@promptbook/remote-server 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/remote-server`
@@ -50,260 +48,48 @@ 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:
@@ -345,8 +131,6 @@ 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)
@@ -377,8 +161,8 @@ 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

@@ -7,7 +7,7 @@ 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
 
 /*! *****************************************************************************
@@ -351,10 +351,10 @@ $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
 ]);
@@ -375,7 +375,7 @@ Object.freeze({
  *
  * @public exported from `@promptbook/core`
  */
-var IS_VERBOSE = false;
+var DEFAULT_IS_VERBOSE = false;
 /**
  * TODO: [🧠][🧜‍♂️] Maybe join remoteUrl and path into single value
  */
@@ -587,8 +587,7 @@ function serializeError(error) {
  * Multiple LLM Execution Tools is a proxy server that uses multiple execution tools internally and exposes the executor interface externally.
  *
  * Note: Internal utility of `joinLlmExecutionTools` but exposed type
- * @public exported from `@promptbook/types`
- * TODO: !!!!!! Export as runtime class not just type
+ * @public exported from `@promptbook/core`
  */
 var MultipleLlmExecutionTools = /** @class */ (function () {
     /**
@@ -987,7 +986,7 @@ 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) {
@@ -1150,7 +1149,7 @@ function $registeredLlmToolsMessage() {
  */
 function createLlmToolsFromConfiguration(configuration, options) {
     if (options === void 0) { options = {}; }
-    var _a = options.isVerbose, isVerbose = _a === void 0 ? IS_VERBOSE : _a;
+    var _a = options.isVerbose, isVerbose = _a === void 0 ? DEFAULT_IS_VERBOSE : _a, userId = options.userId;
     var llmTools = configuration.map(function (llmConfiguration) {
         var registeredItem = $llmToolsRegister
             .list()
@@ -1161,7 +1160,7 @@ function createLlmToolsFromConfiguration(configuration, options) {
         if (registeredItem === undefined) {
             throw new Error(spaceTrim$1(function (block) { return "\n                        There is no constructor for LLM provider `".concat(llmConfiguration.className, "` from `").concat(llmConfiguration.packageName, "`\n\n                        You have probably forgotten install and import the provider package.\n                        To fix this issue, you can:\n\n                        Install:\n\n                        > npm install ").concat(llmConfiguration.packageName, "\n\n                        And import:\n\n                        > import '").concat(llmConfiguration.packageName, "';\n\n\n                        ").concat(block($registeredLlmToolsMessage()), "\n                    "); }));
         }
-        return registeredItem(__assign({ isVerbose: isVerbose }, llmConfiguration.options));
+        return registeredItem(__assign({ isVerbose: isVerbose, userId: userId }, llmConfiguration.options));
     });
     return joinLlmExecutionTools.apply(void 0, __spreadArray([], __read(llmTools), false));
 }
@@ -1186,9 +1185,7 @@ function createLlmToolsFromConfiguration(configuration, options) {
  */
 function startRemoteServer(options) {
     var _this = this;
-    var _a = __assign({ isAnonymousModeAllowed: false, isCollectionModeAllowed: false, collection: null, createLlmExecutionTools: null }, options), port = _a.port, path = _a.path, collection = _a.collection, createLlmExecutionTools = _a.createLlmExecutionTools, 
-    //    <- TODO: [🧠][🤺] Remove `createLlmExecutionTools`, pass just `llmExecutionTools`
-    isAnonymousModeAllowed = _a.isAnonymousModeAllowed, isCollectionModeAllowed = _a.isCollectionModeAllowed, _b = _a.isVerbose, isVerbose = _b === void 0 ? IS_VERBOSE : _b;
+    var _a = __assign({ isAnonymousModeAllowed: false, isApplicationModeAllowed: false, collection: null, createLlmExecutionTools: null }, options), port = _a.port, path = _a.path, collection = _a.collection, createLlmExecutionTools = _a.createLlmExecutionTools, isAnonymousModeAllowed = _a.isAnonymousModeAllowed, isApplicationModeAllowed = _a.isApplicationModeAllowed, _b = _a.isVerbose, isVerbose = _b === void 0 ? DEFAULT_IS_VERBOSE : _b;
     // <- TODO: [🦪] Some helper type to be able to use discriminant union types with destructuring
     var httpServer = http.createServer({}, function (request, response) { return __awaiter(_this, void 0, void 0, function () {
         var _a, _b;
@@ -1206,9 +1203,9 @@ function startRemoteServer(options) {
                             return __generator(this, function (_f) {
                                 switch (_f.label) {
                                     case 0:
