cybermaggedon
29b4300808
Updated test suite for explainability & provenance ( #696 )
...
* Provenance tests
* Embeddings tests
* Test librarian
* Test triples stream
* Test concurrency
* Entity centric graph writes
* Agent tool service tests
* Structured data tests
* RDF tests
* Addition LLM tests
* Reliability tests
2026-03-13 14:27:42 +00:00
cybermaggedon
84941ce645
Fix Cassandra schema and graph filter semantics ( #680 )
...
Schema fix (dtype/lang clustering key):
- Add dtype and lang to PRIMARY KEY in quads_by_entity table
- Add otype, dtype, lang to PRIMARY KEY in quads_by_collection table
- Fixes deduplication bug where literals with same value but different
datatype or language tag were collapsed (e.g., "thing" vs "thing"@en)
- Update delete_collection to pass new clustering columns
- Update tech spec to reflect new schema
Graph filter semantics (simplified, no wildcard constant):
- g=None means all graphs (no filter)
- g="" means default graph only
- g="uri" means specific named graph
- Remove GRAPH_WILDCARD usage from EntityCentricKnowledgeGraph
- Fix service.py streaming and non-streaming paths
- Fix CLI to preserve empty string for -g '' argument
2026-03-10 12:52:51 +00:00
cybermaggedon
7a6197d8c3
GraphRAG Query-Time Explainability ( #677 )
...
Implements full explainability pipeline for GraphRAG queries, enabling
traceability from answers back to source documents.
Renamed throughout for clarity:
- provenance_callback → explain_callback
- provenance_id → explain_id
- provenance_collection → explain_collection
- message_type "provenance" → "explain"
- Queue name "provenance" → "explainability"
GraphRAG queries now emit explainability events as they execute:
1. Session - query text and timestamp
2. Retrieval - edges retrieved from subgraph
3. Selection - selected edges with LLM reasoning (JSONL with id +
reasoning)
4. Answer - reference to synthesized response
Events stream via explain_callback during query(), enabling
real-time UX.
- Answers stored in librarian service (not inline in graph - too large)
- Document ID as URN: urn:trustgraph:answer:{session_id}
- Graph stores tg:document reference (IRI) to librarian document
- Added librarian producer/consumer to graph-rag service
- get_labelgraph() now returns (labeled_edges, uri_map)
- uri_map maps edge_id(label_s, label_p, label_o) →
(uri_s, uri_p, uri_o)
- Explainability data stores original URIs, not labels
- Enables tracing edges back to reifying statements via tg:reifies
- Added serialize_triple() to query service (matches storage format)
- get_term_value() now handles TRIPLE type terms
- Enables querying by quoted triple in object position:
?stmt tg:reifies <<s p o>>
- Displays real-time explainability events during query
- Resolves rdfs:label for edge components (s, p, o)
- Traces source chain via prov:wasDerivedFrom to root document
- Output: "Source: Chunk 1 → Page 2 → Document Title"
- Label caching to avoid repeated queries
GraphRagResponse:
- explain_id: str | None
- explain_collection: str | None
- message_type: str ("chunk" or "explain")
- end_of_session: bool
trustgraph-base/trustgraph/provenance/:
- namespaces.py - Added TG_DOCUMENT predicate
- triples.py - answer_triples() supports document_id reference
- uris.py - Added edge_selection_uri()
trustgraph-base/trustgraph/schema/services/retrieval.py:
- GraphRagResponse with explain_id, explain_collection, end_of_session
trustgraph-flow/trustgraph/retrieval/graph_rag/:
- graph_rag.py - URI preservation, streaming answer accumulation
- rag.py - Librarian integration, real-time explain emission
trustgraph-flow/trustgraph/query/triples/cassandra/service.py:
- Quoted triple serialization for query matching
trustgraph-cli/trustgraph/cli/invoke_graph_rag.py:
- Full explainability display with label resolution and source tracing
2026-03-10 10:00:01 +00:00
cybermaggedon
be358efe67
Fix tests ( #663 )
2026-03-06 12:40:02 +00:00
cybermaggedon
00c1ca681b
Entity-centric graph ( #633 )
...
* Tech spec for new entity-centric graph schema
* Graph implementation
2026-02-16 13:26:43 +00:00
cybermaggedon
6129bb68c1
Fix hard coded vector size ( #555 )
...
* Fixed hard-coded embeddings store size
* Vector store lazy-creates collections, different collections for
different dimension lengths.
* Added tech spec for vector store lifecycle
* Fixed some tests for the new spec
2025-11-10 16:56:51 +00:00
cybermaggedon
13ff7d765d
Collection management ( #520 )
...
* Tech spec
* Refactored Cassanda knowledge graph for single table
* Collection management, librarian services to manage metadata and collection deletion
2025-09-18 15:57:52 +01:00
cybermaggedon
c694b12e9c
Feature/neo4j user collection isolation ( #509 )
...
* Tech spec
* User/collection separation
* Update tests
2025-09-10 22:11:21 +01:00
