This node turns a vector store into a tool by providing it with a name and a description. This tool can then be used by an agent during the execution of the Agent Prompter node to dynamically retrieve relevant documents from the underlying vector store.
A meaningful name and description are very important, for example:
Name : KNIME_Node_Description_QA_System
Description : Use this tool whenever you need information about which nodes a user would need in a given situation or if you need information about nodes' configuration options.
Note : OpenAI Functions Agents require the name to contain no whitespace while other kinds of agents may not have this restriction.
Note : If you use the Credentials Configuration node and do not select the "Save password in configuration (weakly encrypted)" option for passing the API key for the embeddings connector node, the Credentials Configuration node will need to be reconfigured upon reopening the workflow, as the credentials flow variable was not saved and will therefore not be available to downstream nodes.