Package Exports

@promptbook/openai
@promptbook/openai/esm/index.es.js
@promptbook/openai/umd/index.umd.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@promptbook/openai) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

✨ Promptbook: AI Agents

Turn your company's scattered knowledge into AI ready Books

[](https://www.npmjs.com/package/promptbook) [ Quality of package ![Promptbook logo](./design/logo-h1.png) Promptbook ](https://packagequality.com/#?package=promptbook)

🌟 New Features

Gemini 3 Support

⚠ Warning: This is a pre-release version of the library. It is not yet ready for production use. Please look at latest stable release.

📦 Package `@promptbook/openai`

Promptbooks are divided into several packages, all are published from single monorepo.
This package @promptbook/openai is one part of the promptbook ecosystem.

To install this package, run:

# Install entire promptbook ecosystem
npm i ptbk

# Install just this package to save space
npm install @promptbook/openai

OpenAI integration for Promptbook, providing execution tools for OpenAI GPT models, OpenAI Assistants, and OpenAI-compatible APIs within the Promptbook ecosystem.

🎯 Purpose and Motivation

This package bridges the gap between Promptbook's unified pipeline execution system and OpenAI's powerful language models. It provides a standardized interface for accessing OpenAI's various services while maintaining compatibility with Promptbook's execution framework, enabling seamless integration with different OpenAI offerings.

🔧 High-Level Functionality

The package offers three main integration paths:

Standard OpenAI API: Direct integration with OpenAI's chat completions and embeddings
OpenAI Assistants: Integration with OpenAI's Assistant API (GPTs)
OpenAI-Compatible APIs: Support for third-party APIs that follow OpenAI's interface
Model Management: Automatic model selection and configuration
Usage Tracking: Built-in monitoring for tokens and costs

✨ Key Features

🤖 Multiple OpenAI Integrations - Support for standard API, Assistants, and compatible services
🔄 Seamless Provider Switching - Easy integration with other LLM providers
🎯 Model Selection - Access to all available OpenAI models with automatic selection
🔧 Configuration Flexibility - Support for custom endpoints, API keys, and parameters
📊 Usage Tracking - Built-in token usage and cost monitoring
🛡️ Error Handling - Comprehensive error handling and retry logic
🚀 Performance Optimization - Caching and request optimization
🔌 OpenAI-Compatible Server - Use Promptbook books as OpenAI-compatible models

🧡 Usage

import { createPipelineExecutor } from '@promptbook/core';
import {
    createPipelineCollectionFromDirectory,
    $provideExecutionToolsForNode,
    $provideFilesystemForNode,
    $provideScrapersForNode,
    $provideScriptingForNode,
} from '@promptbook/node';
import { JavascriptExecutionTools } from '@promptbook/javascript';
import { OpenAiExecutionTools } from '@promptbook/openai';

// 🛠 Prepare the tools that will be used to compile and run your books
// Note: Here you can allow or deny some LLM providers, such as not providing DeepSeek for privacy reasons
const fs = $provideFilesystemForNode();
const llm = new OpenAiExecutionTools(
    //            <- TODO: [🧱] Implement in a functional (not new Class) way
    {
        isVerbose: true,
        apiKey: process.env.OPENAI_API_KEY,
    },
);
const executables = await $provideExecutablesForNode();
const tools = {
    llm,
    fs,
    scrapers: await $provideScrapersForNode({ fs, llm, executables }),
    script: await $provideScriptingForNode({}),
};

// ▶ Create whole pipeline collection
const collection = await createPipelineCollectionFromDirectory('./books', tools);

// ▶ Get single Pipeline
const pipeline = await collection.getPipelineByUrl(`https://promptbook.studio/my-collection/write-article.book`);

// ▶ Create executor - the function that will execute the Pipeline
const pipelineExecutor = createPipelineExecutor({ pipeline, tools });

// ▶ Prepare input parameters
const inputParameters = { word: 'cat' };

// 🚀▶ Execute the Pipeline
const result = await pipelineExecutor(inputParameters).asPromise({ isCrashedOnError: true });

