langchain/libs/community/langchain_community/utilities/rememberizer.py

53 lines
1.7 KiB
Python
Raw Normal View History

"""Wrapper for Rememberizer APIs."""
infra: update mypy 1.10, ruff 0.5 (#23721) ```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() ```
2024-07-03 17:33:27 +00:00
from typing import Any, Dict, List, Optional, cast
import requests
from langchain_core.documents import Document
from langchain_core.utils import get_from_dict_or_env
from pydantic import BaseModel, model_validator
class RememberizerAPIWrapper(BaseModel):
"""Wrapper for Rememberizer APIs."""
top_k_results: int = 10
rememberizer_api_key: Optional[str] = None
@model_validator(mode="before")
@classmethod
def validate_environment(cls, values: Dict) -> Any:
"""Validate that api key in environment."""
rememberizer_api_key = get_from_dict_or_env(
values, "rememberizer_api_key", "REMEMBERIZER_API_KEY"
)
values["rememberizer_api_key"] = rememberizer_api_key
return values
def search(self, query: str) -> dict:
"""Search for a query in the Rememberizer API."""
url = f"https://api.rememberizer.ai/api/v1/documents/search?q={query}&n={self.top_k_results}"
response = requests.get(
url, headers={"x-api-key": cast(str, self.rememberizer_api_key)}
)
data = response.json()
if response.status_code != 200:
raise ValueError(f"API Error: {data}")
matched_chunks = data.get("matched_chunks", [])
return matched_chunks
def load(self, query: str) -> List[Document]:
matched_chunks = self.search(query)
docs = []
for matched_chunk in matched_chunks:
docs.append(
Document(
page_content=matched_chunk["matched_content"],
metadata=matched_chunk["document"],
)
)
return docs