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 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 automation 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.
Available LLM Models
Here is a list of available models for LLM procedures in Kognitos.
For most document processing tasks, we recommend using Gemini Pro 2.5 (gemini-2.5-pro
) for its accuracy and versatility.
gpt-4o-search-preview
Note: GPT-4 Search Preview currently cannot process images or documents. It supports text input only.
OpenAI
US, EU, UK¹
GPT-4o Latest
gpt-4o-latest
OpenAI
US, EU, UK¹
GPT-4 Turbo Latest
gpt-4-turbo-latest
OpenAI
US
GPT-4 Latest
gpt-4-latest
OpenAI
US
GPT-3.5 Turbo Latest
gpt-3.5-turbo-latest
OpenAI
US
¹ The model is available in the UK product instance—data is provided from the EU region.
OpenAI API Keys
Procedures involving OpenAI models allow you to use an API key for enhanced functionality. Adding the following line to your automation will have Kognitos securely prompt for your key:
the department's openai key
Note: This OpenAI key will be the default for all processes in the agent.
Last updated
Was this helpful?