@promptbook/pdf 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 +71 -170
  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 +16 -9
  27. package/umd/index.umd.js +74 -173
  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('fs/promises'), require('spacetrim'), require('crypto-js'), require('crypto-js/enc-hex'), require('path'), require('prettier'), require('prettier/parser-html'), require('waitasecond'), require('crypto-js/sha256'), require('mime-types'), require('papaparse')) :
3
- typeof define === 'function' && define.amd ? define(['exports', 'fs/promises', 'spacetrim', 'crypto-js', 'crypto-js/enc-hex', 'path', 'prettier', 'prettier/parser-html', 'waitasecond', 'crypto-js/sha256', 'mime-types', 'papaparse'], factory) :
4
- (global = typeof globalThis !== 'undefined' ? globalThis : global || self, factory(global["promptbook-pdf"] = {}, global.promises, global.spaceTrim, global.cryptoJs, global.hexEncoder, global.path, global.prettier, global.parserHtml, global.waitasecond, global.sha256, global.mimeTypes, global.papaparse));
5
- })(this, (function (exports, promises, spaceTrim, cryptoJs, hexEncoder, path, prettier, parserHtml, waitasecond, sha256, mimeTypes, papaparse) { 'use strict';
2
+ typeof exports === 'object' && typeof module !== 'undefined' ? factory(exports, require('fs/promises'), require('spacetrim'), require('crypto-js'), require('crypto-js/enc-hex'), require('path'), require('prettier'), require('prettier/parser-html'), require('waitasecond'), require('mime-types'), require('papaparse')) :
3
+ typeof define === 'function' && define.amd ? define(['exports', 'fs/promises', 'spacetrim', 'crypto-js', 'crypto-js/enc-hex', 'path', 'prettier', 'prettier/parser-html', 'waitasecond', 'mime-types', 'papaparse'], factory) :
4
+ (global = typeof globalThis !== 'undefined' ? globalThis : global || self, factory(global["promptbook-pdf"] = {}, global.promises, global.spaceTrim, global.cryptoJs, global.hexEncoder, global.path, global.prettier, global.parserHtml, global.waitasecond, global.mimeTypes, global.papaparse));
5
+ })(this, (function (exports, promises, spaceTrim, cryptoJs, hexEncoder, path, prettier, parserHtml, waitasecond, 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 hexEncoder__default = /*#__PURE__*/_interopDefaultLegacy(hexEncoder);
11
11
  var parserHtml__default = /*#__PURE__*/_interopDefaultLegacy(parserHtml);
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
@@ -196,12 +195,6 @@
196
195
  * @public exported from `@promptbook/core`
197
196
  */
198
197
  var DEFAULT_BOOK_TITLE = "\u2728 Untitled Book";
199
- /**
200
- * Maximum file size limit
201
- *
202
- * @public exported from `@promptbook/core`
203
- */
204
- var DEFAULT_MAX_FILE_SIZE = 100 * 1024 * 1024; // 100MB
205
198
  // <- TODO: [🧠] Better system for generator warnings - not always "code" and "by `@promptbook/cli`"
206
199
  /**
207
200
  * The maximum number of iterations for a loops
@@ -235,12 +228,6 @@
235
228
  * @private within the repository - too low-level in comparison with other `MAX_...`
236
229
  */
237
230
  var IMMEDIATE_TIME = 10;
238
- /**
239
- * The maximum length of the (generated) filename
240
- *
241
- * @public exported from `@promptbook/core`
242
- */
243
- var MAX_FILENAME_LENGTH = 30;
244
231
  /**
245
232
  * Strategy for caching the intermediate results for knowledge sources
246
233
  *
@@ -260,15 +247,6 @@
260
247
  * @public exported from `@promptbook/core`
261
248
  */
262
249
  var DEFAULT_MAX_EXECUTION_ATTEMPTS = 3; // <- TODO: [🤹‍♂️]
263
- // <- TODO: [🕝] Make also `BOOKS_DIRNAME_ALTERNATIVES`
264
- /**
265
- * Where to store the temporary downloads
266
- *
267
- * Note: When the folder does not exist, it is created recursively
268
- *
269
- * @public exported from `@promptbook/core`
270
- */
271
- var DEFAULT_DOWNLOAD_CACHE_DIRNAME = './.promptbook/download-cache';
272
250
  /**
273
251
  * Where to store the scrape cache
274
252
  *
@@ -963,18 +941,24 @@
963
941
  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"}];
964
942
 
965
943
  /**
966
- * Checks if value is valid email
944
+ * Function isValidJsonString will tell you if the string is valid JSON or not
