@promptbook/types 0.69.0-1 → 0.69.0-11

package/README.md

@@ -65,13 +65,15 @@ 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.
 
@@ -83,7 +85,9 @@ 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.
 
@@ -105,7 +109,6 @@ 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
@@ -400,6 +403,8 @@ 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
@@ -409,6 +414,8 @@ 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)
@@ -421,63 +428,15 @@ 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/typings/src/_packages/core.index.d.ts

@@ -38,13 +38,15 @@ import { PipelineLogicError } from '../errors/PipelineLogicError';
 import { PipelineUrlError } from '../errors/PipelineUrlError';
 import { UnexpectedError } from '../errors/UnexpectedError';
 import { assertsExecutionSuccessful } from '../execution/assertsExecutionSuccessful';
-import { createPipelineExecutor } from '../execution/createPipelineExecutor';
+import { createPipelineExecutor } from '../execution/createPipelineExecutor/00-createPipelineExecutor';
 import { embeddingVectorToString } from '../execution/embeddingVectorToString';
 import { ZERO_USAGE } from '../execution/utils/addUsage';
 import { addUsage } from '../execution/utils/addUsage';
 import { isPassingExpectations } from '../execution/utils/checkExpectations';
 import { usageToHuman } from '../execution/utils/usageToHuman';
 import { usageToWorktime } from '../execution/utils/usageToWorktime';
+import { CsvFormatDefinition } from '../formats/csv/CsvFormatDefinition';
+import { TextFormatDefinition } from '../formats/text/TextFormatDefinition';
 import { CallbackInterfaceTools } from '../knowledge/dialogs/callback/CallbackInterfaceTools';
 import type { CallbackInterfaceToolsOptions } from '../knowledge/dialogs/callback/CallbackInterfaceToolsOptions';
 import { prepareKnowledgePieces } from '../knowledge/prepare-knowledge/_common/prepareKnowledgePieces';
@@ -118,6 +120,8 @@ export { addUsage };
 export { isPassingExpectations };
 export { usageToHuman };
 export { usageToWorktime };
+export { CsvFormatDefinition };
+export { TextFormatDefinition };
 export { CallbackInterfaceTools };
 export type { CallbackInterfaceToolsOptions };
 export { prepareKnowledgePieces };

package/esm/typings/src/_packages/types.index.d.ts

@@ -7,6 +7,7 @@ import type { PipelineTemplateCommandParser } from '../commands/_common/types/Co
 import type { CommandParserInput } from '../commands/_common/types/CommandParser';
 import type { CommandUsagePlace } from '../commands/_common/types/CommandUsagePlaces';
 import type { ExpectCommand } from '../commands/EXPECT/ExpectCommand';
+import type { ForeachJson } from '../commands/FOREACH/ForeachJson';
 import type { FormatCommand } from '../commands/FORMAT/FormatCommand';
 import type { TemplateType } from '../commands/TEMPLATE/TemplateTypes';
 import type { PipelineStringToJsonOptions } from '../conversion/pipelineStringToJson';
@@ -15,6 +16,8 @@ import type { renderPipelineMermaidOptions } from '../conversion/prettify/render
 import type { ErrorJson } from '../errors/utils/ErrorJson';
 import type { AvailableModel } from '../execution/AvailableModel';
 import type { CommonExecutionToolsOptions } from '../execution/CommonExecutionToolsOptions';
+import type { CreatePipelineExecutorOptions } from '../execution/createPipelineExecutor/00-CreatePipelineExecutorOptions';
+import type { CreatePipelineExecutorSettings } from '../execution/createPipelineExecutor/00-CreatePipelineExecutorSettings';
 import type { EmbeddingVector } from '../execution/EmbeddingVector';
 import type { ExecutionTools } from '../execution/ExecutionTools';
 import type { LlmExecutionTools } from '../execution/LlmExecutionTools';
@@ -32,6 +35,7 @@ import type { ScriptExecutionToolsExecuteOptions } from '../execution/ScriptExec
 import type { UncertainNumber } from '../execution/UncertainNumber';
 import type { UserInterfaceTools } from '../execution/UserInterfaceTools';
 import type { UserInterfaceToolsPromptDialogOptions } from '../execution/UserInterfaceTools';
+import type { FormatSubvalueDefinition } from '../formats/_common/FormatSubvalueDefinition';
 import type { CallbackInterfaceToolsOptions } from '../knowledge/dialogs/callback/CallbackInterfaceToolsOptions';
 import type { LlmToolsConfiguration } from '../llm-providers/_common/LlmToolsConfiguration';
 import type { LlmToolsMetadata } from '../llm-providers/_common/LlmToolsMetadata';
@@ -232,6 +236,7 @@ export type { PipelineTemplateCommandParser };
 export type { CommandParserInput };
 export type { CommandUsagePlace };
 export type { ExpectCommand };
+export type { ForeachJson };
 export type { FormatCommand };
 export type { TemplateType };
 export type { PipelineStringToJsonOptions };
@@ -240,6 +245,8 @@ export type { renderPipelineMermaidOptions };
 export type { ErrorJson };
 export type { AvailableModel };
 export type { CommonExecutionToolsOptions };
+export type { CreatePipelineExecutorOptions };
+export type { CreatePipelineExecutorSettings };
 export type { EmbeddingVector };
 export type { ExecutionTools };
 export type { LlmExecutionTools };
@@ -257,6 +264,7 @@ export type { ScriptExecutionToolsExecuteOptions };
 export type { UncertainNumber };
 export type { UserInterfaceTools };
 export type { UserInterfaceToolsPromptDialogOptions };
+export type { FormatSubvalueDefinition };
 export type { CallbackInterfaceToolsOptions };
 export type { LlmToolsConfiguration };
 export type { LlmToolsMetadata };

