@promptbook/website-crawler 0.89.0-1 → 0.89.0-11

package/README.md

@@ -200,7 +200,7 @@ Each part of the book defines one of 3 circles:
 
 ### **What:** Workflows, Tasks and Parameters
 
-What work needs to be done. Each book defines a workflow, which is one or more tasks. Each workflow has a fixed input and output. For example, you have a book that generates an article from a topic. Once it generates an article about AI, once about marketing, once about cooking. The workflow (= your AI program) is the same, only the input and output change.
+What work needs to be done. Each book defines a [workflow *(scenario or pipeline)*](https://github.com/webgptorg/promptbook/discussions/88), which is one or more tasks. Each workflow has a fixed input and output. For example, you have a book that generates an article from a topic. Once it generates an article about AI, once about marketing, once about cooking. The workflow (= your AI program) is the same, only the input and output change.
 
 **Related commands:**
 
@@ -310,6 +310,8 @@ The following glossary is used to clarify certain concepts:
 
 
 
+
+
 _Note: This section is not complete dictionary, more list of general AI / LLM terms that has connection with Promptbook_
 
 

package/esm/index.es.js

@@ -29,7 +29,7 @@ const BOOK_LANGUAGE_VERSION = '1.0.0';
  * @generated
  * @see https://github.com/webgptorg/promptbook
  */
-const PROMPTBOOK_ENGINE_VERSION = '0.89.0-1';
+const PROMPTBOOK_ENGINE_VERSION = '0.89.0-11';
 /**
  * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
  * Note: [💞] Ignore a discrepancy between file name and entity name
@@ -190,6 +190,7 @@ const DEFAULT_MAX_PARALLEL_COUNT = 5; // <- TODO: [🤹‍♂️]
  */
 const DEFAULT_MAX_EXECUTION_ATTEMPTS = 10; // <- TODO: [🤹‍♂️]
 // <- TODO: [🕝] Make also `BOOKS_DIRNAME_ALTERNATIVES`
+// TODO: !!!!!! Just .promptbook dir, hardocode others
 /**
  * Where to store the temporary downloads
  *
@@ -241,7 +242,7 @@ const IS_PIPELINE_LOGIC_VALIDATED = just(
 true);
 /**
  * Note: [💞] Ignore a discrepancy between file name and entity name
- * TODO: [🧠][🧜‍♂️] Maybe join remoteUrl and path into single value
+ * TODO: [🧠][🧜‍♂️] Maybe join remoteServerUrl and path into single value
  */
 
 /**
@@ -2285,6 +2286,19 @@ class CsvFormatError extends AbstractFormatError {
     }
 }
 
+/**
+ * AuthenticationError is thrown from login function which is dependency of remote server
+ *
+ * @public exported from `@promptbook/core`
+ */
+class AuthenticationError extends Error {
+    constructor(message) {
+        super(message);
+        this.name = 'AuthenticationError';
+        Object.setPrototypeOf(this, AuthenticationError.prototype);
+    }
+}
+
 /**
  * This error indicates that the pipeline collection cannot be propperly loaded
  *
@@ -2327,6 +2341,19 @@ class LimitReachedError extends Error {
     }
 }
 
+/**
+ * Error thrown when a fetch request fails
+ *
+ * @public exported from `@promptbook/core`
+ */
+class PromptbookFetchError extends Error {
+    constructor(message) {
+        super(message);
+        this.name = 'PromptbookFetchError';
+        Object.setPrototypeOf(this, PromptbookFetchError.prototype);
+    }
+}
+
 /**
  * Index of all custom errors
  *
@@ -2364,6 +2391,8 @@ const COMMON_JAVASCRIPT_ERRORS = {
     TypeError,
     URIError,
     AggregateError,
+    AuthenticationError,
+    PromptbookFetchError,
     /*
   Note: Not widely supported
   > InternalError,
@@ -2425,6 +2454,7 @@ function assertsTaskSuccessful(executionResult) {
     const { isSuccessful, errors, warnings } = executionResult;
     for (const warning of warnings) {
         console.warn(warning.message);
+        // <- TODO: [🏮] Some standard way how to transform errors into warnings and how to handle non-critical fails during the tasks
     }
     if (isSuccessful === true) {
         return;
@@ -2562,6 +2592,10 @@ function serializeError(error) {
 