-                                        _b = (_a = "\n                    Server for processing promptbook remote requests is running.\n\n                    Version: ".concat(PROMPTBOOK_VERSION, "\n                    Socket.io path: ").concat(path, "/socket.io\n                    Anonymouse mode: ").concat(isAnonymousModeAllowed ? 'enabled' : 'disabled', "\n                    Collection mode: ").concat(isCollectionModeAllowed ? 'enabled' : 'disabled', "\n                    ")).concat;
+                                        _b = (_a = "\n                    Server for processing promptbook remote requests is running.\n\n                    Version: ".concat(PROMPTBOOK_VERSION, "\n                    Socket.io path: ").concat(path, "/socket.io\n                    Anonymouse mode: ").concat(isAnonymousModeAllowed ? 'enabled' : 'disabled', "\n                    Application mode: ").concat(isApplicationModeAllowed ? 'enabled' : 'disabled', "\n                    ")).concat;
                                         _c = block;
-                                        if (!!isCollectionModeAllowed) return [3 /*break*/, 1];
+                                        if (!!isApplicationModeAllowed) return [3 /*break*/, 1];
                                         _d = '';
                                         return [3 /*break*/, 3];
                                     case 1:
@@ -1244,145 +1241,155 @@ function startRemoteServer(options) {
             console.info(colors.gray("Client connected"), socket.id);
         }
         socket.on('prompt-request', function (request) { return __awaiter(_this, void 0, void 0, function () {
-            var _a, isAnonymous, prompt, userId, llmToolsConfiguration, llmExecutionTools, promptResult, _b, error_1;
+            var _a, isAnonymous, prompt, appId, userId, customOptions, llmToolsConfiguration, llmExecutionTools, promptResult, _b, error_1;
             return __generator(this, function (_c) {
                 switch (_c.label) {
                     case 0:
-                        _a = __assign({ userId: null, llmToolsConfiguration: null }, request), isAnonymous = _a.isAnonymous, prompt = _a.prompt, userId = _a.userId, llmToolsConfiguration = _a.llmToolsConfiguration;
+                        _a = __assign({ appId: null, customOptions: undefined, llmToolsConfiguration: null }, request), isAnonymous = _a.isAnonymous, prompt = _a.prompt, appId = _a.appId, userId = _a.userId, customOptions = _a.customOptions, llmToolsConfiguration = _a.llmToolsConfiguration;
                         // <- TODO: [🦪] Some helper type to be able to use discriminant union types with destructuring
                         if (isVerbose) {
                             console.info(colors.bgWhite("Prompt:"), colors.gray(JSON.stringify(request, null, 4)));
                         }
                         _c.label = 1;
                     case 1:
-                        _c.trys.push([1, 14, 15, 16]);
+                        _c.trys.push([1, 15, 16, 17]);
                         if (isAnonymous === true && !isAnonymousModeAllowed) {
                             throw new PipelineExecutionError("Anonymous mode is not allowed"); // <- TODO: [main] !!! Test
                         }
-                        if (isAnonymous === false && !isCollectionModeAllowed) {
-                            throw new PipelineExecutionError("Collection mode is not allowed"); // <- TODO: [main] !!! Test
+                        if (isAnonymous === false && !isApplicationModeAllowed) {
+                            throw new PipelineExecutionError("Application mode is not allowed"); // <- TODO: [main] !!! Test
                         }
                         llmExecutionTools = void 0;
                         if (!(isAnonymous === true && llmToolsConfiguration !== null)) return [3 /*break*/, 2];
                         // Note: Anonymouse mode
                         // TODO: Maybe check that configuration is not empty
                         llmExecutionTools = createLlmToolsFromConfiguration(llmToolsConfiguration, { isVerbose: isVerbose });
-                        return [3 /*break*/, 5];
+                        return [3 /*break*/, 6];
                     case 2:
-                        if (!(isAnonymous === false && createLlmExecutionTools !== null)) return [3 /*break*/, 4];
-                        // Note: Collection mode
-                        llmExecutionTools = createLlmExecutionTools(userId);
-                        return [4 /*yield*/, collection.isResponsibleForPrompt(prompt)];
+                        if (!(isAnonymous === false && createLlmExecutionTools !== null)) return [3 /*break*/, 5];
+                        return [4 /*yield*/, createLlmExecutionTools({
+                                appId: appId,
+                                userId: userId,
+                                customOptions: customOptions,
+                            })];
                     case 3:
+                        // Note: Application mode
+                        llmExecutionTools = _c.sent();
