@promptbook/azure-openai 0.72.0-9 → 0.73.0

package/README.md

@@ -2,7 +2,7 @@
 
 # ![Promptbook logo - cube with letters P and B](./other/design/logo-h1.png) Promptbook
 
-Supercharge your use of large language models
+Build responsible, controlled and transparent applications on top of LLM models!
 
 
 
@@ -18,12 +18,10 @@ Supercharge your use of large language models
 
 ## ✨ New Features
 
+-   💙 Working on [the **Book** language v1](https://github.com/webgptorg/book)
+-   📚 Support of `.docx`, `.doc` and `.pdf` documents
 -   ✨ **Support of [OpenAI o1 model](https://openai.com/o1/)**
 
-<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/azure-openai`
@@ -68,10 +66,11 @@ const llm = new AzureOpenAiExecutionTools(
         apiKey: process.env.AZUREOPENAI_API_KEY,
     },
 );
+const executables = await $provideExecutablesForNode();
 const tools = {
     llm,
     fs,
-    scrapers: await $provideScrapersForNode({ fs, llm }),
+    scrapers: await $provideScrapersForNode({ fs, llm, executables }),
     script: [new JavascriptExecutionTools()],
 };
 
@@ -140,10 +139,11 @@ const llm = [
         },
     ),
 ];
+const executables = await $provideExecutablesForNode();
 const tools = {
     llm,
     fs,
-    scrapers: await $provideScrapersForNode({ fs, llm }),
+    scrapers: await $provideScrapersForNode({ fs, llm, executables }),
     script: [new JavascriptExecutionTools()],
 };
 
@@ -184,260 +184,48 @@ 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.
 
-
-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:
+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.
 
-In all of these situations, but especially in 3., the Promptbook library can make your life easier.
+In all of these situations, but especially in 3., the **✨ Promptbook can make your life waaaaaaaaaay easier**.
 
