core`
824
- */
825
- var MAX_FILENAME_LENGTH = 30;
826
711
  /**
827
712
  * Strategy for caching the intermediate results for knowledge sources
828
713
  *
@@ -842,15 +727,6 @@
842
727
  * @public exported from `@promptbook/core`
843
728
  */
844
729
  var DEFAULT_MAX_EXECUTION_ATTEMPTS = 3; // <- TODO: [🤹‍♂️]
845
- // <- TODO: [🕝] Make also `BOOKS_DIRNAME_ALTERNATIVES`
846
- /**
847
- * Where to store the temporary downloads
848
- *
849
- * Note: When the folder does not exist, it is created recursively
850
- *
851
- * @public exported from `@promptbook/core`
852
- */
853
- var DEFAULT_DOWNLOAD_CACHE_DIRNAME = './.promptbook/download-cache';
854
730
  /**
855
731
  * Where to store the scrape cache
856
732
  *
@@ -1333,6 +1209,35 @@
1333
1209
  return isHostnameOnPrivateNetwork(url.hostname);
1334
1210
  }
1335
1211
 
1212
+ /**
1213
+ * Tests if given string is valid URL.
1214
+ *
1215
+ * Note: Dataurl are considered perfectly valid.
1216
+ * Note: There are two simmilar functions:
1217
+ * - `isValidUrl` which tests any URL
1218
+ * - `isValidPipelineUrl` *(this one)* which tests just promptbook URL
1219
+ *
1220
+ * @public exported from `@promptbook/utils`
1221
+ */
1222
+ function isValidUrl(url) {
1223
+ if (typeof url !== 'string') {
1224
+ return false;
1225
+ }
1226
+ try {
1227
+ if (url.startsWith('blob:')) {
1228
+ url = url.replace(/^blob:/, '');
1229
+ }
1230
+ var urlObject = new URL(url /* because fail is handled */);
1231
+ if (!['http:', 'https:', 'data:'].includes(urlObject.protocol)) {
1232
+ return false;
1233
+ }
1234
+ return true;
1235
+ }
1236
+ catch (error) {
1237
+ return false;
1238
+ }
1239
+ }
1240
+
1336
1241
  /**
1337
1242
  * Tests if given string is valid pipeline URL URL.
1338
1243
  *
@@ -2087,28 +1992,12 @@
2087
1992
  /**
2088
1993
  * Asserts that the execution of a Promptbook is successful
2089
1994
  *
2090
- * Note: If there are only warnings, the execution is still successful but the warnings are logged in the console
2091
- *
2092
1995
  * @param executionResult - The partial result of the Promptbook execution
2093
1996
  * @throws {PipelineExecutionError} If the execution is not successful or if multiple errors occurred
2094
1997
  * @public exported from `@promptbook/core`
2095
1998
  */
2096
1999
  function assertsExecutionSuccessful(executionResult) {
2097
- var e_1, _a;
2098
- var isSuccessful = executionResult.isSuccessful, errors = executionResult.errors, warnings = executionResult.warnings;
2099
- try {
2100
- for (var warnings_1 = __values(warnings), warnings_1_1 = warnings_1.next(); !warnings_1_1.done; warnings_1_1 = warnings_1.next()) {
2101
- var warning = warnings_1_1.value;
2102
- console.warn(warning.message);
2103
- }
2104
- }
2105
- catch (e_1_1) { e_1 = { error: e_1_1 }; }
2106
- finally {
2107
- try {
2108
- if (warnings_1_1 && !warnings_1_1.done && (_a = warnings_1.return)) _a.call(warnings_1);
2109
- }
2110
- finally { if (e_1) throw e_1.error; }
2111
- }
2000
+ var isSuccessful = executionResult.isSuccessful, errors = executionResult.errors;
2112
2001
  if (isSuccessful === true) {
2113
2002
  return;
2114
2003
  }
@@ -2745,7 +2634,7 @@
2745
2634
  if (!(error_1 instanceof Error) || error_1 instanceof UnexpectedError) {
2746
2635
  throw error_1;
2747
2636
  }
2748
- errors.push({ llmExecutionTools: llmExecutionTools, error: error_1 });
2637
+ errors.push(error_1);
2749
2638
  return [3 /*break*/, 13];
2750
2639
  case 13:
2751
2640
  _b = _a.next();
@@ -2772,10 +2661,7 @@
2772
2661
  // 2) AnthropicClaude throw PipelineExecutionError: Parameter `{knowledge}` is not defined
2773
2662
  // 3) ...