                     Cannot serialize error with name "${name}"
 
+                    Authors of Promptbook probably forgot to add this error into the list of errors:
+                    https://github.com/webgptorg/promptbook/blob/main/src/errors/0-index.ts
+
+
                     ${block(stack || message)}
 
                 `));
@@ -2603,30 +2637,42 @@ async function forEachAsync(array, options, callbackfunction) {
     await Promise.all(tasks);
 }
 
+/**
+ * Represents the uncertain value
+ *
+ * @public exported from `@promptbook/core`
+ */
+const ZERO_VALUE = $deepFreeze({ value: 0 });
+/**
+ * Represents the uncertain value
+ *
+ * @public exported from `@promptbook/core`
+ */
+const UNCERTAIN_ZERO_VALUE = $deepFreeze({ value: 0, isUncertain: true });
 /**
  * Represents the usage with no resources consumed
  *
  * @public exported from `@promptbook/core`
  */
 const ZERO_USAGE = $deepFreeze({
-    price: { value: 0 },
+    price: ZERO_VALUE,
     input: {
-        tokensCount: { value: 0 },
-        charactersCount: { value: 0 },
-        wordsCount: { value: 0 },
-        sentencesCount: { value: 0 },
-        linesCount: { value: 0 },
-        paragraphsCount: { value: 0 },
-        pagesCount: { value: 0 },
+        tokensCount: ZERO_VALUE,
+        charactersCount: ZERO_VALUE,
+        wordsCount: ZERO_VALUE,
+        sentencesCount: ZERO_VALUE,
+        linesCount: ZERO_VALUE,
+        paragraphsCount: ZERO_VALUE,
+        pagesCount: ZERO_VALUE,
     },
     output: {
-        tokensCount: { value: 0 },
-        charactersCount: { value: 0 },
-        wordsCount: { value: 0 },
-        sentencesCount: { value: 0 },
-        linesCount: { value: 0 },
-        paragraphsCount: { value: 0 },
-        pagesCount: { value: 0 },
+        tokensCount: ZERO_VALUE,
+        charactersCount: ZERO_VALUE,
+        wordsCount: ZERO_VALUE,
+        sentencesCount: ZERO_VALUE,
+        linesCount: ZERO_VALUE,
+        paragraphsCount: ZERO_VALUE,
+        pagesCount: ZERO_VALUE,
     },
 });
 /**
@@ -2635,24 +2681,24 @@ const ZERO_USAGE = $deepFreeze({
  * @public exported from `@promptbook/core`
  */
 $deepFreeze({
-    price: { value: 0, isUncertain: true },
+    price: UNCERTAIN_ZERO_VALUE,
     input: {
-        tokensCount: { value: 0, isUncertain: true },
-        charactersCount: { value: 0, isUncertain: true },
-        wordsCount: { value: 0, isUncertain: true },
-        sentencesCount: { value: 0, isUncertain: true },
-        linesCount: { value: 0, isUncertain: true },
-        paragraphsCount: { value: 0, isUncertain: true },
-        pagesCount: { value: 0, isUncertain: true },
+        tokensCount: UNCERTAIN_ZERO_VALUE,
+        charactersCount: UNCERTAIN_ZERO_VALUE,
+        wordsCount: UNCERTAIN_ZERO_VALUE,
+        sentencesCount: UNCERTAIN_ZERO_VALUE,
+        linesCount: UNCERTAIN_ZERO_VALUE,
+        paragraphsCount: UNCERTAIN_ZERO_VALUE,
+        pagesCount: UNCERTAIN_ZERO_VALUE,
     },
     output: {
-        tokensCount: { value: 0, isUncertain: true },
-        charactersCount: { value: 0, isUncertain: true },
-        wordsCount: { value: 0, isUncertain: true },
-        sentencesCount: { value: 0, isUncertain: true },
-        linesCount: { value: 0, isUncertain: true },
-        paragraphsCount: { value: 0, isUncertain: true },
-        pagesCount: { value: 0, isUncertain: true },
+        tokensCount: UNCERTAIN_ZERO_VALUE,
+        charactersCount: UNCERTAIN_ZERO_VALUE,
+        wordsCount: UNCERTAIN_ZERO_VALUE,
+        sentencesCount: UNCERTAIN_ZERO_VALUE,
+        linesCount: UNCERTAIN_ZERO_VALUE,
+        paragraphsCount: UNCERTAIN_ZERO_VALUE,
+        pagesCount: UNCERTAIN_ZERO_VALUE,
     },
 });
 /**
@@ -2940,6 +2986,7 @@ function joinLlmExecutionTools(...llmExecutionTools) {
         `);
         // TODO: [🟥] Detect browser / node and make it colorfull
         console.warn(warningMessage);
+        // <- TODO: [🏮] Some standard way how to transform errors into warnings and how to handle non-critical fails during the tasks
         /*
         return {
             async listModels() {
@@ -3211,17 +3258,24 @@ function mimeTypeToExtension(value) {
 /**
  * The built-in `fetch' function with a lightweight error handling wrapper as default fetch function used in Promptbook scrapers
  *
- * @private as default `fetch` function used in Promptbook scrapers
+ * @public exported from `@promptbook/core`
  */
-const scraperFetch = async (url, init) => {
+const promptbookFetch = async (urlOrRequest, init) => {
     try {
-        return await fetch(url, init);
+        return await fetch(urlOrRequest, init);
     }
     catch (error) {
         if (!(error instanceof Error)) {
             throw error;
         }
-        throw new KnowledgeScrapeError(spaceTrim$1((block) => `
+        let url;
+        if (typeof urlOrRequest === 'string') {
+            url = urlOrRequest;
+        }
+        else if (urlOrRequest instanceof Request) {
+            url = urlOrRequest.url;
+        }
+        throw new PromptbookFetchError(spaceTrim$1((block) => `
                     Can not fetch "${url}"
 