967
945
  *
968
946
  * @public exported from `@promptbook/utils`
969
947
  */
970
- function isValidEmail(email) {
971
- if (typeof email !== 'string') {
972
- return false;
948
+ function isValidJsonString(value /* <- [👨‍⚖️] */) {
949
+ try {
950
+ JSON.parse(value);
951
+ return true;
973
952
  }
974
- if (email.split('\n').length > 1) {
953
+ catch (error) {
954
+ if (!(error instanceof Error)) {
955
+ throw error;
956
+ }
957
+ if (error.message.includes('Unexpected token')) {
958
+ return false;
959
+ }
975
960
  return false;
976
961
  }
977
- return /^.+@.+\..+$/.test(email);
978
962
  }
979
963
 
980
964
  /**
@@ -996,27 +980,6 @@
996
980
  * TODO: Maybe split `ParseError` and `ApplyError`
997
981
  */
998
982
 
999
- /**
1000
- * Function isValidJsonString will tell you if the string is valid JSON or not
1001
- *
1002
- * @public exported from `@promptbook/utils`
1003
- */
1004
- function isValidJsonString(value /* <- [👨‍⚖️] */) {
1005
- try {
1006
- JSON.parse(value);
1007
- return true;
1008
- }
1009
- catch (error) {
1010
- if (!(error instanceof Error)) {
1011
- throw error;
1012
- }
1013
- if (error.message.includes('Unexpected token')) {
1014
- return false;
1015
- }
1016
- return false;
1017
- }
1018
- }
1019
-
1020
983
  /**
1021
984
  * Function `validatePipelineString` will validate the if the string is a valid pipeline string
1022
985
  * 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.
@@ -1030,15 +993,6 @@
1030
993
  if (isValidJsonString(pipelineString)) {
1031
994
  throw new ParseError('Expected a book, but got a JSON string');
1032
995
  }
1033
- else if (isValidUrl(pipelineString)) {
1034
- throw new ParseError("Expected a book, but got just the URL \"".concat(pipelineString, "\""));
1035
- }
1036
- else if (isValidFilePath(pipelineString)) {
1037
- throw new ParseError("Expected a book, but got just the file path \"".concat(pipelineString, "\""));
1038
- }
1039
- else if (isValidEmail(pipelineString)) {
1040
- throw new ParseError("Expected a book, but got just the email \"".concat(pipelineString, "\""));
1041
- }
1042
996
  // <- TODO: Implement the validation + add tests when the pipeline logic considered as invalid
1043
997
  return pipelineString;
1044
998
  }
@@ -2420,28 +2374,12 @@
2420
2374
  /**
2421
2375
  * Asserts that the execution of a Promptbook is successful
2422
2376
  *
2423
- * Note: If there are only warnings, the execution is still successful but the warnings are logged in the console
2424
- *
2425
2377
  * @param executionResult - The partial result of the Promptbook execution
2426
2378
  * @throws {PipelineExecutionError} If the execution is not successful or if multiple errors occurred
2427
2379
  * @public exported from `@promptbook/core`
2428
2380
  */
2429
2381
  function assertsExecutionSuccessful(executionResult) {
2430
- var e_1, _a;
2431
- var isSuccessful = executionResult.isSuccessful, errors = executionResult.errors, warnings = executionResult.warnings;
2432
- try {
2433
- for (var warnings_1 = __values(warnings), warnings_1_1 = warnings_1.next(); !warnings_1_1.done; warnings_1_1 = warnings_1.next()) {
2434
- var warning = warnings_1_1.value;
2435
- console.warn(warning.message);
2436
- }
2437
- }
2438
- catch (e_1_1) { e_1 = { error: e_1_1 }; }
2439
- finally {
2440
- try {
2441
- if (warnings_1_1 && !warnings_1_1.done && (_a = warnings_1.return)) _a.call(warnings_1);
2442
- }
2443
- finally { if (e_1) throw e_1.error; }
2444
- }
2382
+ var isSuccessful = executionResult.isSuccessful, errors = executionResult.errors;
2445
2383
  if (isSuccessful === true) {
2446
2384
  return;
2447
2385
  }
@@ -3078,7 +3016,7 @@
3078
3016
  if (!(error_1 instanceof Error) || error_1 instanceof UnexpectedError) {
3079
3017
  throw error_1;
3080
3018
  }
3081
- errors.push({ llmExecutionTools: llmExecutionTools, error: error_1 });
3019
+ errors.push(error_1);
3082
3020
  return [3 /*break*/, 13];
3083
3021
  case 13:
3084
3022
  _b = _a.next();
@@ -3105,10 +3043,7 @@
3105
3043
  // 2) AnthropicClaude throw PipelineExecutionError: Parameter `{knowledge}` is not defined
3106
3044
  // 3) ...