// ▶ Handle the result
const { isSuccessful, errors, outputParameters, executionReport } = result;
console.info(outputParameters);

🤺 Usage with OpenAI's Assistants (GPTs)

TODO: Write a guide how to use OpenAI's Assistants with Promptbook

🧙‍♂️ Wizard

Run books without any settings, boilerplate or struggle in Node.js:

import { wizard } from '@promptbook/wizard';

const {
    outputParameters: { joke },
} = await wizard.execute(`https://github.com/webgptorg/book/blob/main/books/templates/generic.book`, {
    topic: 'Prague',
});

console.info(joke);

🧙‍♂️ Connect to LLM providers automatically

You can just use $provideExecutionToolsForNode function to create all required tools from environment variables like ANTHROPIC_CLAUDE_API_KEY and OPENAI_API_KEY automatically.

import { createPipelineExecutor, createPipelineCollectionFromDirectory } from '@promptbook/core';
import { JavascriptExecutionTools } from '@promptbook/javascript';
import { $provideExecutionToolsForNode } from '@promptbook/node';
import { $provideFilesystemForNode } from '@promptbook/node';

// 🛠 Prepare the tools that will be used to compile and run your books
// Note: Here you can allow or deny some LLM providers, such as not providing DeepSeek for privacy reasons
const tools = await $provideExecutionToolsForNode();

// ▶ Create whole pipeline collection
const collection = await createPipelineCollectionFromDirectory('./books', tools);

// ▶ Get single Pipeline
const pipeline = await collection.getPipelineByUrl(`https://promptbook.studio/my-collection/write-article.book`);

// ▶ Create executor - the function that will execute the Pipeline
const pipelineExecutor = createPipelineExecutor({ pipeline, tools });

// ▶ Prepare input parameters
const inputParameters = { word: 'dog' };

// 🚀▶ Execute the Pipeline
const result = await pipelineExecutor(inputParameters).asPromise({ isCrashedOnError: true });

// ▶ Handle the result
const { isSuccessful, errors, outputParameters, executionReport } = result;
console.info(outputParameters);

💕 Usage of multiple LLM providers

You can use multiple LLM providers in one Promptbook execution. The best model will be chosen automatically according to the prompt and the model's capabilities.

import { createPipelineExecutor } from '@promptbook/core';
import {
    createPipelineCollectionFromDirectory,
    $provideExecutionToolsForNode,
    $provideFilesystemForNode,
} from '@promptbook/node';
import { JavascriptExecutionTools } from '@promptbook/javascript';
import { OpenAiExecutionTools } from '@promptbook/openai';
import { AnthropicClaudeExecutionTools } from '@promptbook/anthropic-claude';
import { AzureOpenAiExecutionTools } from '@promptbook/azure-openai';

// ▶ Prepare multiple tools
const fs = $provideFilesystemForNode();
const llm = [
    // Note: You can use multiple LLM providers in one Promptbook execution.
    //       The best model will be chosen automatically according to the prompt and the model's capabilities.
    new OpenAiExecutionTools(
        //            <- TODO: [🧱] Implement in a functional (not new Class) way
        {
            apiKey: process.env.OPENAI_API_KEY,
        },
    ),
    new AnthropicClaudeExecutionTools(
        //            <- TODO: [🧱] Implement in a functional (not new Class) way
        {
            apiKey: process.env.ANTHROPIC_CLAUDE_API_KEY,
        },
    ),
    new AzureOpenAiExecutionTools(
        //            <- TODO: [🧱] Implement in a functional (not new Class) way
        {
            resourceName: process.env.AZUREOPENAI_RESOURCE_NAME,
            deploymentName: process.env.AZUREOPENAI_DEPLOYMENT_NAME
            apiKey: process.env.AZUREOPENAI_API_KEY,
        },
    ),
];
const executables = await $provideExecutablesForNode();
const tools = {
    llm,
    fs,
    scrapers: await $provideScrapersForNode({ fs, llm, executables }),
    script: await $provideScriptingForNode({}),
};

