Model Console Guide

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

What Is a Model?

A Model in Namirasoft Inference is a direct connection to one AI model. It defines which AI model answers and how that model is accessed, and it stands as one endpoint your application can call.

Any application can use the Model through the Namirasoft Inference API. You can call it from your own software and work with it directly in the console, and every caller uses the same definition, made once in your Model. Namirasoft applications such as Namirasoft Expert and Namirasoft Job Arranger also use it.

The Challenge in Managing AI Models

Teams that use AI across more than one application face the challenge of managing models and providers in a consistent way. Every provider exposes a different API, new models arrive every month, and integrations age faster than they can be rewritten.

Common challenges include:

• A new integration for every model: Each provider exposes its own API, so adopting a new model means developing and maintaining another integration. With the current speed of AI advancement, that becomes a heavy development burden.
• Duplicated setup: Each application may require its own model selection and provider configuration, repeating the same work in several places.
• API key management: Using models directly often requires creating and maintaining a separate account and API key with each provider.
• Difficult model changes: Switching to a different model or provider can require reworking each application that uses it.
• Model selection overhead: Choosing the right model for each use case means comparing options across several providers.

How Namirasoft Inference Solves the Problem

Namirasoft Inference addresses these challenges through Models. Your application already has its UI and its backend. What it needs is AI that keeps advancing without new development on your side.

Instead of building an integration for every provider, you integrate once with the Namirasoft Inference API. You define a Model for the AI model you want, and when a better model arrives, you switch to it in the console, with no new development in your application. When you use a third party AI model, you connect its provider credential to the Model, and the Model uses that credential when sending requests to the provider.

Usage totals stay visible for each Model, so you always know what ran.

Overview of Model Fields and Options

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

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

• User ID (Namirasoft Account’s ID): This identifies the Namirasoft Account that owns the Model. It is used internally for permission control, audit logging, and access management.

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

• Name (String): This is the name used to identify the Model in the console. Use a name that makes its purpose or configured AI model clear, such as “Production Assistant” or “Fast Everyday Model”.

• Model Company (Enum): This identifies the provider of the AI model used by the Model. Selecting a company determines which models are available in Model Name. The catalog includes providers such as OpenAI, Anthropic, Baidu, Nvidia, and many others. See every provider in the catalog.

• Model Name (Enum): This identifies the specific AI model the Model uses. The available options depend on the selected Model Company.

• Providers (Enum): This field applies when the Model Company is Namirasoft. It determines which providers may be used by the configured Namirasoft model, including ChatGPT, Copilot, Gemini, Claude, Perplexity, MetaAI, DeepSeek, Qwen, Grok, and Mistral. You can select one or more providers, or leave the field empty to allow any available provider.

• Result Format (Enum): This field applies when the Model Company is Namirasoft. It determines whether the model returns its response as Markdown or HTML.

• Model API Key Credential (Credential ID): This connects the Model to the provider credential it uses to access the AI model. You need to connect a provider credential through Namirasoft Credential. The Model then uses the connected API key when sending requests to the provider, and the provider bills usage according to its own pricing. See How to obtain and connect your API key.

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

• Wiper (Wiper’s ID): This determines whether stored data associated with the Model 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 Model’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.

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

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