+                        return [4 /*yield*/, collection.isResponsibleForPrompt(prompt)];
+                    case 4:
                         if (!(_c.sent())) {
                             throw new PipelineExecutionError("Pipeline is not in the collection of this server");
                         }
-                        return [3 /*break*/, 5];
-                    case 4: throw new PipelineExecutionError("You must provide either llmToolsConfiguration or non-anonymous mode must be propperly configured");
-                    case 5:
+                        return [3 /*break*/, 6];
+                    case 5: throw new PipelineExecutionError("You must provide either llmToolsConfiguration or non-anonymous mode must be propperly configured");
+                    case 6:
                         promptResult = void 0;
                         _b = prompt.modelRequirements.modelVariant;
                         switch (_b) {
-                            case 'CHAT': return [3 /*break*/, 6];
-                            case 'COMPLETION': return [3 /*break*/, 8];
-                            case 'EMBEDDING': return [3 /*break*/, 10];
+                            case 'CHAT': return [3 /*break*/, 7];
+                            case 'COMPLETION': return [3 /*break*/, 9];
+                            case 'EMBEDDING': return [3 /*break*/, 11];
                         }
-                        return [3 /*break*/, 12];
-                    case 6:
+                        return [3 /*break*/, 13];
+                    case 7:
                         if (llmExecutionTools.callChatModel === undefined) {
                             // Note: [0] This check should not be a thing
                             throw new PipelineExecutionError("Chat model is not available");
                         }
                         return [4 /*yield*/, llmExecutionTools.callChatModel(prompt)];
-                    case 7:
-                        promptResult = _c.sent();
-                        return [3 /*break*/, 13];
                     case 8:
+                        promptResult = _c.sent();
+                        return [3 /*break*/, 14];
+                    case 9:
                         if (llmExecutionTools.callCompletionModel === undefined) {
                             // Note: [0] This check should not be a thing
                             throw new PipelineExecutionError("Completion model is not available");
                         }
                         return [4 /*yield*/, llmExecutionTools.callCompletionModel(prompt)];
-                    case 9:
-                        promptResult = _c.sent();
-                        return [3 /*break*/, 13];
                     case 10:
+                        promptResult = _c.sent();
+                        return [3 /*break*/, 14];
+                    case 11:
                         if (llmExecutionTools.callEmbeddingModel === undefined) {
                             // Note: [0] This check should not be a thing
                             throw new PipelineExecutionError("Embedding model is not available");
                         }
                         return [4 /*yield*/, llmExecutionTools.callEmbeddingModel(prompt)];
-                    case 11:
+                    case 12:
                         promptResult = _c.sent();
-                        return [3 /*break*/, 13];
-                    case 12: throw new PipelineExecutionError("Unknown model variant \"".concat(prompt.modelRequirements.modelVariant, "\""));
-                    case 13:
+                        return [3 /*break*/, 14];
+                    case 13: throw new PipelineExecutionError("Unknown model variant \"".concat(prompt.modelRequirements.modelVariant, "\""));
+                    case 14:
                         if (isVerbose) {
                             console.info(colors.bgGreen("PromptResult:"), colors.green(JSON.stringify(promptResult, null, 4)));
                         }
                         socket.emit('prompt-response', { promptResult: promptResult } /* <- TODO: [🤛] */);
-                        return [3 /*break*/, 16];
-                    case 14:
+                        return [3 /*break*/, 17];
+                    case 15:
                         error_1 = _c.sent();
                         if (!(error_1 instanceof Error)) {
                             throw error_1;
                         }
                         socket.emit('error', serializeError(error_1) /* <- TODO: [🤛] */);
-                        return [3 /*break*/, 16];
-                    case 15:
+                        return [3 /*break*/, 17];
+                    case 16:
                         socket.disconnect();
                         return [7 /*endfinally*/];
-                    case 16: return [2 /*return*/];
