Deliver explainability triples inline in retrieval response stream (#763)
Provenance triples are now included directly in explain messages from
GraphRAG, DocumentRAG, and Agent services, eliminating the need for
follow-up knowledge graph queries to retrieve explainability details.
Each explain message in the response stream now carries:
- explain_id: root URI for this provenance step (unchanged)
- explain_graph: named graph where triples are stored (unchanged)
- explain_triples: the actual provenance triples for this step (new)
Changes across the stack:
- Schema: added explain_triples field to GraphRagResponse,
DocumentRagResponse, and AgentResponse
- Services: all explain message call sites pass triples through
(graph_rag, document_rag, agent react, agent orchestrator)
- Translators: encode explain_triples via TripleTranslator for
gateway wire format
- Python SDK: ProvenanceEvent now includes parsed ExplainEntity
and raw triples; expanded event_type detection
- CLI: invoke_graph_rag, invoke_agent, invoke_document_rag use
inline entity when available, fall back to graph query
- Tech specs updated
Additional explainability test
2026-04-07 12:19:05 +01:00
|
|
|
from dataclasses import dataclass, field
|
|
|
|
|
from ..core.primitives import Error, Term, Triple
|
2024-08-27 21:55:12 +01:00
|
|
|
|
|
|
|
|
############################################################################
|
|
|
|
|
|
|
|
|
|
# Graph RAG text retrieval
|
|
|
|
|
|
2025-12-17 21:40:43 +00:00
|
|
|
@dataclass
|
|
|
|
|
class GraphRagQuery:
|
|
|
|
|
query: str = ""
|
|
|
|
|
user: str = ""
|
|
|
|
|
collection: str = ""
|
|
|
|
|
entity_limit: int = 0
|
|
|
|
|
triple_limit: int = 0
|
|
|
|
|
max_subgraph_size: int = 0
|
|
|
|
|
max_path_length: int = 0
|
2026-03-21 20:06:29 +00:00
|
|
|
edge_score_limit: int = 0
|
Enhance retrieval pipelines: 4-stage GraphRAG, DocRAG grounding (#697)
Enhance retrieval pipelines: 4-stage GraphRAG, DocRAG grounding,
consistent PROV-O
GraphRAG:
- Split retrieval into 4 prompt stages: extract-concepts,
kg-edge-scoring,
kg-edge-reasoning, kg-synthesis (was single-stage)
- Add concept extraction (grounding) for per-concept embedding
- Filter main query to default graph, ignoring
provenance/explainability edges
- Add source document edges to knowledge graph
DocumentRAG:
- Add grounding step with concept extraction, matching GraphRAG's
pattern:
Question → Grounding → Exploration → Synthesis
- Per-concept embedding and chunk retrieval with deduplication
Cross-pipeline:
- Make PROV-O derivation links consistent: wasGeneratedBy for first
entity from Activity, wasDerivedFrom for entity-to-entity chains
- Update CLIs (tg-invoke-agent, tg-invoke-graph-rag,
tg-invoke-document-rag) for new explainability structure
- Fix all affected unit and integration tests
2026-03-16 12:12:13 +00:00
|
|
|
edge_limit: int = 0
|
2025-12-17 21:40:43 +00:00
|
|
|
streaming: bool = False
|
Split Analysis into Analysis+ToolUse and Observation, add message_id (#747)
Refactor agent provenance so that the decision (thought + tool
selection) and the result (observation) are separate DAG entities:
Question ← Analysis+ToolUse ← Observation ← ... ← Conclusion
Analysis gains tg:ToolUse as a mixin RDF type and is emitted
before tool execution via an on_action callback in react().
This ensures sub-traces (e.g. GraphRAG) appear after their
parent Analysis in the streaming event order.
Observation becomes a standalone prov:Entity with tg:Observation
type, emitted after tool execution. The linear DAG chain runs
through Observation — subsequent iterations and the Conclusion
derive from it, not from the Analysis.
message_id is populated on streaming AgentResponse for thought
and observation chunks, using the provenance URI of the entity
being built. This lets clients group streamed chunks by entity.
