@promptbook/utils 0.70.0-0 → 0.71.0-0

package/README.md

@@ -16,6 +16,10 @@ Supercharge your use of large language models
 
 
 
+## ✨ New Features
+
+-   ✨ **Support of [OpenAI o1 model](https://openai.com/o1/)**
+
 ## 📦 Package `@promptbook/utils`
 
 - Promptbooks are [divided into several](#-packages) packages, all are published from [single monorepo](https://github.com/webgptorg/promptbook).
@@ -28,7 +32,7 @@ To install this package, run:
 npm i ptbk
 
 # Install just this package to save space
-npm i @promptbook/utils
+npm install @promptbook/utils
 ```
 
 Utility functions used in the library but also useful for individual use in preprocessing and postprocessing LLM inputs and outputs
@@ -161,13 +165,15 @@ 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 2, 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 drift, word repetition repetition repetition repetition or misuse, lack of context, or just plain w𝒆𝐢rd responses. 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. Use **multiple prompts** in a [pipeline](https://github.com/webgptorg/promptbook/discussions/64) to get the best result.
+3. Orchestrate **multiple prompts** in a [pipeline](https://github.com/webgptorg/promptbook/discussions/64) to get the best result.
 
 In all of these situations, but especially in 3., the Promptbook library can make your life easier.
 
@@ -179,7 +185,9 @@ In all of these situations, but especially in 3., the Promptbook library can mak
 -   Promptbook has built in versioning. You can test multiple **A/B versions** of pipelines and see which one works best.
 -   Promptbook is designed to do [**RAG** (Retrieval-Augmented Generation)](https://github.com/webgptorg/promptbook/discussions/41) and other advanced techniques. You can use **knowledge** to improve the quality of the output.
 
-## 🧔 Promptbook _(for prompt-engeneers)_
+
+
+## 🧔 Pipeline _(for prompt-engeneers)_
 
 **P**romp**t** **b**oo**k** markdown file (or `.ptbk.md` file) is document that describes a **pipeline** - a series of prompts that are chained together to form somewhat reciepe for transforming natural language input.
 
@@ -201,7 +209,6 @@ File `write-website-content.ptbk.md`:
 > Instructions for creating web page content.
 >
 > -   PIPELINE URL https://promptbook.studio/webgpt/write-website-content.ptbk.md
-> -   PROMPTBOOK VERSION 0.0.1
 > -   INPUT  PARAM `{rawTitle}` Automatically suggested a site name or empty text
 > -   INPUT  PARAM `{rawAssigment}` Automatically generated site entry from image recognition
 > -   OUTPUT PARAM `{websiteContent}` Web content
@@ -496,6 +503,8 @@ The following glossary is used to clarify certain concepts:
 -   When you want to **version** your prompts and **test multiple versions**
 -   When you want to **log** the execution of prompts and backtrace the issues
 
+[See more](https://github.com/webgptorg/promptbook/discussions/111)
+
 ### ➖ When not to use
 
 -   When you have already implemented single simple prompt and it works fine for your job
@@ -505,6 +514,8 @@ The following glossary is used to clarify certain concepts:
 -   When your main focus is on something other than text - like images, audio, video, spreadsheets _(other media types may be added in the future, [see discussion](https://github.com/webgptorg/promptbook/discussions/103))_
 -   When you need to use recursion _([see the discussion](https://github.com/webgptorg/promptbook/discussions/38))_
 
+[See more](https://github.com/webgptorg/promptbook/discussions/112)
+
 ## 🐜 Known issues
 
 -   [🤸‍♂️ Iterations not working yet](https://github.com/webgptorg/promptbook/discussions/55)
@@ -517,63 +528,15 @@ The following glossary is used to clarify certain concepts:
 
 ## ❔ FAQ
 
-
-
 If you have a question [start a discussion](https://github.com/webgptorg/promptbook/discussions/), [open an issue](https://github.com/webgptorg/promptbook/issues) or [write me an email](https://www.pavolhejny.com/contact).
 
-### Why not just use the OpenAI SDK / Anthropic Claude SDK / ...?
-
-Different levels of abstraction. OpenAI library is for direct use of OpenAI API. This library is for a higher level of abstraction. It define pipelines that are independent of the underlying library, LLM model, or even LLM provider.
-
-### How is it different from the Langchain library?
-
-Langchain is primarily aimed at ML developers working in Python. This library is for developers working in javascript/typescript and creating applications for end users.
-
-We are considering creating a bridge/converter between these two libraries.
