@promptbook/pdf 0.75.0-2 → 0.75.1

package/README.md

@@ -2,8 +2,6 @@
 
 # ![Promptbook logo - cube with letters P and B](./other/design/logo-h1.png) Promptbook
 
-Build responsible, controlled and transparent applications on top of LLM models!
-
 
 
 
@@ -25,10 +23,6 @@ Build responsible, controlled and transparent applications on top of LLM models!
 
 
 
-<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/pdf`
 
 - Promptbooks are [divided into several](#-packages) packages, all are published from [single monorepo](https://github.com/webgptorg/promptbook).
@@ -53,28 +47,33 @@ Read knowledge from `.pdf` documents
 
 Rest of the documentation is common for **entire promptbook ecosystem**:
 
-## 🤍 The Promptbook Whitepaper
 
-If you have a simple, single prompt for ChatGPT, GPT-4, Anthropic Claude, Google Gemini, Llama 3, or whatever, it doesn't matter how you integrate it. Whether it's calling a REST API directly, using the SDK, hardcoding the prompt into the source code, or importing a text file, the process remains the same.
 
-But often you will struggle with the **limitations of LLMs**, such as **hallucinations, off-topic responses, poor quality output, language and prompt drift, word repetition repetition repetition repetition or misuse, lack of context, or just plain w𝒆𝐢rd resp0nses**. When this happens, you generally have three options:
 
-1. **Fine-tune** the model to your specifications or even train your own.
-2. **Prompt-engineer** the prompt to the best shape you can achieve.
-3. Orchestrate **multiple prompts** in a [pipeline](https://github.com/webgptorg/promptbook/discussions/64) to get the best result.
+## 🤍 The Book Abstract
+
+**It's time for a paradigm shift! The future of software is in plain English, French or Latin.**
+
+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.
 
-In all of these situations, but especially in 3., the **✨ Promptbook can make your life waaaaaaaaaay easier**.
+This shift is going to happen, whether we are ready for it or not. Our mission is to make it excellently, not just good.
 
--   [**Separates concerns**](https://github.com/webgptorg/promptbook/discussions/32) between prompt-engineer and programmer, between code files and prompt files, and between prompts and their execution logic. For this purpose, it introduces a new language called [the **💙 Book**](https://github.com/webgptorg/book).
--   Book allows you to **focus on the business** logic without having to write code or deal with the technicalities of LLMs.
--   **Forget** about **low-level details** like choosing the right model, tokens, context size, `temperature`, `top-k`, `top-p`, or kernel sampling. **Just write your intent** and [**persona**](https://github.com/webgptorg/promptbook/discussions/22) who should be responsible for the task and let the library do the rest.
--   We have built-in **orchestration** of [pipeline](https://github.com/webgptorg/promptbook/discussions/64) execution and many tools to make the process easier, more reliable, and more efficient, such as caching, [compilation+preparation](https://github.com/webgptorg/promptbook/discussions/78), [just-in-time fine-tuning](https://github.com/webgptorg/promptbook/discussions/33), [expectation-aware generation](https://github.com/webgptorg/promptbook/discussions/37), [agent adversary expectations](https://github.com/webgptorg/promptbook/discussions/39), and more.
--   Sometimes even the best prompts with the best framework like Promptbook `:)` can't avoid the problems. In this case, the library has built-in **[anomaly detection](https://github.com/webgptorg/promptbook/discussions/40) and logging** to help you find and fix the problems.
--   Versioning is build in. You can test multiple **A/B versions** of pipelines and see which one works best.
--   Promptbook is designed to use [**RAG** (Retrieval-Augmented Generation)](https://github.com/webgptorg/promptbook/discussions/41) and other advanced techniques to bring the context of your business to generic LLM. You can use **knowledge** to improve the quality of the output.
+**Join us in this journey!**
 
 
 
+## 🚀 Get started
+
+Take a look at the simple starter kit with books integrated into the **Hello World** sample applications:
+
+-   [Hello Book](https://github.com/webgptorg/hello-world)
+-   [Hello Book in Node.js](https://github.com/webgptorg/hello-world-node-js)
+-   [Hello Book in Next.js](https://github.com/webgptorg/hello-world-next-js)
+
 