2774
2663
  spaceTrim__default["default"](function (block) { return "\n All execution tools failed:\n\n ".concat(block(errors
2775
- .map(function (_a, i) {
2776
- var error = _a.error, llmExecutionTools = _a.llmExecutionTools;
2777
- return "".concat(i + 1, ") **").concat(llmExecutionTools.title, "** thrown **").concat(error.name || 'Error', ":** ").concat(error.message);
2778
- })
2664
+ .map(function (error, i) { return "".concat(i + 1, ") **").concat(error.name || 'Error', ":** ").concat(error.message); })
2779
2665
  .join('\n')), "\n\n "); }));
2780
2666
  }
2781
2667
  else if (this.llmExecutionTools.length === 0) {
@@ -3561,15 +3447,6 @@
3561
3447
  * TODO: [🐱‍🐉][🧠] Make some smart crop NOT source-i-m-pavol-a-develop-... BUT source-i-m-pavol-a-developer-...
3562
3448
  */
3563
3449
 
3564
- /**
3565
- * @@@
3566
- *
3567
- * @private for `FileCacheStorage`
3568
- */
3569
- function nameToSubfolderPath(name) {
3570
- return [name.substr(0, 1).toLowerCase(), name.substr(1, 1).toLowerCase()];
3571
- }
3572
-
3573
3450
  /**
3574
3451
  * Convert file extension to mime type
3575
3452
  *
@@ -3626,55 +3503,53 @@
3626
3503
  */
3627
3504
 
3628
3505
  /**
3629
- * Convert mime type to file extension
3630
- *
3631
- * Note: If the mime type is invalid, `null` is returned
3632
- *
3633
- * @private within the repository
3634
- */
3635
- function mimeTypeToExtension(value) {
3636
- return mimeTypes.extension(value) || null;
3637
- }
3638
-
3639
- /**
3640
- * Removes emojis from a string and fix whitespaces
3641
- *
3642
- * @param text with emojis
3643
- * @returns text without emojis
3644
- * @public exported from `@promptbook/utils`
3645
- */
3646
- function removeEmojis(text) {
3647
- // Replace emojis (and also ZWJ sequence) with hyphens
3648
- text = text.replace(/(\p{Extended_Pictographic})\p{Modifier_Symbol}/gu, '$1');
3649
- text = text.replace(/(\p{Extended_Pictographic})[\u{FE00}-\u{FE0F}]/gu, '$1');
3650
- text = text.replace(/(\p{Extended_Pictographic})(\u{200D}\p{Extended_Pictographic})*/gu, '$1');
3651
- text = text.replace(/\p{Extended_Pictographic}/gu, '');
3652
- return text;
3653
- }
3654
-
3655
- /**
3656
- * @@@
3506
+ * Tests if given string is valid URL.
