Overview

Learn how to write automation procedures that interact with LLM models in Kognitos.

Overview

LLM operations in Kognitos allow you to interact with LLM models (OpenAI and Gemini) through structured queries. You can send messages, questions, or tasks to models like GPT-4. Additionally, you have the flexibility to utilize your own OpenAI API key for enhanced functionality.

Using An OpenAI API Key

Procedures involving OpenAI models enable you to use an OpenAI API key for enhanced functionality. Adding the following line will prompt the platform to request your key:

the department's openai key

This OpenAI key will be the default for all processes in the agent.

Available LLM Models

Here is a list of available models for LLM procedures in Kognitos. Note: OpenAI models are hosted by Azure.

For most document processing tasks, we recommend using Gemini Pro 2.5 (gemini-2.5-pro) for its accuracy and versatility.

OpenAI Models Available: EU and UK

• gpt-4.1

• gpt-4

• gpt-4-turbo

• gpt-4o

• gpt-4o-latest

• gpt-4o-mini

OpenAI Models Available: US

• gpt-4.1

• gpt-4o-mini

• gpt-4

• gpt-4o

• gpt-4o-latest

• gpt-4-latest

• gpt-4-turbo

• gpt-4-turbo-latest

• gpt-3.5-turbo

• gpt-3.5-turbo-latest

Gemini Models Available: US

• gemini-2.5-pro

• gemini-2.0-flash

• gemini-2.0-flash-lite

Note: Gemini models are not yet available in the UK and EU regions.