-
-
-
-### Promptbooks vs. OpenAI`s GPTs
-
-GPTs are chat assistants that can be assigned to specific tasks and materials. But they are still chat assistants. Promptbooks are a way to orchestrate many more predefined tasks to have much tighter control over the process. Promptbooks are not a good technology for creating human-like chatbots, GPTs are not a good technology for creating outputs with specific requirements.
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-### Where should I store my promptbooks?
-
-If you use raw SDKs, you just put prompts in the sourcecode, mixed in with typescript, javascript, python or whatever programming language you use.
-
-If you use promptbooks, you can store them in several places, each with its own advantages and disadvantages:
-
-1. As **source code**, typically git-committed. In this case you can use the versioning system and the promptbooks will be tightly coupled with the version of the application. You still get the power of promptbooks, as you separate the concerns of the prompt-engineer and the programmer.
-
-2. As data in a **database** In this case, promptbooks are like posts / articles on the blog. They can be modified independently of the application. You don't need to redeploy the application to change the promptbooks. You can have multiple versions of promptbooks for each user. You can have a web interface for non-programmers to create and modify promptbooks. But you lose the versioning system and you still have to consider the interface between the promptbooks and the application _(= input and output parameters)_.
-
-3. In a **configuration** in environment variables. This is a good way to store promptbooks if you have an application with multiple deployments and you want to have different but simple promptbooks for each deployment and you don't need to change them often.
-
-### What should I do when I need same promptbook in multiple human languages?
-
-A single promptbook can be written for several _(human)_ languages at once. However, we recommend that you have separate promptbooks for each language.
-
-In large language models, you will get better results if you have prompts in the same language as the user input.
-
-The best way to manage this is to have suffixed promptbooks like `write-website-content.en.ptbk.md` and `write-website-content.cs.ptbk.md` for each supported language.
-
-
-
-
+-   [❔ Why not just use the OpenAI SDK / Anthropic Claude SDK / ...?](https://github.com/webgptorg/promptbook/discussions/114)
+-   [❔ How is it different from the OpenAI`s GPTs?](https://github.com/webgptorg/promptbook/discussions/118)
+-   [❔ How is it different from the Langchain?](https://github.com/webgptorg/promptbook/discussions/115)
+-   [❔ How is it different from the DSPy?](https://github.com/webgptorg/promptbook/discussions/117)
+-   [❔ How is it different from _anything_?](https://github.com/webgptorg/promptbook/discussions?discussions_q=is%3Aopen+label%3A%22Promptbook+vs%22)
+-   [❔ Is Promptbook using RAG _(Retrieval-Augmented Generation)_?](https://github.com/webgptorg/promptbook/discussions/123)
+-   [❔ Is Promptbook using function calling?](https://github.com/webgptorg/promptbook/discussions/124)
 
 ## ⌚ Changelog
 

package/esm/index.es.js

@@ -4,8 +4,8 @@ import spaceTrim$1, { spaceTrim } from 'spacetrim';
 /**
  * The version of the Promptbook library
  */
-var PROMPTBOOK_VERSION = '0.69.0-0';
-// TODO: !!!! List here all the versions and annotate + put into script
+var PROMPTBOOK_VERSION = '0.70.0-1';
+// TODO:[main] !!!! List here all the versions and annotate + put into script
 
 /*! *****************************************************************************
 Copyright (c) Microsoft Corporation.