package/esm/typings/src/_packages/utils.index.d.ts

@@ -20,7 +20,6 @@ import { splitIntoSentences } from '../utils/expectation-counters/countSentences
 import { countSentences } from '../utils/expectation-counters/countSentences';
 import { countWords } from '../utils/expectation-counters/countWords';
 import { CountUtils } from '../utils/expectation-counters/index';
-import { extractParameterNames } from '../utils/extractParameterNames';
 import { capitalize } from '../utils/normalization/capitalize';
 import { decapitalize } from '../utils/normalization/decapitalize';
 import { DIACRITIC_VARIANTS_LETTERS } from '../utils/normalization/DIACRITIC_VARIANTS_LETTERS';
@@ -43,11 +42,12 @@ import { parseKeywords } from '../utils/normalization/parseKeywords';
 import { parseKeywordsFromString } from '../utils/normalization/parseKeywordsFromString';
 import { removeDiacritics } from '../utils/normalization/removeDiacritics';
 import { searchKeywords } from '../utils/normalization/searchKeywords';
+import { extractParameterNames } from '../utils/parameters/extractParameterNames';
+import { replaceParameters } from '../utils/parameters/replaceParameters';
 import { parseNumber } from '../utils/parseNumber';
 import { $randomSeed } from '../utils/random/$randomSeed';
 import { removeEmojis } from '../utils/removeEmojis';
 import { removeQuotes } from '../utils/removeQuotes';
-import { replaceParameters } from '../utils/replaceParameters';
 import { $deepFreeze } from '../utils/serialization/$deepFreeze';
 import { checkSerializableAsJson } from '../utils/serialization/checkSerializableAsJson';
 import { clonePipeline } from '../utils/serialization/clonePipeline';
@@ -91,7 +91,6 @@ export { splitIntoSentences };
 export { countSentences };
 export { countWords };
 export { CountUtils };
-export { extractParameterNames };
 export { capitalize };
 export { decapitalize };
 export { DIACRITIC_VARIANTS_LETTERS };
@@ -114,11 +113,12 @@ export { parseKeywords };
 export { parseKeywordsFromString };
 export { removeDiacritics };
 export { searchKeywords };
+export { extractParameterNames };
+export { replaceParameters };
 export { parseNumber };
 export { $randomSeed };
 export { removeEmojis };
 export { removeQuotes };
-export { replaceParameters };
 export { $deepFreeze };
 export { checkSerializableAsJson };
 export { clonePipeline };

