Gateway Console Guide

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

What Is a Gateway?

A Gateway is an inferencer that wraps another inferencer with the controls around it. It gives your application one entry point, screens the input and the output with your Guard Rails, feeds the execution with your Knowledgebases and Memory, and validates the response before returning it.

The Challenge a Gateway Solves

Execution alone is not enough for production AI. Requests need screening, context, and validation, and building those controls into every application multiplies the same work.

Common challenges include:

• Unprotected input and output: Without screening, unsafe prompts reach the model and unwanted content can reach users. Every application ends up building its own filters.
• Context wired by hand: Knowledge and conversation history must be fetched and injected by each application. The wiring repeats wherever AI is used, and each copy drifts.
• Unchecked responses: A response in the wrong shape can break the application that consumes it. Validation code spreads through every integration, one exception handler at a time.

How Namirasoft Inference Solves the Problem

You choose the inferencer the Gateway wraps, from a single Model to a whole workflow, and attach the components that should run before and after execution. When a request arrives, the guard rails screen the input first. The wrapped inferencer then executes, drawing on the attached knowledgebases and memory. On the way back, the guard rails screen the output, and the Validator checks the response. Your application integrates once, and the workflow behind the Gateway can change freely.

Overview of Gateway Fields and Options

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

• ID (String): This is a unique identifier automatically assigned to the Gateway when it is created. The system uses it to track, reference, and manage this specific Gateway. 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 Gateway. 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 Gateway 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 Gateway in the console. A good name describes the flow it protects. For example: “Support Assistant Gateway”.

• Inferencer (Inferencer Type and ID): This is the inferencer the Gateway wraps, the execution flow that actually answers each request. Select the type first, a Model, Load Balancer, Failover, Race, or Router, and then the specific inferencer.

• Guard Rails (List of Guard Rail IDs): A Guard Rail screens the user prompt, the AI output, or both, against the rules it defines, and a request stops with a clear error when a banning rule matches. Attach one or more here, and every request through this Gateway is screened by all of them.

• Knowledgebases (List of Knowledgebase IDs): A Knowledgebase holds items of content you always want present. Attach one or more here, and their items reach the execution flow as context on every request, whichever model answers.

• Validator (Validator’s ID): This determines whether the Gateway’s responses are checked against a defined response format. When a Validator is connected, it checks each response and can reject or correct a response that does not meet the required format.

• Budget (Budget’s ID): This determines whether spending through the Gateway is subject to a defined limit. A Budget can set spending ceilings per run, chat, day, week, or month. The same Budget can be used by several inferencers.

• Memory (Memory’s ID): This determines whether the Gateway keeps conversation context across requests. When a Memory is connected, relevant conversation history is stored and provided as context when the Gateway handles later requests.

• Wiper (Wiper’s ID): This determines whether stored data associated with the Gateway 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 Gateway’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 Gateway. Use it to describe the flow it wraps and the controls it applies.

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

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