 
 
@@ -93,7 +92,7 @@ Promptbook project is ecosystem of multiple projects and tools, following is a l
   <tbody>
     <tr>
       <td>Core</td>
-      <td>Promptbook core is a description and documentation of basic innerworkings how should be Promptbook implemented and defines which fetures must be descriable by book language</td>
+      <td>Promptbook Core is a description and documentation of the basic concepts, ideas and inner workings of how Promptbook should be implemented, and defines what features must be describable by book language.</td>
       <td rowspan=2>https://ptbk.io<br/>https://github.com/webgptorg/book</td>
     </tr>
     <tr>
@@ -104,17 +103,23 @@ Promptbook project is ecosystem of multiple projects and tools, following is a l
     </tr>
     <tr>
       <td>Promptbook typescript project</td>
-      <td>Implementation of Promptbook in TypeScript published into multiple packages to NPM</td>
+      <td>Promptbook implementation in TypeScript released as multiple NPM packages</td>
       <td>https://github.com/webgptorg/promptbook + Multiple packages on NPM</td>
     </tr>
     <tr>
       <td>Promptbook studio</td>
-      <td>No-code studio to write book without need to write even the markdown</td>
-      <td rowspan=2>https://promptbook.studio<br/>https://github.com/hejny/promptbook-studio</td>
-    </tr>
-    <tr>
-      <td>Promptbook miniapps</td>
-      <td>Builder of LLM miniapps from book notation</td>
+      <td>Studio to write Books and instantly publish them as miniapps</td>
+      <td>
+        https://promptbook.studio<br/>
+        https://github.com/hejny/promptbook-studio</td>
+      </tr><tr>
+      <td>Hello World</td>
+      <td>Simple starter kit with Books integrated into the sample applications</td>
+       <td>
+          https://github.com/webgptorg/hello-world<br/>
+          https://github.com/webgptorg/hello-world-node-js<br/>
+          https://github.com/webgptorg/hello-world-next-js
+       </td>
     </tr>
   </tbody>
 </table>
@@ -183,7 +188,9 @@ Reserved words:
 
 #### Parameter notation
 
-### Template
+### Task
+
+### Task type
 
 Todo todo
 
@@ -244,6 +251,11 @@ Or you can install them separately:
 
 ## 📚 Dictionary
 
+
+
+
+
+
 ### 📚 Dictionary
 
 The following glossary is used to clarify certain concepts:
@@ -259,6 +271,8 @@ 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
@@ -295,7 +309,7 @@ _Note: Thos section is not complete dictionary, more list of general AI / LLM te
 
 -   [📚 Collection of pipelines](https://github.com/webgptorg/promptbook/discussions/65)
 -   [📯 Pipeline](https://github.com/webgptorg/promptbook/discussions/64)
--   [🎺 Pipeline templates](https://github.com/webgptorg/promptbook/discussions/88)
+-   [🙇‍♂️ Tasks and pipeline sections](https://github.com/webgptorg/promptbook/discussions/88)
 -   [🤼 Personas](https://github.com/webgptorg/promptbook/discussions/22)
 -   [⭕ Parameters](https://github.com/webgptorg/promptbook/discussions/83)
 -   [🚀 Pipeline execution](https://github.com/webgptorg/promptbook/discussions/84)
@@ -319,6 +333,8 @@ _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

package/esm/index.es.js

@@ -20,7 +20,7 @@ var BOOK_LANGUAGE_VERSION = '1.0.0';
  *
  * @see https://github.com/webgptorg/promptbook
  */
-var PROMPTBOOK_ENGINE_VERSION = '0.75.0-1';
+var PROMPTBOOK_ENGINE_VERSION = '0.75.0';
 /**
  * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
  * Note: [💞] Ignore a discrepancy between file name and entity name
@@ -174,7 +174,7 @@ var NotYetImplementedError = /** @class */ (function (_super) {
 function TODO_USE() {
 }
 
