mirror of
https://github.com/hwchase17/langchain.git
synced 2025-11-23 00:10:58 +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()
```
84 lines
2.5 KiB
Python
84 lines
2.5 KiB
Python
"""Milvus Retriever"""
|
|
|
|
import warnings
|
|
from typing import Any, Dict, List, Optional
|
|
|
|
from langchain_core.callbacks import CallbackManagerForRetrieverRun
|
|
from langchain_core.documents import Document
|
|
from langchain_core.embeddings import Embeddings
|
|
from langchain_core.pydantic_v1 import root_validator
|
|
from langchain_core.retrievers import BaseRetriever
|
|
|
|
from langchain_community.vectorstores.milvus import Milvus
|
|
|
|
# TODO: Update to MilvusClient + Hybrid Search when available
|
|
|
|
|
|
class MilvusRetriever(BaseRetriever):
|
|
"""`Milvus API` retriever."""
|
|
|
|
embedding_function: Embeddings
|
|
collection_name: str = "LangChainCollection"
|
|
collection_properties: Optional[Dict[str, Any]] = None
|
|
connection_args: Optional[Dict[str, Any]] = None
|
|
consistency_level: str = "Session"
|
|
search_params: Optional[dict] = None
|
|
|
|
store: Milvus
|
|
retriever: BaseRetriever
|
|
|
|
@root_validator(pre=True)
|
|
def create_retriever(cls, values: Dict) -> Dict:
|
|
"""Create the Milvus store and retriever."""
|
|
values["store"] = Milvus(
|
|
values["embedding_function"],
|
|
values["collection_name"],
|
|
values["collection_properties"],
|
|
values["connection_args"],
|
|
values["consistency_level"],
|
|
)
|
|
values["retriever"] = values["store"].as_retriever(
|
|
search_kwargs={"param": values["search_params"]}
|
|
)
|
|
return values
|
|
|
|
def add_texts(
|
|
self, texts: List[str], metadatas: Optional[List[dict]] = None
|
|
) -> None:
|
|
"""Add text to the Milvus store
|
|
|
|
Args:
|
|
texts (List[str]): The text
|
|
metadatas (List[dict]): Metadata dicts, must line up with existing store
|
|
"""
|
|
self.store.add_texts(texts, metadatas)
|
|
|
|
def _get_relevant_documents(
|
|
self,
|
|
query: str,
|
|
*,
|
|
run_manager: CallbackManagerForRetrieverRun,
|
|
**kwargs: Any,
|
|
) -> List[Document]:
|
|
return self.retriever.invoke(
|
|
query, run_manager=run_manager.get_child(), **kwargs
|
|
)
|
|
|
|
|
|
def MilvusRetreiver(*args: Any, **kwargs: Any) -> MilvusRetriever:
|
|
"""Deprecated MilvusRetreiver. Please use MilvusRetriever ('i' before 'e') instead.
|
|
|
|
Args:
|
|
*args:
|
|
**kwargs:
|
|
|
|
Returns:
|
|
MilvusRetriever
|
|
"""
|
|
warnings.warn(
|
|
"MilvusRetreiver will be deprecated in the future. "
|
|
"Please use MilvusRetriever ('i' before 'e') instead.",
|
|
DeprecationWarning,
|
|
)
|
|
return MilvusRetriever(*args, **kwargs)
|