Vector Store to Tool

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:

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 that OpenAI Functions Agents require the name to contain no whitespace while other kinds of agents may not have this restriction.

Options

Tool name

The name for the tool. Note that OpenAI Functions Agents require the name to contain no whitespace, while other types of agents may not have this restriction.

Tool description

The description of the tool by which an agent decides whether or not to use the tool. Provide a meaningful description to make the agent decide more optimally. Note that the tool description cannot be empty for OpenAI Functions Agents.

Retrieved documents

The number of top results that the tool will provide from the vector store.

Retrieve sources from documents

Whether or not to retrieve document sources if provided.

Source metadata

The metadata containing the sources of the documents.

Input Ports

Icon

A large language model.

Icon

A loaded vector store.

Output Ports

Icon

A tool for an agent to use.

Popular Predecessors

  • No recommendations found

Popular Successors

  • No recommendations found

Views

This node has no views

Workflows

  • No workflows found

Links

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.