-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"]}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/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"]}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-knowledge-keywords.book.md"},{title:"Prepare 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-   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.book.md"},{title:"Prepare Keywords",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"]}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-persona.book.md"}];
+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"]}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],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"]}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./books/prepare-knowledge-keywords.book.md"},{title:"Prepare 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-   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:"./books/prepare-knowledge-title.book.md"},{title:"Prepare Keywords",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"]}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./books/prepare-persona.book.md"}];
 
 /**
  * Prettify the html code
@@ -249,7 +249,7 @@ function pipelineJsonToString(pipelineJson) {
             return isInput;
         })), _h = _g.next(); !_h.done; _h = _g.next()) {
             var parameter = _h.value;
-            commands.push("INPUT PARAMETER ".concat(templateParameterJsonToString(parameter)));
+            commands.push("INPUT PARAMETER ".concat(taskParameterJsonToString(parameter)));
         }
     }
     catch (e_1_1) { e_1 = { error: e_1_1 }; }
@@ -265,7 +265,7 @@ function pipelineJsonToString(pipelineJson) {
             return isOutput;
         })), _k = _j.next(); !_k.done; _k = _j.next()) {
             var parameter = _k.value;
-            commands.push("OUTPUT PARAMETER ".concat(templateParameterJsonToString(parameter)));
+            commands.push("OUTPUT PARAMETER ".concat(taskParameterJsonToString(parameter)));
         }
     }
     catch (e_2_1) { e_2 = { error: e_2_1 }; }
@@ -279,12 +279,12 @@ function pipelineJsonToString(pipelineJson) {
     pipelineString += commands.map(function (command) { return "- ".concat(command); }).join('\n');
     try {
         for (var tasks_1 = __values(tasks), tasks_1_1 = tasks_1.next(); !tasks_1_1.done; tasks_1_1 = tasks_1.next()) {
-            var template = tasks_1_1.value;
+            var task = tasks_1_1.value;
             var 
             /* Note: Not using:> name, */
-            title_1 = template.title, description_1 = template.description, 
+            title_1 = task.title, description_1 = task.description, 
             /* Note: dependentParameterNames, */
-            jokers = template.jokerParameterNames, taskType = template.taskType, content = template.content, postprocessing = template.postprocessingFunctionNames, expectations = template.expectations, format = template.format, resultingParameterName = template.resultingParameterName;
+            jokers = task.jokerParameterNames, taskType = task.taskType, content = task.content, postprocessing = task.postprocessingFunctionNames, expectations = task.expectations, format = task.format, resultingParameterName = task.resultingParameterName;
             pipelineString += '\n\n';
             pipelineString += "## ".concat(title_1);
             if (description_1) {
@@ -294,9 +294,10 @@ function pipelineJsonToString(pipelineJson) {
             var commands_1 = [];
             var contentLanguage = 'text';
             if (taskType === 'PROMPT_TASK') {
-                var modelRequirements = template.modelRequirements;
+                var modelRequirements = task.modelRequirements;
                 var _l = modelRequirements || {}, modelName = _l.modelName, modelVariant = _l.modelVariant;
-                commands_1.push("EXECUTE PROMPT TEMPLATE");
+                // Note: Do nothing, it is default
+                // commands.push(`PROMPT`);
                 if (modelVariant) {
                     commands_1.push("MODEL VARIANT ".concat(capitalize(modelVariant)));
                 }
@@ -309,16 +310,16 @@ function pipelineJsonToString(pipelineJson) {
                 // Note: Nothing special here
             }
             else if (taskType === 'SCRIPT_TASK') {
-                commands_1.push("SCRIPT TEMPLATE");
-                if (template.contentLanguage) {
-                    contentLanguage = template.contentLanguage;