@@ -625,6 +625,9 @@ function renderPromptbookMermaid(pipelineJson, options) {
     return promptbookMermaid;
 }
 /**
+ * TODO: !!!!! FOREACH in mermaid graph
+ * TODO: !!!!! Knowledge in mermaid graph
+ * TODO: !!!!! Personas in mermaid graph
  * TODO: Maybe use some Mermaid package instead of string templating
  * TODO: [🕌] When more than 2 functionalities, split into separate functions
  */
@@ -734,52 +737,72 @@ function extractVariables(script) {
  * @public exported from `@promptbook/utils`
  */
 function extractParameterNamesFromTemplate(template) {
-    var e_1, _a, e_2, _b, e_3, _c;
-    var title = template.title, description = template.description, templateType = template.templateType, content = template.content, preparedContent = template.preparedContent, jokerParameterNames = template.jokerParameterNames;
+    var e_1, _a, e_2, _b, e_3, _c, e_4, _d;
+    var title = template.title, description = template.description, templateType = template.templateType, content = template.content, preparedContent = template.preparedContent, jokerParameterNames = template.jokerParameterNames, foreach = template.foreach;
     var parameterNames = new Set();
     try {
-        for (var _d = __values(__spreadArray(__spreadArray(__spreadArray(__spreadArray([], __read(extractParameterNames(title)), false), __read(extractParameterNames(description || '')), false), __read(extractParameterNames(content)), false), __read(extractParameterNames(preparedContent || '')), false)), _e = _d.next(); !_e.done; _e = _d.next()) {
-            var parameterName = _e.value;
+        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()) {
+            var parameterName = _f.value;
             parameterNames.add(parameterName);
         }
     }
     catch (e_1_1) { e_1 = { error: e_1_1 }; }
     finally {
         try {
-            if (_e && !_e.done && (_a = _d.return)) _a.call(_d);
+            if (_f && !_f.done && (_a = _e.return)) _a.call(_e);
         }
         finally { if (e_1) throw e_1.error; }
     }
     if (templateType === 'SCRIPT_TEMPLATE') {
         try {
-            for (var _f = __values(extractVariables(content)), _g = _f.next(); !_g.done; _g = _f.next()) {
-                var parameterName = _g.value;
+            for (var _g = __values(extractVariables(content)), _h = _g.next(); !_h.done; _h = _g.next()) {
+                var parameterName = _h.value;
                 parameterNames.add(parameterName);
             }
         }
         catch (e_2_1) { e_2 = { error: e_2_1 }; }
         finally {
             try {
-                if (_g && !_g.done && (_b = _f.return)) _b.call(_f);
+                if (_h && !_h.done && (_b = _g.return)) _b.call(_g);
             }
             finally { if (e_2) throw e_2.error; }
         }
     }
     try {
-        for (var _h = __values(jokerParameterNames || []), _j = _h.next(); !_j.done; _j = _h.next()) {
-            var jokerName = _j.value;
+        for (var _j = __values(jokerParameterNames || []), _k = _j.next(); !_k.done; _k = _j.next()) {
+            var jokerName = _k.value;
             parameterNames.add(jokerName);
         }
     }
     catch (e_3_1) { e_3 = { error: e_3_1 }; }
     finally {
         try {
-            if (_j && !_j.done && (_c = _h.return)) _c.call(_h);
+            if (_k && !_k.done && (_c = _j.return)) _c.call(_j);
         }
         finally { if (e_3) throw e_3.error; }
     }
     parameterNames.delete('content');
     //                      <- Note {websiteContent} is used in `preparedContent`
+    // Note: [🍭] Fixing dependent subparameterName from FOREACH command
+    if (foreach !== undefined) {
+        try {
+            for (var _l = __values(foreach.subparameterNames), _m = _l.next(); !_m.done; _m = _l.next()) {
+                var subparameterName = _m.value;
+                if (parameterNames.has(subparameterName)) {
+                    parameterNames.delete(subparameterName);
+                    parameterNames.add(foreach.parameterName);
+                    // <- TODO: [🚎] Warn/logic error when `subparameterName` not used
+                }
+            }
+        }
+        catch (e_4_1) { e_4 = { error: e_4_1 }; }
+        finally {
+            try {
+                if (_m && !_m.done && (_d = _l.return)) _d.call(_l);
+            }
+            finally { if (e_4) throw e_4.error; }
+        }
+    }
     return parameterNames;
 }
 /**
@@ -1264,6 +1287,9 @@ var CountUtils = {
     LINES: countLines,
