Overview

Learn how to use automation procedures that interact with LLM models.

Overview

LLM procedures in Kognitos offer a flexible and powerful interface for interacting with large language models (LLMs), including OpenAI’s GPT-4 and Google’s Gemini. These procedures allow you to integrate advanced natural language understanding, generation, and reasoning directly into your automation workflows.

Capabilities

With LLM procedures, you can:

  • Generate Text – Create summaries, explanations, or creative content based on prompts.

  • Answer Questions – Return answers based on prompts or external document content.

  • Summarize Content – Produce concise summaries of lengthy documents automatically.

  • Extract Information – Identify and extract specific data points, key insights, or relevant details from text or documents.

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.

Model Name
Model Name in Kognitos
Type
Availability Regions

gemini-2.5-pro

Gemini

US, EU, UK

gemini-2.0-flash

Gemini

US, EU, UK

gemini-2.0-flash-lite

Gemini

US, EU, UK

gpt-4.1

OpenAI

US, EU, UK

gpt-4o-search-preview

Note: GPT-4 Search Preview currently cannot process images or documents. It supports text input only.

OpenAI

US, EU, UK

GPT-4o latest

gpt-4o-latest

OpenAI

US, EU, UK

GPT-4 turbo latest

gpt-4-turbo-latest

OpenAI

US

gpt-4-turbo

OpenAI

US, EU, UK

gpt-4o-mini

OpenAI

US, EU, UK

gpt-4o

OpenAI

US, EU, UK

gpt-4

OpenAI

US, EU, UK

GPT-4 latest

gpt-4-latest

OpenAI

US

GPT-3.5 Turbo latest

gpt-3.5-turbo-latest

OpenAI

US

gpt-3.5-turbo

OpenAI

US

Last updated

Was this helpful?