gmakstutis/graphiti
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update graphiti_core/prompts/eval.py

Browse source 
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
This commit is contained in:
Preston Rasmussen 2025-04-08 12:30:50 -04:00 • committed by GitHub
parent b35729643d
commit 120967e371
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
graphiti_core/prompts/eval.py
View file

@ -130,7 +130,7 @@ def eval_add_episode_results(context: dict[str, Any]) -> list[Message]:
conversation is higher quality than the CANDIDATE graph data extracted from the conversation. conversation is higher quality than the CANDIDATE graph data extracted from the conversation.
Return False if the BASELINE extraction is better, and True otherwise. If the CANDIDATE extraction and Return False if the BASELINE extraction is better, and True otherwise. If the CANDIDATE extraction and
BASELINE extraction are near identical in quality, return True. BASELINE extraction are nearly identical in quality, return True.
<PREVIOUS MESSAGES> <PREVIOUS MESSAGES>
{context['previous_messages']} {context['previous_messages']}