gpt-engineer

gpt-engineer copied to clipboard

Clearer contribution and merging directives for github

1

ATheorell

KeyError in apply_edits breaking improve mode

8

I am running improve mode, creating c# and xaml. GPT Engineer is attempting to make updates to a xaml user control (here renamed to be "myExistingUserControl.xaml") and running into an...

baldmanwithbeard

potential fix for some/dir/ bug #928

2

The problem in bug #928 is that "some/dir/" is used as a placeholder to indicate that a filename should be represented by a relative path. The placeholder is introduced in...

ATheorell

Docker command show error on running

9

when try to run the gpt-engineer from docker I recieve this error : docker run -it --rm -e OPENAI_API_KEY=sk-iv9R5S5u0XqSmTdR1JnOT3BlbkFJSxxxxxxxxx -v .\:/project gpt-engineer **/app/entrypoint.sh: line 3: $'\r': command not found unning...

cor277

docker install get a error Multiple top-level packages discovered in a flat-layout: ['docker', 'projects', 'gpt_engineer'].

2

` => ERROR [8/9] RUN sudo pip install -e . 4.1s ------ > [8/9] RUN sudo pip install -e .: 0.442 Looking in indexes: https://pypi.doubanio.com/simple 0.442 Obtaining file:///app 0.448 Installing...

xjspace

Run Langsmith Evals

3

Two steps to run (after getting a [Langsmith API Key)](https://docs.smith.langchain.com/) 1. Upload dataset (currently just using the existing benchmark) ```python python langsmith_evals --action upload ``` 2. Run eval ```python python...

hinthornw

Add Missing Docstrings in Test Files

7

### PR Feedback (click) - [ ] 👍 Sweep Did Well - [ ] 👎 Sweep Needs Improvement ### I created this PR to address this rule: "Ensure all new...

sweep-ai[bot]

## Feature description We have a way to easily add benchmarks: https://www.loom.com/share/206805143fbb4302b5455a5329eaab17?sid=f689608f-8e49-44f7-b55f-4c81e9dc93e6 This issue is about looking into if [mbpp](https://huggingface.co/datasets/mbpp) is a good benchmark to add and then add a...

AntonOsika

Automatic benchmarking of gpt-engineer with swe-bench

6

## Feature description We have a way to easily add benchmarks: https://www.loom.com/share/206805143fbb4302b5455a5329eaab17?sid=f689608f-8e49-44f7-b55f-4c81e9dc93e6 This issue is about looking into if [swe-bench](https://github.com/princeton-nlp/SWE-bench) is a good benchmark to add and then add a...

AntonOsika

Automatic benchmarking of gpt-engineer with APPS

2

## Feature description gpt-engineer has an automatic evals suite in "evals/eval_new_code.py". However, only 2 test cases are given in evals/new_code_eval.yaml . An alternative to filling in more testcases manually, we...

ATheorell