+                commands_1.push("SCRIPT");
+                if (task.contentLanguage) {
+                    contentLanguage = task.contentLanguage;
                 }
                 else {
                     contentLanguage = '';
                 }
             }
             else if (taskType === 'DIALOG_TASK') {
-                commands_1.push("DIALOG TEMPLATE");
+                commands_1.push("DIALOG");
                 // Note: Nothing special here
             } // <- }else if([🅱]
             if (jokers) {
@@ -393,7 +394,7 @@ function pipelineJsonToString(pipelineJson) {
             pipelineString += '\n';
             pipelineString += '```';
             pipelineString += '\n\n';
-            pipelineString += "`-> {".concat(resultingParameterName, "}`"); // <- TODO: [main] !!! If the parameter here has description, add it and use templateParameterJsonToString
+            pipelineString += "`-> {".concat(resultingParameterName, "}`"); // <- TODO: [main] !!! If the parameter here has description, add it and use taskParameterJsonToString
         }
     }
     catch (e_3_1) { e_3 = { error: e_3_1 }; }
@@ -408,8 +409,8 @@ function pipelineJsonToString(pipelineJson) {
 /**
  * @private internal utility of `pipelineJsonToString`
  */
-function templateParameterJsonToString(templateParameterJson) {
-    var name = templateParameterJson.name, description = templateParameterJson.description;
+function taskParameterJsonToString(taskParameterJson) {
+    var name = taskParameterJson.name, description = taskParameterJson.description;
     var parameterString = "{".concat(name, "}");
     if (description) {
         parameterString = "".concat(parameterString, " ").concat(description);
@@ -417,7 +418,7 @@ function templateParameterJsonToString(templateParameterJson) {
     return parameterString;
 }
 /**
- * TODO: [🛋] Implement new features and commands into `pipelineJsonToString` + `templateParameterJsonToString` , use `stringifyCommand`
+ * TODO: [🛋] Implement new features and commands into `pipelineJsonToString` + `taskParameterJsonToString` , use `stringifyCommand`
  * TODO: [🧠] Is there a way to auto-detect missing features in pipelineJsonToString
  * TODO: [🏛] Maybe make some markdown builder
  * TODO: [🏛] Escape all
@@ -1121,20 +1122,20 @@ function validatePipelineCore(pipeline) {
         }
         finally { if (e_3) throw e_3.error; }
     }
-    var unresovedTemplates = __spreadArray([], __read(pipeline.tasks), false);
+    var unresovedTasks = __spreadArray([], __read(pipeline.tasks), false);
     var loopLimit = LOOP_LIMIT;
     var _loop_3 = function () {
         if (loopLimit-- < 0) {
             // Note: Really UnexpectedError not LimitReachedError - this should not happen and be caught below
             throw new UnexpectedError(spaceTrim(function (block) { return "\n                        Loop limit reached during detection of circular dependencies in `validatePipeline`\n\n                        ".concat(block(pipelineIdentification), "\n                    "); }));
         }
-        var currentlyResovedTemplates = unresovedTemplates.filter(function (task) {
+        var currentlyResovedTasks = unresovedTasks.filter(function (task) {
             return task.dependentParameterNames.every(function (name) { return resovedParameters.includes(name); });
         });
-        if (currentlyResovedTemplates.length === 0) {
+        if (currentlyResovedTasks.length === 0) {
             throw new PipelineLogicError(
             // TODO: [🐎] DRY
-            spaceTrim(function (block) { return "\n\n                        Can not resolve some parameters:\n                        Either you are using a parameter that is not defined, or there are some circular dependencies.\n\n                        ".concat(block(pipelineIdentification), "\n\n                        **Can not resolve:**\n                        ").concat(block(unresovedTemplates
+            spaceTrim(function (block) { return "\n\n                        Can not resolve some parameters:\n                        Either you are using a parameter that is not defined, or there are some circular dependencies.\n\n                        ".concat(block(pipelineIdentification), "\n\n                        **Can not resolve:**\n                        ").concat(block(unresovedTasks
                 .map(function (_a) {
                 var resultingParameterName = _a.resultingParameterName, dependentParameterNames = _a.dependentParameterNames;
