rockstarflo

I think regex can beat SLM for a specific use case. But for the general case, there is no chance you come up with a pattern that works for all sites.

What is the tradeoff there?

Generates fun stories by just providing a single image :D

Oh the command got corrupted. This is how it should look like: gptdeploy generate --description "Given a search query, find articles on hacker news using the hacker news api and return a list of (title, author, website_link, first_image_on_the_website)" --test "searching for GPT gives results" --model gpt-4 --path microservice

The following code generates a new Hacker News website, that even shows images in the results similar to Google.

pip install gptdeploy

gptdeploy generate \ --description "Given a search query, find articles on hacker news using the hacker news api and return a list of (title, author, website_link, first_image_on_the_website)" \ --test "searching for GPT gives results" \ --model gpt-4 \ --path microservice

We are working on 3.5 Trubo support and also Open Assistant

You are right. I will now work on local deployment.

With this, you turn your natural language descriptions into fully functional, deployed microservices with a single command! Your imagination is the limit!