// ▶ Create whole pipeline collection
const collection = await createPipelineCollectionFromDirectory('./books', tools);

// ▶ Get single Pipeline
const pipeline = await collection.getPipelineByUrl(`https://promptbook.studio/my-collection/write-article.book`);

// ▶ Create executor - the function that will execute the Pipeline
const pipelineExecutor = createPipelineExecutor({ pipeline, tools });

// ▶ Prepare input parameters
const inputParameters = { word: 'dog' };

// 🚀▶ Execute the Pipeline
const result = await pipelineExecutor(inputParameters).asPromise({ isCrashedOnError: true });

// ▶ Handle the result
const { isSuccessful, errors, outputParameters, executionReport } = result;
console.info(outputParameters);

💙 Integration with other models

See the other model integrations:

🤖 Using Promptbook as an OpenAI-compatible model

You can use Promptbook books as if they were OpenAI models by using the OpenAI-compatible endpoint. This allows you to use the standard OpenAI SDK with Promptbook books.

First, start the Promptbook server:

import { startRemoteServer } from '@promptbook/remote-server';

// Start the server
await startRemoteServer({
    port: 3000,
    collection: await createPipelineCollectionFromDirectory('./books'),
    isAnonymousModeAllowed: true,
    isApplicationModeAllowed: true,
});

Then use the standard OpenAI SDK with the server URL:

import OpenAI from 'openai';

// Create OpenAI client pointing to your Promptbook server
const openai = new OpenAI({
    baseURL: 'http://localhost:3000', // Your Promptbook server URL
    apiKey: 'not-needed', // API key is not needed for Promptbook
});

// Use any Promptbook book as a model
const response = await openai.chat.completions.create({
    model: 'https://promptbook.studio/my-collection/write-article.book', // Book URL as model name
    messages: [
        {
            role: 'user',
            content: 'Write a short story about a cat',
        },
    ],
});

console.log(response.choices[0].message.content);

This allows you to:

Use Promptbook books with any OpenAI-compatible client
Integrate Promptbook into existing OpenAI-based applications
Use Promptbook books as models in other AI frameworks

📦 Exported Entities

Version Information

BOOK_LANGUAGE_VERSION - Current book language version
PROMPTBOOK_ENGINE_VERSION - Current engine version

Execution Tools Creation Functions

createOpenAiAssistantExecutionTools - Create OpenAI Assistant execution tools
createOpenAiCompatibleExecutionTools - Create OpenAI-compatible execution tools
createOpenAiExecutionTools - Create standard OpenAI execution tools

Model Information

OPENAI_MODELS - Available OpenAI models configuration

Execution Tools Classes

OpenAiAssistantExecutionTools - OpenAI Assistant execution tools class
OpenAiCompatibleExecutionTools - OpenAI-compatible execution tools class
OpenAiExecutionTools - Standard OpenAI execution tools class

Configuration Types

OpenAiAssistantExecutionToolsOptions - Configuration options for OpenAI Assistant tools (type)
OpenAiCompatibleExecutionToolsOptions - Configuration options for OpenAI-compatible tools (type)
OpenAiCompatibleExecutionToolsNonProxiedOptions - Non-proxied configuration options (type)
OpenAiCompatibleExecutionToolsProxiedOptions - Proxied configuration options (type)
OpenAiExecutionToolsOptions - Configuration options for standard OpenAI tools (type)

Provider Registrations

_OpenAiRegistration - Standard OpenAI provider registration
_OpenAiAssistantRegistration - OpenAI Assistant provider registration
_OpenAiCompatibleRegistration - OpenAI-compatible provider registration

💡 This package provides OpenAI integration for promptbook applications. For the core functionality, see @promptbook/core or install all packages with npm i ptbk

Rest of the documentation is common for entire promptbook ecosystem:

📖 The Book Whitepaper

For most business applications nowadays, the biggest challenge isn't about the raw capabilities of AI models. Large language models like GPT-5 or Claude-4.1 are extremely capable.

