Replies: 1 comment 1 reply
-
@izdi this is a great question. The model currently is not "framed" to support extracting multiple lineitems. This is a limitation both in the data used to train it as well as the output of the model itself (specifically how the logits are used). We are actually working right now on a new iteration of the model that supports extracting lineitems. Our commercial product (http://impira.com/) already supports them if you need it sooner. |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Moving the conversation from #26 over to a new discussion (CC @izdi):
@ankrgyl yes. Playing with it looks promising!
One question, tho', if you ask, "What is the description of all items?" it returns only the first one or the last one depending on the framing of the question. Why do you think that might happen?
Beta Was this translation helpful? Give feedback.
All reactions