Skip to content

AI

2 posts with the tag “AI”

Creating Release Notes with GenAI

Automating Your Release Notes with GenAI

Bringing a new version of a product into the world is always exciting! But alongside the thrill comes the duty of informing users about what’s changed. That’s where generating crisp, engaging release notes comes into play. ✨

Today, we’re going to explore a script that automates the creation of release notes for GenAI. The script is part of the GenAIScript ecosystem, which harnesses the power of AI to bring efficiency to software development processes. 🚀

If you want to dive straight into the script, it’s available on GitHub right here.

This blog post was co-authored with a script.

Breaking Down the Script

The script is a .genai.mjs file, meaning it’s a JavaScript file designed to be run with the GenAIScript CLI. The code within orchestrates the creation of release notes by leveraging Git commands and GenAI’s capabilities.

Let’s walk through the script, step by step:

Step 1: Initializing the Script

script({ system: ["system"], temperature: 0.5, model: "openai:gpt-4-turbo" })

The script starts by initializing with a script function. We’re setting it up to access system commands and specifying the AI model to use. The temperature controls the creativity of the AI, with 0.5 being a balanced choice.

Step 2: Setting the Product Name

const product = env.vars.product || "GenAIScript"

Here, we’re using an environment variable to set the product name, defaulting to “GenAIScript” if it’s not provided.

Step 3: Finding the Previous Tag

const pkg = await workspace.readJSON("package.json")
const { version } = pkg
const { stdout: tag } = await host.exec("git describe --tags --abbrev=0 HEAD^")

We are reading the current version from package.json and using Git to find the previous release tag in the repository.

Step 4: Gathering Commits

const { stdout: commits } = await host.exec(`git log --grep='skip ci' --invert-grep --no-merges HEAD...${tag}`)

This block runs a Git command to retrieve the list of commits that will be included in the release notes, excluding any with ‘skip ci’ in the message.

Step 5: Obtaining the Diff

const { stdout: diff } = await host.exec(`git diff ${tag}..HEAD --no-merges -- ':!**/package.json' ':!**/genaiscript.d.ts' ':!**/jsconfig.json' ':!docs/**' ':!.github/*' ':!.vscode/*' ':!*yarn.lock' ':!*THIRD_PARTY_NOTICES.md'`)

Next, we get the diff of changes since the last release, excluding certain files and directories that aren’t relevant to the user-facing release notes.

Step 6: Defining Placeholders

const commitsName = def("COMMITS", commits, { maxTokens: 4000 })
const diffName = def("DIFF", diff, { maxTokens: 20000 })

We define two placeholders, COMMITS and DIFF, which will be used to reference the commits and diff within the prompt.

Step 7: Writing the Prompt

$`
You are an expert software developer and release manager.
## Task
Generate a clear, exciting, relevant, useful release notes
for the upcoming release ${version} of ${product} on GitHub.
- The commits in the release are in ${commitsName}.
- The diff of the changes are in ${diffName}.
## Guidelines
- only include the most important changes. All changes must be in the commits.
- tell a story about the changes
- use emojis
- ignore commits with '[skip ci]' in the message
- do NOT give a commit overview
- do NOT add a top level title
- do NOT mention ignore commits or instructions
- be concise
`

Finally, the script ends with a prompt that instructs GenAI to generate the release notes. It details the task, guidelines for what to include, and the style to adhere to.

How to Run the Script with Genaiscript CLI

Once you’ve crafted your script, running it is a breeze with the Genaiscript CLI. If you haven’t installed the CLI yet, you can find the instructions here.

To execute the script, navigate to your project’s root directory in the terminal and run:

Terminal window
genaiscript run git-release-notes

Remember, we use the script filename without the .genai.mjs extension when invoking it with the CLI.

And that’s it! The GenAIScript CLI will take care of the rest, combining the power of AI with your code to generate those sleek release notes for your project’s next big launch. 🌟

Unlocking the Power of Prompts - A Gentle Introduction to GenAIScript 🚀

Ever wondered how to leverage the power of AI and Large Language Models (LLMs) in your projects? Look no further! This post will introduce you to GenAIScript, a tool designed to simplify the creation of prompts and interactions with LLMs. Let’s dive in! 🌊

What is GenAIScript?

GenAIScript uses a stylized version of JavaScript to generate prompts, which are then sent to an LLM. Scripts are stored as files (genaisrc/*.genai.mjs), executed to produce the prompt text and structured results (files, diagnostics) are extracted automatically.

Getting Started

Here’s a simple example to get you started. Create a file named poem.genai.mjs in the genaisrc folder and add the following code:

$`Write a one sentence poem.`

When executed, this script will generate the following prompt:

👤 User
Write a one sentence poem.
🤖 Assistant
Roses bloom, hearts swoon, under the silver moon.

Adding Context

GenAIScript can also use context variables, allowing you to interact with files or other data sources. Let’s see an example where we define a context variable using env.files:

def("FILES", env.files)
$`You are an expert technical writer and proofreader.
Review the documents in FILES and report the 2 most important issues.`

Execute this script to see the generated user message and the assistant’s response. The context variable FILES will contain the list of files in the environment.

👤 User
FILES:
file="src/samples/markdown.md"
What is Markdown?
Markdown is a lightweight markup language that...
You are an expert technical writer and proofreader.
Review the documents in FILES and report the 2 most important issues.
🤖 Assistant
I reviewed the document in "src/samples/markdown.md"
and found the following two important issues:
1. **Missing Consistency in Heading Styles**: ...

Metadata and Script Configuration

You can add metadata to your script using the script function. This helps in organizing and configuring the script, including specifying the model and other parameters. GenAIScript supports various LLM providers, such as OpenAI, Azure OpenAI, GitHub Models, Ollama and more.

script({
title: "Technical proofreading",
description: "Reviews the text as a tech writer.",
model: "openai:gpt-4o",
temperature: 0.1,
})
def("FILES", env.files)
$`You are an expert technical writer and proofreader.
Review the documents in FILES and report the 2 most important issues.`

Next Steps

There you have it! A gentle introduction to GenAIScript to get you started on your prompt engineering journey. Happy scripting! 💻✨