The main challenge is to narrow it down, constrain it, set the proper context, rules, knowledge, and personality. There are a lot of tools which can do exactly this. On one side, there are no-code platforms which can launch your agent in seconds. On the other side, there are heavy frameworks like Langchain or Semantic Kernel, which can give you deep control.

Promptbook takes the best from both worlds. You are defining your AI behavior by simple books, which are very explicit. They are automatically enforced, but they are very easy to understand, very easy to write, and very reliable and portable.

Aspects of great AI agent

We have created a language called Book, which allows you to write AI agents in their native language and create your own AI persona. Book provides a guide to define all the traits and commitments.

You can look at it as prompting (or writing a system message), but decorated by commitments.

`Persona` commitment

Personas define the character of your AI persona, its role, and how it should interact with users. It sets the tone and style of communication.

`Knowledge` commitment

Knowledge Commitment allows you to provide specific information, facts, or context that the AI should be aware of when responding.

This can include domain-specific knowledge, company policies, or any other relevant information.

Promptbook Engine will automatically enforce this knowledge during interactions. When the knowledge is short enough, it will be included in the prompt. When it is too long, it will be stored in vector databases and RAG retrieved when needed. But you don't need to care about it.

Paul Smith & Associés

PERSONA You are a company lawyer.
Your job is to provide legal advice and support to the company and its employees.
You are knowledgeable, professional, and detail-oriented.

KNOWLEDGE https://company.com/company-policies.pdf
KNOWLEDGE https://company.com/internal-documents/employee-handbook.docx

`Rule` commitment

Rules will enforce specific behaviors or constraints on the AI's responses. This can include ethical guidelines, communication styles, or any other rules you want the AI to follow.

Depending on rule strictness, Promptbook will either propagate it to the prompt or use other techniques, like adversary agent, to enforce it.

Paul Smith & Associés

PERSONA You are a company lawyer.
Your job is to provide legal advice and support to the company and its employees.
You are knowledgeable, professional, and detail-oriented.

RULE Always ensure compliance with laws and regulations.
RULE Never provide legal advice outside your area of expertise.
RULE Never provide legal advice about criminal law.
KNOWLEDGE https://company.com/company-policies.pdf
KNOWLEDGE https://company.com/internal-documents/employee-handbook.docx

`Action` commitment

Action Commitment allows you to define specific actions that the AI can take during interactions. This can include things like posting on a social media platform, sending emails, creating calendar events, or interacting with your internal systems.

Paul Smith & Associés

PERSONA You are a company lawyer.
Your job is to provide legal advice and support to the company and its employees.
You are knowledgeable, professional, and detail-oriented.

RULE Always ensure compliance with laws and regulations.
RULE Never provide legal advice outside your area of expertise.
RULE Never provide legal advice about criminal law.
KNOWLEDGE https://company.com/company-policies.pdf
KNOWLEDGE https://company.com/internal-documents/employee-handbook.docx
ACTION When a user asks about an issue that could be treated as a crime, notify legal@company.com.

Where to use your AI agent in book

Books can be useful in various applications and scenarios. Here are some examples:

Chat apps:

Create your own chat shopping assistant and place it in your eShop. You will be able to answer customer questions, help them find products, and provide personalized recommendations. Everything is tightly controlled by the book you have written.

Reply Agent:

Create your own AI agent, which will look at your emails and reply to them. It can even create drafts for you to review before sending.

Coding Agent:

Do you love Vibecoding, but the AI code is not always aligned with your coding style and architecture, rules, security, etc.? Create your own coding agent to help enforce your specific coding standards and practices.

This can be integrated to almost any Vibecoding platform, like GitHub Copilot, Amazon CodeWhisperer, Cursor, Cline, Kilocode, Roocode,...

They will work the same as you are used to, but with your specific rules written in book.

Internal Expertise

Do you have an app written in TypeScript, Python, C#, Java, or any other language, and you are integrating the AI.