--   [**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.
--   Establishes a [**common format `.ptbk.md`**](https://github.com/webgptorg/promptbook/discussions/85) that can be used to describe your prompt 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.
--   Has 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.
+-   [**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.
--   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.
-
-
-
-## 🧔 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.
-
--   Multiple pipelines forms a **collection** which will handle core **know-how of your LLM application**.
--   Theese pipelines are designed such as they **can be written by non-programmers**.
-
-
-
-### Sample:
-
-File `write-website-content.ptbk.md`:
-
-
-
-
-
-> # 🌍 Create website content
->
-> Instructions for creating web page content.
->
-> -   PIPELINE URL https://promptbook.studio/webgpt/write-website-content.ptbk.md
-> -   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
-> -   OUTPUT PARAM `{keywords}` Keywords
->
-> ## 👤 Specifying the assigment
->
-> What is your web about?
->
-> -   DIALOG TEMPLATE
->
-> ```
-> {rawAssigment}
-> ```
->
-> `-> {assigment}` Website assignment and specification
->
-> ## ✨ Improving the title
->
-> -   PERSONA Jane, Copywriter and Marketing Specialist.
->
-> ```
-> As an experienced marketing specialist, you have been entrusted with improving the name of your client's business.
->
-> A suggested name from a client:
-> "{rawTitle}"
->
-> Assignment from customer:
->
-> > {assigment}
->
-> ## Instructions:
->
-> -   Write only one name suggestion
-> -   The name will be used on the website, business cards, visuals, etc.
-> ```
->
-> `-> {enhancedTitle}` Enhanced title
->
-> ## 👤 Website title approval
->
-> Is the title for your website okay?
->
-> -   DIALOG TEMPLATE
->
-> ```
-> {enhancedTitle}
-> ```
->
-> `-> {title}` Title for the website
->
-> ## 🐰 Cunning subtitle
->
-> -   PERSONA Josh, a copywriter, tasked with creating a claim for the website.
->
-> ```
-> As an experienced copywriter, you have been entrusted with creating a claim for the "{title}" web page.
->
-> A website assignment from a customer:
->
-> > {assigment}
->
-> ## Instructions:
->
-> -   Write only one name suggestion
-> -   Claim will be used on website, business cards, visuals, etc.
-> -   Claim should be punchy, funny, original
-> ```
->
-> `-> {claim}` Claim for the web
->
-> ## 🚦 Keyword analysis
->
-> -   PERSONA Paul, extremely creative SEO specialist.
->
-> ```
-> As an experienced SEO specialist, you have been entrusted with creating keywords for the website "{title}".
->
-> Website assignment from the customer:
->
-> > {assigment}
->
-> ## Instructions:
->
-> -   Write a list of keywords
-> -   Keywords are in basic form
->
-> ## Example:
->
-> -   Ice cream
-> -   Olomouc
-> -   Quality
-> -   Family
-> -   Tradition
-> -   Italy
-> -   Craft
->
-> ```
->
-> `-> {keywords}` Keywords
->
-> ## 🔗 Combine the beginning
->
-> -   SIMPLE TEMPLATE
->
-> ```
->
-> # {title}
->
-> > {claim}
->
-> ```
->
-> `-> {contentBeginning}` Beginning of web content
->
-> ## 🖋 Write the content
->
-> -   PERSONA Jane
->
-> ```
-> As an experienced copywriter and web designer, you have been entrusted with creating text for a new website {title}.
->
-> A website assignment from a customer:
->
-> > {assigment}
->
-> ## Instructions:
->
-> -   Text formatting is in Markdown
-> -   Be concise and to the point
-> -   Use keywords, but they should be naturally in the text
-> -   This is the complete content of the page, so don't forget all the important information and elements the page should contain
-> -   Use headings, bullets, text formatting
->
-> ## Keywords:
->
-> {keywords}
->
-> ## Web Content:
->
-> {contentBeginning}
-> ```
->
-> `-> {contentBody}` Middle of the web content
->
-> ## 🔗 Combine the content
->
-> -   SIMPLE TEMPLATE
->
-> ```markdown
-> {contentBeginning}
->
-> {contentBody}
-> ```
->
-> `-> {websiteContent}`
-
-
-
-Following is the scheme how the promptbook above is executed:
-
-```mermaid
-%% 🔮 Tip: Open this on GitHub or in the VSCode website to see the Mermaid graph visually
-
-flowchart LR
-  subgraph "🌍 Create website content"
-
-      direction TB
-
-      input((Input)):::input
-      templateSpecifyingTheAssigment(👤 Specifying the assigment)
-      input--"{rawAssigment}"-->templateSpecifyingTheAssigment
-      templateImprovingTheTitle(✨ Improving the title)
-      input--"{rawTitle}"-->templateImprovingTheTitle
-      templateSpecifyingTheAssigment--"{assigment}"-->templateImprovingTheTitle
-      templateWebsiteTitleApproval(👤 Website title approval)
-      templateImprovingTheTitle--"{enhancedTitle}"-->templateWebsiteTitleApproval
-      templateCunningSubtitle(🐰 Cunning subtitle)
-      templateWebsiteTitleApproval--"{title}"-->templateCunningSubtitle
-      templateSpecifyingTheAssigment--"{assigment}"-->templateCunningSubtitle
-      templateKeywordAnalysis(🚦 Keyword analysis)
-      templateWebsiteTitleApproval--"{title}"-->templateKeywordAnalysis
-      templateSpecifyingTheAssigment--"{assigment}"-->templateKeywordAnalysis
-      templateCombineTheBeginning(🔗 Combine the beginning)
-      templateWebsiteTitleApproval--"{title}"-->templateCombineTheBeginning
-      templateCunningSubtitle--"{claim}"-->templateCombineTheBeginning
-      templateWriteTheContent(🖋 Write the content)
-      templateWebsiteTitleApproval--"{title}"-->templateWriteTheContent
-      templateSpecifyingTheAssigment--"{assigment}"-->templateWriteTheContent
-      templateKeywordAnalysis--"{keywords}"-->templateWriteTheContent
-      templateCombineTheBeginning--"{contentBeginning}"-->templateWriteTheContent
-      templateCombineTheContent(🔗 Combine the content)
-      templateCombineTheBeginning--"{contentBeginning}"-->templateCombineTheContent
-      templateWriteTheContent--"{contentBody}"-->templateCombineTheContent
-
-      templateCombineTheContent--"{websiteContent}"-->output
-      output((Output)):::output
-
-      classDef input color: grey;
-      classDef output color: grey;
-
-  end;
-```
+-   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.
+
+
+
+## 💙 Book language _(for prompt-engineer)_
+
+Promptbook [pipelines](https://github.com/webgptorg/promptbook/discussions/64) are written in markdown-like language called [Book](https://github.com/webgptorg/book). It is designed to be understandable by non-programmers and non-technical people.
 
