@promptbook/node 0.86.0-8 → 0.86.6

package/README.md

@@ -5,8 +5,8 @@
 
 
 
-[![NPM Version of ![Promptbook logo - cube with letters P and B](./other/design/logo-h1.png) Promptbook](https://badge.fury.io/js/promptbook.svg)](https://www.npmjs.com/package/promptbook)
-[![Quality of package ![Promptbook logo - cube with letters P and B](./other/design/logo-h1.png) Promptbook](https://packagequality.com/shield/promptbook.svg)](https://packagequality.com/#?package=promptbook)
+[![NPM Version of ![Promptbook logo - cube with letters P and B](./design/logo-h1.png) Promptbook](https://badge.fury.io/js/promptbook.svg)](https://www.npmjs.com/package/promptbook)
+[![Quality of package ![Promptbook logo - cube with letters P and B](./design/logo-h1.png) Promptbook](https://packagequality.com/shield/promptbook.svg)](https://packagequality.com/#?package=promptbook)
 [![Known Vulnerabilities](https://snyk.io/test/github/webgptorg/promptbook/badge.svg)](https://snyk.io/test/github/webgptorg/promptbook)
 [![Issues](https://img.shields.io/github/issues/webgptorg/promptbook.svg?style=flat)](https://github.com/webgptorg/promptbook/issues)
 
@@ -17,18 +17,12 @@
 ## 🌟 New Features
 
 -   📂 We have plugin for [VSCode](https://github.com/webgptorg/book-extension) to support `.book` file extension
+-   🐳 Available [Docker image](https://hub.docker.com/r/hejny/promptbook/)
 -   💫 Support of [`o3-mini` model by OpenAI](https://openai.com/index/openai-o3-mini/)
 -   🐋 **Support of [DeepSeek models](https://www.npmjs.com/package/@promptbook/deepseek)**
--   💙 Working [the **Book** language v1.0.0](https://github.com/webgptorg/book)
--   🖤 Run books from CLI - `npx ptbk run path/to/your/book`
--   📚 Support of `.docx`, `.doc` and `.pdf` documents as knowledge
 
 
 
-<blockquote style="color: #ff8811">
-    <b>⚠ Warning:</b> This is a pre-release version of the library. It is not yet ready for production use. Please look at <a href="https://www.npmjs.com/package/@promptbook/core?activeTab=versions">latest stable release</a>.
-</blockquote>
-
 ## 📦 Package `@promptbook/node`
 
 - Promptbooks are [divided into several](#-packages) packages, all are published from [single monorepo](https://github.com/webgptorg/promptbook).
@@ -64,6 +58,8 @@ Rest of the documentation is common for **entire promptbook ecosystem**:
 
 During the computer revolution, we have seen [multiple generations of computer languages](https://github.com/webgptorg/promptbook/discussions/180), from the physical rewiring of the vacuum tubes through low-level machine code to the high-level languages like Python or JavaScript. And now, we're on the edge of the **next revolution**!
 
+
+
 It's a revolution of writing software in **plain human language** that is understandable and executable by both humans and machines – and it's going to change everything!
 
 The incredible growth in power of microprocessors and the Moore's Law have been the driving force behind the ever-more powerful languages, and it's been an amazing journey! Similarly, the large language models (like GPT or Claude) are the next big thing in language technology, and they're set to transform the way we interact with computers.
@@ -100,17 +96,22 @@ Promptbook project is ecosystem of multiple projects and tools, following is a l
     <tr>
       <td><a href="https://github.com/webgptorg/book">Book language</a></td>
       <td>
-          Book is a markdown-like language to define core entities like personas, knowledge, tasks,.... It is designed to be understandable by non-programmers and non-technical people<hr>
+          Book is a human-understandable markup language for writing AI applications such as chatbots, knowledge bases, agents, avarars, translators, automations and more.
+          <hr>
           There is also <a href="https://github.com/webgptorg/book-extension">a plugin for VSCode</a> to support <code>.book</code> file extension
       </td>
     </tr>
     <tr>
       <td><a href="https://github.com/webgptorg/promptbook">Promptbook Engine</a></td>
-      <td>Promptbook implementation in TypeScript released as <a href="https://www.npmjs.com/package/@promptbook/core#-packages-for-developers">multiple NPM packages</a> and <a href="https://hub.docker.com/r/hejny/promptbook">Docker HUB</a></td>
+      <td>
+          Promptbook engine can run applications written in Book language. It is released as <a href="https://www.npmjs.com/package/@promptbook/core#-packages-for-developers">multiple NPM packages</a> and <a href="https://hub.docker.com/r/hejny/promptbook">Docker HUB</a>
+      </td>
     </tr>
     <tr>
       <td><a href="https://promptbook.studio">Promptbook Studio</a></td>
-      <td>Studio to write Books and instantly publish them as miniapps</td>
+      <td>
+          Promptbook.studio is a web-based editor and runner for book applications. It is still in the experimental MVP stage.
+      </td>
     </tr>
   </tbody>
 </table>
@@ -121,16 +122,21 @@ We also have a community of developers and users of **Promptbook**:
 -   [Landing page `ptbk.io`](https://ptbk.io)
 -   [Github discussions](https://github.com/webgptorg/promptbook/discussions)
 -   [LinkedIn `Promptbook`](https://linkedin.com/company/promptbook)
--   [Facebook `Promptbook`](https://www.facebook.com/61560776453536)
+-   [Facebook `Promptbook`](https://www.facebook.com/61560776453536) 
 