3107
3045
  spaceTrim__default["default"](function (block) { return "\n All execution tools failed:\n\n ".concat(block(errors
3108
- .map(function (_a, i) {
3109
- var error = _a.error, llmExecutionTools = _a.llmExecutionTools;
3110
- return "".concat(i + 1, ") **").concat(llmExecutionTools.title, "** thrown **").concat(error.name || 'Error', ":** ").concat(error.message);
3111
- })
3046
+ .map(function (error, i) { return "".concat(i + 1, ") **").concat(error.name || 'Error', ":** ").concat(error.message); })
3112
3047
  .join('\n')), "\n\n "); }));
3113
3048
  }
3114
3049
  else if (this.llmExecutionTools.length === 0) {
@@ -3590,17 +3525,6 @@
3590
3525
  return match ? match[1].toLowerCase() : null;
3591
3526
  }
3592
3527
 
3593
- /**
3594
- * Convert mime type to file extension
3595
- *
3596
- * Note: If the mime type is invalid, `null` is returned
3597
- *
3598
- * @private within the repository
3599
- */
3600
- function mimeTypeToExtension(value) {
3601
- return mimeTypes.extension(value) || null;
3602
- }
3603
-
3604
3528
  /**
3605
3529
  * The built-in `fetch' function with a lightweight error handling wrapper as default fetch function used in Promptbook scrapers
3606
3530
  *
@@ -3636,9 +3560,9 @@
3636
3560
  function makeKnowledgeSourceHandler(knowledgeSource, tools, options) {
3637
3561
  var _a;
3638
3562
  return __awaiter(this, void 0, void 0, function () {
3639
- var _b, fetch, knowledgeSourceContent, name, _c, _d, rootDirname, url, response_1, mimeType, basename, hash, rootDirname_1, filepath, fileContent, _f, _g, filename_1, fileExtension, mimeType;
3640
- return __generator(this, function (_h) {
3641
- switch (_h.label) {
3563
+ var _b, fetch, knowledgeSourceContent, name, _c, _d, rootDirname, url, response_1, mimeType, filename_1, fileExtension, mimeType;
3564
+ return __generator(this, function (_f) {
3565
+ switch (_f.label) {
3642
3566
  case 0:
3643
3567
  _b = tools.fetch, fetch = _b === void 0 ? scraperFetch : _b;
3644
3568
  knowledgeSourceContent = knowledgeSource.knowledgeSourceContent;
@@ -3647,76 +3571,54 @@
3647
3571
  if (!name) {
3648
3572
  name = knowledgeSourceContentToName(knowledgeSourceContent);
3649
3573
  }
3650
- if (!isValidUrl(knowledgeSourceContent)) return [3 /*break*/, 5];
3574
+ if (!isValidUrl(knowledgeSourceContent)) return [3 /*break*/, 2];
3651
3575
  url = knowledgeSourceContent;
3652
3576
  return [4 /*yield*/, fetch(url)];
3653
3577
  case 1:
3654
- response_1 = _h.sent();
3578
+ response_1 = _f.sent();
3655
3579
  mimeType = ((_a = response_1.headers.get('content-type')) === null || _a === void 0 ? void 0 : _a.split(';')[0]) || 'text/html';
3656
- if (tools.fs === undefined || !url.endsWith('.pdf' /* <- TODO: [💵] */)) {
3657
- return [2 /*return*/, {
3658
- source: name,
3659
- filename: null,
3660
- url: url,
3661
- mimeType: mimeType,
3662
- /*
3663
- TODO: [🥽]
3664
- > async asBlob() {
3665
- > // TODO: [👨🏻‍🤝‍👨🏻] This can be called multiple times BUT when called second time, response in already consumed
3666
- > const content = await response.blob();
3667
- > return content;
3668
- > },
3669
- */
3670
- asJson: function () {
3671
- return __awaiter(this, void 0, void 0, function () {
3672
- var content;
3673
- return __generator(this, function (_a) {
3674
- switch (_a.label) {
3675
