Lockpicking (?) on nutrition dataset #17
Description
The rational of this task is to find a okayish recipe for NLU. Currently we employ Kaldi that cannot work with the open dictionary. We need to extend this solution to the cases when the dictionary is open, also when there is a repeating entities in the incoming sentence. The model task for this is a "nutrition task", so the chatbot can record consumed foods to later provide the calories.
Presumably, this repository contains the code that can help to select the prompt for the LLM so that the LLM with this prompt solves a dataset.
Check out if its true with the nutrition dataset https://huggingface.co/datasets/Spierocho/food_json_extract
If it's indeed the case, implement the lockpicking as a decider in the Brainbox.