Files
gpt-engineer/scripts/benchmark.py
Anton Osika e90ac46fc8 Merge branch 'main' of github.com:AntonOsika/gpt-engineer
* 'main' of github.com:AntonOsika/gpt-engineer:
  Mark test as failed because it requires OpenAI API access currently
  `black`
  Create test_ai.py
  fix to_files
  execute_workspace -> gen_entrypoint; execute_entrypoint
  Ignore my-new-project/
  Added CODE_OF_CONDUCT.md to the .github directory (#147)
  make pre commit pass in the whole codebase (#149)
  Create ci.yaml
  Fix linting
  Add support for directory paths in filenames and improve code splitting - Enforce an explicit markdown code block format - Add a token to split the output to clearly detect when the code blocks start - Save all non-code output to a `README.md` file - Update RegEx to extract and strip text more reliably and clean up the output - Update the identify prompts appropriately
  Enhance philosophy to include supporting documents - Create instructions for running/compiling the project - Create any package manager files
  Generate instructions for all platforms - Update prompt to create instructions for all 3 major OS platforms - Fix small typo
  Add support for directory creation and binary files - Use the `Path` module instead of `os` - Add ability to create any amount of missing directories for a given file - Add ability to save both text and binary files to save images (or other file types) later
  Add cleanup & move `projects` to their own directory - Add optional argument to clean and delete the working directories of the project before running the prompt - Add `.gitignore` entry to ignore all possible projects - Update readme
2023-06-18 15:13:34 +02:00

68 lines
1.8 KiB
Python

# list all folders in benchmark folder
# for each folder, run the benchmark
import os
import subprocess
from itertools import islice
from pathlib import Path
from typer import run
def main(
n_benchmarks: int | None = None,
):
path = Path("benchmark")
folders = path.iterdir()
if n_benchmarks:
folders = islice(folders, n_benchmarks)
benchmarks = []
for bench_folder in folders:
if os.path.isdir(bench_folder):
print("Running benchmark for {}".format(bench_folder))
log_path = bench_folder / "log.txt"
log_file = open(log_path, "w")
process = subprocess.Popen(
[
"python",
"-u", # Unbuffered output
"-m",
"gpt_engineer.main",
bench_folder,
"--steps-config",
"benchmark",
],
stdout=log_file,
stderr=log_file,
bufsize=0,
)
benchmarks.append((bench_folder, process, log_file))
print("You can stream the log file by running: tail -f {}".format(log_path))
for bench_folder, process, file in benchmarks:
process.wait()
file.close()
print("process", bench_folder.name, "finished with code", process.returncode)
print('Running it. Original benchmark prompt:')
print()
with open(bench_folder / "main_prompt") as f:
print(f.read())
print()
try:
subprocess.run(
['python', "-m", "gpt_engineer.main", bench_folder, "--steps-config", "execute_only"],
)
except KeyboardInterrupt:
pass
if __name__ == "__main__":
run(main)