A Large Language Model such as GPT-3.5 Turbo can perform simple tasks if well instructed. In this instance we provide 10 possible labels and we require the model to answer with 1 word answer (the label).
A vector store is provided for experimental purposes. Usually vector stores are useful to ask the model to retrieve the right doc or answer a question based on the knowledge base of the documents corpus.
Workflow
08_Topic Labeling via a Large Language Model (LLM) via Prompt Engineering (Experimental)
Used extensions & nodes
Created with KNIME Analytics Platform version 5.1.0
- Go to item
- Go to item
- Go to item
- Go to item
- Go to item
- Go to item
Legal
By using or downloading the workflow, you agree to our terms and conditions.