mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-27 01:16:22 +02:00
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
This commit is contained in:
parent
d2d71f859d
commit
7a6197d8c3
24 changed files with 2001 additions and 323 deletions
|
|
@ -547,21 +547,21 @@ class TestServiceHelperFunctions:
|
|||
"""Test cases for helper functions in service.py"""
|
||||
|
||||
def test_create_term_with_uri_otype(self):
|
||||
"""Test create_term creates IRI Term for otype='u'"""
|
||||
"""Test create_term creates IRI Term for term_type='u'"""
|
||||
from trustgraph.query.triples.cassandra.service import create_term
|
||||
from trustgraph.schema import IRI
|
||||
|
||||
term = create_term('http://example.org/Alice', otype='u')
|
||||
term = create_term('http://example.org/Alice', term_type='u')
|
||||
|
||||
assert term.type == IRI
|
||||
assert term.iri == 'http://example.org/Alice'
|
||||
|
||||
def test_create_term_with_literal_otype(self):
|
||||
"""Test create_term creates LITERAL Term for otype='l'"""
|
||||
"""Test create_term creates LITERAL Term for term_type='l'"""
|
||||
from trustgraph.query.triples.cassandra.service import create_term
|
||||
from trustgraph.schema import LITERAL
|
||||
|
||||
term = create_term('Alice Smith', otype='l', dtype='xsd:string', lang='en')
|
||||
term = create_term('Alice Smith', term_type='l', datatype='xsd:string', language='en')
|
||||
|
||||
assert term.type == LITERAL
|
||||
assert term.value == 'Alice Smith'
|
||||
|
|
@ -569,7 +569,7 @@ class TestServiceHelperFunctions:
|
|||
assert term.language == 'en'
|
||||
|
||||
def test_create_term_with_triple_otype(self):
|
||||
"""Test create_term creates TRIPLE Term for otype='t' with valid JSON"""
|
||||
"""Test create_term creates TRIPLE Term for term_type='t' with valid JSON"""
|
||||
from trustgraph.query.triples.cassandra.service import create_term
|
||||
from trustgraph.schema import TRIPLE, IRI
|
||||
import json
|
||||
|
|
@ -581,7 +581,7 @@ class TestServiceHelperFunctions:
|
|||
"o": {"type": "i", "iri": "http://example.org/Bob"},
|
||||
})
|
||||
|
||||
term = create_term(triple_json, otype='t')
|
||||
term = create_term(triple_json, term_type='t')
|
||||
|
||||
assert term.type == TRIPLE
|
||||
assert term.triple is not None
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue