Spencer Miskoviak retweeted
Loved working with @ternsoftware on their RubyLLM 2.0 upgrade.
I designed and built the multi-phase migration with rename/copy strategies, now part of RubyLLM itself.
Need a hand with RubyLLM? You can hire the guy who built it. 😉
Our AI stack runs on RubyLLM, and we'd built up several workarounds the past few months.
We just upgraded to 2.0. A few of our use cases were promoted into first-class APIs, including our multi-phase migration pattern that was upstreamed!
tern.travel/blog/workarounds…
Our AI stack runs on RubyLLM, and we'd built up several workarounds the past few months.
We just upgraded to 2.0. A few of our use cases were promoted into first-class APIs, including our multi-phase migration pattern that was upstreamed!
tern.travel/blog/workarounds…
RubyLLM 2.0.0.rc4 is out!
- Fixes .with_caching + .cache_until_here interactions
- Adds --discard-incomplete-tool-calls to the copy-upgrade finish migration
and more.
Big thanks to @spencerskovy for discovering those!
github.com/crmne/ruby_llm/re…
Spencer Miskoviak retweeted
Asktro now provides a plugin and UI support for @docusaurus 🦖
In just a few lines of code, you can add document search and an AI assistant tailored to your documentation.
See a demo: docusaurus.asktro.com
Get started: asktro.com/docs/docusaurus
ALT screenshot of Docusaurus with Asktro demo
LLM Markdown (a demo to render rich responses from LLMs) now supports LaTeX as well. 🧮
Give it a try: llm-markdown.vercel.app
ALT screenshot of LLM Markdown with a prompt to render an equation in LaTeX syntax and a response with the equation for gravity as LaTeX
ALT Example of rendering the LaTeX equation from the LLM response
2
133
Spencer Miskoviak retweeted
Want to see a production-like demo of how Asktro works? 🔎
Checkout this fork of the Nextra docs with Asktro search enabled to compare with the default search results. 📊
Asktro Nextra docs demo: nextra.asktro.com
Nextra docs: nextra.site
It took some experimentation to build the @asktro_ UI component package with tsup and Tailwind, and to output the CSS in a way to avoid class name collisions, avoid global resets, and support dark mode.
These were the steps to get it working:
skovy.dev/blog/build-compone…
Excited to share a small project I've been working on inspired by the rich search experience @supabase built for their docs.
Asktro is a Nextra plugin that extracts, embeds, and persists the docs in @qdrant_engine and surfaces the search and AI-assistant in static docs.
The search UI is built with @tailwindcss, cmdk, @vercel AI, @_phosphoricons, and more
teapaw.org/spencerskovy/status/16…
🔍 Exploring a rich search experience for static documentation
💽 A webpack plugin extracts the Nextra docs which are embedded/stored with @qdrant_engine
✨ The custom search component is built with cmdk from @pacocoursey
🤖 Next up: use an LLM to answer directly based on docs
4
134
Spencer Miskoviak retweeted
Learn how to use Vercel’s AI SDK with Next.js to build an AI app that understands markup languages for formatting and rendering diagrams in MermaidJS
teapaw.org/spencerskovy/status/16…
An overview for rendering rich responses 🎨 (markdown and diagrams) from OpenAI 🤖 with @nextjs, @vercel ai SDK, @unifiedjs, and @mermaidjs_.
📝 skovy.dev/blog/vercel-ai-ren…
🔍 Exploring a rich search experience for static documentation
💽 A webpack plugin extracts the Nextra docs which are embedded/stored with @qdrant_engine
✨ The custom search component is built with cmdk from @pacocoursey
🤖 Next up: use an LLM to answer directly based on docs
An overview for rendering rich responses 🎨 (markdown and diagrams) from OpenAI 🤖 with @nextjs, @vercel ai SDK, @unifiedjs, and @mermaidjs_.
📝 skovy.dev/blog/vercel-ai-ren…
LLMs like GPT are capable of producing responses with popular formatting like Markdown, and Mermaid diagrams. 📊
LLM Markdown demonstrates how to leverage this with @vercel AI, @unifiedjs, and @mermaidjs_ to render rich-text responses. 🎨
🖥 Demo: llm-markdown.vercel.app
LLMs like GPT are capable of producing responses with popular formatting like Markdown, and Mermaid diagrams. 📊
LLM Markdown demonstrates how to leverage this with @vercel AI, @unifiedjs, and @mermaidjs_ to render rich-text responses. 🎨
🖥 Demo: llm-markdown.vercel.app
🤖 A system prompt is used to encourage this formatting in the response. The response is then parsed and rendered with popular JavaScript libraries to turn the text-only formatting into richer responses.
📝 Source: github.com/skovy/llm-markdow…
2
79
It’s been fun building this, learning new techniques, and watching how fast the tooling is evolving in the space 🤯
At a high-level, how we built this…👇
- Chunk each file into smaller pieces
- Vectorize each chunk/metadata with embeddings and persisted in a vector store
- The query is also vectorized and compared to chunks for context
- Construct a prompt with the original query and relevant context
- Send the prompt to an LLM
1
1
65
Spencer Miskoviak retweeted
New blog post! 📰 How to ship higher quality apps faster by adopting mobile release trains: wolfia.com/blog/all-aboard-t…
And by the way, @wolfia_app can automate your mobile app releases 🚀, including setting up a CI for free! Ping us at [email protected] or DM me to learn more.
Spencer Miskoviak retweeted
We've fully migrated the Wealthfront web app to TypeScript and are excited to share our journey, and how we plan to continue improving the type safety in our codebase! eng.wealthfront.com/2022/11/…