                 return "- Parameter `{".concat(resultingParameterName, "}` which depends on ").concat(dependentParameterNames
@@ -1153,13 +1154,13 @@ function validatePipelineCore(pipeline) {
                 .map(function (name) { return "- Parameter `{".concat(name, "}`"); })
                 .join('\n')), "\n\n\n                    "); }));
         }
-        resovedParameters = __spreadArray(__spreadArray([], __read(resovedParameters), false), __read(currentlyResovedTemplates.map(function (_a) {
+        resovedParameters = __spreadArray(__spreadArray([], __read(resovedParameters), false), __read(currentlyResovedTasks.map(function (_a) {
             var resultingParameterName = _a.resultingParameterName;
             return resultingParameterName;
         })), false);
-        unresovedTemplates = unresovedTemplates.filter(function (task) { return !currentlyResovedTemplates.includes(task); });
+        unresovedTasks = unresovedTasks.filter(function (task) { return !currentlyResovedTasks.includes(task); });
     };
-    while (unresovedTemplates.length > 0) {
+    while (unresovedTasks.length > 0) {
         _loop_3();
     }
     // TODO: !!!!!! Test that pipeline interface implements declared formfactor interface
@@ -1221,7 +1222,7 @@ var PipelineUrlError = /** @class */ (function (_super) {
 /**
  * Parses the task and returns the list of all parameter names
  *
- * @param template the task with parameters in {curly} braces
+ * @param template the string template with parameters in {curly} braces
  * @returns the list of parameter names
  * @public exported from `@promptbook/utils`
  */
@@ -1255,13 +1256,13 @@ function unpreparePipeline(pipeline) {
     var personas = pipeline.personas, knowledgeSources = pipeline.knowledgeSources, tasks = pipeline.tasks;
     personas = personas.map(function (persona) { return (__assign(__assign({}, persona), { modelRequirements: undefined, preparationIds: undefined })); });
     knowledgeSources = knowledgeSources.map(function (knowledgeSource) { return (__assign(__assign({}, knowledgeSource), { preparationIds: undefined })); });
-    tasks = tasks.map(function (template) {
-        var dependentParameterNames = template.dependentParameterNames;
-        var parameterNames = extractParameterNames(template.preparedContent || '');
+    tasks = tasks.map(function (task) {
+        var dependentParameterNames = task.dependentParameterNames;
+        var parameterNames = extractParameterNames(task.preparedContent || '');
         dependentParameterNames = dependentParameterNames.filter(function (dependentParameterName) { return !parameterNames.has(dependentParameterName); });
-        var templateUnprepared = __assign(__assign({}, template), { dependentParameterNames: dependentParameterNames });
-        delete templateUnprepared.preparedContent;
-        return templateUnprepared;
+        var taskUnprepared = __assign(__assign({}, task), { dependentParameterNames: dependentParameterNames });
+        delete taskUnprepared.preparedContent;
+        return taskUnprepared;
     });
     return $asDeeplyFrozenSerializableJson('Unprepared PipelineJson', __assign(__assign({}, pipeline), { tasks: tasks, knowledgeSources: knowledgeSources, knowledgePieces: [], personas: personas, preparations: [] }));
 }
@@ -1959,7 +1960,7 @@ function isPipelinePrepared(pipeline) {
  * TODO: [🐠] Maybe base this on `makeValidator`
  * TODO: [🧊] Pipeline can be partially prepared, this should return true ONLY if fully prepared
  * TODO: [🧿] Maybe do same process with same granularity and subfinctions as `preparePipeline`
- *     - [🏍] ? Is context in each template
+ *     - [🏍] ? Is context in each task
  *     - [♨] Are examples prepared
  *     - [♨] Are tasks prepared
  */
@@ -3333,10 +3334,10 @@ function prepareTasks(pipeline, tools, options) {
                     _a = options.maxParallelCount, maxParallelCount = _a === void 0 ? DEFAULT_MAX_PARALLEL_COUNT : _a;
                     tasks = pipeline.tasks, pipeline.parameters, knowledgePiecesCount = pipeline.knowledgePiecesCount;
                     tasksPrepared = new Array(tasks.length);
-                    return [4 /*yield*/, forEachAsync(tasks, { maxParallelCount: maxParallelCount /* <- TODO: [🪂] When there are subtasks, this maximul limit can be broken */ }, function (template, index) { return __awaiter(_this, void 0, void 0, function () {
-                            var dependentParameterNames, preparedContent, preparedTemplate;
