You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/libs/community/langchain_community/query_constructors/astradb.py

72 lines
2.1 KiB
Python

multiple: langchain 0.2 in master (#21191) 0.2rc migrations - [x] Move memory - [x] Move remaining retrievers - [x] graph_qa chains - [x] some dependency from evaluation code potentially on math utils - [x] Move openapi chain from `langchain.chains.api.openapi` to `langchain_community.chains.openapi` - [x] Migrate `langchain.chains.ernie_functions` to `langchain_community.chains.ernie_functions` - [x] migrate `langchain/chains/llm_requests.py` to `langchain_community.chains.llm_requests` - [x] Moving `langchain_community.cross_enoders.base:BaseCrossEncoder` -> `langchain_community.retrievers.document_compressors.cross_encoder:BaseCrossEncoder` (namespace not ideal, but it needs to be moved to `langchain` to avoid circular deps) - [x] unit tests langchain -- add pytest.mark.community to some unit tests that will stay in langchain - [x] unit tests community -- move unit tests that depend on community to community - [x] mv integration tests that depend on community to community - [x] mypy checks Other todo - [x] Make deprecation warnings not noisy (need to use warn deprecated and check that things are implemented properly) - [x] Update deprecation messages with timeline for code removal (likely we actually won't be removing things until 0.4 release) -- will give people more time to transition their code. - [ ] Add information to deprecation warning to show users how to migrate their code base using langchain-cli - [ ] Remove any unnecessary requirements in langchain (e.g., is SQLALchemy required?) --------- Co-authored-by: Erick Friis <erick@langchain.dev>
5 months ago
"""Logic for converting internal query language to a valid AstraDB query."""
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() ```
3 months ago
multiple: langchain 0.2 in master (#21191) 0.2rc migrations - [x] Move memory - [x] Move remaining retrievers - [x] graph_qa chains - [x] some dependency from evaluation code potentially on math utils - [x] Move openapi chain from `langchain.chains.api.openapi` to `langchain_community.chains.openapi` - [x] Migrate `langchain.chains.ernie_functions` to `langchain_community.chains.ernie_functions` - [x] migrate `langchain/chains/llm_requests.py` to `langchain_community.chains.llm_requests` - [x] Moving `langchain_community.cross_enoders.base:BaseCrossEncoder` -> `langchain_community.retrievers.document_compressors.cross_encoder:BaseCrossEncoder` (namespace not ideal, but it needs to be moved to `langchain` to avoid circular deps) - [x] unit tests langchain -- add pytest.mark.community to some unit tests that will stay in langchain - [x] unit tests community -- move unit tests that depend on community to community - [x] mv integration tests that depend on community to community - [x] mypy checks Other todo - [x] Make deprecation warnings not noisy (need to use warn deprecated and check that things are implemented properly) - [x] Update deprecation messages with timeline for code removal (likely we actually won't be removing things until 0.4 release) -- will give people more time to transition their code. - [ ] Add information to deprecation warning to show users how to migrate their code base using langchain-cli - [ ] Remove any unnecessary requirements in langchain (e.g., is SQLALchemy required?) --------- Co-authored-by: Erick Friis <erick@langchain.dev>
5 months ago
from typing import Dict, Tuple, Union
from langchain_core.structured_query import (
Comparator,
Comparison,
Operation,
Operator,
StructuredQuery,
Visitor,
)
MULTIPLE_ARITY_COMPARATORS = [Comparator.IN, Comparator.NIN]
class AstraDBTranslator(Visitor):
"""Translate AstraDB internal query language elements to valid filters."""
"""Subset of allowed logical comparators."""
allowed_comparators = [
Comparator.EQ,
Comparator.NE,
Comparator.GT,
Comparator.GTE,
Comparator.LT,
Comparator.LTE,
Comparator.IN,
Comparator.NIN,
]
"""Subset of allowed logical operators."""
allowed_operators = [Operator.AND, Operator.OR]
def _format_func(self, func: Union[Operator, Comparator]) -> str:
self._validate_func(func)
map_dict = {
Operator.AND: "$and",
Operator.OR: "$or",
Comparator.EQ: "$eq",
Comparator.NE: "$ne",
Comparator.GTE: "$gte",
Comparator.LTE: "$lte",
Comparator.LT: "$lt",
Comparator.GT: "$gt",
Comparator.IN: "$in",
Comparator.NIN: "$nin",
}
return map_dict[func]
def visit_operation(self, operation: Operation) -> Dict:
args = [arg.accept(self) for arg in operation.arguments]
return {self._format_func(operation.operator): args}
def visit_comparison(self, comparison: Comparison) -> Dict:
if comparison.comparator in MULTIPLE_ARITY_COMPARATORS and not isinstance(
comparison.value, list
):
comparison.value = [comparison.value]
comparator = self._format_func(comparison.comparator)
return {comparison.attribute: {comparator: comparison.value}}
def visit_structured_query(
self, structured_query: StructuredQuery
) -> Tuple[str, dict]:
if structured_query.filter is None:
kwargs = {}
else:
kwargs = {"filter": structured_query.filter.accept(self)}
return structured_query.query, kwargs