Wire changes:
- provenance/agent.py: Add ToolUse type, new
agent_observation_triples(), remove observation from iteration
- agent_manager.py: Add on_action callback between reason() and
tool execution
- orchestrator/pattern_base.py: Split emit, wire message_id,
chain through observation URIs
- orchestrator/react_pattern.py: Emit Analysis via on_action
before tool runs
- agent/react/service.py: Same for non-orchestrator path
- api/explainability.py: New Observation class, updated dispatch
and chain walker
- api/types.py: Add message_id to AgentThought/AgentObservation
- cli: Render Observation separately, [analysis: tool] labels
2026-03-31 17:51:22 +01:00
|
|
|
parent_uri: str = ""
|
2025-12-17 21:40:43 +00:00
|
|
|
|
|
|
|
|
@dataclass
|
|
|
|
|
class GraphRagResponse:
|
|
|
|
|
error: Error | None = None
|
|
|
|
|
response: str = ""
|
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
|
|
|
end_of_stream: bool = False # LLM response stream complete
|
Deliver explainability triples inline in retrieval response stream (#763)
Provenance triples are now included directly in explain messages from
GraphRAG, DocumentRAG, and Agent services, eliminating the need for
follow-up knowledge graph queries to retrieve explainability details.
Each explain message in the response stream now carries:
- explain_id: root URI for this provenance step (unchanged)
- explain_graph: named graph where triples are stored (unchanged)
- explain_triples: the actual provenance triples for this step (new)
Changes across the stack:
- Schema: added explain_triples field to GraphRagResponse,
DocumentRagResponse, and AgentResponse
- Services: all explain message call sites pass triples through
(graph_rag, document_rag, agent react, agent orchestrator)
- Translators: encode explain_triples via TripleTranslator for
gateway wire format
- Python SDK: ProvenanceEvent now includes parsed ExplainEntity
and raw triples; expanded event_type detection
- CLI: invoke_graph_rag, invoke_agent, invoke_document_rag use
inline entity when available, fall back to graph query
- Tech specs updated
Additional explainability test
2026-04-07 12:19:05 +01:00
|
|
|
explain_id: str | None = None # Root URI for this explain step
|
|
|
|
|
explain_graph: str | None = None # Named graph (e.g., urn:graph:retrieval)
|
|
|
|
|
explain_triples: list[Triple] = field(default_factory=list) # Provenance triples for this step
|
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
|
|
|
message_type: str = "" # "chunk" or "explain"
|
|
|
|
|
end_of_session: bool = False # Entire session complete
|
2024-08-27 21:55:12 +01:00
|
|
|
|
|
|
|
|
############################################################################
|
|
|
|
|
|
|
|
|
|
# Document RAG text retrieval
|
|
|
|
|
|
2025-12-17 21:40:43 +00:00
|
|
|
@dataclass
|
|
|
|
|
class DocumentRagQuery:
|
|
|
|
|
query: str = ""
|
|
|
|
|
user: str = ""
|
|
|
|
|
collection: str = ""
|
|
|
|
|
doc_limit: int = 0
|
|
|
|
|
streaming: bool = False
|
|
|
|
|
|
|
|
|
|
@dataclass
|
|
|
|
|
class DocumentRagResponse:
|
|
|
|
|
error: Error | None = None
|
Adding explainability to the ReACT agent (#689)
* Added tech spec
* Add provenance recording to React agent loop
Enables agent sessions to be traced and debugged using the same
explainability infrastructure as GraphRAG. Agent traces record:
- Session start with query and timestamp
- Each iteration's thought, action, arguments, and observation
- Final answer with derivation chain
Changes:
- Add session_id and collection fields to AgentRequest schema
- Add agent predicates (TG_THOUGHT, TG_ACTION, etc.) to namespaces
- Create agent provenance triple generators in provenance/agent.py
- Register explainability producer in agent service
- Emit provenance triples during agent execution
- Update CLI tools to detect and render agent traces alongside GraphRAG
* Updated explainability taxonomy:
GraphRAG: tg:Question → tg:Exploration → tg:Focus → tg:Synthesis
Agent: tg:Question → tg:Analysis(s) → tg:Conclusion
All entities also have their PROV-O type (prov:Activity or prov:Entity).
Updated commit message:
Add provenance recording to React agent loop
Enables agent sessions to be traced and debugged using the same
explainability infrastructure as GraphRAG.
