@promptbook/fake-llm
Advanced tools
PromptbookSupercharge your use of large language models
@promptbook/fake-llm@promptbook/fake-llm 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/fake-llm
Mock objects for testing the execution tools without token usage.
Rest of the documentation is common for entire promptbook ecosystem:
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 w๐๐ขrd responses. When this happens, you generally have three options:
In all of these situations, but especially in 3., the Promptbook library can make your life easier.
.ptbk.md that can be used to describe your prompt business logic without having to write code or deal with the technicalities of LLMs.:) can't avoid the problems. In this case, the library has built-in anomaly detection and logging to help you find and fix the problems.Prompt book 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.
File write-website-content.ptbk.md:
๐ Create website content
Instructions for creating web page content.
- PIPELINE URL https://promptbook.studio/webgpt/write-website-content.ptbk.md
- INPUTโฏโฏPARAM
{rawTitle}Automatically suggested a site name or empty text- INPUTโฏโฏPARAM
{rawAssigment}Automatically generated site entry from image recognition- OUTPUTโฏPARAM
{websiteContent}Web content- OUTPUTโฏPARAM
{keywords}Keywords๐ค Specifying the assigment
What is your web about?
- DIALOG TEMPLATE
{rawAssigment}
-> {assigment}Website assignment and specificationโจ 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 title๐ค Website title approval
Is the title for your website okay?
- DIALOG TEMPLATE
{enhancedTitle}
-> {title}Title for the website๐ฐ 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 web๐ฆ 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}Keywords๐ Combine the beginning
- SIMPLE TEMPLATE
# {title} > {claim}
-> {contentBeginning}Beginning of web content๐ 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 content๐ Combine the content
- SIMPLE TEMPLATE
{contentBeginning} {contentBody}
-> {websiteContent}
Following is the scheme how the promptbook above is executed:
%% ๐ฎ Tip: Open this on GitHub or in the VSCode website to see the Mermaid graph visually
flowchart LR
subgraph "๐ Create website content"
direction TB
input((Input)):::input
templateSpecifyingTheAssigment(๐ค Specifying the assigment)
input--"{rawAssigment}"-->templateSpecifyingTheAssigment
templateImprovingTheTitle(โจ Improving the title)
input--"{rawTitle}"-->templateImprovingTheTitle
templateSpecifyingTheAssigment--"{assigment}"-->templateImprovingTheTitle
templateWebsiteTitleApproval(๐ค Website title approval)
templateImprovingTheTitle--"{enhancedTitle}"-->templateWebsiteTitleApproval
templateCunningSubtitle(๐ฐ Cunning subtitle)
templateWebsiteTitleApproval--"{title}"-->templateCunningSubtitle
templateSpecifyingTheAssigment--"{assigment}"-->templateCunningSubtitle
templateKeywordAnalysis(๐ฆ Keyword analysis)
templateWebsiteTitleApproval--"{title}"-->templateKeywordAnalysis
templateSpecifyingTheAssigment--"{assigment}"-->templateKeywordAnalysis
templateCombineTheBeginning(๐ Combine the beginning)
templateWebsiteTitleApproval--"{title}"-->templateCombineTheBeginning
templateCunningSubtitle--"{claim}"-->templateCombineTheBeginning
templateWriteTheContent(๐ Write the content)
templateWebsiteTitleApproval--"{title}"-->templateWriteTheContent
templateSpecifyingTheAssigment--"{assigment}"-->templateWriteTheContent
templateKeywordAnalysis--"{keywords}"-->templateWriteTheContent
templateCombineTheBeginning--"{contentBeginning}"-->templateWriteTheContent
templateCombineTheContent(๐ Combine the content)
templateCombineTheBeginning--"{contentBeginning}"-->templateCombineTheContent
templateWriteTheContent--"{contentBody}"-->templateCombineTheContent
templateCombineTheContent--"{websiteContent}"-->output
output((Output)):::output
classDef input color: grey;
classDef output color: grey;
end;
Note: We are using postprocessing functions like unwrapResult that can be used to postprocess the result.
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:
โญ Marked packages are worth to try first
ptbkThe following glossary is used to clarify certain concepts:
If you have a question start a discussion, open an issue or write me an email.
See CHANGELOG.md
Promptbook by Pavol Hejnรฝ is licensed under CC BY 4.0
See TODO.md
I am open to pull requests, feedback, and suggestions. Or if you like this utility, you can โ buy me a coffee or donate via cryptocurrencies.
You can also โญ star the promptbook package, follow me on GitHub or various other social networks.
FAQs
It's time for a paradigm shift. The future of software in plain English, French or Latin
The npm package @promptbook/fake-llm receives a total of 1,004 weekly downloads. As such, @promptbook/fake-llm popularity was classified as popular.
We found that @promptbook/fake-llm demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago.ย It has 0 open source maintainers collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
Research
The Socket Research Team breaks down a malicious wrapper package that uses obfuscation to harvest credentials and exfiltrate sensitive data.
Research
Security News
Attackers used a malicious npm package typosquatting a popular ESLint plugin to steal sensitive data, execute commands, and exploit developer systems.
Security News
The Ultralytics' PyPI Package was compromised four times in one weekend through GitHub Actions cache poisoning and failure to rotate previously compromised API tokens.