langchain/libs/community/langchain_community/query_constructors/elasticsearch.py
Eugene Yurtsev f92006de3c
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 16:46:52 -04:00

101 lines
3.2 KiB
Python

from typing import Dict, Tuple, Union
from langchain_core.structured_query import (
Comparator,
Comparison,
Operation,
Operator,
StructuredQuery,
Visitor,
)
class ElasticsearchTranslator(Visitor):
"""Translate `Elasticsearch` internal query language elements to valid filters."""
allowed_comparators = [
Comparator.EQ,
Comparator.GT,
Comparator.GTE,
Comparator.LT,
Comparator.LTE,
Comparator.CONTAIN,
Comparator.LIKE,
]
"""Subset of allowed logical comparators."""
allowed_operators = [Operator.AND, Operator.OR, Operator.NOT]
"""Subset of allowed logical operators."""
def _format_func(self, func: Union[Operator, Comparator]) -> str:
self._validate_func(func)
map_dict = {
Operator.OR: "should",
Operator.NOT: "must_not",
Operator.AND: "must",
Comparator.EQ: "term",
Comparator.GT: "gt",
Comparator.GTE: "gte",
Comparator.LT: "lt",
Comparator.LTE: "lte",
Comparator.CONTAIN: "match",
Comparator.LIKE: "match",
}
return map_dict[func]
def visit_operation(self, operation: Operation) -> Dict:
args = [arg.accept(self) for arg in operation.arguments]
return {"bool": {self._format_func(operation.operator): args}}
def visit_comparison(self, comparison: Comparison) -> Dict:
# ElasticsearchStore filters require to target
# the metadata object field
field = f"metadata.{comparison.attribute}"
is_range_comparator = comparison.comparator in [
Comparator.GT,
Comparator.GTE,
Comparator.LT,
Comparator.LTE,
]
if is_range_comparator:
value = comparison.value
if isinstance(comparison.value, dict) and "date" in comparison.value:
value = comparison.value["date"]
return {"range": {field: {self._format_func(comparison.comparator): value}}}
if comparison.comparator == Comparator.CONTAIN:
return {
self._format_func(comparison.comparator): {
field: {"query": comparison.value}
}
}
if comparison.comparator == Comparator.LIKE:
return {
self._format_func(comparison.comparator): {
field: {"query": comparison.value, "fuzziness": "AUTO"}
}
}
# we assume that if the value is a string,
# we want to use the keyword field
field = f"{field}.keyword" if isinstance(comparison.value, str) else field
if isinstance(comparison.value, dict):
if "date" in comparison.value:
comparison.value = comparison.value["date"]
return {self._format_func(comparison.comparator): {field: 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