                     Fetch error:
@@ -3242,7 +3296,7 @@ const scraperFetch = async (url, init) => {
 async function makeKnowledgeSourceHandler(knowledgeSource, tools, options) {
     // console.log('!! makeKnowledgeSourceHandler', knowledgeSource);
     var _a;
-    const { fetch = scraperFetch } = tools;
+    const { fetch = promptbookFetch } = tools;
     const { knowledgeSourceContent } = knowledgeSource;
     let { name } = knowledgeSource;
     const { rootDirname = null, 
@@ -3383,63 +3437,73 @@ async function prepareKnowledgePieces(knowledgeSources, tools, options) {
     const { maxParallelCount = DEFAULT_MAX_PARALLEL_COUNT, rootDirname, isVerbose = DEFAULT_IS_VERBOSE } = options;
     const knowledgePreparedUnflatten = new Array(knowledgeSources.length);
     await forEachAsync(knowledgeSources, { maxParallelCount }, async (knowledgeSource, index) => {
-        let partialPieces = null;
-        const sourceHandler = await makeKnowledgeSourceHandler(knowledgeSource, tools, { rootDirname, isVerbose });
-        const scrapers = arrayableToArray(tools.scrapers);
-        for (const scraper of scrapers) {
-            if (!scraper.metadata.mimeTypes.includes(sourceHandler.mimeType)
-            // <- TODO: [🦔] Implement mime-type wildcards
-            ) {
-                continue;
-            }
-            const partialPiecesUnchecked = await scraper.scrape(sourceHandler);
-            if (partialPiecesUnchecked !== null) {
-                partialPieces = [...partialPiecesUnchecked];
-                // <- TODO: [🪓] Here should be no need for spreading new array, just `partialPieces = partialPiecesUnchecked`
-                break;
-            }
-            console.warn(spaceTrim$1((block) => `
-                        Cannot scrape knowledge from source despite the scraper \`${scraper.metadata.className}\` supports the mime type "${sourceHandler.mimeType}".
+        try {
+            let partialPieces = null;
+            const sourceHandler = await makeKnowledgeSourceHandler(knowledgeSource, tools, { rootDirname, isVerbose });
+            const scrapers = arrayableToArray(tools.scrapers);
+            for (const scraper of scrapers) {
+                if (!scraper.metadata.mimeTypes.includes(sourceHandler.mimeType)
+                // <- TODO: [🦔] Implement mime-type wildcards
+                ) {
+                    continue;
+                }
+                const partialPiecesUnchecked = await scraper.scrape(sourceHandler);
+                if (partialPiecesUnchecked !== null) {
+                    partialPieces = [...partialPiecesUnchecked];
+                    // <- TODO: [🪓] Here should be no need for spreading new array, just `partialPieces = partialPiecesUnchecked`
+                    break;
+                }
+                console.warn(spaceTrim$1((block) => `
+                            Cannot scrape knowledge from source despite the scraper \`${scraper.metadata.className}\` supports the mime type "${sourceHandler.mimeType}".
 
-                        The source:
-                        ${block(knowledgeSource.knowledgeSourceContent
-                .split('\n')
-                .map((line) => `> ${line}`)
-                .join('\n'))}
+                            The source:
+                            ${block(knowledgeSource.knowledgeSourceContent
+                    .split('\n')
+                    .map((line) => `> ${line}`)
+                    .join('\n'))}
 
-                        ${block($registeredScrapersMessage(scrapers))}
+                            ${block($registeredScrapersMessage(scrapers))}
 
 
-                    `));
-        }
-        if (partialPieces === null) {
-            throw new KnowledgeScrapeError(spaceTrim$1((block) => `
-                        Cannot scrape knowledge
+                        `));
+                // <- TODO: [🏮] Some standard way how to transform errors into warnings and how to handle non-critical fails during the tasks
+            }
+            if (partialPieces === null) {
+                throw new KnowledgeScrapeError(spaceTrim$1((block) => `
+                            Cannot scrape knowledge
 
-                        The source:
-                        > ${block(knowledgeSource.knowledgeSourceContent
-                .split('\n')
-                .map((line) => `> ${line}`)
-                .join('\n'))}
+                            The source:
+                            > ${block(knowledgeSource.knowledgeSourceContent
+                    .split('\n')
+                    .map((line) => `> ${line}`)
+                    .join('\n'))}
 
-                        No scraper found for the mime type "${sourceHandler.mimeType}"
+                            No scraper found for the mime type "${sourceHandler.mimeType}"
 
-                        ${block($registeredScrapersMessage(scrapers))}
+                            ${block($registeredScrapersMessage(scrapers))}
 
 
-                    `));
+                        `));
+            }
+            const pieces = partialPieces.map((partialPiece) => ({
+                ...partialPiece,
+                sources: [
+                    {
+                        name: knowledgeSource.name,
+                        // line, column <- TODO: [☀]
+                        // <- TODO: [❎]
+                    },
+                ],
+            }));
+            knowledgePreparedUnflatten[index] = pieces;
+        }
+        catch (error) {
+            if (!(error instanceof Error)) {
+                throw error;
+            }
+            console.warn(error);
+            // <- TODO: [🏮] Some standard way how to transform errors into warnings and how to handle non-critical fails during the tasks
         }
-        const pieces = partialPieces.map((partialPiece) => ({
-            ...partialPiece,
-            sources: [
-                {
-                    name: knowledgeSource.name,
-                    // line, column <- TODO: [☀]
-                    // <- TODO: [❎]
-                },
-            ],
-        }));
-        knowledgePreparedUnflatten[index] = pieces;
     });
     const knowledgePrepared = knowledgePreparedUnflatten.flat();
     return knowledgePrepared;
@@ -3857,7 +3921,7 @@ function extractParameterNamesFromTask(task) {
             if (parameterNames.has(subparameterName)) {
                 parameterNames.delete(subparameterName);
                 parameterNames.add(foreach.parameterName);
-                // <- TODO: [🚎] Warn/logic error when `subparameterName` not used
+                // <- TODO: [🏮] Warn/logic error when `subparameterName` not used
             }
         }
     }
@@ -5453,6 +5517,7 @@ function createPipelineExecutor(options) {
 
                     @see more at https://ptbk.io/prepare-pipeline
                 `));
+        // <- TODO: [🏮] Some standard way how to transform errors into warnings and how to handle non-critical fails during the tasks
     }
     let runCount = 0;
     const pipelineExecutorWithCallback = async (inputParameters, onProgress) => {