Promptbook

Library to supercharge your use of large language models

⚠ Warning: This library is still in early development.

🤍 Whitepaper

When you have a simple, single prompt for ChatGPT, GPT-4, Anthropic Claude, Google Gemini, Llama 2, or whatever, it doesn't matter how it is integrated. Whether it's the direct calling of a REST API, using the SDK, hardcoding the prompt in the source code, or importing a text file, the process remains the same.

If you need something more advanced or want to extend the capabilities of LLMs, you generally have three ways to proceed:

Fine-tune the model to your specifications or even train your own.
Prompt-engineer the prompt to the best shape you can achieve.
Use multiple prompts in a pipeline to get the best result.

In any of these situations, but especially in (3), the Promptbook library can make your life easier and make orchestraror for your prompts.

Separation of concerns between prompt engineer and programmer; between code files and prompt files; and between prompts, templates, templating pipelines, and their execution logic.
Set up a common format for prompts that is interchangeable between projects and language/technology stacks.
Preprocessing and cleaning the input data from the user.
Use default values - Jokers to bypass some parts of the pipeline.
Expect some specific output from the model.
Retry mismatched outputs.
Combine multiple models together.
Interactive User interaction with the model and the user.
Leverage external sources (like ChatGPT plugins or OpenAI's GPTs).
Simplify your code to be DRY and not repeat all the boilerplate code for each prompt.
Versioning of promptbooks
Reuse parts of promptbooks in/between projects.
Run the LLM optimally in parallel, with the best cost/quality ratio or speed/quality ratio.
Execution report to see what happened during the execution.
Logging the results of the promptbooks.
(Not ready yet) Caching calls to LLMs to save money and time.
(Not ready yet) Extend one prompt book from another one.
(Not ready yet) Leverage the streaming to make super cool UI/UX.
(Not ready yet) A/B testing to determine which prompt works best for the job.

🧔 Promptbook (for prompt-engeneers)

Prompt book markdown file (PTBK for short, or .ptbk.md) is document that describes a series of prompts that are chained together to form somewhat reciepe for transforming natural language input. Inside a PTBK you can use chat prompts, completion prompts, scripting or trigger interaction with user to ask for additional information.

Multiple promptbooks forms a library which will become a part of your application codebase.
Theese promptbooks 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.

PROMPTBOOK URL https://promptbook.webgpt.com/en/write-website-content.ptbk.md@v0.1.0

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 {content} Web content

OUTPUT PARAM {keywords} Keywords

👤 Specifying the assigment

What is your web about?

PROMPT DIALOG
{rawAssigment}
-> {assigment} Website assignment and specification

✨ Improving the title

MODEL VARIANT Chat

MODEL NAME gpt-4

POSTPROCESSING unwrapResult
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?

PROMPT DIALOG
{enhancedTitle}
-> {title} Title for the website

🐰 Cunning subtitle

MODEL VARIANT Chat

MODEL NAME gpt-4

POSTPROCESSING unwrapResult
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

MODEL VARIANT Chat

MODEL NAME gpt-4
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

MODEL VARIANT Completion

MODEL NAME gpt-3.5-turbo-instruct
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
{contentBeginning}

{contentBody}
-> {content}

Following is the scheme how the promptbook above is executed:

%% 🔮 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--"{content}"-->output
      output((Output)):::output

      classDef input color: grey;
      classDef output color: grey;

  end;

Loading

More template samples

Note: We are using postprocessing functions like unwrapResult that can be used to postprocess the result.

📚 Dictionary

The following glossary is used to clarify certain basic concepts:

Prompt

Prompt in a text along with model requirements, but without any execution or templating logic.

For example:

{
    "request": "Which sound does a cat make?",
    "modelRequirements": {
        "variant": "CHAT"
    }
}

{
    "request": "I am a cat.\nI like to eat fish.\nI like to sleep.\nI like to play with a ball.\nI l",
    "modelRequirements": {
        "variant": "COMPLETION"
    }
}

Prompt Template

Similar concept to Prompt, but with templating logic.

For example:

{
    "request": "Which sound does a {animalName} make?",
    "modelRequirements": {
        "variant": "CHAT"
    }
}

Model Requirements

Abstract way to specify the LLM. It does not specify the LLM with concrete version itself, only the requirements for the LLM. NOT chatgpt-3.5-turbo BUT CHAT variant of GPT-3.5.

For example:

{
    "variant": "CHAT",
    "version": "GPT-3.5",
    "temperature": 0.7
}

Execution type

Each block of promptbook can have a different execution type. It is specified in list of requirements for the block. By default, it is Prompt template

(default) Prompt template The block is a prompt template and is executed by LLM (OpenAI, Azure,...)
SIMPLE TEMPLATE The block is a simple text template which is just filled with parameters
Script The block is a script that is executed by some script runtime, the runtime is determined by block type, currently only javascript is supported but we plan to add python and typescript in the future.
PROMPT DIALOG Ask user for input

Parameters

Parameters that are placed in the prompt template and replaced to create the prompt. It is a simple key-value object.

