@promptbook/website-crawler 0.84.0-10 → 0.84.0-12

package/esm/index.es.js

@@ -8,6 +8,7 @@ import { basename, join, dirname } from 'path';
 import { format } from 'prettier';
 import parserHtml from 'prettier/parser-html';
 import { forTime } from 'waitasecond';
+import sha256 from 'crypto-js/sha256';
 import { lookup } from 'mime-types';
 import { unparse, parse } from 'papaparse';
 import { Converter } from 'showdown';
@@ -26,7 +27,7 @@ var BOOK_LANGUAGE_VERSION = '1.0.0';
  * @generated
  * @see https://github.com/webgptorg/promptbook
  */
-var PROMPTBOOK_ENGINE_VERSION = '0.84.0-9';
+var PROMPTBOOK_ENGINE_VERSION = '0.84.0-11';
 /**
  * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
  * Note: [💞] Ignore a discrepancy between file name and entity name
@@ -268,6 +269,12 @@ var SMALL_NUMBER = 0.001;
  * @private within the repository - too low-level in comparison with other `MAX_...`
  */
 var IMMEDIATE_TIME = 10;
+/**
+ * The maximum length of the (generated) filename
+ *
+ * @public exported from `@promptbook/core`
+ */
+var MAX_FILENAME_LENGTH = 30;
 /**
  * Strategy for caching the intermediate results for knowledge sources
  *
@@ -287,6 +294,15 @@ var DEFAULT_MAX_PARALLEL_COUNT = 5; // <- TODO: [🤹‍♂️]
  * @public exported from `@promptbook/core`
  */
 var DEFAULT_MAX_EXECUTION_ATTEMPTS = 3; // <- TODO: [🤹‍♂️]
+// <- TODO: [🕝] Make also `BOOKS_DIRNAME_ALTERNATIVES`
+/**
+ * Where to store the temporary downloads
+ *
+ * Note: When the folder does not exist, it is created recursively
+ *
+ * @public exported from `@promptbook/core`
+ */
+var DEFAULT_DOWNLOAD_CACHE_DIRNAME = './.promptbook/download-cache';
 /**
  * Where to store the scrape cache
  *
@@ -1119,24 +1135,18 @@ function getScraperIntermediateSource(source, options) {
 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"}];
 
 /**
- * Function isValidJsonString will tell you if the string is valid JSON or not
+ * Checks if value is valid email
  *
  * @public exported from `@promptbook/utils`
  */
-function isValidJsonString(value /* <- [👨‍⚖️] */) {
-    try {
-        JSON.parse(value);
-        return true;
+function isValidEmail(email) {
+    if (typeof email !== 'string') {
+        return false;
     }
-    catch (error) {
-        if (!(error instanceof Error)) {
-            throw error;
-        }
-        if (error.message.includes('Unexpected token')) {
-            return false;
-        }
+    if (email.split('\n').length > 1) {
         return false;
     }
+    return /^.+@.+\..+$/.test(email);
 }
 
 /**
@@ -1158,6 +1168,27 @@ var ParseError = /** @class */ (function (_super) {
  * TODO: Maybe split `ParseError` and `ApplyError`
  */
 
