mirror of
https://github.com/hwchase17/langchain
synced 2024-11-10 01:10:59 +00:00
f92006de3c
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>
89 lines
2.6 KiB
Python
89 lines
2.6 KiB
Python
"""Logic for converting internal query language to a valid Chroma query."""
|
|
from typing import Tuple, Union
|
|
|
|
from langchain_core.structured_query import (
|
|
Comparator,
|
|
Comparison,
|
|
Operation,
|
|
Operator,
|
|
StructuredQuery,
|
|
Visitor,
|
|
)
|
|
|
|
COMPARATOR_TO_TQL = {
|
|
Comparator.EQ: "==",
|
|
Comparator.GT: ">",
|
|
Comparator.GTE: ">=",
|
|
Comparator.LT: "<",
|
|
Comparator.LTE: "<=",
|
|
}
|
|
|
|
|
|
OPERATOR_TO_TQL = {
|
|
Operator.AND: "and",
|
|
Operator.OR: "or",
|
|
Operator.NOT: "NOT",
|
|
}
|
|
|
|
|
|
def can_cast_to_float(string: str) -> bool:
|
|
"""Check if a string can be cast to a float."""
|
|
try:
|
|
float(string)
|
|
return True
|
|
except ValueError:
|
|
return False
|
|
|
|
|
|
class DeepLakeTranslator(Visitor):
|
|
"""Translate `DeepLake` internal query language elements to valid filters."""
|
|
|
|
allowed_operators = [Operator.AND, Operator.OR, Operator.NOT]
|
|
"""Subset of allowed logical operators."""
|
|
allowed_comparators = [
|
|
Comparator.EQ,
|
|
Comparator.GT,
|
|
Comparator.GTE,
|
|
Comparator.LT,
|
|
Comparator.LTE,
|
|
]
|
|
"""Subset of allowed logical comparators."""
|
|
|
|
def _format_func(self, func: Union[Operator, Comparator]) -> str:
|
|
self._validate_func(func)
|
|
if isinstance(func, Operator):
|
|
value = OPERATOR_TO_TQL[func.value] # type: ignore
|
|
elif isinstance(func, Comparator):
|
|
value = COMPARATOR_TO_TQL[func.value] # type: ignore
|
|
return f"{value}"
|
|
|
|
def visit_operation(self, operation: Operation) -> str:
|
|
args = [arg.accept(self) for arg in operation.arguments]
|
|
operator = self._format_func(operation.operator)
|
|
return "(" + (" " + operator + " ").join(args) + ")"
|
|
|
|
def visit_comparison(self, comparison: Comparison) -> str:
|
|
comparator = self._format_func(comparison.comparator)
|
|
values = comparison.value
|
|
if isinstance(values, list):
|
|
tql = []
|
|
for value in values:
|
|
comparison.value = value
|
|
tql.append(self.visit_comparison(comparison))
|
|
|
|
return "(" + (" or ").join(tql) + ")"
|
|
|
|
if not can_cast_to_float(comparison.value):
|
|
values = f"'{values}'"
|
|
return f"metadata['{comparison.attribute}'] {comparator} {values}"
|
|
|
|
def visit_structured_query(
|
|
self, structured_query: StructuredQuery
|
|
) -> Tuple[str, dict]:
|
|
if structured_query.filter is None:
|
|
kwargs = {}
|
|
else:
|
|
tqL = f"SELECT * WHERE {structured_query.filter.accept(self)}"
|
|
kwargs = {"tql": tqL}
|
|
return structured_query.query, kwargs
|