Chat Model Prompter

The Chat Model Prompter takes a statement (prompt) and the conversation history with human and AI messages. It then generates a response for the prompt with the knowledge of the previous conversation.

If you want to reduce the amount of tokens being used, consider reducing the conversation table length to a reasonable (e.g. 5 conversation steps) length before feeding it into the Chat Model Prompter.

Input ports

1. Type: org.knime.python3.nodes.PythonBinaryBlobFileStorePortObject
   Chat Model Port

   A chat model model.

2. Type: Table
   Conversation

   A table containing an empty or filled conversation.

Output ports

1. Type: Table
   Conversation

   A table containing the conversation history.