3657
3507
  *
3658
- * @param value @@@
3659
- * @returns @@@
3660
- * @example @@@
3508
+ * Note: This does not check if the file exists only if the path is valid
3661
3509
  * @public exported from `@promptbook/utils`
3662
3510
  */
3663
- function titleToName(value) {
3664
- if (isValidUrl(value)) {
3665
- value = value.replace(/^https?:\/\//, '');
3666
- value = value.replace(/\.html$/, '');
3511
+ function isValidFilePath(filename) {
3512
+ if (typeof filename !== 'string') {
3513
+ return false;
3667
3514
  }
3668
- else if (isValidFilePath(value)) {
3669
- value = path.basename(value);
3670
- // Note: Keeping extension in the name
3515
+ if (filename.split('\n').length > 1) {
3516
+ return false;
3671
3517
  }
3672
- value = value.split('/').join('-');
3673
- value = removeEmojis(value);
3674
- value = normalizeToKebabCase(value);
3675
- // TODO: [🧠] Maybe warn or add some padding to short name which are not good identifiers
3676
- return value;
3518
+ if (filename.split(' ').length >
3519
+ 5 /* <- TODO: [🧠][🈷] Make some better non-arbitrary way how to distinct filenames from informational texts */) {
3520
+ return false;
3521
+ }
3522
+ var filenameSlashes = filename.split('\\').join('/');
3523
+ // Absolute Unix path: /hello.txt
3524
+ if (/^(\/)/i.test(filenameSlashes)) {
3525
+ // console.log(filename, 'Absolute Unix path: /hello.txt');
3526
+ return true;
3527
+ }
3528
+ // Absolute Windows path: /hello.txt
3529
+ if (/^([A-Z]{1,2}:\/?)\//i.test(filenameSlashes)) {
3530
+ // console.log(filename, 'Absolute Windows path: /hello.txt');
3531
+ return true;
3532
+ }
3533
+ // Relative path: ./hello.txt
3534
+ if (/^(\.\.?\/)+/i.test(filenameSlashes)) {
3535
+ // console.log(filename, 'Relative path: ./hello.txt');
3536
+ return true;
3537
+ }
3538
+ // Allow paths like foo/hello
3539
+ if (/^[^/]+\/[^/]+/i.test(filenameSlashes)) {
3540
+ // console.log(filename, 'Allow paths like foo/hello');
3541
+ return true;
3542
+ }
3543
+ // Allow paths like hello.book
3544
+ if (/^[^/]+\.[^/]+$/i.test(filenameSlashes)) {
3545
+ // console.log(filename, 'Allow paths like hello.book');
3546
+ return true;
3547
+ }
3548
+ return false;
3677
3549
  }
3550
+ /**
3551
+ * TODO: [🍏] Implement for MacOs
3552
+ */
3678
3553
 
3679
3554
  /**
3680
3555
  * The built-in `fetch' function with a lightweight error handling wrapper as default fetch function used in Promptbook scrapers
@@ -3711,9 +3586,9 @@
3711
3586
  function makeKnowledgeSourceHandler(knowledgeSource, tools, options) {
3712
3587
  var _a;
3713
3588
  return __awaiter(this, void 0, void 0, function () {
3714
- var _b, fetch, knowledgeSourceContent, name, _c, _d, rootDirname, url, response_1, mimeType, basename, hash, rootDirname_1, filepath, fileContent, _f, _g, filename_1, fileExtension, mimeType;
3715
- return __generator(this, function (_h) {
3716
- switch (_h.label) {
3589
+ var _b, fetch, knowledgeSourceContent, name, _c, _d, rootDirname, url, response_1, mimeType, filename_1, fileExtension, mimeType;
3590
+ return __generator(this, function (_f) {
3591
+ switch (_f.label) {
3717
3592
  case 0:
3718
3593
  _b = tools.fetch, fetch = _b === void 0 ? scraperFetch : _b;
3719
3594
  knowledgeSourceContent = knowledgeSource.knowledgeSourceContent;
@@ -3722,76 +3597,54 @@
3722
3597
  if (!name) {
3723
3598
  name = knowledgeSourceContentToName(knowledgeSourceContent);
3724
3599
  }
3725
- if (!isValidUrl(knowledgeSourceContent)) return [3 /*break*/, 5];
3600
+ if (!isValidUrl(knowledgeSourceContent)) return [3 /*break*/, 2];
3726
3601
  url = knowledgeSourceContent;
