mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-05-03 04:12:37 +02:00
1a7b654bd3
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 |
||
|---|---|---|
| .. | ||
| core | ||
| knowledge | ||
| services | ||
| __init__.py | ||
| README.flows | ||
pdf-
decoder
|
v
chunker
|
,------------------+----------- . . .
| |
v v
extract- extract-
relationships definitions
| | |
+----------------' |
| v
v
vectorize
triple-
store |
v
ge-write
Refactor:
[] Change vectorize
[] Re-route chunker to extract-*
[] Re-route vectorize to ge-write*
[] Re-route extract-definitions to ge-write*
[] Remove extract-relationships to ge-write routing