developer

developer copied to clipboard

rate limits

8

I think the repo seems to be making too many API calls to OpenAI in successive fashion. Any plans to to rate limit this?: openai.error.RateLimitError: The server is currently overloaded...

varunmayya

Not working without Modal

2

I tried the instructions without Modal: ``` python main_no_modal.py "A basic React app that just displays a page that says 'Hello, World!'" ``` Result: ``` Traceback (most recent call last):...

localjo

Ther should be a Dark Mode Toggle button in the navbar in Header Section of this Webpage

kumarankit999

github -> GitHub

eltociear

Feature: `-- plan` flag

2

this is an easy one - https://news.ycombinator.com/item?id=35970653 - Self-planning Code Generation with Large Language Model https://arxiv.org/pdf/2303.06689.pdf [idea](https://twitter.com/Diogenes_Dev/status/1658296850309316609/photo/1) - https://news.ycombinator.com/item?id=35735375

swyxio

its too powerful

swyxio

InvalidRequestError: This model's maximum context length is 4097 tokens. However, your messages resulted in 7575 tokens. Please reduce the length of the messages.

7

While following the workflow shown in the YouTube video, I run into this error. I had run a prompt and gotten an error. I tried running debugger on the traceback...

kcramp858

Support full token limits

6

Nice project. I saw a note here: https://github.com/smol-ai/developer/blob/03dc5d6d28d38fabf2276ab9a002b273529998b8/main.py#L10 You can get the total tokens for a request, then subtract it from the max tokens the model allows. Here's the cookbook...

IanCal

`filepaths_string` does not consistently generate correct Python code

2

Given this prompt: ```An example web page using React and HTML. It should have a text box for the user to enter some text with a button to submit it,...

thatliuser

rodaveli