--   [More template samples](./samples/pipelines/)
--   [Read more about `.ptbk.md` file format here](https://github.com/webgptorg/promptbook/discussions/categories/concepts?discussions_q=is%3Aopen+label%3A.ptbk.md+category%3AConcepts)
 
-_Note: We are using [postprocessing functions](#postprocessing-functions) like `unwrapResult` that can be used to postprocess the result._
 
-## 📦 Packages
+```markdown
+# 🌟 My first Book
+
+-   PERSONA Jane, marketing specialist with prior experience in writing articles about technology and artificial intelligence
+-   KNOWLEDGE https://ptbk.io
+-   KNOWLEDGE ./promptbook.pdf
+-   EXPECT MIN 1 Sentence
+-   EXPECT MAX 1 Paragraph
+
+> Write an article about the future of artificial intelligence in the next 10 years and how metalanguages will change the way AI is used in the world.
+> Look specifically at the impact of Promptbook on the AI industry.
+
+-> {article}
+```
+
+## 📦 Packages _(for developers)_
 
 This library is divided into several packages, all are published from [single monorepo](https://github.com/webgptorg/promptbook).
 You can install all of them at once:
@@ -479,8 +267,6 @@ Or you can install them separately:
 
 The following glossary is used to clarify certain concepts:
 
-
-
 ### Core concepts
 
 -   [📚 Collection of pipelines](https://github.com/webgptorg/promptbook/discussions/65)
@@ -511,8 +297,8 @@ The following glossary is used to clarify certain concepts:
 
 ## 🔌 Usage in Typescript / Javascript
 
--   [Simple usage](./samples/usage/simple-script)
--   [Usage with client and remote server](./samples/usage/remote)
+-   [Simple usage](./examples/usage/simple-script)
+-   [Usage with client and remote server](./examples/usage/remote)
 
 ## ➕➖ When to use Promptbook?
 

package/esm/index.es.js

@@ -6,7 +6,7 @@ import spaceTrim$1, { spaceTrim } from 'spacetrim';
 /**
  * The version of the Promptbook library
  */
-var PROMPTBOOK_VERSION = '0.72.0-8';
+var PROMPTBOOK_VERSION = '0.72.0';
 // TODO: [main] !!!! List here all the versions and annotate + put into script
 
