langchain/libs/community/langchain_community/query_constructors/vectara.py

71 lines
2.1 KiB
Python
Raw Normal View History

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>
2024-05-08 20:46:52 +00:00
from typing import Tuple, Union
from langchain_core.structured_query import (
Comparator,
Comparison,
Operation,
Operator,
StructuredQuery,
Visitor,
)
def process_value(value: Union[int, float, str]) -> str:
"""Convert a value to a string and add single quotes if it is a string."""
if isinstance(value, str):
return f"'{value}'"
else:
return str(value)
class VectaraTranslator(Visitor):
"""Translate `Vectara` internal query language elements to valid filters."""
allowed_operators = [Operator.AND, Operator.OR]
"""Subset of allowed logical operators."""
allowed_comparators = [
Comparator.EQ,
Comparator.NE,
Comparator.GT,
Comparator.GTE,
Comparator.LT,
Comparator.LTE,
]
"""Subset of allowed logical comparators."""
def _format_func(self, func: Union[Operator, Comparator]) -> str:
map_dict = {
Operator.AND: " and ",
Operator.OR: " or ",
Comparator.EQ: "=",
Comparator.NE: "!=",
Comparator.GT: ">",
Comparator.GTE: ">=",
Comparator.LT: "<",
Comparator.LTE: "<=",
}
self._validate_func(func)
return map_dict[func]
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)
processed_value = process_value(comparison.value)
attribute = comparison.attribute
return (
"( " + "doc." + attribute + " " + comparator + " " + processed_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