Skip to content

How do I configure the In-memory vector store node?#

Vector stores are specially designed databases used to store a one-dimensional array of numerical data used to map bias and weight in machine learning models.

Store vector data in memory while a pathway is running with the In-memory vector store node.

Before you begin#

Step 1 - add the node#

  • Click + to open the nodes panel
  • Search for In-memory vector store in the node search field.
  • Click the node to add it to the canvas.

Step 2 - define node parameters#

There are three ways to add parameters to Fixed or Expression fields in a given node:

Method Description Additional information
Load from previous nodes Click Execute previous nodes in the Input panel to load parameters from connected and configured nodes Not available for Triggers
Add a fixed value Click Fixed on available fields to enter plain-text or JSON values Learn how to edit fixed responses
Add a JSON expression Click Expression on available fields to enter a JSON expression Learn how to edit expressions

Note

The Expression editor loads all possible parameters from connected nodes. These can then be added to fields as required

  • Set an Operation Mode parameter:
Parameter Description Additional information
Get many Retrieve vector values from a connected vector based on the numerical similarity to a given prompt Learn about vector stores
Insert documents Insert vector values to a connected vector store Learn about vector stores
Retrieve documents (for Agent/Chain) Retrieve vector values from a vector store, then supply them to a Vector retriever connected to an Agent or Chain node * Learn about Agent nodes
* Learn about chain nodes
  • Set additional parameters based on the Operation Mode:
Parameter Description Used with
Memory key Unique identifier that takes the form <workflow-id><vector-store-key> * Get Many
* Insert documents * Retrieve documents
Prompt Search query Get Many
Limit Number of results to retrieve from the Vector store Get Many
Clear store Delete data at a specified memory key before inserting new data

Next steps#