- case 0: return [4 /*yield*/, response_1.json()];
3676
- case 1:
3677
- content = _a.sent();
3678
- return [2 /*return*/, content];
3679
- }
3680
- });
3580
+ return [2 /*return*/, {
3581
+ source: name,
3582
+ filename: null,
3583
+ url: url,
3584
+ mimeType: mimeType,
3585
+ /*
3586
+ TODO: [🥽]
3587
+ > async asBlob() {
3588
+ > // TODO: [👨🏻‍🤝‍👨🏻] This can be called multiple times BUT when called second time, response in already consumed
3589
+ > const content = await response.blob();
3590
+ > return content;
3591
+ > },
3592
+ */
3593
+ asJson: function () {
3594
+ return __awaiter(this, void 0, void 0, function () {
3595
+ var content;
3596
+ return __generator(this, function (_a) {
3597
+ switch (_a.label) {
3598
+ case 0: return [4 /*yield*/, response_1.json()];
3599
+ case 1:
3600
+ content = _a.sent();
3601
+ return [2 /*return*/, content];
3602
+ }
3681
3603
  });
3682
- },
3683
- asText: function () {
3684
- return __awaiter(this, void 0, void 0, function () {
3685
- var content;
3686
- return __generator(this, function (_a) {
3687
- switch (_a.label) {
3688
- case 0: return [4 /*yield*/, response_1.text()];
3689
- case 1:
3690
- content = _a.sent();
3691
- return [2 /*return*/, content];
3692
- }
3693
- });
3604
+ });
3605
+ },
3606
+ asText: function () {
3607
+ return __awaiter(this, void 0, void 0, function () {
3608
+ var content;
3609
+ return __generator(this, function (_a) {
3610
+ switch (_a.label) {
3611
+ case 0: return [4 /*yield*/, response_1.text()];
3612
+ case 1:
3613
+ content = _a.sent();
3614
+ return [2 /*return*/, content];
3615
+ }
3694
3616
  });
3695
- },
3696
- }];
3697
- }
3698
- basename = url.split('/').pop() || titleToName(url);
3699
- hash = sha256__default["default"](hexEncoder__default["default"].parse(url)).toString( /* hex */);
3700
- rootDirname_1 = path.join(process.cwd(), DEFAULT_DOWNLOAD_CACHE_DIRNAME);
3701
- 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));
3702
- return [4 /*yield*/, tools.fs.mkdir(path.dirname(path.join(rootDirname_1, filepath)), { recursive: true })];
3617
+ });
3618
+ },
3619
+ }];
3703
3620
  case 2:
3704
- _h.sent();
3705
- _g = (_f = Buffer).from;
3706
- return [4 /*yield*/, response_1.arrayBuffer()];
3707
- case 3:
3708
- fileContent = _g.apply(_f, [_h.sent()]);
3709
- if (fileContent.length > DEFAULT_MAX_FILE_SIZE /* <- TODO: Allow to pass different value to remote server */) {
3710
- 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."));
3711
- }
3712
- return [4 /*yield*/, tools.fs.writeFile(path.join(rootDirname_1, filepath), fileContent)];
3713
- case 4:
3714
- _h.sent();
3715
- // TODO: [💵] Check the file security
3716
- // TODO: [🧹][🧠] Delete the file after the scraping is done
3717
- return [2 /*return*/, makeKnowledgeSourceHandler({ name: name, knowledgeSourceContent: filepath }, tools, __assign(__assign({}, options), { rootDirname: rootDirname_1 }))];
3718
- case 5:
3719
- if (!isValidFilePath(knowledgeSourceContent)) return [3 /*break*/, 7];
3621
+ if (!isValidFilePath(knowledgeSourceContent)) return [3 /*break*/, 4];
3720
3622
  if (tools.fs === undefined) {
3721
3623
  throw new EnvironmentMismatchError('Can not import file knowledge without filesystem tools');
3722
3624
  // <- TODO: [🧠] What is the best error type here`
@@ -3729,8 +3631,8 @@
3729
3631
  fileExtension = getFileExtension(filename_1);
3730
3632
  mimeType = extensionToMimeType(fileExtension || '');
3731
3633
  return [4 /*yield*/, isFileExisting(filename_1, tools.fs)];
3732
- case 6:
3733
- if (!(_h.sent())) {
3634
+ case 3:
3635
+ if (!(_f.sent())) {
3734
3636
  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 "); }));
3735
3637
  }
3736
3638
  // TODO: [🧠][😿] Test security file - file is scoped to the project (BUT maybe do this in `filesystemTools`)
@@ -3776,7 +3678,7 @@
3776
3678
  });
3777
3679
  },
3778
3680
  }];
3779
- case 7: return [2 /*return*/, {
3681
+ case 4: return [2 /*return*/, {
3780
3682
  source: name,
3781
3683
  filename: null,
3782
3684
  url: null,
@@ -6332,7 +6234,7 @@
6332
6234
  className: 'MarkitdownScraper',
6333
6235
  mimeTypes: [
6334
6236
  'application/pdf',
6335
- // TODO: [💵] Make priority for scrapers and than analyze which mime-types can Markitdown scrape and allow all mime types here:
6237
+ // TODO: Make priority for scrapers and than allow all mime types here:
6336
6238
  // 'text/html',
6337
6239
  // 'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
6338
6240
  ],
@@ -6368,10 +6270,10 @@
6368
6270
  this.tools = tools;
6369
6271
  this.options = options;
6370
6272
  this.markdownScraper = new MarkdownScraper(tools, options);
6371
- // Note: Module `markitdown-ts` has no types available, so it is imported using `require`
6372
6273
  // eslint-disable-next-line @typescript-eslint/no-var-requires
6373
6274
  var MarkItDown = require('markitdown-ts').MarkItDown;
6374
- // <- TODO: [🍀] Use Markitdown directly not through this package
6275
+ // <- TODO: !!! Use Markitdown directly not through this package
6276
+ // <- Note: !!!!!!!
6375
6277
  this.markitdown = new MarkItDown();
6376
6278
  }
6377
6279
  Object.defineProperty(MarkitdownScraper.prototype, "metadata", {
@@ -6416,12 +6318,12 @@
6416
6318
  case 2:
6417
6319
  if (!!(_f.sent())) return [3 /*break*/, 5];
6418
6320
  src = source.filename || source.url || null;
6419
- // console.log('!!', { src, source, cacheFilehandler });
6321
+ console.log('!!!', { src: src, source: source, cacheFilehandler: cacheFilehandler });
6420
6322
  if (src === null) {
6421
6323
  throw new UnexpectedError('Source has no filename or url');
6422
6324
  }
6423
6325
  return [4 /*yield*/, this.markitdown.convert(src, {
6424
- // TODO: Pass when sacraping Youtube
6326
+ // TODO: !!!!!! Pass when sacraping Youtube
6425
6327
  // enableYoutubeTranscript: true,
6426
6328
  // youtubeTranscriptLanguage: 'en',
6427
6329
  })];
@@ -6429,12 +6331,11 @@
6429
6331
  result = _f.sent();
6430
6332
  if (result === null || result === undefined) {
6431
6333
  throw new Error("Markitdown could not convert the \"".concat(source.source, "\""));
6432
- // <- TODO: [🍀] Make MarkitdownError
6334
+ // <- TODO: !!! Make MarkitdownError
6433
6335
  }
6434
- // console.log('!!', { result, cacheFilehandler });
6336
+ console.log('!!!', { result: result, cacheFilehandler: cacheFilehandler });
6435
6337
  return [4 /*yield*/, this.tools.fs.writeFile(cacheFilehandler.filename, result.text_content)];
6436
6338
  case 4:
6437
- // console.log('!!', { result, cacheFilehandler });
6438
6339
  _f.sent();
6439
6340
  _f.label = 5;
6440
6341
  case 5: return [2 /*return*/, cacheFilehandler];