package/esm/typings/src/commands/FOREACH/ForeachCommand.d.ts

@@ -1,5 +1,4 @@
-import type { string_parameter_name } from '../../types/typeAliases';
-import type { TODO_string } from '../../utils/organization/TODO_string';
+import type { ForeachJson } from './ForeachJson';
 /**
  * Parsed FOREACH command <- Write [🍭] !!!!!!
  *
@@ -8,7 +7,4 @@ import type { TODO_string } from '../../utils/organization/TODO_string';
  */
 export type ForeachCommand = {
     readonly type: 'FOREACH';
-    formatName: TODO_string;
-    cellName: TODO_string;
-    parameterName: string_parameter_name;
-};
+} & ForeachJson;

package/esm/typings/src/commands/FOREACH/ForeachJson.d.ts

@@ -0,0 +1,26 @@
+import type { string_parameter_name } from '../../types/typeAliases';
+import type { TODO_string } from '../../utils/organization/TODO_string';
+/**
+ * @@@
+ */
+export type ForeachJson = {
+    /**
+     * @@@
+     */
+    readonly formatName: TODO_string;
+    /**
+     * @@@
+     */
+    readonly cellName: TODO_string;
+    /**
+     * @@@
+     */
+    readonly parameterName: string_parameter_name;
+    /**
+     * @@@
+     */
+    readonly subparameterNames: Array<string_parameter_name>;
+};
+/**
+ * TODO: [🧠][🦥] Better (less confusing) name for "cell" / "subvalue" / "subparameter"
+ */

package/esm/typings/src/commands/FOREACH/foreachCommand.test.d.ts

@@ -1 +1,4 @@
 export {};
+/**
+ * TODO: [🧠][🦥] Better (less confusing) name for "cell" / "subvalue" / "subparameter"
+ */

package/esm/typings/src/commands/FOREACH/foreachCommandParser.d.ts

@@ -10,6 +10,7 @@ import type { ForeachCommand } from './ForeachCommand';
  */
 export declare const foreachCommandParser: PipelineTemplateCommandParser<ForeachCommand>;
 /**
- * TODO: !!!!!! Comment console logs
+ * TODO: !!!!!! Remove console logs
+ * TODO: [🧠][🦥] Better (less confusing) name for "cell" / "subvalue" / "subparameter"
  * TODO: [🍭] !!!!!! Make .ptbk.md file with examples of the FOREACH command and also with wrong parsing and logic
  */

package/esm/typings/src/commands/_common/types/CommandParser.d.ts

@@ -156,28 +156,28 @@ export type CommandParserInput = {
      * @@@
      *
      * @example 'promptbook version 0.62.0'
-     * @example 'FOREACH List Line -> `{customer}`'
+     * @example 'FOREACH Text Line `{customers}` -> `{customer}`'
      */
     readonly raw: string_markdown_text;
     /**
      * @@@
      *
      * @example '0.62.0'
-     * @example 'List Line -> `{customer}`'
+     * @example 'List Line `{customers}` -> `{customer}`'
      */
     readonly rawArgs: string_markdown_text;
     /**
      * @@@
      *
      * @example 'PROMPTBOOK_VERSION_0_62_0'
-     * @example 'FOREACH_LIST_LINE_CUSTOMER'
+     * @example 'FOREACH_LIST_LINE_CUSTOMERS_CUSTOMER'
      */
     readonly normalized: string_name & string_SCREAMING_CASE;
     /**
      * @@@
      *
      * @example [ '0.62.0' ]
-     * @example [ 'List', 'Line', '', '{customer}' ]
+     * @example [ 'List', 'Line', '{customers}', '', '{customer}' ]
      */
     readonly args: Array<string_name>;
 };

package/esm/typings/src/config.d.ts

@@ -148,7 +148,13 @@ export declare const IS_VERBOSE = false;
  *
  * @private within the repository
  */
-export declare const DEBUG_ALLOW_PAYED_TESTING: boolean;
+export declare const IS_PIPELINE_LOGIC_VALIDATED: boolean;
+/**
+ * @@@
+ *
+ * @private within the repository
+ */
+export declare const IS_COST_PREVENTED: boolean;
 /**
  * TODO: [🧠][🧜‍♂️] Maybe join remoteUrl and path into single value
  */