 And **Promptbook.studio** branded socials:
 
+
+
 -   [Instagram `@promptbook.studio`](https://www.instagram.com/promptbook.studio/)
 
 And **Promptujeme** sub-brand:
 
 _/Subbrand for Czech clients/_
 
+
+
+
 -   [Promptujeme.cz](https://www.promptujeme.cz/)
 -   [Facebook `Promptujeme`](https://www.facebook.com/promptujeme/)
 
@@ -139,16 +145,18 @@ And **Promptbook.city** branded socials:
 _/Sub-brand for images and graphics generated via Promptbook prompting/_
 
 -   [Instagram `@promptbook.city`](https://www.instagram.com/promptbook.city/)
--   [Facebook `Promptbook City`](https://www.facebook.com/61565718625569)
+-   [Facebook `Promptbook City`](https://www.facebook.com/61565718625569) 
+
+## 
+
 
 
 
-## 💙 Book language _(for prompt-engineer)_
 
 
+## 💙 The Book language
 
 
-## 💙 The blueprint of book language
 
 Following is the documentation and blueprint of the Book language.
 
@@ -157,6 +165,11 @@ Following is the documentation and blueprint of the Book language.
 ```markdown
 # 🌟 My first Book
 
+-   BOOK VERSION 1.0.0
+-   URL https://promptbook.studio/my-first-book/
+
+# Write an article
+
 -   PERSONA Jane, marketing specialist with prior experience in writing articles about technology and artificial intelligence
 -   KNOWLEDGE https://ptbk.io
 -   KNOWLEDGE ./promptbook.pdf
@@ -169,59 +182,31 @@ Following is the documentation and blueprint of the Book language.
 -> {article}
 ```
 
-### Goals and principles of book language
+### **What:** Workflows, Tasks and Parameters
 
-File is designed to be easy to read and write. It is strict subset of markdown. It is designed to be understandable by both humans and machines and without specific knowledge of the language.
-
-It has file with `.book.md` or `.book` extension with `UTF-8` non BOM encoding.
-
-As it is source code, it can leverage all the features of version control systems like git and does not suffer from the problems of binary formats, proprietary formats, or no-code solutions.
-
-But unlike programming languages, it is designed to be understandable by non-programmers and non-technical people.
+-   [PARAMETER](https://github.com/webgptorg/promptbook/blob/main/documents/commands/PARAMETER.md)
 
-### Structure
+### **Who:** Personas
 
-Book is divided into sections. Each section starts with heading. The language itself is not sensitive to the type of heading _(`h1`, `h2`, `h3`, ...)_ but it is recommended to use `h1` for header section and `h2` for other sections.
+-   [PERSONA](https://github.com/webgptorg/promptbook/blob/main/documents/commands/PERSONA.md)
 
-### Header
+### **How:** Knowledge, Instruments and Actions
 
-Header is the first section of the book. It contains metadata about the pipeline. It is recommended to use `h1` heading for header section but it is not required.
+-   [KNOWLEDGE](https://github.com/webgptorg/promptbook/blob/main/documents/commands/KNOWLEDGE.md)
+-   [INSTRUMENT](https://github.com/webgptorg/promptbook/blob/main/documents/commands/INSTRUMENT.md)
+-   [ACTION](https://github.com/webgptorg/promptbook/blob/main/documents/commands/ACTION.md)
 
-### Parameter
+### General principles of book language
 
-Foo bar
+Book language is based on markdown. It is subset of markdown. It is designed to be easy to read and write. It is designed to be understandable by both humans and machines and without specific knowledge of the language.
 