Entity types follow human reasoning patterns:
- tg:Question - the user's query (shared with GraphRAG)
- tg:Analysis - each think/act/observe cycle
- tg:Conclusion - the final answer
Also adds explicit TG types to GraphRAG entities:
- tg:Question, tg:Exploration, tg:Focus, tg:Synthesis
All types retain their PROV-O base types (prov:Activity, prov:Entity).
Changes:
- Add session_id and collection fields to AgentRequest schema
- Add explainability entity types to namespaces.py
- Create agent provenance triple generators
- Register explainability producer in agent service
- Emit provenance triples during agent execution
- Update CLI tools to detect and render both trace types
* Document RAG explainability is now complete. Here's a summary of the
changes made:
Schema Changes:
- trustgraph-base/trustgraph/schema/services/retrieval.py: Added
explain_id and explain_graph fields to DocumentRagResponse
- trustgraph-base/trustgraph/messaging/translators/retrieval.py:
Updated translator to handle explainability fields
Provenance Changes:
- trustgraph-base/trustgraph/provenance/namespaces.py: Added
TG_CHUNK_COUNT and TG_SELECTED_CHUNK predicates
- trustgraph-base/trustgraph/provenance/uris.py: Added
docrag_question_uri, docrag_exploration_uri, docrag_synthesis_uri
generators
- trustgraph-base/trustgraph/provenance/triples.py: Added
docrag_question_triples, docrag_exploration_triples,
docrag_synthesis_triples builders
- trustgraph-base/trustgraph/provenance/__init__.py: Exported all
new Document RAG functions and predicates
Service Changes:
- trustgraph-flow/trustgraph/retrieval/document_rag/document_rag.py:
Added explainability callback support and triple emission at each
phase (Question → Exploration → Synthesis)
- trustgraph-flow/trustgraph/retrieval/document_rag/rag.py:
Registered explainability producer and wired up the callback
Documentation:
- docs/tech-specs/agent-explainability.md: Added Document RAG entity
types and provenance model documentation
Document RAG Provenance Model:
Question (urn:trustgraph:docrag:{uuid})
│
│ tg:query, prov:startedAtTime
│ rdf:type = prov:Activity, tg:Question
│
↓ prov:wasGeneratedBy
│
Exploration (urn:trustgraph:docrag:{uuid}/exploration)
│
│ tg:chunkCount, tg:selectedChunk (multiple)
│ rdf:type = prov:Entity, tg:Exploration
│
↓ prov:wasDerivedFrom
│
Synthesis (urn:trustgraph:docrag:{uuid}/synthesis)
│
│ tg:content = "The answer..."
│ rdf:type = prov:Entity, tg:Synthesis
* Specific subtype that makes the retrieval mechanism immediately
obvious:
System: GraphRAG
TG Types on Question: tg:Question, tg:GraphRagQuestion
URI Pattern: urn:trustgraph:question:{uuid}
────────────────────────────────────────
System: Document RAG
TG Types on Question: tg:Question, tg:DocRagQuestion
URI Pattern: urn:trustgraph:docrag:{uuid}
────────────────────────────────────────
System: Agent
TG Types on Question: tg:Question, tg:AgentQuestion
URI Pattern: urn:trustgraph:agent:{uuid}
Files modified:
- trustgraph-base/trustgraph/provenance/namespaces.py - Added
TG_GRAPH_RAG_QUESTION, TG_DOC_RAG_QUESTION, TG_AGENT_QUESTION
- trustgraph-base/trustgraph/provenance/triples.py - Added subtype to
question_triples and docrag_question_triples
- trustgraph-base/trustgraph/provenance/agent.py - Added subtype to
agent_session_triples
- trustgraph-base/trustgraph/provenance/__init__.py - Exported new types
- docs/tech-specs/agent-explainability.md - Documented the subtypes
This allows:
- Query all questions: ?q rdf:type tg:Question
- Query only GraphRAG: ?q rdf:type tg:GraphRagQuestion
- Query only Document RAG: ?q rdf:type tg:DocRagQuestion
- Query only Agent: ?q rdf:type tg:AgentQuestion
* Fixed tests
2026-03-11 15:28:15 +00:00
|
|
|
response: str | None = ""
|
Add unified explainability support and librarian storage for (#693)
Add unified explainability support and librarian storage for all retrieval engines
Implements consistent explainability/provenance tracking
across GraphRAG, DocumentRAG, and Agent retrieval
engines. All large content (answers, thoughts, observations)
is now stored in librarian rather than as inline literals in
the knowledge graph.
