@promptbook/website-crawler 0.71.0-13 → 0.71.0-15

package/esm/index.es.js

@@ -1,6 +1,6 @@
 import spaceTrim$1, { spaceTrim } from 'spacetrim';
 import { Readability } from '@mozilla/readability';
-import { mkdir, rm, stat, access, constants, readFile, writeFile } from 'fs/promises';
+import { mkdir, rm, readFile, writeFile } from 'fs/promises';
 import { JSDOM } from 'jsdom';
 import { forTime } from 'waitasecond';
 import { SHA256 } from 'crypto-js';
@@ -16,7 +16,7 @@ import { Converter } from 'showdown';
 /**
  * The version of the Promptbook library
  */
-var PROMPTBOOK_VERSION = '0.71.0-12';
+var PROMPTBOOK_VERSION = '0.71.0-14';
 // TODO: [main] !!!! List here all the versions and annotate + put into script
 
 /*! *****************************************************************************
@@ -656,6 +656,35 @@ var KnowledgeScrapeError = /** @class */ (function (_super) {
     return KnowledgeScrapeError;
 }(Error));
 
+/**
+ * Tests if given string is valid URL.
+ *
+ * Note: Dataurl are considered perfectly valid.
+ * Note: There are two simmilar functions:
+ * - `isValidUrl` which tests any URL
+ * - `isValidPipelineUrl` *(this one)* which tests just promptbook URL
+ *
+ * @public exported from `@promptbook/utils`
+ */
+function isValidUrl(url) {
+    if (typeof url !== 'string') {
+        return false;
+    }
+    try {
+        if (url.startsWith('blob:')) {
+            url = url.replace(/^blob:/, '');
+        }
+        var urlObject = new URL(url /* because fail is handled */);
+        if (!['http:', 'https:', 'data:'].includes(urlObject.protocol)) {
+            return false;
+        }
+        return true;
+    }
+    catch (error) {
+        return false;
+    }
+}
+
 var defaultDiacriticsRemovalMap = [
     {
         base: 'A',
@@ -976,35 +1005,6 @@ function normalizeToKebabCase(text) {
     return normalizedName;
 }
 
-/**
- * Tests if given string is valid URL.
- *
- * Note: Dataurl are considered perfectly valid.
- * Note: There are two simmilar functions:
- * - `isValidUrl` which tests any URL
- * - `isValidPipelineUrl` *(this one)* which tests just promptbook URL
- *
- * @public exported from `@promptbook/utils`
- */
-function isValidUrl(url) {
-    if (typeof url !== 'string') {
-        return false;
-    }
-    try {
-        if (url.startsWith('blob:')) {
-            url = url.replace(/^blob:/, '');
-        }
-        var urlObject = new URL(url /* because fail is handled */);
-        if (!['http:', 'https:', 'data:'].includes(urlObject.protocol)) {
-            return false;
-        }
-        return true;
-    }
-    catch (error) {
-        return false;
-    }
-}
-
 /**
  * Removes emojis from a string and fix whitespaces
  *
@@ -1167,6 +1167,7 @@ function getScraperIntermediateSource(source, options) {
  * 1) Need to store more than serialized JSONs
  * 2) Need to switch between a `rootDirname` and `cacheDirname` <- TODO: !!!!
  * TODO: [🐱‍🐉][🧠] Make some smart crop
+ * 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.ptbk.md",parameters:[{name:"knowledgeContent",description:"Markdown document content",isInput:true,isOutput:false},{name:"knowledgePieces",description:"The knowledge JSON object",isInput:false,isOutput:true}],templates:[{templateType:"PROMPT_TEMPLATE",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"]}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-knowledge-from-markdown.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-keywords.ptbk.md",parameters:[{name:"knowledgePieceContent",description:"The content",isInput:true,isOutput:false},{name:"keywords",description:"Keywords separated by comma",isInput:false,isOutput:true}],templates:[{templateType:"PROMPT_TEMPLATE",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"]}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-knowledge-keywords.ptbk.md"},{title:"Prepare Title",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-title.ptbk.md",parameters:[{name:"knowledgePieceContent",description:"The content",isInput:true,isOutput:false},{name:"title",description:"The title of the document",isInput:false,isOutput:true}],templates:[{templateType:"PROMPT_TEMPLATE",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"]}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-knowledge-title.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-persona.ptbk.md",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}],templates:[{templateType:"PROMPT_TEMPLATE",name:"make-model-requirements",title:"Make modelRequirements",content:"You are experienced AI engineer, you need to create virtual assistant.\nWrite\n\n## Sample\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"]}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-persona.ptbk.md"}];
@@ -3039,39 +3040,45 @@ function sourceContentToName(sourceContent) {
  */
 
 /**
- * Detects if the code is running in a Node.js environment
+ * Convert file extension to mime type
  *
- * Note: `$` is used to indicate that this function is not a pure function - it looks at the global object to determine the environment
+ * @private within the repository
+ */
+function extensionToMimeType(value) {
+    return lookup(value) || 'application/octet-stream';
+}
+
+/**
+ * Get the file extension from a file name
  *
- * @public exported from `@promptbook/utils`
+ * @private within the repository
  */
-var $isRunningInNode = new Function("\n    try {\n        return this === global;\n    } catch (e) {\n        return false;\n    }\n");
+function getFileExtension(value) {
+    var match = value.match(/\.([0-9a-z]+)(?:[?#]|$)/i);
+    return match ? match[1].toLowerCase() : null;
+}
 