You can avoid struggle with choosing the best model, its settings like temperature, max tokens, etc., by writing a book agent and using it as your AI expertise.

Doesn't matter if you do automations, data analysis, customer support, sentiment analysis, classification, or any other task. Your AI agent will be tailored to your specific needs and requirements.

Even works in no-code platforms!

How to create your AI agent in book

Now you want to use it. There are several ways how to write your first book:

From scratch with help from Paul

We have written ai asistant in book who can help you with writing your first book.

Your AI twin

Copy your own behavior, personality, and knowledge into book and create your AI twin. It can help you with your work, personal life, or any other task.

AI persona workpool

Or you can pick from our library of pre-written books for various roles and tasks. You can find books for customer support, coding, marketing, sales, HR, legal, and many other roles.

🚀 Get started

Take a look at the simple starter kit with books integrated into the Hello World sample applications:

💜 The Promptbook Project

Promptbook project is ecosystem of multiple projects and tools, following is a list of most important pieces of the project:

Project	About
Book language	Book is a human-understandable markup language for writing AI applications such as chatbots, knowledge bases, agents, avarars, translators, automations and more. There is also a plugin for VSCode to support `.book` file extension
Promptbook Engine	Promptbook engine can run applications written in Book language. It is released as multiple NPM packages and Docker HUB
Promptbook Studio	Promptbook.studio is a web-based editor and runner for book applications. It is still in the experimental MVP stage.

Hello world examples:

Join our growing community of developers and users:

Platform	Description
💬 Discord	Join our active developer community for discussions and support
🗣️ GitHub Discussions	Technical discussions, feature requests, and community Q&A
👔 LinkedIn	Professional updates and industry insights
📱 Facebook	General announcements and community engagement
🔗 ptbk.io	Official landing page with project information

🖼️ Product & Brand Channels

Promptbook.studio

📸 Instagram @promptbook.studio

Visual updates, UI showcases, and design inspiration

📚 Documentation

See detailed guides and API reference in the docs or online.

🔒 Security

For information on reporting security vulnerabilities, see our Security Policy.

📦 Packages (for developers)

This library is divided into several packages, all are published from single monorepo. You can install all of them at once:

npm i ptbk

Or you can install them separately:

⭐ Marked packages are worth to try first

⭐ ptbk - Bundle of all packages, when you want to install everything and you don't care about the size
promptbook - Same as ptbk
⭐🧙‍♂️ @promptbook/wizard - Wizard to just run the books in node without any struggle
@promptbook/core - Core of the library, it contains the main logic for promptbooks
@promptbook/node - Core of the library for Node.js environment
@promptbook/browser - Core of the library for browser environment
⭐ @promptbook/utils - Utility functions used in the library but also useful for individual use in preprocessing and postprocessing LLM inputs and outputs
@promptbook/markdown-utils - Utility functions used for processing markdown
(Not finished) @promptbook/wizard - Wizard for creating+running promptbooks in single line
@promptbook/javascript - Execution tools for javascript inside promptbooks
@promptbook/openai - Execution tools for OpenAI API, wrapper around OpenAI SDK
@promptbook/anthropic-claude - Execution tools for Anthropic Claude API, wrapper around Anthropic Claude SDK
@promptbook/vercel - Adapter for Vercel functionalities
@promptbook/google - Integration with Google's Gemini API
@promptbook/deepseek - Integration with DeepSeek API
@promptbook/ollama - Integration with Ollama API
@promptbook/azure-openai - Execution tools for Azure OpenAI API
@promptbook/fake-llm - Mocked execution tools for testing the library and saving the tokens
@promptbook/remote-client - Remote client for remote execution of promptbooks
@promptbook/remote-server - Remote server for remote execution of promptbooks
@promptbook/pdf - Read knowledge from .pdf documents
@promptbook/documents - Integration of Markitdown by Microsoft
@promptbook/documents - Read knowledge from documents like .docx, .odt,…
@promptbook/legacy-documents - Read knowledge from legacy documents like .doc, .rtf,…
@promptbook/website-crawler - Crawl knowledge from the web
@promptbook/editable - Editable book as native javascript object with imperative object API
@promptbook/templates - Useful templates and examples of books which can be used as a starting point
@promptbook/types - Just typescript types used in the library
@promptbook/color - Color manipulation library
⭐ @promptbook/cli - Command line interface utilities for promptbooks
🐋 Docker image - Promptbook server

