GPT Repo Loader
Dev tools
ai coding context
SHOW HN2023
373points
149comments
#93of 3,109 in 2023
Top 3%of 2023 by points
How HN took it
CuriousMostly questions and neutral comments
10 positive, 28 neutral or asking, 0 mixed, 17 critical, out of 55 comments about the project. Thread score -0.18.
Idea: 3 for, 7 againstExecution: 3 for, 4 againstPerformance: 0 for, 2 againstPrivacy: 0 for, 2 againstPricing: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Useful tool and nice idea
From 2 comments
Seems to be very useful! Thanks for making it!
yangjunyu on HNnow that's a name I haven't seen in years, hi mpoon! also this is slick as hell
fire on HN
Objections
Token limits make whole-repo loading impractical for real projects
From 3 comments
So I just tried it out. The output.txt which was generated was... 375mb of mostly binary junk. I'm a lazy lark and have lots of nonsense in this repo which I shouldn't, but I was…
joenot443 on HNI’m curious to see how this turns out as well, though you’ll probably have to devise a workaround for the token limit for this to be effective for all but the smallest projects.
textninja on HNI'm waiting on my GPT-4 API access so I can use gpt-4-32k which maybe can soak up 10k LOC? Clearly this will break eventually, but I am playing around with some ideas to extend…
mpoon on HN
Sending code to OpenAI raises privacy and commercial IP concerns
From 2 comments
Before anyone working on commercial code bases thinks to use this, stop. Uploaded code becomes part of OpenAI.
tflinton on HNisn't this a massive privacy violation? any employer would most likely not be okay with this.
hackernewds on HN
API cost per call is very high
From 2 comments
Just remember the API charge is 6c per input token [1]. If you push 32k input tokens in, you're looking at $2000 per API call just as input. You... might wanna consider a self…
wokwokwok on HN6c per thousand tokens, so $2 per maxed out API call
dangond on HN
Slow for interactive use
From 1 comment
It's just so slow for the autocompletion use case to do it like that. Ideally, you're never chaining serial requests to the LLM. Even if you do stuff in all the data into a…
alooPotato on HN
Requests
Embeddings or retrieval instead of dumping the whole repo into the prompt
From 3 comments
Im no expert, but wouldn't it make more sense to give the repo-context (structure, source code, PRs, Issues, ...) as embeddings? You could use langchain to generate an embedding…
underlines on HNThis will fail to get the commit history over time, as it's just reads files in the directory. If this was using the git library and…
amrb on HNFrom what I understand this seems useful if you have a model that will accept a large or unlimited number of tokens. I was looking into doing the same thing with ChatGPT and went…
bebrws on HN
Let the model pick relevant files first
From 1 comment
This is awesome, can't wait to get api access to the 32k token model. Rather than this approach of just converting the whole repo to a text file, what I'm thinking is, you can…
ftufek on HN
Questions
How does the output file get used with ChatGPT?
From 1 comment
Maybe I didn't understand the usage of this but how is this output.txt file that this repo generates to be used and provided as an input to chatgpt. Can someone eloborate this…
printvoid on HN
How much text can GPT-4 accept?
From 2 comments
How much text can you feed GPT-4? Our codebase is 1 million lines of code. Can we feed the documentation to it? What are the limits? Is it possible to train it on our data…
EGreg on HNnice. general question: how many lines of code (at 120 char col len) could you send in one prompt? also, the entire thing is literally 60 lines of python. sometimes i don't get…
kanyethegreat on HN
Alternatives named
GitHub Copilot
From 1 comment
Wouldn't GitHub copilot not solve the repository load problem?
darshanps on HN
Embeddings with langchain or ada
From 2 comments
Im no expert, but wouldn't it make more sense to give the repo-context (structure, source code, PRs, Issues, ...) as embeddings? You could use langchain to generate an embedding…
underlines on HNFrom what I understand this seems useful if you have a model that will accept a large or unlimited number of tokens. I was looking into doing the same thing with ChatGPT and went…
bebrws on HN
AutoPR GitHub Action
From 1 comment
So I have been toying with an AutoPR GitHub Action for a bit but seeing this spurred me to actually put it into a format for y'all to try. It uses GPT-4 to automatically generate…
irgolic on HN
Fine-tuning a model on business data
From 1 comment
Seeing a lot of comments in here about the token limits. Another path you can take is to fine tune a model on your business. Each training item has to fit within the token limit,…
bob1029 on HN