-#### Parameter names
+The file has `.book` extension. It uses `UTF-8` non BOM encoding.
 
-Reserved words:
+Book has two variants: flat - which is just a prompt with no structure, and full - which has a structure with tasks, commands and prompts.
 
--   _each command_ like `PERSONA`, `EXPECT`, `KNOWLEDGE`, etc.
--   `content`
--   `context`
--   `knowledge`
--   `examples`
--   `modelName`
--   `currentDate`
-
-#### Parameter notation
-
-### Task
-
-### Task type
-
-Todo todo
-
-### Command
-
-Todo todo
-
-### Block
-
-Todo todo
-
-### Return parameter
+As it is source code, it can leverage all the features of version control systems like git and does not suffer from the problems of binary formats, proprietary formats, or no-code solutions.
 
-### Examples
+But unlike programming languages, it is designed to be understandable by non-programmers and non-technical people.
 
 
 
@@ -267,6 +252,7 @@ Or you can install them separately:
 -   **[@promptbook/templates](https://www.npmjs.com/package/@promptbook/templates)** - Usefull templates and examples of books which can be used as a starting point
 -   **[@promptbook/types](https://www.npmjs.com/package/@promptbook/types)** - Just typescript types used in the library
 -   ⭐ **[@promptbook/cli](https://www.npmjs.com/package/@promptbook/cli)** - Command line interface utilities for promptbooks
+-   🐋 **[Docker image](https://hub.docker.com/r/hejny/promptbook/)** - Promptbook server
 
 
 
@@ -275,6 +261,11 @@ Or you can install them separately:
 
 ## 📚 Dictionary
 
+
+
+
+
+
 ### 📚 Dictionary
 
 The following glossary is used to clarify certain concepts:
@@ -290,6 +281,8 @@ The following glossary is used to clarify certain concepts:
 -   **Retrieval-augmented generation** is a machine learning paradigm where a model generates text by retrieving relevant information from a large database of text. This approach combines the benefits of generative models and retrieval models.
 -   **Longtail** refers to non-common or rare events, items, or entities that are not well-represented in the training data of machine learning models. Longtail items are often challenging for models to predict accurately.
 
+
+
 _Note: Thos section is not complete dictionary, more list of general AI / LLM terms that has connection with Promptbook_
 
 #### Promptbook core
@@ -350,6 +343,8 @@ _Note: Thos section is not complete dictionary, more list of general AI / LLM te
 -   [👮 Agent adversary expectations](https://github.com/webgptorg/promptbook/discussions/39)
 -   [view more](https://github.com/webgptorg/promptbook/discussions/categories/concepts)
 
+
+
 ### Terms specific to Promptbook TypeScript implementation
 
 -   Anonymous mode
@@ -429,7 +424,7 @@ See [TODO.md](./TODO.md)
 <div style="display: flex; align-items: center; gap: 20px;">
 
   <a href="https://promptbook.studio/">
-    <img src="./other/design/promptbook-studio-logo.png" alt="Partner 3" height="100">
+    <img src="./design/promptbook-studio-logo.png" alt="Partner 3" height="100">
   </a>
 
   <a href="https://technologickainkubace.org/en/about-technology-incubation/about-the-project/">