+                    return [4 /*yield*/, forEachAsync(tasks, { maxParallelCount: maxParallelCount /* <- TODO: [🪂] When there are subtasks, this maximul limit can be broken */ }, function (task, index) { return __awaiter(_this, void 0, void 0, function () {
+                            var dependentParameterNames, preparedContent, preparedTask;
                             return __generator(this, function (_a) {
-                                dependentParameterNames = template.dependentParameterNames;
+                                dependentParameterNames = task.dependentParameterNames;
                                 preparedContent = undefined;
                                 if (knowledgePiecesCount > 0 && !dependentParameterNames.includes('knowledge')) {
                                     preparedContent = spaceTrim("\n                    {content}\n\n                    ## Knowledge\n\n                    {knowledge}\n                ");
@@ -3345,8 +3346,8 @@ function prepareTasks(pipeline, tools, options) {
                                         'knowledge',
                                     ], false);
                                 }
-                                preparedTemplate = __assign(__assign({}, template), { dependentParameterNames: dependentParameterNames, preparedContent: preparedContent });
-                                tasksPrepared[index] = preparedTemplate;
+                                preparedTask = __assign(__assign({}, task), { dependentParameterNames: dependentParameterNames, preparedContent: preparedContent });
+                                tasksPrepared[index] = preparedTask;
                                 return [2 /*return*/];
                             });
                         }); })];
@@ -3358,8 +3359,8 @@ function prepareTasks(pipeline, tools, options) {
     });
 }
 /**
- * TODO: [🧠] Add context to each template (if missing)
- * TODO: [🧠] What is better name `prepareTemplate` or `prepareTemplateAndParameters`
+ * TODO: [🧠] Add context to each task (if missing)
+ * TODO: [🧠] What is better name `prepareTask` or `prepareTaskAndParameters`
  * TODO: [♨][main] !!! Prepare index the examples and maybe tasks
  * TODO: Write tests for `preparePipeline`
  * TODO: [🏏] Leverage the batch API and build queues @see https://platform.openai.com/docs/guides/batch
@@ -3445,7 +3446,7 @@ function preparePipeline(pipeline, tools, options) {
                         })];
                 case 3:
                     tasksPrepared = (_c.sent()).tasksPrepared;
-                    // ----- /Templates preparation -----
+                    // ----- /Tasks preparation -----
                     // Note: Count total usage
                     currentPreparation.usage = llmToolsWithUsage.getTotalUsage();
                     return [2 /*return*/, $asDeeplyFrozenSerializableJson('Prepared PipelineJson', __assign(__assign({}, clonePipeline(pipeline)), { tasks: __spreadArray([], __read(tasksPrepared), false), 
@@ -3514,16 +3515,16 @@ function extractVariables(script) {
  */
 
 /**
- * Parses the template and returns the set of all used parameters
+ * Parses the task and returns the set of all used parameters
  *
- * @param template the template with used parameters
+ * @param task the task with used parameters
  * @returns the set of parameter names
  * @throws {ParseError} if the script is invalid
  * @public exported from `@promptbook/utils`
  */
-function extractParameterNamesFromTask(template) {
+function extractParameterNamesFromTask(task) {
     var e_1, _a, e_2, _b, e_3, _c, e_4, _d;
-    var title = template.title, description = template.description, taskType = template.taskType, content = template.content, preparedContent = template.preparedContent, jokerParameterNames = template.jokerParameterNames, foreach = template.foreach;
+    var title = task.title, description = task.description, taskType = task.taskType, content = task.content, preparedContent = task.preparedContent, jokerParameterNames = task.jokerParameterNames, foreach = task.foreach;
     var parameterNames = new Set();
     try {
         for (var _e = __values(__spreadArray(__spreadArray(__spreadArray(__spreadArray([], __read(extractParameterNames(title)), false), __read(extractParameterNames(description || '')), false), __read(extractParameterNames(content)), false), __read(extractParameterNames(preparedContent || '')), false)), _f = _e.next(); !_f.done; _f = _e.next()) {