{
    "animalName": "cat",
    "animalSound": "Meow!"
}

There are three types of template parameters, depending on how they are used in the promptbook:

INPUT PARAMETERs are required to execute the promptbook.
Intermediate parameters are used internally in the promptbook.
OUTPUT PARAMETERs are explicitelly marked and they are returned as the result of the promptbook execution.

Note: Parameter can be both intermedite and output at the same time.

Promptbook

Promptbook is core concept of this library. It represents a series of prompt templates chained together to form a pipeline / one big prompt template with input and result parameters.

Internally it can have multiple formats:

.ptbk.md file in custom markdown format described above
(concept) .ptbk format, custom fileextension based on markdown
(internal) JSON format, parsed from the .ptbk.md file

Promptbook Library

Library of all promptbooks used in your application.

Prompt Result

Prompt result is the simplest concept of execution. It is the result of executing one prompt (NOT a template).

For example:

{
    "response": "Meow!",
    "model": "chatgpt-3.5-turbo"
}

Execution Tools

ExecutionTools is an interface which contains all the tools needed to execute prompts. It contais 3 subtools:

NaturalExecutionTools
ScriptExecutionTools
UserInterfaceTools

Which are described below:

Natural Execution Tools

NaturalExecutionTools is a container for all the tools needed to execute prompts to large language models like GPT-4. On its interface it exposes common methods for prompt execution. Internally it calls OpenAI, Azure, GPU, proxy, cache, logging,...

NaturalExecutionTools an abstract interface that is implemented by concrete execution tools:

OpenAiExecutionTools
(Not implemented yet) AnthropicClaudeExecutionTools
(Not implemented yet) AzureOpenAiExecutionTools
(Not implemented yet) BardExecutionTools
(Not implemented yet) LamaExecutionTools
(Not implemented yet) GpuExecutionTools
And a special case are RemoteNaturalExecutionTools that connect to a remote server and run one of the above execution tools on that server.
The second special case is MockedEchoNaturalExecutionTools that is used for testing and mocking.
The third special case is LogNaturalExecutionToolsWrapper that is technically also an execution tools but it is more proxy wrapper around other execution tools that logs all calls to execution tools.

Script Execution Tools

ScriptExecutionTools is an abstract container that represents all the tools needed to EXECUTE SCRIPTs. It is implemented by concrete execution tools:

JavascriptExecutionTools is a wrapper around vm2 module that executes javascript code in a sandbox.
JavascriptEvalExecutionTools is wrapper around eval function that executes javascript. It is used for testing and mocking NOT intended to use in the production due to its unsafe nature, use JavascriptExecutionTools instead.
(Not implemented yet) TypescriptExecutionTools executes typescript code in a sandbox.
(Not implemented yet) PythonExecutionTools executes python code in a sandbox.

There are postprocessing functions that can be used to postprocess the result.

User Interface Tools

UserInterfaceTools is an abstract container that represents all the tools needed to interact with the user. It is implemented by concrete execution tools:

(Not implemented yet) ConsoleInterfaceTools is a wrapper around readline module that interacts with the user via console.
SimplePromptInterfaceTools is a wrapper around window.prompt synchronous function that interacts with the user via browser prompt. It is used for testing and mocking NOT intended to use in the production due to its synchronous nature.
CallbackInterfaceTools delagates the user interaction to a async callback function. You need to provide your own implementation of this callback function and its bind to UI.

Executor

Executor is a simple async function that takes input parameters and returns output parameters. It is constructed by combining execution tools and promptbook to execute together.

🃏 Jokers

Joker is a previously defined parameter that is used to bypass some parts of the pipeline. If the joker is present in the template, it is checked to see if it meets the requirements (without postprocessing), and if so, it is used instead of executing that prompt template. There can be multiple wildcards in a prompt template, if so they are checked in order and the first one that meets the requirements is used.

If none of the jokers meet the requirements, the prompt template is executed as usual.

This can be useful, for example, if you want to use some predefined data, or if you want to use some data from the user, but you are not sure if it is suitable form.

When using wildcards, you must have at least one minimum expectation. If you do not have a minimum expectation, the joker will always fulfil the expectation because it has none, so it makes no logical sense.

Look at jokers.ptbk.md sample.

Postprocessing functions

You can define postprocessing functions when creating JavascriptEvalExecutionTools:

Additionally there are some usefull string-manipulation build-in functions, which are listed here.

Expectations

Expect command describes the desired output of the prompt template (after post-processing) It can set limits for the maximum/minimum length of the output, measured in characters, words, sentences, paragraphs,...

Note: LLMs work with tokens, not characters, but in Promptbooks we want to use some human-recognisable and cross-model interoperable units.