package/esm/index.es.js

@@ -29,7 +29,7 @@ var BOOK_LANGUAGE_VERSION = '1.0.0';
  * @generated
  * @see https://github.com/webgptorg/promptbook
  */
-var PROMPTBOOK_ENGINE_VERSION = '0.86.0-7';
+var PROMPTBOOK_ENGINE_VERSION = '0.86.6';
 /**
  * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
  * Note: [💞] Ignore a discrepancy between file name and entity name
@@ -548,7 +548,7 @@ function capitalize(word) {
  * Converts promptbook in JSON format to string format
  *
  * @deprecated TODO: [🥍][🧠] Backup original files in `PipelineJson` same as in Promptbook.studio
- * @param pipelineJson Promptbook in JSON format (.book.json)
+ * @param pipelineJson Promptbook in JSON format (.bookc)
  * @returns Promptbook in string format (.book.md)
  * @public exported from `@promptbook/core`
  */
@@ -5908,7 +5908,9 @@ function prepareTasks(pipeline, tools, options) {
                             return __generator(this, function (_a) {
                                 dependentParameterNames = task.dependentParameterNames;
                                 preparedContent = undefined;
-                                if (knowledgePiecesCount > 0 && !dependentParameterNames.includes('knowledge')) {
+                                if (task.taskType === 'PROMPT_TASK' &&
+                                    knowledgePiecesCount > 0 &&
+                                    !dependentParameterNames.includes('knowledge')) {
                                     preparedContent = spaceTrim$1("\n                    {content}\n\n                    ## Knowledge\n\n                    {knowledge}\n                ");
                                     // <- TODO: [🧠][🧻] Cutomize shape/language/formatting of the addition to the prompt
                                     dependentParameterNames = __spreadArray(__spreadArray([], __read(dependentParameterNames), false), [
@@ -9070,7 +9072,7 @@ function flattenMarkdown(markdown) {
  * Note: This function acts as compilation process
  *
  * @param pipelineString {Promptbook} in string markdown format (.book.md)
- * @returns {Promptbook} compiled in JSON format (.book.json)
+ * @returns {Promptbook} compiled in JSON format (.bookc)
  * @throws {ParseError} if the promptbook string is not valid
  * @public exported from `@promptbook/core`
  */
@@ -9538,7 +9540,7 @@ function parsePipeline(pipelineString) {
  * @param pipelineString {Promptbook} in string markdown format (.book.md)
  * @param tools - Tools for the preparation and scraping - if not provided together with `llm`, the preparation will be skipped
  * @param options - Options and tools for the compilation
- * @returns {Promptbook} compiled in JSON format (.book.json)
+ * @returns {Promptbook} compiled in JSON format (.bookc)
  * @throws {ParseError} if the promptbook string is not valid
  * @public exported from `@promptbook/core`
  */
@@ -11266,7 +11268,7 @@ function createCollectionFromDirectory(rootPath, tools, options) {
                     }
                     madeLibraryFilePath = join(rootPath, "".concat(DEFAULT_PIPELINE_COLLECTION_BASE_FILENAME
                     // <- TODO: [🦒] Allow to override (pass different value into the function)
-                    , ".json"));
+                    , ".bookc"));
                     return [4 /*yield*/, isFileExisting(madeLibraryFilePath, tools.fs)];
                 case 3:
                     if (!(_f.sent())) ;
@@ -11288,13 +11290,13 @@ function createCollectionFromDirectory(rootPath, tools, options) {
                                     return [4 /*yield*/, listAllFiles(rootPath, isRecursive, tools.fs)];
                                 case 1:
                                     fileNames = _b.sent();
-                                    // Note: First load all `.book.json` and then `.book` / `.book` files
-                                    //       `.book.json` can be prepared so it is faster to load
+                                    // Note: First load compiled `.bookc` files and then source `.book` files
+                                    //       `.bookc` are already compiled and can be used faster
                                     fileNames.sort(function (a, b) {
-                                        if (a.endsWith('.json') && (b.endsWith('.book') || b.endsWith('.book'))) {
+                                        if ((a.endsWith('.bookc') || a.endsWith('.book.json')) && (b.endsWith('.book') || b.endsWith('.book.md'))) {
                                             return -1;
                                         }
-                                        if ((a.endsWith('.book') || a.endsWith('.book')) && b.endsWith('.json')) {
+                                        if ((a.endsWith('.book') || a.endsWith('.book.md')) && (b.endsWith('.bookc') || b.endsWith('.book.json'))) {
                                             return 1;
                                         }
                                         return 0;
@@ -11311,7 +11313,7 @@ function createCollectionFromDirectory(rootPath, tools, options) {
                                                 case 1:
                                                     _f.trys.push([1, 8, , 9]);
                                                     pipeline = null;
-                                                    if (!(fileName.endsWith('.book') || fileName.endsWith('.book'))) return [3 /*break*/, 4];
+                                                    if (!(fileName.endsWith('.book') || fileName.endsWith('.book.md'))) return [3 /*break*/, 4];
                                                     _c = validatePipelineString;
                                                     return [4 /*yield*/, readFile(fileName, 'utf-8')];
                                                 case 2:
@@ -11324,7 +11326,7 @@ function createCollectionFromDirectory(rootPath, tools, options) {
                                                     pipeline = __assign(__assign({}, pipeline), { sourceFile: sourceFile });
                                                     return [3 /*break*/, 7];
                                                 case 4:
-                                                    if (!fileName.endsWith('.book.json')) return [3 /*break*/, 6];
+                                                    if (!(fileName.endsWith('.bookc') || fileName.endsWith('.book.json'))) return [3 /*break*/, 6];
                                                     _e = (_d = JSON).parse;
                                                     return [4 /*yield*/, readFile(fileName, 'utf-8')];
                                                 case 5: