mirror of
https://github.com/hwchase17/langchain
synced 2024-11-10 01:10:59 +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()
```
70 lines
2.2 KiB
Python
70 lines
2.2 KiB
Python
"""Experimental implementation of jsonformer wrapped LLM."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from typing import TYPE_CHECKING, Any, List, Optional, cast
|
|
|
|
from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline
|
|
from langchain_core.callbacks.manager import CallbackManagerForLLMRun
|
|
|
|
from langchain_experimental.pydantic_v1 import Field, root_validator
|
|
|
|
if TYPE_CHECKING:
|
|
import jsonformer
|
|
|
|
|
|
def import_jsonformer() -> jsonformer:
|
|
"""Lazily import of the jsonformer package."""
|
|
try:
|
|
import jsonformer
|
|
except ImportError:
|
|
raise ImportError(
|
|
"Could not import jsonformer python package. "
|
|
"Please install it with `pip install jsonformer`."
|
|
)
|
|
return jsonformer
|
|
|
|
|
|
class JsonFormer(HuggingFacePipeline):
|
|
"""Jsonformer wrapped LLM using HuggingFace Pipeline API.
|
|
|
|
This pipeline is experimental and not yet stable.
|
|
"""
|
|
|
|
json_schema: dict = Field(..., description="The JSON Schema to complete.")
|
|
max_new_tokens: int = Field(
|
|
default=200, description="Maximum number of new tokens to generate."
|
|
)
|
|
debug: bool = Field(default=False, description="Debug mode.")
|
|
|
|
# TODO: move away from `root_validator` since it is deprecated in pydantic v2
|
|
# and causes mypy type-checking failures (hence the `type: ignore`)
|
|
@root_validator # type: ignore[call-overload]
|
|
def check_jsonformer_installation(cls, values: dict) -> dict:
|
|
import_jsonformer()
|
|
return values
|
|
|
|
def _call(
|
|
self,
|
|
prompt: str,
|
|
stop: Optional[List[str]] = None,
|
|
run_manager: Optional[CallbackManagerForLLMRun] = None,
|
|
**kwargs: Any,
|
|
) -> str:
|
|
jsonformer = import_jsonformer()
|
|
from transformers import Text2TextGenerationPipeline
|
|
|
|
pipeline = cast(Text2TextGenerationPipeline, self.pipeline)
|
|
|
|
model = jsonformer.Jsonformer(
|
|
model=pipeline.model,
|
|
tokenizer=pipeline.tokenizer,
|
|
json_schema=self.json_schema,
|
|
prompt=prompt,
|
|
max_number_tokens=self.max_new_tokens,
|
|
debug=self.debug,
|
|
)
|
|
text = model()
|
|
return json.dumps(text)
|