Asktro now provides a plugin and UI support for @docusaurus ๐ฆ
In just a few lines of code, you can add document search and an AI assistant tailored to your documentation.
See a demo: https://t.co/3zjqxBiAiR
Get started: https://t.co/kQrL3eYZNi
Want to see a production-like demo of how Asktro works? ๐
Checkout this fork of the Nextra docs with Asktro search enabled to compare with the default search results. ๐
Asktro Nextra docs demo: https://t.co/rYlnsxrknP
Nextra docs: https://t.co/BcbQsrjU5O
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:
https://t.co/0NsV5iWz7M
๐ Exploring a rich search experience for static documentation
๐ฝ A webpack plugin extracts the Nextra docs which are embedded/stored with @qdrant_engine
โจ The custom search component is built with cmdk from @pacocoursey
๐ค Next up: use an LLM to answer directly based on docs
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.
๐ Asktro is live for early access!
๐จโ๐ Asktro brings a dynamic, AI-enabled search experience to static documentation (currently, Nextra).
๐ Powered by the latest embedded text similarity search and large language models.
Learn how to use Vercelโs AI SDK with Next.js to build an AI app that understands markup languages for formatting and rendering diagrams in MermaidJS
https://t.co/xmPheUlBeT
๐ Exploring a rich search experience for static documentation
๐ฝ A webpack plugin extracts the Nextra docs which are embedded/stored with @qdrant_engine
โจ The custom search component is built with cmdk from @pacocoursey
๐ค Next up: use an LLM to answer directly based on docs
An overview for rendering rich responses ๐จ (markdown and diagrams) from OpenAI ๐ค with @nextjs, @vercel ai SDK, @unifiedjs, and @mermaidjs_.
๐ https://t.co/goKymFgidX
LLMs like GPT are capable of producing responses with popular formatting like Markdown, and Mermaid diagrams. ๐
LLM Markdown demonstrates how to leverage this with @vercel AI, @unifiedjs, and @mermaidjs_ to render rich-text responses. ๐จ
๐ฅ Demo: https://t.co/nTV9QrgTUD
@remcohaszing @vercel@unifiedjs@mermaidjs_ Nice, that would be useful!
A challenge is Mermaidjs isn't as forgiving at parsing invalid diagrams. Markdown is more forgiving rendering invalid while streaming. This is why the demo required a click to render the diagrams. I imagine this plugin would run into the same issue?
LLMs like GPT are capable of producing responses with popular formatting like Markdown, and Mermaid diagrams. ๐
LLM Markdown demonstrates how to leverage this with @vercel AI, @unifiedjs, and @mermaidjs_ to render rich-text responses. ๐จ
๐ฅ Demo: https://t.co/nTV9QrgTUD
๐ค 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.
๐ Source: https://t.co/7zuX7NThNx
Lots of ideas on how to improve this with AST/LLM-based chunking, hierarchical indexing, metadata generation (summaries), query expansion, etc.
Excited to see what this tool can unlock!
Itโs been fun building this, learning new techniques, and watching how fast the tooling is evolving in the space ๐คฏ
At a high-level, how we built thisโฆ๐
- 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
New blog post! ๐ฐ How to ship higher quality apps faster by adopting mobile release trains: https://t.co/9cWUum8wEM
And by the way, @wolfia_app can automate your mobile app releases ๐, including setting up a CI for free! Ping us at [email protected] or DM me to learn more.
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! https://t.co/cMeECkwYTj
Trying to build an MDX powered blog with Nextjs? It can be challenging to use the Nextjs Image component with mdx-bundler to get all the experience and performance image optimizations.
Hereโs how I solved it for my blog: https://t.co/2pcuQ6VYj7