# ✨ Sample: Expectations

-   PROMPTBOOK URL https://promptbook.example.com/samples/postprocessing-2.ptbk.md@v1
-   PROMPTBOOK VERSION 1.0.0
-   INPUT  PARAMETER {yourName} Name of the hero

## 💬 Question

-   EXPECT MAX 30 CHARACTERS
-   EXPECT MIN 2 CHARACTERS
-   EXPECT MAX 3 WORDS
-   EXPECT EXACTLY 1 SENTENCE
-   EXPECT EXACTLY 1 LINE

...

There are two types of expectations which are not strictly symmetrical:

Minimal expectations

EXPECT MIN 0 ... is not valid minimal expectation. It makes no sense.
EXPECT JSON is both minimal and maximal expectation
When you are using JOKER in same prompt template, you need to have at least one minimal expectation

Maximal expectations

EXPECT MAX 0 ... is valid maximal expectation. For example, you can expect 0 pages and 2 sentences.
EXPECT JSON is both minimal and maximal expectation

Look at expectations.ptbk.md and expect-json.ptbk.md samples for more.

Execution report

Execution report is a simple object or markdown that contains information about the execution of the promptbook.

See the example of such a report

Remote server

Remote server is a proxy server that uses its execution tools internally and exposes the executor interface externally.

You can simply use RemoteExecutionTools on client-side javascript and connect to your remote server. This is useful to make all logic on browser side but not expose your API keys or no need to use customer's GPU.

👨‍💻 Usage and integration (for developers)

🔌 Usage in Typescript / Javascript

Simple usage
Usage with client and remote server

❔ FAQ

If you have a question start a discussion, open an issue or write me an email.

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 is for creating prompt templates and promptbooks 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:

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.
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).
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.

⌚ Changelog

See CHANGELOG.md

🎯 TODOs

[ ][🧙‍♂️] Make Wizzard
Make from this folder a separate repository + npm package
Add tests
Annotate all entities
Make internal string aliases
Make branded types instead of pure string aliases
Remove all any
[ ][👧] Make strongy typed input+output parameters in executors
Make promptbooks non-linear
Logging pipeline name, version, step,...
[ ][🧠] Wording: "param" vs "parameter" vs "variable" vs "argument"
All entities must have public / private / protected modifiers
Everything not needed should be private or not exported
Refactor circular dependencies
Importing subtemplates
Use spaceTrim more effectively
[🤹‍♂️] Allow chats to be continued with previous message
[🧠][🤹‍♂️] How to mark continued chat in .ptbk.md format?
Use newest version of socket.io for remote server
[🧠] Allow to use and define function calling
Register .ptbk file extension
Fix error content.js:73 Uncaught (in promise) TypeError: object null is not iterable (cannot read property Symbol(Symbol.iterator))
Aborting execution, maybe use native AbortController
Change import {...} from '...'; to import type {...} from '...'; when importing only types
Wrap OpenAI billing errors:
Integrate word stemmer https://github.com/maxpatiiuk/porter-stemming/blob/main/src/index.ts
Integrate faker to generate simple mocked data
Put postprocessing + expectations into mermaid graphs
mermaid graphs as exported CLI util
Preprocessing
System to bundle up Preprocessing + Postprocessing + Expectations
Integrate ceaser-cipher to auto preprocess some and postprocess templates
Scenario: Expect all information (for example in incomming email), when not then return = kinda reverse joker
Make VSCode extension for validation/syntax highlite (and for other editors)
- "Billing hard limit has been reached"
- "You exceeded your current quota, please check your plan and billing details."

🖋️ Contributing

I am open to pull requests, feedback, and suggestions. Or if you like this utility, you can ☕ buy me a coffee or donate via cryptocurrencies.

You can also ⭐ star the promptbook package, follow me on GitHub or various other social networks.

✨ Partners

Become a partner

Files

README.md

Latest commit

History

README.md

File metadata and controls

Promptbook

🤍 Whitepaper

🧔 Promptbook (for prompt-engeneers)

Sample:

🌍 Create website content

👤 Specifying the assigment

✨ Improving the title

👤 Website title approval

🐰 Cunning subtitle

🚦 Keyword analysis

🔗 Combine the beginning

🖋 Write the content

🔗 Combine the content

📚 Dictionary

Prompt

Prompt Template

Model Requirements

Execution type

Parameters

Promptbook

Promptbook Library

Prompt Result

Execution Tools

Natural Execution Tools

Script Execution Tools

User Interface Tools

Executor

🃏 Jokers

Postprocessing functions

Expectations

Minimal expectations

Maximal expectations

Execution report

Remote server

👨‍💻 Usage and integration (for developers)

🔌 Usage in Typescript / Javascript

❔ FAQ

Why not just use the OpenAI SDK / Anthropic Claude SDK / ...?

How is it different from the Langchain library?

Promptbooks vs. OpenAI`s GPTs

Where should I store my promptbooks?

What should I do when I need same promptbook in multiple human languages?

⌚ Changelog

🎯 TODOs

🖋️ Contributing

✨ Partners