trustgraph/docs/tech-specs
cybermaggedon aa4f5c6c00
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
2026-03-11 10:51:39 +00:00
..
__TEMPLATE.md Add template (#463) 2025-08-21 14:50:57 +01:00
architecture-principles.md More config cli (#466) 2025-08-22 13:36:10 +01:00
cassandra-consolidation.md Feature/consolidate cassandra config (#483) 2025-09-03 23:41:22 +01:00
cassandra-performance-refactor.md Collection delete pt. 3 (#542) 2025-09-30 16:02:33 +01:00
collection-management.md Address legacy issues in storage management (#595) 2026-01-05 13:45:14 +00:00
document-embeddings-chunk-id.md Document chunks not stored in vector store (#665) 2026-03-07 23:10:45 +00:00
embeddings-batch-processing.md Batch embeddings (#668) 2026-03-08 18:36:54 +00:00
entity-centric-graph.md Fix Cassandra schema and graph filter semantics (#680) 2026-03-10 12:52:51 +00:00
extraction-flows.md Remove redundant metadata (#685) 2026-03-11 10:51:39 +00:00
extraction-time-provenance.md Extract-time provenance (#661) 2026-03-05 18:36:10 +00:00
flow-class-definition.md Fix config inconsistency (#609) 2026-01-14 12:31:40 +00:00
flow-configurable-parameters.md Fix config inconsistency (#609) 2026-01-14 12:31:40 +00:00
graph-contexts.md Changed schema for Value -> Term, majorly breaking change (#622) 2026-01-27 13:48:08 +00:00
graphql-query.md Feature/graphql table query (#486) 2025-09-03 23:39:11 +01:00
graphrag-performance-optimization.md Graph rag optimisations (#527) 2025-09-23 21:05:51 +01:00
import-export-graceful-shutdown.md Fix import export graceful shutdown (#476) 2025-08-28 13:39:28 +01:00
jsonl-prompt-output.md Feature/prompts jsonl (#619) 2026-01-26 17:38:00 +00:00
large-document-loading.md Incremental / large document loading (#659) 2026-03-04 16:57:58 +00:00
logging-strategy.md Loki logging (#586) 2025-12-09 23:24:41 +00:00
mcp-tool-arguments.md More config cli (#466) 2025-08-22 13:36:10 +01:00
mcp-tool-bearer-token.md MCP auth for the simple case (#557) 2025-11-11 12:28:53 +00:00
minio-to-s3-migration.md Change MinIO integration options in librarian to be more generic - to support a Garage integration (#594) 2025-12-27 18:01:51 +00:00
more-config-cli.md More config cli (#466) 2025-08-22 13:36:10 +01:00
multi-tenant-support.md Address legacy issues in storage management (#595) 2026-01-05 13:45:14 +00:00
neo4j-user-collection-isolation.md Feature/neo4j user collection isolation (#509) 2025-09-10 22:11:21 +01:00
ontology-extract-phase-2.md Feature/improve ontology extract (#576) 2025-12-03 13:36:10 +00:00
ontology.md OntoRAG: Ontology-Based Knowledge Extraction and Query Technical Specification (#523) 2025-11-12 20:38:08 +00:00
ontorag.md Update tech spec (#558) 2025-11-13 16:29:20 +00:00
openapi-spec.md REST API OpenAPI spec (#612) 2026-01-15 11:04:37 +00:00
pubsub.md Messaging fabric plugins (#592) 2025-12-17 21:40:43 +00:00
python-api-refactor.md Python API implements streaming interfaces (#577) 2025-12-04 17:38:57 +00:00
query-time-explainability.md Update tech spec (#678) 2026-03-10 10:07:37 +00:00
rag-streaming-support.md Streaming rag responses (#568) 2025-11-26 19:47:39 +00:00
schema-refactoring-proposal.md More config cli (#466) 2025-08-22 13:36:10 +01:00
streaming-llm-responses.md Feature/streaming llm phase 1 (#566) 2025-11-26 09:59:10 +00:00
structured-data-2.md Row embeddings APIs exposed (#646) 2026-02-23 21:52:56 +00:00
structured-data-descriptor.md Structured data loader cli (#498) 2025-09-05 15:38:18 +01:00
structured-data-schemas.md More config cli (#466) 2025-08-22 13:36:10 +01:00
structured-data.md Remove graphql collection param (#489) 2025-09-04 10:04:09 +01:00
structured-diag-service.md Structure data diagnosis service (#518) 2025-09-16 21:43:23 +01:00
tool-group.md Feature/tool group (#484) 2025-09-03 23:39:49 +01:00
tool-services.md Tool services - dynamically pluggable tool implementations for agent frameworks (#658) 2026-03-04 14:51:32 +00:00
vector-store-lifecycle.md Fix hard coded vector size (#555) 2025-11-10 16:56:51 +00:00