 /**
  * Checks if the file exists
  *
- * Note: `$` is used to indicate that this function is not a pure function - it looks at the filesystem
- *
  * @private within the repository
  */
-function $isFileExisting(filename) {
+function isFileExisting(filename, fs) {
     return __awaiter(this, void 0, void 0, function () {
         var isReadAccessAllowed, isFile;
         return __generator(this, function (_a) {
             switch (_a.label) {
-                case 0:
-                    if (!$isRunningInNode()) {
-                        throw new EnvironmentMismatchError('Function `$isFileExisting` works only in Node environment.js');
-                    }
-                    return [4 /*yield*/, access(filename, constants.R_OK)
-                            .then(function () { return true; })
-                            .catch(function () { return false; })];
+                case 0: return [4 /*yield*/, fs
+                        .access(filename, fs.constants.R_OK)
+                        .then(function () { return true; })
+                        .catch(function () { return false; })];
                 case 1:
                     isReadAccessAllowed = _a.sent();
                     if (!isReadAccessAllowed) {
                         return [2 /*return*/, false];
                     }
-                    return [4 /*yield*/, stat(filename)
+                    return [4 /*yield*/, fs
+                            .stat(filename)
                             .then(function (fileStat) { return fileStat.isFile(); })
                             .catch(function () { return false; })];
                 case 2:
@@ -3082,36 +3089,17 @@ function $isFileExisting(filename) {
     });
 }
 /**
- * Note: [🟢 !!!!!! After fix makeKnowledgeSourceHandler] Code in this file should never be published outside of `@promptbook/node` and `@promptbook/cli`
+ * Note: Not [~🟢~] because it is not directly dependent on `fs
  * TODO: [🐠] This can be a validator - with variants that return true/false and variants that throw errors with meaningless messages
  * TODO: [🖇] What about symlinks?
  */
 
-/**
- * Convert file extension to mime type
- *
- * @private within the repository
- */
-function extensionToMimeType(value) {
-    return lookup(value) || 'application/octet-stream';
-}
-
-/**
- * Get the file extension from a file name
- *
- * @private within the repository
- */
-function getFileExtension(value) {
-    var match = value.match(/\.([0-9a-z]+)(?:[?#]|$)/i);
-    return match ? match[1].toLowerCase() : null;
-}
-
 /**
  * @@@
  *
  * @private for scraper utilities
  */
-function makeKnowledgeSourceHandler(knowledgeSource, options) {
+function makeKnowledgeSourceHandler(knowledgeSource, tools, options) {
     var _a;
     return __awaiter(this, void 0, void 0, function () {
         var sourceContent, name, _b, _c, rootDirname, _d, 
@@ -3180,8 +3168,9 @@ function makeKnowledgeSourceHandler(knowledgeSource, options) {
                         }];
                 case 2:
                     if (!(isValidFilePath(sourceContent) || /\.[a-z]{1,10}$/i.exec(sourceContent))) return [3 /*break*/, 4];
-                    if (!$isRunningInNode()) {
-                        throw new EnvironmentMismatchError('Importing knowledge source file works only in Node.js environment');
+                    if (tools.fs === undefined) {
+                        throw new EnvironmentMismatchError('Can not import file knowledge without filesystem tools');
+                        //          <- TODO: [🧠] What is the best error type here`
                     }
                     if (rootDirname === null) {
                         throw new EnvironmentMismatchError('Can not import file knowledge in non-file pipeline');
@@ -3190,7 +3179,7 @@ function makeKnowledgeSourceHandler(knowledgeSource, options) {
                     filename_1 = join(rootDirname, sourceContent).split('\\').join('/');
                     fileExtension = getFileExtension(filename_1);
                     mimeType_1 = extensionToMimeType(fileExtension || '');
-                    return [4 /*yield*/, $isFileExisting(filename_1)];
+                    return [4 /*yield*/, isFileExisting(filename_1, tools.fs)];
                 case 3:
                     if (!(_e.sent())) {
                         throw new NotFoundError(spaceTrim$1(function (block) { return "\n                          Can not make source handler for file which does not exist:\n\n                          File:\n                          ".concat(block(filename_1), "\n                      "); }));
@@ -3206,7 +3195,7 @@ function makeKnowledgeSourceHandler(knowledgeSource, options) {
                                     var content;
                                     return __generator(this, function (_a) {
                                         switch (_a.label) {
-                                            case 0: return [4 /*yield*/, readFile(filename_1)];
+                                            case 0: return [4 /*yield*/, tools.fs.readFile(filename_1)];
                                             case 1:
                                                 content = _a.sent();
                                                 return [2 /*return*/, new Blob([
@@ -3260,9 +3249,6 @@ function makeKnowledgeSourceHandler(knowledgeSource, options) {
         });
     });
 }
-/**
- * TODO: !!!!!!! Maybe constrain to @promptbook/node bundle
- */
 
 /**
  * Prepares the knowle
@@ -3286,7 +3272,7 @@ function prepareKnowledgePieces(knowledgeSources, tools, options) {
                                 switch (_d.label) {
                                     case 0:
                                         partialPieces = null;
-                                        return [4 /*yield*/, makeKnowledgeSourceHandler(knowledgeSource, { rootDirname: rootDirname, isVerbose: isVerbose })];
+                                        return [4 /*yield*/, makeKnowledgeSourceHandler(knowledgeSource, tools, { rootDirname: rootDirname, isVerbose: isVerbose })];
                                     case 1:
                                         sourceHandler = _d.sent();
                                         _d.label = 2;