📚 Dictionary

The following glossary is used to clarify certain concepts:

General LLM / AI terms

Prompt drift is a phenomenon where the AI model starts to generate outputs that are not aligned with the original prompt. This can happen due to the model's training data, the prompt's wording, or the model's architecture.
Pipeline, workflow scenario or chain is a sequence of tasks that are executed in a specific order. In the context of AI, a pipeline can refer to a sequence of AI models that are used to process data.
Fine-tuning is a process where a pre-trained AI model is further trained on a specific dataset to improve its performance on a specific task.
Zero-shot learning is a machine learning paradigm where a model is trained to perform a task without any labeled examples. Instead, the model is provided with a description of the task and is expected to generate the correct output.
Few-shot learning is a machine learning paradigm where a model is trained to perform a task with only a few labeled examples. This is in contrast to traditional machine learning, where models are trained on large datasets.
Meta-learning is a machine learning paradigm where a model is trained on a variety of tasks and is able to learn new tasks with minimal additional training. This is achieved by learning a set of meta-parameters that can be quickly adapted to new tasks.
Retrieval-augmented generation is a machine learning paradigm where a model generates text by retrieving relevant information from a large database of text. This approach combines the benefits of generative models and retrieval models.
Longtail refers to non-common or rare events, items, or entities that are not well-represented in the training data of machine learning models. Longtail items are often challenging for models to predict accurately.

Note: This section is not a complete dictionary, more list of general AI / LLM terms that has connection with Promptbook

💯 Core concepts

📚 Collection of pipelines
📯 Pipeline
🙇‍♂️ Tasks and pipeline sections
🤼 Personas
⭕ Parameters
🚀 Pipeline execution
🧪 Expectations - Define what outputs should look like and how they're validated
✂️ Postprocessing - How outputs are refined after generation
🔣 Words not tokens - The human-friendly way to think about text generation
☯ Separation of concerns - How Book language organizes different aspects of AI workflows

Advanced concepts

Data & Knowledge Management	Pipeline Control
📚 Knowledge (RAG) - Retrieve and use external information 📽 Media handling - Working with images, audio, video, spreadsheets 🔴 Anomaly detection - Identifying unusual patterns or outputs	🌏 Remote server - Executing workflows on remote infrastructure 🃏 Jokers (conditions) - Adding conditional logic to workflows 🔳 Metaprompting - Creating prompts that generate other prompts
Language & Output Control	Advanced Generation
🌏 Linguistically typed languages - Type systems for natural language 🌍 Auto-Translations - Automatic multilingual support 👮 Agent adversary expectations - Safety and control mechanisms	🔙 Expectation-aware generation - Outputs that meet defined criteria ⏳ Just-in-time fine-tuning - Dynamic model adaptation

🔍 View more concepts

🚂 Promptbook Engine

Schema of Promptbook Engine

➕➖ When to use Promptbook?

➕ When to use

When you are writing app that generates complex things via LLM - like websites, articles, presentations, code, stories, songs,...
When you want to separate code from text prompts
When you want to describe complex prompt pipelines and don't want to do it in the code
When you want to orchestrate multiple prompts together
When you want to reuse parts of prompts in multiple places
When you want to version your prompts and test multiple versions
When you want to log the execution of prompts and backtrace the issues

➖ When not to use

When you have already implemented single simple prompt and it works fine for your job
When OpenAI Assistant (GPTs) is enough for you
When you need streaming (this may be implemented in the future, see discussion).
When you need to use something other than JavaScript or TypeScript (other languages are on the way, see the discussion)
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)
When you need to use recursion (see the discussion)