+/**
+ * Function isValidJsonString will tell you if the string is valid JSON or not
+ *
+ * @public exported from `@promptbook/utils`
+ */
+function isValidJsonString(value /* <- [👨‍⚖️] */) {
+    try {
+        JSON.parse(value);
+        return true;
+    }
+    catch (error) {
+        if (!(error instanceof Error)) {
+            throw error;
+        }
+        if (error.message.includes('Unexpected token')) {
+            return false;
+        }
+        return false;
+    }
+}
+
 /**
  * Function `validatePipelineString` will validate the if the string is a valid pipeline string
  * 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.
@@ -1171,6 +1202,15 @@ function validatePipelineString(pipelineString) {
     if (isValidJsonString(pipelineString)) {
         throw new ParseError('Expected a book, but got a JSON string');
     }
+    else if (isValidUrl(pipelineString)) {
+        throw new ParseError("Expected a book, but got just the URL \"".concat(pipelineString, "\""));
+    }
+    else if (isValidFilePath(pipelineString)) {
+        throw new ParseError("Expected a book, but got just the file path \"".concat(pipelineString, "\""));
+    }
+    else if (isValidEmail(pipelineString)) {
+        throw new ParseError("Expected a book, but got just the email \"".concat(pipelineString, "\""));
+    }
     // <- TODO: Implement the validation + add tests when the pipeline logic considered as invalid
     return pipelineString;
 }
@@ -2498,12 +2538,28 @@ function deserializeError(error) {
 /**
  * Asserts that the execution of a Promptbook is successful
  *
+ * Note: If there are only warnings, the execution is still successful but the warnings are logged in the console
+ *
  * @param executionResult - The partial result of the Promptbook execution
  * @throws {PipelineExecutionError} If the execution is not successful or if multiple errors occurred
  * @public exported from `@promptbook/core`
  */
 function assertsExecutionSuccessful(executionResult) {
-    var isSuccessful = executionResult.isSuccessful, errors = executionResult.errors;
+    var e_1, _a;
+    var isSuccessful = executionResult.isSuccessful, errors = executionResult.errors, warnings = executionResult.warnings;
+    try {
+        for (var warnings_1 = __values(warnings), warnings_1_1 = warnings_1.next(); !warnings_1_1.done; warnings_1_1 = warnings_1.next()) {
+            var warning = warnings_1_1.value;
+            console.warn(warning.message);
+        }
+    }
+    catch (e_1_1) { e_1 = { error: e_1_1 }; }
+    finally {
+        try {
+            if (warnings_1_1 && !warnings_1_1.done && (_a = warnings_1.return)) _a.call(warnings_1);
+        }
+        finally { if (e_1) throw e_1.error; }
+    }
     if (isSuccessful === true) {
         return;
     }
@@ -3569,10 +3625,11 @@ var scraperFetch = function (url, init) { return __awaiter(void 0, void 0, void
 function makeKnowledgeSourceHandler(knowledgeSource, tools, options) {
     var _a;
     return __awaiter(this, void 0, void 0, function () {
-        var _b, fetch, knowledgeSourceContent, name, _c, _d, rootDirname, url, response_1, mimeType, filename_1, fileExtension, mimeType;
-        return __generator(this, function (_f) {
-            switch (_f.label) {
+        var _b, fetch, knowledgeSourceContent, name, _c, _d, rootDirname, url, response, mimeType, filename, hash, rootDirname_1, filepath, _f, _g, _h, _j, _k, filename_1, fileExtension, mimeType;
+        return __generator(this, function (_l) {
+            switch (_l.label) {
                 case 0:
+                    console.log('!!! makeKnowledgeSourceHandler', knowledgeSource);
                     _b = tools.fetch, fetch = _b === void 0 ? scraperFetch : _b;
                     knowledgeSourceContent = knowledgeSource.knowledgeSourceContent;
                     name = knowledgeSource.name;
@@ -3580,54 +3637,32 @@ function makeKnowledgeSourceHandler(knowledgeSource, tools, options) {
                     if (!name) {
                         name = knowledgeSourceContentToName(knowledgeSourceContent);
                     }
-                    if (!isValidUrl(knowledgeSourceContent)) return [3 /*break*/, 2];
+                    if (!isValidUrl(knowledgeSourceContent)) return [3 /*break*/, 5];
                     url = knowledgeSourceContent;
                     return [4 /*yield*/, fetch(url)];
                 case 1:
-                    response_1 = _f.sent();
-                    mimeType = ((_a = response_1.headers.get('content-type')) === null || _a === void 0 ? void 0 : _a.split(';')[0]) || 'text/html';
-                    return [2 /*return*/, {
-                            source: name,
-                            filename: null,
-                            url: url,
-                            mimeType: mimeType,
-                            /*
-                            TODO: [🥽]
-                                > async asBlob() {
-                                >     // TODO: [👨🏻‍🤝‍👨🏻] This can be called multiple times BUT when called second time, response in already consumed
