mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-25 00:16:23 +02:00
7a6197d8c3
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
|
||
|---|---|---|
| .. | ||
| components | ||
| paths | ||
| security | ||
| openapi.yaml | ||
| README.md | ||
TrustGraph OpenAPI Specification
This directory contains the modular OpenAPI 3.1 specification for the TrustGraph REST API Gateway.
Structure
specs/api/
├── openapi.yaml # Main entry point
├── paths/ # Endpoint definitions
│ ├── config.yaml
│ ├── flow.yaml
│ ├── flow-services/ # Flow-hosted services
│ └── import-export/
├── components/
│ ├── schemas/ # Request/response schemas
│ │ ├── config/
│ │ ├── flow/
│ │ ├── ai-services/
│ │ ├── common/
│ │ └── errors/
│ ├── parameters/ # Reusable parameters
│ ├── responses/ # Reusable responses
│ └── examples/ # Example payloads
└── security/ # Security schemes
└── bearerAuth.yaml
Viewing the Spec
Swagger UI
# Install swagger-ui
npm install -g swagger-ui-watcher
# View in browser
swagger-ui-watcher specs/api/openapi.yaml
Redoc
# Install redoc-cli
npm install -g redoc-cli
# Generate static HTML
redoc-cli bundle specs/api/openapi.yaml -o api-docs.html
# View
open api-docs.html
Online Validators
Upload openapi.yaml to:
Validation
# Install openapi-spec-validator
pip install openapi-spec-validator
# Validate
openapi-spec-validator specs/api/openapi.yaml
Development
When adding a new service:
- Create schema files in
components/schemas/{service}/ - Create path file in
paths/orpaths/flow-services/ - Add examples if needed
- Reference from
openapi.yaml - Validate