apunkt/trustgraph
1
0
Fork 0
mirror of https://github.com/trustgraph-ai/trustgraph.git synced 2026-06-22 05:08:06 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add semantic pre-filter for GraphRAG edge scoring (#702)

Browse source 
Embed edge descriptions and compute cosine similarity against grounding
concepts to reduce the number of edges sent to expensive LLM scoring.
Controlled by edge_score_limit parameter (default 30), skipped when edge
count is already below the limit.

Also plumbs edge_score_limit and edge_limit parameters end-to-end:
- CLI args (--edge-score-limit, --edge-limit) in both invoke and service
- Socket client: fix parameter mapping to use hyphenated wire-format keys
- Flow API, message translator, gateway all pass through correctly
- Explainable code path (_question_explainable_api) now forwards all params
- Default edge_score_limit changed from 50 to 30 based on typical subgraph
  sizes
This commit is contained in:
cybermaggedon 2026-03-21 20:06:29 +00:00 • committed by GitHub
parent bc68738c37
commit 1a7b654bd3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 166 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

44
trustgraph-base/trustgraph/api/socket_client.py
View file

@ -699,9 +699,12 @@ class SocketFlowInstance:
query: str,
user: str,
collection: str,
entity_limit: int = 50,
triple_limit: int = 30,
max_subgraph_size: int = 1000,
max_subgraph_count: int = 5,
max_entity_distance: int = 3,
max_path_length: int = 2,
edge_score_limit: int = 30,
edge_limit: int = 25,
streaming: bool = False,
**kwargs: Any
) -> Union[str, Iterator[str]]:
@ -715,9 +718,12 @@ class SocketFlowInstance:
query: Natural language query
user: User/keyspace identifier
collection: Collection identifier
entity_limit: Maximum entities to retrieve (default: 50)
triple_limit: Maximum triples per entity (default: 30)
max_subgraph_size: Maximum total triples in subgraph (default: 1000)
max_subgraph_count: Maximum number of subgraphs (default: 5)
max_entity_distance: Maximum traversal depth (default: 3)
max_path_length: Maximum traversal depth (default: 2)
edge_score_limit: Max edges for semantic pre-filter (default: 50)
edge_limit: Max edges after LLM scoring (default: 25)
streaming: Enable streaming mode (default: False)
**kwargs: Additional parameters passed to the service
@ -743,9 +749,12 @@ class SocketFlowInstance:
"query": query,
"user": user,
"collection": collection,
"entity-limit": entity_limit,
"triple-limit": triple_limit,
"max-subgraph-size": max_subgraph_size,
"max-subgraph-count": max_subgraph_count,
"max-entity-distance": max_entity_distance,
"max-path-length": max_path_length,
"edge-score-limit": edge_score_limit,
"edge-limit": edge_limit,
"streaming": streaming
}
request.update(kwargs)
@ -762,9 +771,12 @@ class SocketFlowInstance:
query: str,
user: str,
collection: str,
entity_limit: int = 50,
triple_limit: int = 30,
max_subgraph_size: int = 1000,
max_subgraph_count: int = 5,
max_entity_distance: int = 3,
max_path_length: int = 2,
edge_score_limit: int = 30,
edge_limit: int = 25,
**kwargs: Any
) -> Iterator[Union[RAGChunk, ProvenanceEvent]]:
"""
@ -778,9 +790,12 @@ class SocketFlowInstance:
query: Natural language query
user: User/keyspace identifier
collection: Collection identifier
entity_limit: Maximum entities to retrieve (default: 50)
triple_limit: Maximum triples per entity (default: 30)
max_subgraph_size: Maximum total triples in subgraph (default: 1000)
max_subgraph_count: Maximum number of subgraphs (default: 5)
max_entity_distance: Maximum traversal depth (default: 3)
max_path_length: Maximum traversal depth (default: 2)
edge_score_limit: Max edges for semantic pre-filter (default: 50)
edge_limit: Max edges after LLM scoring (default: 25)
**kwargs: Additional parameters passed to the service
Yields:
@ -823,11 +838,14 @@ class SocketFlowInstance:
"query": query,
"user": user,
"collection": collection,
"entity-limit": entity_limit,
"triple-limit": triple_limit,
"max-subgraph-size": max_subgraph_size,
"max-subgraph-count": max_subgraph_count,
"max-entity-distance": max_entity_distance,
"max-path-length": max_path_length,
"edge-score-limit": edge_score_limit,
"edge-limit": edge_limit,
"streaming": True,
"explainable": True, # Enable explainability mode
"explainable": True,
}
request.update(kwargs)