admin/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

fix: metadata filtering condition variable unassigned; fix External K… (#19208)

Browse Source
This commit is contained in:
Will
2025-05-07 14:52:09 +08:00
committed by GitHub
parent d1c08a810b
commit bfa652f2d0
10 changed files with 101 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
api/core/rag/retrieval/dataset_retrieval.py
View File

@@ -149,7 +149,7 @@ class DatasetRetrieval:
else:
inputs = {}
available_datasets_ids = [dataset.id for dataset in available_datasets]
metadata_filter_document_ids, metadata_condition = self._get_metadata_filter_condition(
metadata_filter_document_ids, metadata_condition = self.get_metadata_filter_condition(
available_datasets_ids,
query,
tenant_id,
@@ -649,6 +649,8 @@ class DatasetRetrieval:
return_resource: bool,
invoke_from: InvokeFrom,
hit_callback: DatasetIndexToolCallbackHandler,
user_id: str,
inputs: dict,
) -> Optional[list[DatasetRetrieverBaseTool]]:
"""
A dataset tool is a tool that can be used to retrieve information from a dataset
@@ -706,6 +708,9 @@ class DatasetRetrieval:
hit_callbacks=[hit_callback],
return_resource=return_resource,
retriever_from=invoke_from.to_source(),
retrieve_config=retrieve_config,
user_id=user_id,
inputs=inputs,
)
tools.append(tool)
@@ -826,7 +831,7 @@ class DatasetRetrieval:
)
return filter_documents[:top_k] if top_k else filter_documents
def _get_metadata_filter_condition(
def get_metadata_filter_condition(
self,
dataset_ids: list,
query: str,
@@ -876,20 +881,31 @@ class DatasetRetrieval:
)
elif metadata_filtering_mode == "manual":
if metadata_filtering_conditions:
metadata_condition = MetadataCondition(**metadata_filtering_conditions.model_dump())
conditions = []
for sequence, condition in enumerate(metadata_filtering_conditions.conditions): # type: ignore
metadata_name = condition.name
expected_value = condition.value
if expected_value is not None or condition.comparison_operator in ("empty", "not empty"):
if expected_value is not None and condition.comparison_operator not in ("empty", "not empty"):
if isinstance(expected_value, str):
expected_value = self._replace_metadata_filter_value(expected_value, inputs)
filters = self._process_metadata_filter_func(
sequence,
condition.comparison_operator,
metadata_name,
expected_value,
filters,
conditions.append(
Condition(
name=metadata_name,
comparison_operator=condition.comparison_operator,
value=expected_value,
)
)
filters = self._process_metadata_filter_func(
sequence,
condition.comparison_operator,
metadata_name,
expected_value,
filters,
)
metadata_condition = MetadataCondition(
logical_operator=metadata_filtering_conditions.logical_operator,
conditions=conditions,
)
else:
raise ValueError("Invalid metadata filtering mode")
if filters: