mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-28 18:06:21 +02:00
Remove redundant metadata (#685)
The metadata field (list of triples) in the pipeline Metadata class was redundant. Document metadata triples already flow directly from librarian to triple-store via emit_document_provenance() - they don't need to pass through the extraction pipeline. Additionally, chunker and PDF decoder were overwriting metadata to [] anyway, so any metadata passed through the pipeline was being discarded. Changes: - Remove metadata field from Metadata dataclass (schema/core/metadata.py) - Update all Metadata instantiations to remove metadata=[] parameter - Remove metadata handling from translators (document_loading, knowledge) - Remove metadata consumption from extractors (ontology, agent) - Update gateway serializers and import handlers - Update all unit, integration, and contract tests
This commit is contained in:
parent
1837d73f34
commit
aa4f5c6c00
37 changed files with 106 additions and 343 deletions
|
|
@ -55,13 +55,6 @@ def sample_objects_message():
|
|||
return {
|
||||
"metadata": {
|
||||
"id": "obj-123",
|
||||
"metadata": [
|
||||
{
|
||||
"s": {"v": "obj-123", "e": False},
|
||||
"p": {"v": "source", "e": False},
|
||||
"o": {"v": "test", "e": False}
|
||||
}
|
||||
],
|
||||
"user": "testuser",
|
||||
"collection": "testcollection"
|
||||
},
|
||||
|
|
@ -244,7 +237,6 @@ class TestRowsImportMessageProcessing:
|
|||
assert sent_object.metadata.id == "obj-123"
|
||||
assert sent_object.metadata.user == "testuser"
|
||||
assert sent_object.metadata.collection == "testcollection"
|
||||
assert len(sent_object.metadata.metadata) == 1 # One triple in metadata
|
||||
|
||||
@patch('trustgraph.gateway.dispatch.rows_import.Publisher')
|
||||
@pytest.mark.asyncio
|
||||
|
|
@ -277,7 +269,6 @@ class TestRowsImportMessageProcessing:
|
|||
assert sent_object.values[0]["field1"] == "value1"
|
||||
assert sent_object.confidence == 1.0 # Default value
|
||||
assert sent_object.source_span == "" # Default value
|
||||
assert len(sent_object.metadata.metadata) == 0 # Default empty list
|
||||
|
||||
@patch('trustgraph.gateway.dispatch.rows_import.Publisher')
|
||||
@pytest.mark.asyncio
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue