Introduction 

The Embedding LLM in Kernaro is a mandatory configuration that enables Kernaro to understand and process the semantic meaning of your documents. It works by transforming uploaded documents into vector representations, allowing Kernaro to perform accurate context-based searches and retrieve the most relevant information during a chat or query. 

This setup is essential for enabling document intelligence within Kernaro, helping it interpret relationships, topics, and meanings beyond just keywords. 

Once configured, the Embedding LLM supports Kernaro’s Document Explorer and other agents that rely on vectorized data to deliver precise and context-aware answers. 

The following section explains the steps to configure the Embedding LLM. 

Supported LLM Providers 

Kernaro currently supports the following Embedding LLM providers: 

Provider	Models
Azure -OpenAI	text-embedding-3-large, text-embedding-3-small
AWS Bedrock	Amazon Titan Embed Text v2
OpenAI	text-embedding-3-large, text-embedding-3-small

Steps to Access Embedding LLM Configuration 

1. Navigate to Configuration  

2. And choose LLMs → Embedding LLM 

3. Locate the Select your LLM provider dropdown  

4. The default provider is Azure - Open AI. 

5. Selecting a different provider automatically updates the page to show the relevant configuration fields required for that provider. 

Provider-Compatible Gateway or Proxy 

This LLM Gateway menu securely routes requests from Kernaro AI to your AI provider, adding an extra layer of security, control, and management. Learn more to configure this using this Link 

Configuring Embedding LLM Providers 

To configure the Embedding LLM , the following fields are mandatory: 

Azure - Open AI 

Required Fields 

Name	Description
API Endpoint*	The endpoint URL where requests are sent to your Azure OpenAI service.
API Key*	The authentication key used to securely connect with your Azure OpenAI resource.
Deployment Name*	The name of the deployed Azure OpenAI model configured in your Azure portal.
API Version*	The version of the Azure OpenAI API to be used for communication.

Steps 

1. Enter all required details for the selected LLM provider. 

2. Click “Save” to validate and store the configuration securely. 

Note: For security purposes, the API Key will be hidden after validation and saving, ensuring it is not visible or accessible from the interface. 

Open AI 

Required Fields

Name	Description
Model Id*	The identifier of the OpenAI model to be used for reasoning and responses.
API Key*	The authentication key used to securely connect with the OpenAI API.

Steps

1. Enter all required details for the selected LLM provide

2. Click “Save” to validate and store the configuration securely.

Note: For security purposes, the API Key will be hidden after validation and saving, ensuring it is not visible or accessible from the interface. 

AWS Bedrock

 Required Fields

Name	Description
Model Id*	The identifier of the Claude model deployed in AWS Bedrock to be used for reasoning.
Region Name*	The AWS region where the Bedrock model is hosted and accessed.

 Steps

1. Enter all required details for the selected LLM provider. 

2. Click “Save” to validate and store the configuration securely. 

Note: For security purposes, the API Key will be hidden after validation and saving, ensuring it is not visible or accessible from the interface.