You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello,
I'm in a project where I am analyzing 100k documents and extracting information from them to build a knowledge graph for RAG. So the standard RAG+Graph model.
I don't want my model to do duplicates, so I want to pass in a context of what was already found for the model before. So the messages should be populated just-in-time before the LLM extraction.
Does Distilabel support just-in-time editing? Because otherwise it serves my needs perfectly. I'm kind of reluctant to change because I'm not sure whether this is supported or not.
Cheers.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Hello,
I'm in a project where I am analyzing 100k documents and extracting information from them to build a knowledge graph for RAG. So the standard RAG+Graph model.
I don't want my model to do duplicates, so I want to pass in a context of what was already found for the model before. So the messages should be populated just-in-time before the LLM extraction.
Does Distilabel support just-in-time editing? Because otherwise it serves my needs perfectly. I'm kind of reluctant to change because I'm not sure whether this is supported or not.
Cheers.
Beta Was this translation helpful? Give feedback.
All reactions