mirror of
https://github.com/hwchase17/langchain.git
synced 2025-08-10 13:27:36 +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()
```
31 lines
1.2 KiB
Python
31 lines
1.2 KiB
Python
"""Test RetrievalQA functionality."""
|
|
|
|
from pathlib import Path
|
|
|
|
from langchain.chains import RetrievalQA
|
|
from langchain.chains.loading import load_chain
|
|
from langchain_text_splitters.character import CharacterTextSplitter
|
|
|
|
from langchain_community.document_loaders import TextLoader
|
|
from langchain_community.embeddings.openai import OpenAIEmbeddings
|
|
from langchain_community.llms import OpenAI
|
|
from langchain_community.vectorstores import FAISS
|
|
|
|
|
|
def test_retrieval_qa_saving_loading(tmp_path: Path) -> None:
|
|
"""Test saving and loading."""
|
|
loader = TextLoader("docs/extras/modules/state_of_the_union.txt")
|
|
documents = loader.load()
|
|
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
|
|
texts = text_splitter.split_documents(documents)
|
|
embeddings = OpenAIEmbeddings()
|
|
docsearch = FAISS.from_documents(texts, embeddings)
|
|
qa = RetrievalQA.from_llm(llm=OpenAI(), retriever=docsearch.as_retriever())
|
|
qa.run("What did the president say about Ketanji Brown Jackson?")
|
|
|
|
file_path = tmp_path / "RetrievalQA_chain.yaml"
|
|
qa.save(file_path=file_path)
|
|
qa_loaded = load_chain(file_path, retriever=docsearch.as_retriever())
|
|
|
|
assert qa_loaded == qa
|