 /*! *****************************************************************************
@@ -349,10 +349,10 @@ $asDeeplyFrozenSerializableJson('RESERVED_PARAMETER_NAMES', [
     'content',
     'context',
     'knowledge',
-    'samples',
+    'examples',
     'modelName',
     'currentDate',
-    // <- TODO: !!!!! list here all command names
+    // <- TODO: list here all command names
     // <- TODO: Add more like 'date', 'modelName',...
     // <- TODO: Add [emoji] + instructions ACRY when adding new reserved parameter
 ]);
@@ -1362,12 +1362,12 @@ var AzureOpenAiExecutionTools = /** @class */ (function () {
      * Calls OpenAI API to use a chat model.
      */
     AzureOpenAiExecutionTools.prototype.callChatModel = function (prompt) {
-        var _a, _b;
+        var _a, _b, _c;
         return __awaiter(this, void 0, void 0, function () {
             var content, parameters, modelRequirements, client, modelName, modelSettings, rawPromptContent, messages, start, complete, rawRequest, rawResponse, resultContent, usage, error_1;
             var _this = this;
-            return __generator(this, function (_c) {
-                switch (_c.label) {
+            return __generator(this, function (_d) {
+                switch (_d.label) {
                     case 0:
                         if (this.options.isVerbose) {
                             console.info('💬 OpenAI callChatModel call');
@@ -1375,20 +1375,20 @@ var AzureOpenAiExecutionTools = /** @class */ (function () {
                         content = prompt.content, parameters = prompt.parameters, modelRequirements = prompt.modelRequirements;
                         return [4 /*yield*/, this.getClient()];
                     case 1:
-                        client = _c.sent();
+                        client = _d.sent();
                         // TODO: [☂] Use here more modelRequirements
                         if (modelRequirements.modelVariant !== 'CHAT') {
                             throw new PipelineExecutionError('Use callChatModel only for CHAT variant');
                         }
-                        _c.label = 2;
+                        _d.label = 2;
                     case 2:
-                        _c.trys.push([2, 4, , 5]);
+                        _d.trys.push([2, 4, , 5]);
                         modelName = prompt.modelRequirements.modelName || this.options.deploymentName;
                         modelSettings = {
                             maxTokens: modelRequirements.maxTokens,
                             //                                      <- TODO: [🌾] Make some global max cap for maxTokens
                             temperature: modelRequirements.temperature,
-                            user: this.options.user,
+                            user: (_a = this.options.userId) === null || _a === void 0 ? void 0 : _a.toString(),
                             // <- TODO: [🈁] Use `seed` here AND/OR use is `isDeterministic` for entire execution tools
                             // <- Note: [🧆]
                         };
@@ -1419,7 +1419,7 @@ var AzureOpenAiExecutionTools = /** @class */ (function () {
                                 throw error;
                             })];
                     case 3:
-                        rawResponse = _c.sent();
+                        rawResponse = _d.sent();
                         if (this.options.isVerbose) {
                             console.info(colors.bgWhite('rawResponse'), JSON.stringify(rawResponse, null, 4));
                         }
@@ -1438,8 +1438,8 @@ var AzureOpenAiExecutionTools = /** @class */ (function () {
                         complete = getCurrentIsoDate();
                         usage = {
                             price: uncertainNumber() /* <- TODO: [🐞] Compute usage */,
-                            input: __assign({ tokensCount: uncertainNumber((_a = rawResponse.usage) === null || _a === void 0 ? void 0 : _a.promptTokens) }, computeUsageCounts(prompt.content)),
-                            output: __assign({ tokensCount: uncertainNumber((_b = rawResponse.usage) === null || _b === void 0 ? void 0 : _b.completionTokens) }, computeUsageCounts(prompt.content)),
+                            input: __assign({ tokensCount: uncertainNumber((_b = rawResponse.usage) === null || _b === void 0 ? void 0 : _b.promptTokens) }, computeUsageCounts(prompt.content)),
+                            output: __assign({ tokensCount: uncertainNumber((_c = rawResponse.usage) === null || _c === void 0 ? void 0 : _c.completionTokens) }, computeUsageCounts(prompt.content)),
                         };
                         return [2 /*return*/, $asDeeplyFrozenSerializableJson('AzureOpenAiExecutionTools ChatPromptResult', {
                                 content: resultContent,
@@ -1455,7 +1455,7 @@ var AzureOpenAiExecutionTools = /** @class */ (function () {
                                 // <- [🗯]
                             })];
                     case 4:
-                        error_1 = _c.sent();
+                        error_1 = _d.sent();
                         throw this.transformAzureError(error_1);
                     case 5: return [2 /*return*/];
