mirror of
https://github.com/hwchase17/langchain
synced 2024-11-11 19:11:02 +00:00
a0c2281540
```python
"""python scripts/update_mypy_ruff.py"""
import glob
import tomllib
from pathlib import Path
import toml
import subprocess
import re
ROOT_DIR = Path(__file__).parents[1]
def main():
for path in glob.glob(str(ROOT_DIR / "libs/**/pyproject.toml"), recursive=True):
print(path)
with open(path, "rb") as f:
pyproject = tomllib.load(f)
try:
pyproject["tool"]["poetry"]["group"]["typing"]["dependencies"]["mypy"] = (
"^1.10"
)
pyproject["tool"]["poetry"]["group"]["lint"]["dependencies"]["ruff"] = (
"^0.5"
)
except KeyError:
continue
with open(path, "w") as f:
toml.dump(pyproject, f)
cwd = "/".join(path.split("/")[:-1])
completed = subprocess.run(
"poetry lock --no-update; poetry install --with typing; poetry run mypy . --no-color",
cwd=cwd,
shell=True,
capture_output=True,
text=True,
)
logs = completed.stdout.split("\n")
to_ignore = {}
for l in logs:
if re.match("^(.*)\:(\d+)\: error:.*\[(.*)\]", l):
path, line_no, error_type = re.match(
"^(.*)\:(\d+)\: error:.*\[(.*)\]", l
).groups()
if (path, line_no) in to_ignore:
to_ignore[(path, line_no)].append(error_type)
else:
to_ignore[(path, line_no)] = [error_type]
print(len(to_ignore))
for (error_path, line_no), error_types in to_ignore.items():
all_errors = ", ".join(error_types)
full_path = f"{cwd}/{error_path}"
try:
with open(full_path, "r") as f:
file_lines = f.readlines()
except FileNotFoundError:
continue
file_lines[int(line_no) - 1] = (
file_lines[int(line_no) - 1][:-1] + f" # type: ignore[{all_errors}]\n"
)
with open(full_path, "w") as f:
f.write("".join(file_lines))
subprocess.run(
"poetry run ruff format .; poetry run ruff --select I --fix .",
cwd=cwd,
shell=True,
capture_output=True,
text=True,
)
if __name__ == "__main__":
main()
```
65 lines
1.4 KiB
Python
65 lines
1.4 KiB
Python
"""
|
|
**RL (Reinforcement Learning) Chain** leverages the `Vowpal Wabbit (VW)` models
|
|
for reinforcement learning with a context, with the goal of modifying
|
|
the prompt before the LLM call.
|
|
|
|
[Vowpal Wabbit](https://vowpalwabbit.org/) provides fast, efficient,
|
|
and flexible online machine learning techniques for reinforcement learning,
|
|
supervised learning, and more.
|
|
"""
|
|
|
|
import logging
|
|
|
|
from langchain_experimental.rl_chain.base import (
|
|
AutoSelectionScorer,
|
|
BasedOn,
|
|
Embed,
|
|
Embedder,
|
|
Policy,
|
|
SelectionScorer,
|
|
ToSelectFrom,
|
|
VwPolicy,
|
|
embed,
|
|
stringify_embedding,
|
|
)
|
|
from langchain_experimental.rl_chain.pick_best_chain import (
|
|
PickBest,
|
|
PickBestEvent,
|
|
PickBestFeatureEmbedder,
|
|
PickBestRandomPolicy,
|
|
PickBestSelected,
|
|
)
|
|
|
|
|
|
def configure_logger() -> None:
|
|
logger = logging.getLogger(__name__)
|
|
logger.setLevel(logging.INFO)
|
|
ch = logging.StreamHandler()
|
|
formatter = logging.Formatter(
|
|
"%(asctime)s - %(name)s - %(levelname)s - %(message)s"
|
|
)
|
|
ch.setFormatter(formatter)
|
|
ch.setLevel(logging.INFO)
|
|
logger.addHandler(ch)
|
|
|
|
|
|
configure_logger()
|
|
|
|
__all__ = [
|
|
"PickBest",
|
|
"PickBestEvent",
|
|
"PickBestSelected",
|
|
"PickBestFeatureEmbedder",
|
|
"PickBestRandomPolicy",
|
|
"Embed",
|
|
"BasedOn",
|
|
"ToSelectFrom",
|
|
"SelectionScorer",
|
|
"AutoSelectionScorer",
|
|
"Embedder",
|
|
"Policy",
|
|
"VwPolicy",
|
|
"embed",
|
|
"stringify_embedding",
|
|
]
|