package/esm/typings/src/conversion/prettify/renderPipelineMermaidOptions.d.ts

@@ -22,6 +22,9 @@ export type renderPipelineMermaidOptions = {
  */
 export declare function renderPromptbookMermaid(pipelineJson: PipelineJson, options?: renderPipelineMermaidOptions): string;
 /**
+ * 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
  */

package/esm/typings/src/conversion/utils/extractParameterNamesFromTemplate.d.ts

@@ -1,3 +1,4 @@
+import type { ReadonlyDeep } from 'type-fest';
 import type { TemplateJson } from '../../types/PipelineJson/TemplateJson';
 import type { string_parameter_name } from '../../types/typeAliases';
 /**
@@ -8,7 +9,7 @@ import type { string_parameter_name } from '../../types/typeAliases';
  * @throws {ParseError} if the script is invalid
  * @public exported from `@promptbook/utils`
  */
-export declare function extractParameterNamesFromTemplate(template: Pick<TemplateJson, 'title' | 'description' | 'templateType' | 'content' | 'preparedContent' | 'jokerParameterNames'>): Set<string_parameter_name>;
+export declare function extractParameterNamesFromTemplate(template: ReadonlyDeep<Pick<TemplateJson, 'title' | 'description' | 'templateType' | 'content' | 'preparedContent' | 'jokerParameterNames' | 'foreach'>>): Set<string_parameter_name>;
 /**
  * TODO: [🔣] If script require contentLanguage
  */

package/esm/typings/src/conversion/validation/validatePipeline.d.ts

@@ -16,6 +16,11 @@ import type { PipelineJson } from '../../types/PipelineJson/PipelineJson';
  */
 export declare function validatePipeline(pipeline: PipelineJson): PipelineJson;
 /**
+ * @private internal function for `validatePipeline`
+ */
+export declare function validatePipelineCore(pipeline: PipelineJson): void;
+/**
+ * TODO: !!!!!! [🧞‍♀️] Do not allow joker + foreach
  * TODO: [🧠] Work with promptbookVersion
  * TODO: Use here some json-schema, Zod or something similar and change it to:
  *     > /**

package/esm/typings/src/execution/PipelineExecutorResult.d.ts

@@ -1,7 +1,8 @@
+import { ReadonlyDeep } from 'type-fest';
+import type { ErrorJson } from '../errors/utils/ErrorJson';
 import type { ExecutionReportJson } from '../types/execution-report/ExecutionReportJson';
-import type { Parameters } from '../types/typeAliases';
 import type { PipelineJson } from '../types/PipelineJson/PipelineJson';
-import type { ErrorJson } from '../errors/utils/ErrorJson';
+import type { Parameters } from '../types/typeAliases';
 import type { PromptResultUsage } from './PromptResultUsage';
 /**
  * @@@
@@ -41,9 +42,10 @@ export type PipelineExecutorResult = {
      * Note: If you called `createPipelineExecutor` with fully prepared pipeline, this is the same object as this pipeline
      *       If you passed not fully prepared pipeline, this is same pipeline but fully prepared
      */
-    readonly preparedPipeline: PipelineJson;
+    readonly preparedPipeline: ReadonlyDeep<PipelineJson>;
 };
 /**
+ * TODO: !!!!!! Maybe add ReadonlyDeep< to all
  * TODO: [🧠] Should this file be in /execution or /types folder?
  * TODO: [🧠] Maybe constrain `ErrorJson` -> `ErrorJson & { name: 'PipelineExecutionError' | 'Error' }`
  */

package/esm/typings/src/execution/createPipelineExecutor/$OngoingTemplateResult.d.ts