                 }
@@ -1466,12 +1466,12 @@ var AzureOpenAiExecutionTools = /** @class */ (function () {
      * Calls Azure OpenAI API to use a complete model.
      */
     AzureOpenAiExecutionTools.prototype.callCompletionModel = function (prompt) {
-        var _a, _b;
+        var _a, _b, _c;
         return __awaiter(this, void 0, void 0, function () {
             var content, parameters, modelRequirements, client, modelName, modelSettings, start, complete, rawPromptContent, rawRequest, rawResponse, resultContent, usage, error_2;
             var _this = this;
-            return __generator(this, function (_c) {
-                switch (_c.label) {
+            return __generator(this, function (_d) {
+                switch (_d.label) {
                     case 0:
                         if (this.options.isVerbose) {
                             console.info('🖋 OpenAI callCompletionModel call');
@@ -1479,20 +1479,20 @@ var AzureOpenAiExecutionTools = /** @class */ (function () {
                         content = prompt.content, parameters = prompt.parameters, modelRequirements = prompt.modelRequirements;
                         return [4 /*yield*/, this.getClient()];
                     case 1:
-                        client = _c.sent();
+                        client = _d.sent();
                         // TODO: [☂] Use here more modelRequirements
                         if (modelRequirements.modelVariant !== 'COMPLETION') {
                             throw new PipelineExecutionError('Use callCompletionModel only for COMPLETION variant');
                         }
-                        _c.label = 2;
+                        _d.label = 2;
                     case 2:
-                        _c.trys.push([2, 4, , 5]);
+                        _d.trys.push([2, 4, , 5]);
                         modelName = prompt.modelRequirements.modelName || this.options.deploymentName;
                         modelSettings = {
                             maxTokens: modelRequirements.maxTokens || 2000,
                             //                                                  <- TODO: [🌾] Make some global max cap for maxTokens
                             temperature: modelRequirements.temperature,
-                            user: this.options.user,
+                            user: (_a = this.options.userId) === null || _a === void 0 ? void 0 : _a.toString(),
                             // <- TODO: [🈁] Use `seed` here AND/OR use is `isDeterministic` for entire execution tools
                             // <- Note: [🧆]
                         };
@@ -1515,7 +1515,7 @@ var AzureOpenAiExecutionTools = /** @class */ (function () {
                                 throw error;
                             })];
                     case 3:
-                        rawResponse = _c.sent();
+                        rawResponse = _d.sent();
                         if (this.options.isVerbose) {
                             console.info(colors.bgWhite('rawResponse'), JSON.stringify(rawResponse, null, 4));
                         }
@@ -1531,8 +1531,8 @@ var AzureOpenAiExecutionTools = /** @class */ (function () {
                         complete = getCurrentIsoDate();
                         usage = {
                             price: uncertainNumber() /* <- TODO: [🐞] Compute usage */,
-                            input: __assign({ tokensCount: uncertainNumber((_a = rawResponse.usage) === null || _a === void 0 ? void 0 : _a.promptTokens) }, computeUsageCounts(prompt.content)),
-                            output: __assign({ tokensCount: uncertainNumber((_b = rawResponse.usage) === null || _b === void 0 ? void 0 : _b.completionTokens) }, computeUsageCounts(prompt.content)),
+                            input: __assign({ tokensCount: uncertainNumber((_b = rawResponse.usage) === null || _b === void 0 ? void 0 : _b.promptTokens) }, computeUsageCounts(prompt.content)),
+                            output: __assign({ tokensCount: uncertainNumber((_c = rawResponse.usage) === null || _c === void 0 ? void 0 : _c.completionTokens) }, computeUsageCounts(prompt.content)),
                         };
                         return [2 /*return*/, $asDeeplyFrozenSerializableJson('AzureOpenAiExecutionTools CompletionPromptResult', {
                                 content: resultContent,
@@ -1548,7 +1548,7 @@ var AzureOpenAiExecutionTools = /** @class */ (function () {
                                 // <- [🗯]
                             })];
                     case 4:
-                        error_2 = _c.sent();
+                        error_2 = _d.sent();
                         throw this.transformAzureError(error_2);
                     case 5: return [2 /*return*/];
                 }
@@ -1737,7 +1737,7 @@ var $Register = /** @class */ (function () {
         this.storage = globalScope[storageName];
     }
     $Register.prototype.list = function () {
-        // <- TODO: ReadonlyDeep<Array<TRegistered>>
+        // <- TODO: ReadonlyDeep<ReadonlyArray<TRegistered>>
         return this.storage;
     };
     $Register.prototype.register = function (registered) {