We added ChatGPT to our documentation to make them fully portable
TLDR: Check out our documentation search here: https://xata.io/docs/overview Hello HN. I'm a designer over at Xata. We build a serverless database platform on top of Postgres and Elastic-like search that provides goodies like a native TypeScript client for type support in your IDE. Long story short, we're trying to bundle all the normal stuff you need out of a database along with branching, so you don't have to glue everything together. Today we added a new /ask/ endpoint to our search product that bundles in ChatGPT support into any stored data. Why would you…
What it does
In the maker’s words, at launch
TLDR: Check out our documentation search here: https://xata.io/docs/overview Hello HN. I'm a designer over at Xata. We build a serverless database platform on top of Postgres and Elastic-like search that provides goodies like a native TypeScript client for type support in your IDE. Long story short, we're trying to bundle all the normal stuff you need out of a database along with branching, so you don't have to glue everything together. Today we added a new /ask/ endpoint to our search product that bundles in ChatGPT support into any stored data. Why would you want this, you might ask? Fantastic question. Let's say you have a bunch of documentation stored in OpenAPI with a jumble of random markdown files in a Github repo. Sound familiar? With Xata you could push that content into a Xata DB on publish, and immediately get text and vector based search against that content. The new /ask/ endpoint only needs some rules, and suddenly you have natural language responses. Because it's all just markdown, you can then render the response back in your documentation site with syntax highlighting and all that goodness. Ok yeah, yeah. Docs chat. I get it. What makes this really cool is that because the content is now in a database, along with those endpoints, our documentation is suddenly portable. We can now provide helpful links throughout the product that ask "How do search boosts work?" that can answer things inline without linking you somewhere. We're still kicking the tires on this stuff, but it's nice to get the authoring experience of writing markdown in Github repos and seeing it suddenly show up anywhere, not just a static website. Obviously there's more you can do with it than this docs uses case, but it's the one we wanted to build for ourselves. Here's a 5-minute video that explains the basics along with some other resources if you want to build something similar yourself. Video https://www.youtube.com/watch?v=pbH9OHXvok0 The new ask endpoint https://xata.io/docs/api-reference/db/db_branch_name/tables/... A deeper technical dive on how this works https://xata.io/blog/chatgpt-on-your-data A starter repo with examples against Pokemon! https://github.com/xataio/examples/tree/main/apps/sample-cha...
Does the same job
all alternatives →
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 2d ago · opentrailpaper.com
Launched alongside, March 2023
the whole month →
- BI
I'm a big fan of the BBC podcast In Our Time -- and (like most people) I've been playing with the OpenAI APIs. In Our Time has almost 1,000 episodes on everything from Cleopatra to the evolution of teeth to plasma physics, all still available, so it's my starting point to learn about most topics. But it's not well organised. So here are the episodes sorted by library code. It's fun to explore. Web scraping is usually pretty tedious, but I found that I could send the minimised HTML to GPT-3 and get (almost) perfect JSON back: the prompt includes the Typescript definition. At the same time I…
AI · 2023 · genmon.github.io