@@ -0,0 +1,21 @@
+import { ExpectError } from '../../errors/ExpectError';
+import type { Prompt } from '../../types/Prompt';
+import type { ChatPromptResult } from '../PromptResult';
+import type { CompletionPromptResult } from '../PromptResult';
+import type { EmbeddingPromptResult } from '../PromptResult';
+import type { PromptResult } from '../PromptResult';
+/**
+ * @@@
+ *
+ * @private internal utility of `createPipelineExecutor`
+ */
+export type $OngoingTemplateResult = {
+    $prompt?: Prompt;
+    $chatResult?: ChatPromptResult;
+    $completionResult?: CompletionPromptResult;
+    $embeddingResult?: EmbeddingPromptResult;
+    $result: PromptResult | null;
+    $resultString: string | null;
+    $expectError: ExpectError | null;
+    $scriptPipelineExecutionErrors: Array<Error>;
+};

package/esm/typings/src/execution/createPipelineExecutor/00-CreatePipelineExecutorOptions.d.ts

@@ -0,0 +1,20 @@
+import type { PipelineJson } from '../../types/PipelineJson/PipelineJson';
+import type { ExecutionTools } from '../ExecutionTools';
+import type { CreatePipelineExecutorSettings } from './00-CreatePipelineExecutorSettings';
+/**
+ * Options for `createPipelineExecutor`
+ */
+export interface CreatePipelineExecutorOptions {
+    /**
+     * The pipeline to be executed
+     */
+    readonly pipeline: PipelineJson;
+    /**
+     * The execution tools to be used during the execution of the pipeline
+     */
+    readonly tools: ExecutionTools;
+    /**
+     * Optional settings for the pipeline executor
+     */
+    readonly settings?: Partial<CreatePipelineExecutorSettings>;
+}

package/esm/typings/src/execution/createPipelineExecutor/00-CreatePipelineExecutorSettings.d.ts

@@ -0,0 +1,33 @@
+export type CreatePipelineExecutorSettings = {
+    /**
+     * When executor does not satisfy expectations it will be retried this amount of times
+     *
+     * @default MAX_EXECUTION_ATTEMPTS
+     */
+    readonly maxExecutionAttempts: number;
+    /**
+     * Maximum number of tasks running in parallel
+     *
+     * @default MAX_PARALLEL_COUNT
+     */
+    readonly maxParallelCount: number;
+    /**
+     * If true, the preparation logs additional information
+     *
+     * @default false
+     */
+    readonly isVerbose: boolean;
+    /**
+     * If you pass fully prepared pipeline, this does not matter
+     *
+     * Otherwise:
+     * If false or not set, warning is shown when pipeline is not prepared
+     * If true, warning is suppressed
+     *
+     * @default false
+     */
+    readonly isNotPreparedWarningSupressed: boolean;
+};
+/**
+ * TODO: [🤹‍♂️] More granular setting for limits of execution + better waiting for queue
+ */

package/esm/typings/src/execution/createPipelineExecutor/00-createPipelineExecutor.d.ts

@@ -0,0 +1,10 @@
+import type { PipelineExecutor } from '../PipelineExecutor';
+import type { CreatePipelineExecutorOptions } from './00-CreatePipelineExecutorOptions';
+/**
+ * Creates executor function from pipeline and execution tools.
+ *
+ * @returns The executor function
+ * @throws {PipelineLogicError} on logical error in the pipeline
+ * @public exported from `@promptbook/core`
+ */
+export declare function createPipelineExecutor(options: CreatePipelineExecutorOptions): PipelineExecutor;

package/esm/typings/src/execution/createPipelineExecutor/10-executePipeline.d.ts

@@ -0,0 +1,55 @@
+import type { Promisable, ReadonlyDeep } from 'type-fest';
+import type { PipelineJson } from '../../types/PipelineJson/PipelineJson';
+import type { TaskProgress } from '../../types/TaskProgress';
+import type { Parameters } from '../../types/typeAliases';
+import type { ExecutionTools } from '../ExecutionTools';
+import type { PipelineExecutorResult } from '../PipelineExecutorResult';
+import type { CreatePipelineExecutorSettings } from './00-CreatePipelineExecutorSettings';
+/**
+ * @@@
+ *
+ * @private internal type of `executePipelinex`
+ */
+type ExecutePipelineOptions = {
+    /**
+     * @@@
+     */
+    readonly inputParameters: Readonly<Parameters>;
+    /**
+     * @@@
+     */
+    readonly tools: ExecutionTools;
+    /**
+     * @@@
+     */
+    readonly onProgress?: (taskProgress: TaskProgress) => Promisable<void>;
+    /**
+     * @@@
+     */
+    readonly pipeline: PipelineJson;
+    /**
+     * @@@
+     */
+    readonly preparedPipeline: ReadonlyDeep<PipelineJson>;
+    /**
+     * @@@
+     */
+    readonly setPreparedPipeline: (preparedPipeline: ReadonlyDeep<PipelineJson>) => void;
+    /**
+     * @@@
+     */
+    readonly pipelineIdentification: string;
+    /**
+     * Settings for the pipeline executor
+     */
+    readonly settings: CreatePipelineExecutorSettings;
+};
+/**
+ * @@@
+ *
+ * Note: This is not a `PipelineExecutor` (which is binded with one exact pipeline), but a utility function of `createPipelineExecutor` which creates `PipelineExecutor`
+ *
+ * @private internal utility of `createPipelineExecutor`
+ */
+export declare function executePipeline(options: ExecutePipelineOptions): Promise<PipelineExecutorResult>;
+export {};