3727
3602
  return [4 /*yield*/, fetch(url)];
3728
3603
  case 1:
3729
- response_1 = _h.sent();
3604
+ response_1 = _f.sent();
3730
3605
  mimeType = ((_a = response_1.headers.get('content-type')) === null || _a === void 0 ? void 0 : _a.split(';')[0]) || 'text/html';
3731
- if (tools.fs === undefined || !url.endsWith('.pdf' /* <- TODO: [💵] */)) {
3732
- return [2 /*return*/, {
3733
- source: name,
3734
- filename: null,
3735
- url: url,
3736
- mimeType: mimeType,
3737
- /*
3738
- TODO: [🥽]
3739
- > async asBlob() {
3740
- > // TODO: [👨🏻‍🤝‍👨🏻] This can be called multiple times BUT when called second time, response in already consumed
3741
- > const content = await response.blob();
3742
- > return content;
3743
- > },
3744
- */
3745
- asJson: function () {
3746
- return __awaiter(this, void 0, void 0, function () {
3747
- var content;
3748
- return __generator(this, function (_a) {
3749
- switch (_a.label) {
3750
- case 0: return [4 /*yield*/, response_1.json()];
3751
- case 1:
3752
- content = _a.sent();
3753
- return [2 /*return*/, content];
3754
- }
3755
- });
3606
+ return [2 /*return*/, {
3607
+ source: name,
3608
+ filename: null,
3609
+ url: url,
3610
+ mimeType: mimeType,
3611
+ /*
3612
+ TODO: [🥽]
3613
+ > async asBlob() {
3614
+ > // TODO: [👨🏻‍🤝‍👨🏻] This can be called multiple times BUT when called second time, response in already consumed
3615
+ > const content = await response.blob();
3616
+ > return content;
3617
+ > },
3618
+ */
3619
+ asJson: function () {
3620
+ return __awaiter(this, void 0, void 0, function () {
3621
+ var content;
3622
+ return __generator(this, function (_a) {
3623
+ switch (_a.label) {
3624
+ case 0: return [4 /*yield*/, response_1.json()];
3625
+ case 1:
3626
+ content = _a.sent();
3627
+ return [2 /*return*/, content];
3628
+ }
3756
3629
  });
3757
- },
3758
- asText: function () {
3759
- return __awaiter(this, void 0, void 0, function () {
3760
- var content;
3761
- return __generator(this, function (_a) {
3762
- switch (_a.label) {
3763
- case 0: return [4 /*yield*/, response_1.text()];
3764
- case 1:
3765
- content = _a.sent();
3766
- return [2 /*return*/, content];
3767
- }
3768
- });
3630
+ });
3631
+ },
3632
+ asText: function () {
3633
+ return __awaiter(this, void 0, void 0, function () {
3634
+ var content;
3635
+ return __generator(this, function (_a) {
3636
+ switch (_a.label) {
3637
+ case 0: return [4 /*yield*/, response_1.text()];
3638
+ case 1:
3639
+ content = _a.sent();
3640
+ return [2 /*return*/, content];
3641
+ }
3769
3642
  });
3770
- },
3771
- }];
3772
- }
3773
- basename = url.split('/').pop() || titleToName(url);
3774
- hash = sha256__default["default"](hexEncoder__default["default"].parse(url)).toString( /* hex */);
3775
- rootDirname_1 = path.join(process.cwd(), DEFAULT_DOWNLOAD_CACHE_DIRNAME);
3776
- filepath = path.join.apply(void 0, __spreadArray(__spreadArray([], __read(nameToSubfolderPath(hash /* <- TODO: [🎎] Maybe add some SHA256 prefix */)), false), ["".concat(basename.substring(0, MAX_FILENAME_LENGTH), ".").concat(mimeTypeToExtension(mimeType))], false));
3777
- return [4 /*yield*/, tools.fs.mkdir(path.dirname(path.join(rootDirname_1, filepath)), { recursive: true })];
3643
+ });
3644
+ },
3645
+ }];
3778
3646
  case 2:
3779
- _h.sent();
3780
- _g = (_f = Buffer).from;
3781
- return [4 /*yield*/, response_1.arrayBuffer()];
3782
- case 3:
3783
- fileContent = _g.apply(_f, [_h.sent()]);
3784
- if (fileContent.length > DEFAULT_MAX_FILE_SIZE /* <- TODO: Allow to pass different value to remote server */) {
3785
