mirror of
https://github.com/hwchase17/langchain.git
synced 2025-11-22 15:58:15 +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()
```
96 lines
3.1 KiB
Python
96 lines
3.1 KiB
Python
"""
|
|
We provide two strategies for generating thoughts in the Tree of Thoughts (ToT)
|
|
framework to avoid repetition:
|
|
|
|
These strategies ensure that the language model generates diverse and
|
|
non-repeating thoughts, which are crucial for problem-solving tasks that require
|
|
exploration.
|
|
"""
|
|
|
|
from abc import abstractmethod
|
|
from typing import Any, Dict, List, Tuple
|
|
|
|
from langchain.chains.llm import LLMChain
|
|
from langchain_core.prompts.base import BasePromptTemplate
|
|
|
|
from langchain_experimental.pydantic_v1 import Field
|
|
from langchain_experimental.tot.prompts import get_cot_prompt, get_propose_prompt
|
|
|
|
|
|
class BaseThoughtGenerationStrategy(LLMChain):
|
|
"""
|
|
Base class for a thought generation strategy.
|
|
"""
|
|
|
|
c: int = 3
|
|
"""The number of children thoughts to propose at each step."""
|
|
|
|
@abstractmethod
|
|
def next_thought(
|
|
self,
|
|
problem_description: str,
|
|
thoughts_path: Tuple[str, ...] = (),
|
|
**kwargs: Any,
|
|
) -> str:
|
|
"""
|
|
Generate the next thought given the problem description and the thoughts
|
|
generated so far.
|
|
"""
|
|
|
|
|
|
class SampleCoTStrategy(BaseThoughtGenerationStrategy):
|
|
"""
|
|
Sample strategy from a Chain-of-Thought (CoT) prompt.
|
|
|
|
This strategy works better when the thought space is rich, such as when each
|
|
thought is a paragraph. Independent and identically distributed samples
|
|
lead to diversity, which helps to avoid repetition.
|
|
"""
|
|
|
|
prompt: BasePromptTemplate = Field(default_factory=get_cot_prompt)
|
|
|
|
def next_thought(
|
|
self,
|
|
problem_description: str,
|
|
thoughts_path: Tuple[str, ...] = (),
|
|
**kwargs: Any,
|
|
) -> str:
|
|
response_text = self.predict_and_parse(
|
|
problem_description=problem_description, thoughts=thoughts_path, **kwargs
|
|
)
|
|
return response_text if isinstance(response_text, str) else ""
|
|
|
|
|
|
class ProposePromptStrategy(BaseThoughtGenerationStrategy):
|
|
"""
|
|
Strategy that is sequentially using a "propose prompt".
|
|
|
|
This strategy works better when the thought space is more constrained, such
|
|
as when each thought is just a word or a line. Proposing different thoughts
|
|
in the same prompt completion helps to avoid duplication.
|
|
"""
|
|
|
|
prompt: BasePromptTemplate = Field(default_factory=get_propose_prompt)
|
|
tot_memory: Dict[Tuple[str, ...], List[str]] = Field(default_factory=dict)
|
|
|
|
def next_thought(
|
|
self,
|
|
problem_description: str,
|
|
thoughts_path: Tuple[str, ...] = (),
|
|
**kwargs: Any,
|
|
) -> str:
|
|
if thoughts_path not in self.tot_memory or not self.tot_memory[thoughts_path]:
|
|
new_thoughts = self.predict_and_parse(
|
|
problem_description=problem_description,
|
|
thoughts=thoughts_path,
|
|
n=self.c,
|
|
**kwargs,
|
|
)
|
|
if not new_thoughts:
|
|
return ""
|
|
if isinstance(new_thoughts, list):
|
|
self.tot_memory[thoughts_path] = new_thoughts[::-1]
|
|
else:
|
|
return ""
|
|
return self.tot_memory[thoughts_path].pop()
|