+                    case 17: return [2 /*return*/];
                 }
             });
         }); });
         // TODO: [👒] Listing models (and checking configuration) probbably should go through REST API not Socket.io
         socket.on('listModels-request', function (request) { return __awaiter(_this, void 0, void 0, function () {
-            var _a, isAnonymous, llmToolsConfiguration, llmExecutionTools, models, error_2;
+            var _a, isAnonymous, appId, userId, customOptions, llmToolsConfiguration, llmExecutionTools, models, error_2;
             return __generator(this, function (_b) {
                 switch (_b.label) {
                     case 0:
-                        _a = __assign({ llmToolsConfiguration: null }, request), isAnonymous = _a.isAnonymous, llmToolsConfiguration = _a.llmToolsConfiguration;
+                        _a = __assign({ appId: null, customOptions: undefined, llmToolsConfiguration: null }, request), isAnonymous = _a.isAnonymous, appId = _a.appId, userId = _a.userId, customOptions = _a.customOptions, llmToolsConfiguration = _a.llmToolsConfiguration;
                         // <- TODO: [🦪] Some helper type to be able to use discriminant union types with destructuring
                         if (isVerbose) {
                             console.info(colors.bgWhite("Listing models"));
                         }
                         _b.label = 1;
                     case 1:
-                        _b.trys.push([1, 3, 4, 5]);
+                        _b.trys.push([1, 6, 7, 8]);
                         if (isAnonymous === true && !isAnonymousModeAllowed) {
                             throw new PipelineExecutionError("Anonymous mode is not allowed"); // <- TODO: [main] !!! Test
                         }
-                        if (isAnonymous === false && !isCollectionModeAllowed) {
-                            throw new PipelineExecutionError("Collection mode is not allowed"); // <- TODO: [main] !!! Test
+                        if (isAnonymous === false && !isApplicationModeAllowed) {
+                            throw new PipelineExecutionError("Application mode is not allowed"); // <- TODO: [main] !!! Test
                         }
                         llmExecutionTools = void 0;
-                        if (isAnonymous === true) {
-                            // Note: Anonymouse mode
-                            // TODO: Maybe check that configuration is not empty
-                            llmExecutionTools = createLlmToolsFromConfiguration(llmToolsConfiguration, { isVerbose: isVerbose });
-                        }
-                        else {
-                            // Note: Collection mode
-                            llmExecutionTools = createLlmExecutionTools(
-                            /* userId: */ undefined);
-                        }
-                        return [4 /*yield*/, llmExecutionTools.listModels()];
-                    case 2:
+                        if (!(isAnonymous === true)) return [3 /*break*/, 2];
+                        // Note: Anonymouse mode
+                        // TODO: Maybe check that configuration is not empty
+                        llmExecutionTools = createLlmToolsFromConfiguration(llmToolsConfiguration, { isVerbose: isVerbose });
+                        return [3 /*break*/, 4];
+                    case 2: return [4 /*yield*/, createLlmExecutionTools({
+                            appId: appId,
+                            userId: userId,
+                            customOptions: customOptions,
+                        })];
+                    case 3:
+                        // Note: Application mode
+                        llmExecutionTools = _b.sent();
+                        _b.label = 4;
+                    case 4: return [4 /*yield*/, llmExecutionTools.listModels()];
+                    case 5:
                         models = _b.sent();
                         socket.emit('listModels-response', { models: models } /* <- TODO: [🤛] */);
-                        return [3 /*break*/, 5];
-                    case 3:
+                        return [3 /*break*/, 8];
+                    case 6:
                         error_2 = _b.sent();
                         if (!(error_2 instanceof Error)) {
                             throw error_2;
                         }
                         socket.emit('error', serializeError(error_2));
-                        return [3 /*break*/, 5];
-                    case 4:
+                        return [3 /*break*/, 8];
+                    case 7:
                         socket.disconnect();
                         return [7 /*endfinally*/];
-                    case 5: return [2 /*return*/];
+                    case 8: return [2 /*return*/];
                 }
             });
         }); });