- throw new LimitReachedError("File is too large (".concat(Math.round(fileContent.length / 1024 / 1024), "MB). Maximum allowed size is ").concat(Math.round(DEFAULT_MAX_FILE_SIZE / 1024 / 1024), "MB."));
3786
- }
3787
- return [4 /*yield*/, tools.fs.writeFile(path.join(rootDirname_1, filepath), fileContent)];
3788
- case 4:
3789
- _h.sent();
3790
- // TODO: [💵] Check the file security
3791
- // TODO: [🧹][🧠] Delete the file after the scraping is done
3792
- return [2 /*return*/, makeKnowledgeSourceHandler({ name: name, knowledgeSourceContent: filepath }, tools, __assign(__assign({}, options), { rootDirname: rootDirname_1 }))];
3793
- case 5:
3794
- if (!isValidFilePath(knowledgeSourceContent)) return [3 /*break*/, 7];
3647
+ if (!isValidFilePath(knowledgeSourceContent)) return [3 /*break*/, 4];
3795
3648
  if (tools.fs === undefined) {
3796
3649
  throw new EnvironmentMismatchError('Can not import file knowledge without filesystem tools');
3797
3650
  // <- TODO: [🧠] What is the best error type here`
@@ -3804,8 +3657,8 @@
3804
3657
  fileExtension = getFileExtension(filename_1);
3805
3658
  mimeType = extensionToMimeType(fileExtension || '');
3806
3659
  return [4 /*yield*/, isFileExisting(filename_1, tools.fs)];
3807
- case 6:
3808
- if (!(_h.sent())) {
3660
+ case 3:
3661
+ if (!(_f.sent())) {
3809
3662
  throw new NotFoundError(spaceTrim__default["default"](function (block) { return "\n Can not make source handler for file which does not exist:\n\n File:\n ".concat(block(knowledgeSourceContent), "\n\n Full file path:\n ").concat(block(filename_1), "\n "); }));
3810
3663
  }
3811
3664
  // TODO: [🧠][😿] Test security file - file is scoped to the project (BUT maybe do this in `filesystemTools`)
@@ -3851,7 +3704,7 @@
3851
3704
  });
3852
3705
  },
3853
3706
  }];
3854
- case 7: return [2 /*return*/, {
3707
+ case 4: return [2 /*return*/, {
3855
3708
  source: name,
3856
3709
  filename: null,
3857
3710
  url: null,
@@ -6081,6 +5934,46 @@
6081
5934
  * TODO: [🐚] Change onProgress to object that represents the running execution, can be subscribed via RxJS to and also awaited
6082
5935
  */
6083
5936
 
5937
+ /**
5938
+ * Removes emojis from a string and fix whitespaces
5939
+ *
5940
+ * @param text with emojis
5941
+ * @returns text without emojis
5942
+ * @public exported from `@promptbook/utils`
5943
+ */
5944
+ function removeEmojis(text) {
5945
+ // Replace emojis (and also ZWJ sequence) with hyphens
5946
+ text = text.replace(/(\p{Extended_Pictographic})\p{Modifier_Symbol}/gu, '$1');
5947
+ text = text.replace(/(\p{Extended_Pictographic})[\u{FE00}-\u{FE0F}]/gu, '$1');
5948
+ text = text.replace(/(\p{Extended_Pictographic})(\u{200D}\p{Extended_Pictographic})*/gu, '$1');
5949
+ text = text.replace(/\p{Extended_Pictographic}/gu, '');
5950
+ return text;
5951
+ }
5952
+
5953
+ /**
5954
+ * @@@
5955
+ *
5956
+ * @param value @@@
5957
+ * @returns @@@
5958
+ * @example @@@
5959
+ * @public exported from `@promptbook/utils`
5960
+ */
5961
+ function titleToName(value) {
5962
+ if (isValidUrl(value)) {
5963
+ value = value.replace(/^https?:\/\//, '');
5964
+ value = value.replace(/\.html$/, '');
5965
+ }
5966
+ else if (isValidFilePath(value)) {
5967
+ value = path.basename(value);
5968
+ // Note: Keeping extension in the name
5969
+ }
5970
+ value = value.split('/').join('-');
5971
+ value = removeEmojis(value);
5972
+ value = normalizeToKebabCase(value);
5973
+ // TODO: [🧠] Maybe warn or add some padding to short name which are not good identifiers
5974
+ return value;
5975
+ }
5976
+
6084
5977
  /**
6085
5978
  * Metadata of the scraper
6086
5979
  *