package/esm/typings/src/execution/createPipelineExecutor/20-executeTemplate.d.ts

@@ -0,0 +1,62 @@
+import { Promisable, ReadonlyDeep } from 'type-fest';
+import { MultipleLlmExecutionTools } from '../../llm-providers/multiple/MultipleLlmExecutionTools';
+import type { ExecutionReportJson } from '../../types/execution-report/ExecutionReportJson';
+import type { PipelineJson } from '../../types/PipelineJson/PipelineJson';
+import type { TemplateJson } from '../../types/PipelineJson/TemplateJson';
+import type { TaskProgress } from '../../types/TaskProgress';
+import type { Parameters } from '../../types/typeAliases';
+import type { ExecutionTools } from '../ExecutionTools';
+import type { CreatePipelineExecutorSettings } from './00-CreatePipelineExecutorSettings';
+/**
+ * @@@
+ *
+ * @private internal type of `executeTemplate`
+ */
+type executeSingleTemplateOptions = {
+    /**
+     * @@@
+     */
+    readonly currentTemplate: ReadonlyDeep<TemplateJson>;
+    /**
+     * @@@
+     */
+    readonly preparedPipeline: ReadonlyDeep<PipelineJson>;
+    /**
+     * @@@
+     */
+    readonly parametersToPass: Readonly<Parameters>;
+    /**
+     * @@@
+     */
+    readonly tools: Omit<ExecutionTools, 'llm'>;
+    /**
+     * @@@
+     */
+    readonly llmTools: MultipleLlmExecutionTools;
+    /**
+     * @@@
+     */
+    readonly onProgress: (taskProgress: TaskProgress) => Promisable<void>;
+    /**
+     * Settings for the pipeline executor
+     */
+    readonly settings: CreatePipelineExecutorSettings;
+    /**
+     * @@@
+     */
+    readonly $executionReport: ExecutionReportJson;
+    /**
+     * @@@
+     */
+    readonly pipelineIdentification: string;
+};
+/**
+ * @@@
+ *
+ * @private internal utility of `createPipelineExecutor`
+ */
+export declare function executeTemplate(options: executeSingleTemplateOptions): Promise<Readonly<Parameters>>;
+export {};
+/**
+ * TODO: [🤹‍♂️]
+ */

package/esm/typings/src/execution/createPipelineExecutor/30-executeFormatCells.d.ts

@@ -0,0 +1,21 @@
+import type { TODO_any } from '../../utils/organization/TODO_any';
+import type { ExecuteAttemptsOptions } from './40-executeAttempts';
+/**
+ * @@@
+ *
+ * @private internal type of `executeFormatCells`
+ */
+type ExecuteFormatCellsOptions = ExecuteAttemptsOptions;
+/**
+ * @@@
+ *
+ * @private internal utility of `createPipelineExecutor`
+ */
+export declare function executeFormatCells(options: ExecuteFormatCellsOptions): Promise<TODO_any>;
+export {};
+/**
+ * TODO: !!!!!! Make pipelineIdentification more precise
+ * TODO: !!!!!! How FOREACH execution looks in the report
+ * TODO: [🧠][🦥] Better (less confusing) name for "cell" / "subvalue" / "subparameter"
+ * TODO: []
+ */