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
00c1ca681b
Entity-centric graph ( #633 )
...
* Tech spec for new entity-centric graph schema
* Graph implementation
2026-02-16 13:26:43 +00:00
cybermaggedon
cf0daedefa
Changed schema for Value -> Term, majorly breaking change ( #622 )
...
* Changed schema for Value -> Term, majorly breaking change
* Following the schema change, Value -> Term into all processing
* Updated Cassandra for g, p, s, o index patterns (7 indexes)
* Reviewed and updated all tests
* Neo4j, Memgraph and FalkorDB remain broken, will look at once settled down
2026-01-27 13:48:08 +00:00
cybermaggedon
d378db9370
Cassandra performance enhancement ( #521 )
...
* Tech spec
* Tech spec complete
* Cassandra multi-table for performance
2025-09-18 19:52:05 +01:00
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
85e669c763
Fixing more Cassandra consistency issues ( #488 )
...
* Fixing more Cassandra work
* Fix tests
2025-09-04 00:58:11 +01:00
cybermaggedon
ccaec88a72
Feature/consolidate cassandra config ( #483 )
...
* Cassandra consolidation of parameters
* New Cassandra configuration helper
* Implemented Cassanda config refactor
* New tests
2025-09-03 23:41:22 +01:00
cybermaggedon
2f7fddd206
Test suite executed from CI pipeline ( #433 )
...
* Test strategy & test cases
* Unit tests
* Integration tests
2025-07-14 14:57:44 +01:00