Explainability API:
- New explainability.py module with entity classes (Question,
Exploration, Focus, Synthesis, Analysis, Conclusion) and
ExplainabilityClient
- Quiescence-based eventual consistency handling for trace
fetching
- Content fetching from librarian with retry logic
CLI updates:
- tg-invoke-graph-rag -x/--explainable flag returns
explain_id
- tg-invoke-document-rag -x/--explainable flag returns
explain_id
- tg-invoke-agent -x/--explainable flag returns explain_id
- tg-list-explain-traces uses new explainability API
- tg-show-explain-trace handles all three trace types
Agent provenance:
- Records session, iterations (think/act/observe), and conclusion
- Stores thoughts and observations in librarian with document
references
- New predicates: tg:thoughtDocument, tg:observationDocument
DocumentRAG provenance:
- Records question, exploration (chunk retrieval), and synthesis
- Stores answers in librarian with document references
Schema changes:
- AgentResponse: added explain_id, explain_graph fields
- RetrievalResponse: added explain_id, explain_graph fields
- agent_iteration_triples: supports thought_document_id,
observation_document_id
Update tests.
2026-03-12 21:40:09 +00:00
|
|
|
end_of_stream: bool = False # LLM response stream complete
|
Deliver explainability triples inline in retrieval response stream (#763)
Provenance triples are now included directly in explain messages from
GraphRAG, DocumentRAG, and Agent services, eliminating the need for
follow-up knowledge graph queries to retrieve explainability details.
Each explain message in the response stream now carries:
- explain_id: root URI for this provenance step (unchanged)
- explain_graph: named graph where triples are stored (unchanged)
- explain_triples: the actual provenance triples for this step (new)
Changes across the stack:
- Schema: added explain_triples field to GraphRagResponse,
DocumentRagResponse, and AgentResponse
- Services: all explain message call sites pass triples through
(graph_rag, document_rag, agent react, agent orchestrator)
- Translators: encode explain_triples via TripleTranslator for
gateway wire format
- Python SDK: ProvenanceEvent now includes parsed ExplainEntity
and raw triples; expanded event_type detection
- CLI: invoke_graph_rag, invoke_agent, invoke_document_rag use
inline entity when available, fall back to graph query
- Tech specs updated
Additional explainability test
2026-04-07 12:19:05 +01:00
|
|
|
explain_id: str | None = None # Root URI for this explain step
|
|
|
|
|
explain_graph: str | None = None # Named graph (e.g., urn:graph:retrieval)
|
|
|
|
|
explain_triples: list[Triple] = field(default_factory=list) # Provenance triples for this step
|
Add unified explainability support and librarian storage for (#693)
Add unified explainability support and librarian storage for all retrieval engines
Implements consistent explainability/provenance tracking
across GraphRAG, DocumentRAG, and Agent retrieval
engines. All large content (answers, thoughts, observations)
is now stored in librarian rather than as inline literals in
the knowledge graph.
Explainability API:
- New explainability.py module with entity classes (Question,
Exploration, Focus, Synthesis, Analysis, Conclusion) and
ExplainabilityClient
- Quiescence-based eventual consistency handling for trace
fetching
- Content fetching from librarian with retry logic
CLI updates:
- tg-invoke-graph-rag -x/--explainable flag returns
explain_id
- tg-invoke-document-rag -x/--explainable flag returns
explain_id
- tg-invoke-agent -x/--explainable flag returns explain_id
- tg-list-explain-traces uses new explainability API
- tg-show-explain-trace handles all three trace types
Agent provenance:
- Records session, iterations (think/act/observe), and conclusion
- Stores thoughts and observations in librarian with document
references
- New predicates: tg:thoughtDocument, tg:observationDocument
DocumentRAG provenance:
- Records question, exploration (chunk retrieval), and synthesis
- Stores answers in librarian with document references
Schema changes:
- AgentResponse: added explain_id, explain_graph fields
- RetrievalResponse: added explain_id, explain_graph fields
- agent_iteration_triples: supports thought_document_id,
observation_document_id
Update tests.
2026-03-12 21:40:09 +00:00
|
|
|
message_type: str = "" # "chunk" or "explain"
|
|
|
|
|
end_of_session: bool = False # Entire session complete
|