     PAGES: countPages,
 };
+/**
+ * TODO: [🧠][🤠] This should be probbably as part of `TextFormatDefinition`
+ */
 
 /**
  * Makes first letter of a string uppercase
@@ -1518,108 +1544,6 @@ function searchKeywords(haystack, needle) {
     return true;
 }
 
-/**
- * Function parseNumber will parse number from string
- *
- * Unlike Number.parseInt, Number.parseFloat it will never ever result in NaN
- * Note: it also works only with decimal numbers
- *
- * @returns parsed number
- * @throws {ParseError} if the value is not a number
- *
- * @public exported from `@promptbook/utils`
- */
-function parseNumber(value) {
-    var originalValue = value;
-    if (typeof value === 'number') {
-        value = value.toString(); // <- TODO: Maybe more efficient way to do this
-    }
-    if (typeof value !== 'string') {
-        return 0;
-    }
-    value = value.trim();
-    if (value.startsWith('+')) {
-        return parseNumber(value.substring(1));
-    }
-    if (value.startsWith('-')) {
-        var number = parseNumber(value.substring(1));
-        if (number === 0) {
-            return 0; // <- Note: To prevent -0
-        }
-        return -number;
-    }
-    value = value.replace(/,/g, '.');
-    value = value.toUpperCase();
-    if (value === '') {
-        return 0;
-    }
-    if (value === '♾' || value.startsWith('INF')) {
-        return Infinity;
-    }
-    if (value.includes('/')) {
-        var _a = __read(value.split('/'), 2), numerator_ = _a[0], denominator_ = _a[1];
-        var numerator = parseNumber(numerator_);
-        var denominator = parseNumber(denominator_);
-        if (denominator === 0) {
-            throw new ParseError("Unable to parse number from \"".concat(originalValue, "\" because denominator is zero"));
-        }
-        return numerator / denominator;
-    }
-    if (/^(NAN|NULL|NONE|UNDEFINED|ZERO|NO.*)$/.test(value)) {
-        return 0;
-    }
-    if (value.includes('E')) {
-        var _b = __read(value.split('E'), 2), significand = _b[0], exponent = _b[1];
-        return parseNumber(significand) * Math.pow(10, parseNumber(exponent));
-    }
-    if (!/^[0-9.]+$/.test(value) || value.split('.').length > 2) {
-        throw new ParseError("Unable to parse number from \"".concat(originalValue, "\""));
-    }
-    var num = parseFloat(value);
-    if (isNaN(num)) {
-        throw new ParseError("Unexpected NaN when parsing number from \"".concat(originalValue, "\""));
-    }
-    return num;
-}
-/**
- * TODO: Maybe use sth. like safe-eval in fraction/calculation case @see https://www.npmjs.com/package/safe-eval
- * TODO: [🧠][🌻] Maybe export through `@promptbook/markdown-utils` not `@promptbook/utils`
- */
-
-/**
- * Generates random seed
- *
- * Note: `$` is used to indicate that this function is not a pure function - it is not deterministic
- * Warning: This function is not cryptographically secure (it uses Math.random internally)
- * @public exported from `@promptbook/utils`
- */
-function $randomSeed() {
-    return Math.random();
-}
-
-/**
- * Removes quotes from a string
- *
- * Tip: This is very usefull for post-processing of the result of the LLM model
- * Note: This function removes only the same quotes from the beginning and the end of the string
- * Note: There are two simmilar functions:
- * - `removeQuotes` which removes only bounding quotes
- * - `unwrapResult` which removes whole introduce sentence
- *
- * @param text optionally quoted text
- * @returns text without quotes
- * @public exported from `@promptbook/utils`
- */
-function removeQuotes(text) {
-    if (text.startsWith('"') && text.endsWith('"')) {
-        return text.slice(1, -1);
-    }
-    if (text.startsWith('\'') && text.endsWith('\'')) {
-        return text.slice(1, -1);
-    }
-    return text;
-}
-
 /**
  * @@@
  *
@@ -1773,7 +1697,7 @@ function checkSerializableAsJson(name, value) {
 }
 /**
  * TODO: [🧠][🛣] More elegant way to tracking than passing `name`
- * TODO: [🧠] !!! In-memory cache of same values to prevent multiple checks
+ * TODO: [🧠][main] !!! In-memory cache of same values to prevent multiple checks
  * Note: [🐠] This is how `checkSerializableAsJson` + `isSerializableAsJson` together can just retun true/false or rich error message
  */
 
@@ -1822,6 +1746,7 @@ $asDeeplyFrozenSerializableJson('RESERVED_PARAMETER_NAMES', [
     'samples',
     'modelName',
     'currentDate',
+    // <- TODO: !!!!! list here all command names
     // <- TODO: Add more like 'date', 'modelName',...
     // <- TODO: Add [emoji] + instructions ACRY when adding new reserved parameter
 ]);
@@ -1837,6 +1762,18 @@ var RESERVED_PARAMETER_MISSING_VALUE = 'MISSING-' + REPLACING_NONCE;
  * @private within the repository
  */
 var RESERVED_PARAMETER_RESTRICTED = 'RESTRICTED-' + REPLACING_NONCE;
+// <- TODO: [🧜‍♂️]
+/**
+ * @@@
+ *
+ * @public exported from `@promptbook/core`
+ */
+Object.freeze({
+    delimiter: ',',
+    quoteChar: '"',
+    newline: '\n',
+    skipEmptyLines: true,
+});
 /**
  * TODO: [🧠][🧜‍♂️] Maybe join remoteUrl and path into single value
  */
@@ -1920,6 +1857,108 @@ function replaceParameters(template, parameters) {
     return replacedTemplate;
 }
 
+/**
+ * Function parseNumber will parse number from string
+ *
+ * Unlike Number.parseInt, Number.parseFloat it will never ever result in NaN
+ * Note: it also works only with decimal numbers
+ *
+ * @returns parsed number
+ * @throws {ParseError} if the value is not a number
+ *
+ * @public exported from `@promptbook/utils`
+ */
+function parseNumber(value) {
+    var originalValue = value;
+    if (typeof value === 'number') {
+        value = value.toString(); // <- TODO: Maybe more efficient way to do this
+    }
+    if (typeof value !== 'string') {
+        return 0;
+    }
+    value = value.trim();
+    if (value.startsWith('+')) {
+        return parseNumber(value.substring(1));
+    }
+    if (value.startsWith('-')) {
+        var number = parseNumber(value.substring(1));
+        if (number === 0) {
+            return 0; // <- Note: To prevent -0
+        }
+        return -number;
+    }
+    value = value.replace(/,/g, '.');
+    value = value.toUpperCase();
+    if (value === '') {
+        return 0;
+    }
+    if (value === '♾' || value.startsWith('INF')) {
+        return Infinity;
+    }
+    if (value.includes('/')) {
+        var _a = __read(value.split('/'), 2), numerator_ = _a[0], denominator_ = _a[1];
+        var numerator = parseNumber(numerator_);
+        var denominator = parseNumber(denominator_);
+        if (denominator === 0) {
+            throw new ParseError("Unable to parse number from \"".concat(originalValue, "\" because denominator is zero"));
+        }
+        return numerator / denominator;
+    }
+    if (/^(NAN|NULL|NONE|UNDEFINED|ZERO|NO.*)$/.test(value)) {
+        return 0;
+    }
+    if (value.includes('E')) {
+        var _b = __read(value.split('E'), 2), significand = _b[0], exponent = _b[1];
+        return parseNumber(significand) * Math.pow(10, parseNumber(exponent));
+    }
+    if (!/^[0-9.]+$/.test(value) || value.split('.').length > 2) {
+        throw new ParseError("Unable to parse number from \"".concat(originalValue, "\""));
+    }
+    var num = parseFloat(value);
+    if (isNaN(num)) {
+        throw new ParseError("Unexpected NaN when parsing number from \"".concat(originalValue, "\""));
+    }
+    return num;
+}
+/**
+ * TODO: Maybe use sth. like safe-eval in fraction/calculation case @see https://www.npmjs.com/package/safe-eval
+ * TODO: [🧠][🌻] Maybe export through `@promptbook/markdown-utils` not `@promptbook/utils`
+ */
+
+/**
+ * Generates random seed
+ *
+ * Note: `$` is used to indicate that this function is not a pure function - it is not deterministic
+ * Warning: This function is not cryptographically secure (it uses Math.random internally)
+ * @public exported from `@promptbook/utils`
+ */
+function $randomSeed() {
+    return Math.random();
+}
+
+/**
+ * Removes quotes from a string
+ *
+ * Tip: This is very usefull for post-processing of the result of the LLM model
+ * Note: This function removes only the same quotes from the beginning and the end of the string
+ * Note: There are two simmilar functions:
+ * - `removeQuotes` which removes only bounding quotes
+ * - `unwrapResult` which removes whole introduce sentence
+ *
+ * @param text optionally quoted text
+ * @returns text without quotes
+ * @public exported from `@promptbook/utils`
+ */
+function removeQuotes(text) {
+    if (text.startsWith('"') && text.endsWith('"')) {
+        return text.slice(1, -1);
+    }
+    if (text.startsWith('\'') && text.endsWith('\'')) {
+        return text.slice(1, -1);
+    }
+    return text;
+}
+
 /**
  * @@@
  *
@@ -2001,7 +2040,7 @@ function isSerializableAsJson(value) {
     }
 }
 /**
- * TODO: [🧠] !!! In-memory cache of same values to prevent multiple checks
+ * TODO: [🧠][main] !!! In-memory cache of same values to prevent multiple checks
  * TODO: [🧠][💺] Can be done this on type-level?
  */
 
@@ -2316,7 +2355,7 @@ function isValidPromptbookVersion(version) {
     if ( /* version === '1.0.0' || */version === '2.0.0' || version === '3.0.0') {
         return false;
     }
-    // <- TODO: !!! Check isValidPromptbookVersion against PROMPTBOOK_VERSIONS
+    // <- TODO:[main] !!! Check isValidPromptbookVersion against PROMPTBOOK_VERSIONS
     return true;
 }