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

fix multiple metadata filter's confusing setting (#16771)

Browse Source
This commit is contained in:
Jyong
2025-03-26 14:16:21 +08:00
committed by GitHub
parent 2da780e4dc
commit 6a857e01f6
2 changed files with 52 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
api/core/rag/retrieval/dataset_retrieval.py
View File

@@ -850,8 +850,9 @@ class DatasetRetrieval:
)
if automatic_metadata_filters:
conditions = []
for filter in automatic_metadata_filters:
for sequence, filter in enumerate(automatic_metadata_filters):
self._process_metadata_filter_func(
sequence,
filter.get("condition"), # type: ignore
filter.get("metadata_name"), # type: ignore
filter.get("value"),
@@ -871,14 +872,18 @@ class DatasetRetrieval:
elif metadata_filtering_mode == "manual":
if metadata_filtering_conditions:
metadata_condition = MetadataCondition(**metadata_filtering_conditions.model_dump())
for condition in metadata_filtering_conditions.conditions: # type: ignore
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 isinstance(expected_value, str):
expected_value = self._replace_metadata_filter_value(expected_value, inputs)
filters = self._process_metadata_filter_func(
condition.comparison_operator, metadata_name, expected_value, filters
sequence,
condition.comparison_operator,
metadata_name,
expected_value,
filters,
)
else:
raise ValueError("Invalid metadata filtering mode")
@@ -960,26 +965,36 @@ class DatasetRetrieval:
return None
return automatic_metadata_filters
def _process_metadata_filter_func(self, condition: str, metadata_name: str, value: Optional[Any], filters: list):
def _process_metadata_filter_func(
self, sequence: int, condition: str, metadata_name: str, value: Optional[Any], filters: list
):
key = f"{metadata_name}_{sequence}"
key_value = f"{metadata_name}_{sequence}_value"
match condition:
case "contains":
filters.append(
(text("documents.doc_metadata ->> :key LIKE :value")).params(key=metadata_name, value=f"%{value}%")
(text(f"documents.doc_metadata ->> :{key} LIKE :{key_value}")).params(
**{key: metadata_name, key_value: f"%{value}%"}
)
)
case "not contains":
filters.append(
(text("documents.doc_metadata ->> :key NOT LIKE :value")).params(
key=metadata_name, value=f"%{value}%"
(text(f"documents.doc_metadata ->> :{key} NOT LIKE :{key_value}")).params(
**{key: metadata_name, key_value: f"%{value}%"}
)
)
case "start with":
filters.append(
(text("documents.doc_metadata ->> :key LIKE :value")).params(key=metadata_name, value=f"{value}%")
(text(f"documents.doc_metadata ->> :{key} LIKE :{key_value}")).params(
**{key: metadata_name, key_value: f"{value}%"}
)
)
case "end with":
filters.append(
(text("documents.doc_metadata ->> :key LIKE :value")).params(key=metadata_name, value=f"%{value}")
(text(f"documents.doc_metadata ->> :{key} LIKE :{key_value}")).params(
**{key: metadata_name, key_value: f"%{value}"}
)
)
case "is" | "=":
if isinstance(value, str):