-                                >     const content = await response.blob();
-                                >     return content;
-                                > },
-                            */
-                            asJson: function () {
-                                return __awaiter(this, void 0, void 0, function () {
-                                    var content;
-                                    return __generator(this, function (_a) {
-                                        switch (_a.label) {
-                                            case 0: return [4 /*yield*/, response_1.json()];
-                                            case 1:
-                                                content = _a.sent();
-                                                return [2 /*return*/, content];
-                                        }
-                                    });
-                                });
-                            },
-                            asText: function () {
-                                return __awaiter(this, void 0, void 0, function () {
-                                    var content;
-                                    return __generator(this, function (_a) {
-                                        switch (_a.label) {
-                                            case 0: return [4 /*yield*/, response_1.text()];
-                                            case 1:
-                                                content = _a.sent();
-                                                return [2 /*return*/, content];
-                                        }
-                                    });
-                                });
-                            },
-                        }];
+                    response = _l.sent();
+                    mimeType = ((_a = response.headers.get('content-type')) === null || _a === void 0 ? void 0 : _a.split(';')[0]) || 'text/html';
+                    filename = url.split('/').pop() || titleToName(url);
+                    hash = sha256(hexEncoder.parse(url)).toString( /* hex */);
+                    rootDirname_1 = join(process.cwd(), DEFAULT_DOWNLOAD_CACHE_DIRNAME);
+                    filepath = join.apply(void 0, __spreadArray(__spreadArray([], __read(nameToSubfolderPath(hash /* <- TODO: [🎎] Maybe add some SHA256 prefix */)), false), ["".concat(filename.substring(0, MAX_FILENAME_LENGTH), ".pdf")], false));
+                    return [4 /*yield*/, tools.fs.mkdir(dirname(join(rootDirname_1, filepath)), { recursive: true })];
                 case 2:
-                    if (!isValidFilePath(knowledgeSourceContent)) return [3 /*break*/, 4];
+                    _l.sent();
+                    _g = (_f = tools.fs).writeFile;
+                    _h = [join(rootDirname_1, filepath)];
+                    _k = (_j = Buffer).from;
+                    return [4 /*yield*/, response.arrayBuffer()];
+                case 3: return [4 /*yield*/, _g.apply(_f, _h.concat([_k.apply(_j, [_l.sent()])]))];
+                case 4:
+                    _l.sent();
+                    // TODO: !!!!!!!! Check the file security
+                    // TODO: !!!!!!!! Check the file size (if it is not too big)
+                    // TODO: !!!!!!!! Delete the file
+                    return [2 /*return*/, makeKnowledgeSourceHandler({ name: name, knowledgeSourceContent: filepath }, tools, __assign(__assign({}, options), { rootDirname: rootDirname_1 }))];
+                case 5:
+                    if (!isValidFilePath(knowledgeSourceContent)) return [3 /*break*/, 7];
                     if (tools.fs === undefined) {
                         throw new EnvironmentMismatchError('Can not import file knowledge without filesystem tools');
                         //          <- TODO: [🧠] What is the best error type here`
@@ -3640,8 +3675,8 @@ function makeKnowledgeSourceHandler(knowledgeSource, tools, options) {
                     fileExtension = getFileExtension(filename_1);
                     mimeType = extensionToMimeType(fileExtension || '');
                     return [4 /*yield*/, isFileExisting(filename_1, tools.fs)];
-                case 3:
-                    if (!(_f.sent())) {
+                case 6:
+                    if (!(_l.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(knowledgeSourceContent), "\n\n                          Full file path:\n                          ").concat(block(filename_1), "\n                      "); }));
                     }
                     // TODO: [🧠][😿] Test security file - file is scoped to the project (BUT maybe do this in `filesystemTools`)
@@ -3687,7 +3722,7 @@ function makeKnowledgeSourceHandler(knowledgeSource, tools, options) {
                                 });
                             },
                         }];
-                case 4: return [2 /*return*/, {
+                case 7: return [2 /*return*/, {
                         source: name,
                         filename: null,
                         url: null,