Memory Console Guide

This page provides a guide to the Memory entity in the Namirasoft Inference Console. It defines the concepts and configuration fields used when creating and managing Memorys. Use this guide to understand the purpose and behavior of each setting available during Memory configuration.

What Is a Memory?

Memory keeps conversation context across chats, and it stays independent of the model, so switching models never loses what came before. The exchanges that produce the final response are stored automatically, so even when several targets run inside a Race or a Failover, only the winning exchange is kept.

The Challenge a Memory Solves

Models do not remember. Every request starts blank unless context is carried in, and carrying it is work applications repeat.

Common challenges include:

• Context lost between chats: A conversation that continues tomorrow starts from nothing. The user repeats what the system should already know.
• History wired by hand: Each application stores, trims, and replays its own transcript. The logic is duplicated and never quite the same.
• Memory tied to one model: Context kept inside one provider’s session dies with the switch. Changing models means losing the conversation.

How Namirasoft Inference Solves the Problem

You create a Memory and attach it to any inferencer, or to a Gateway. From then on, the conversation’s winning interactions are stored, and the stored context is provided to the model with each request, so the conversation continues naturally. You can clear the stored context from a date, down to a count, or completely, and a Wiper can clean it up automatically.

Overview of Memory Fields and Options

Below is a detailed explanation of the fields available when creating or managing a Memory. Understanding these fields helps ensure your Memory is configured correctly for your requirements.

• ID (String): This is a unique identifier automatically assigned to the Memory when it is created. The system uses it to track, reference, and manage this specific Memory. This value is auto-generated and cannot be modified.

• User ID (Namirasoft Account’s ID): This is the unique identifier of the Namirasoft Account user who owns this Memory. It is used internally for permission control, audit logging, and access management.

• Workspace ID (Namirasoft Workspace’s ID): This is the identifier of the workspace this Memory belongs to, as defined in Namirasoft Workspace. A workspace is a shared organizational space where teams group their work, projects, and members.

• Name (String): This is a label used to identify this Memory in the console. A good name states the conversation it belongs to. For example: “Support Assistant Memory”.

• Wiper (Wiper’s ID): This determines whether stored data associated with the Memory is cleaned up according to a defined policy. A Wiper can remove data based on time or count limits.

• Log Group (Log Group’s ID): This determines where the Memory’s execution logs are recorded. When a Log Group, defined in Namirasoft Log, is connected, request activity and errors are recorded there for debugging and review.

• Description (String): This is optional explanatory text about this Memory. Use it to describe which workflow relies on it.

• Created At (DateTime): This is the date and time when this Memory was created. This value is automatically generated and cannot be modified.

• Updated At (DateTime): This is the date and time when this Memory configuration was last modified. This value is updated automatically whenever any field is changed.