Skip to main content

5 docs tagged with "Large Language Models (LLM)"

Recipes that interact with Large Language Models, such as ChatGPT.

View all tags

AI-Generated Product Descriptions

In this recipe, we are feeding product data along with customer segment data to an LLM (in this case OpenAI) in order to generate customized product descriptions. The scenario is that we have customers with different priorities viewing the same products. Serving up the same product description to every customer may, however, turn some of them off. If we can appeal directly to a particular customer segment, spin the product information in such a way that it becomes attractive to them, we can increase conversions.

Batch Microservice Workflows

Conscia Recipes are designed to be intentionally open-ended, providing a robust starting point for building custom workflows. However, just as Components can come togther to form more complex Flows or populate bespoke experiences, Recipes can be built using others as a foundation.

Leveraging LLMs to Orchestrate LLMs

This recipe demonstrates the procedural orchestration of three different targeted applications of LLM technology using an LLM "master router". Designed in a chat-bot context, executing this recipe grants the business user a framework for a comprehensive automated support solution using Conscia, with opportunities for capability expansion and levers available for tuning and manipulation. While a human customer service agent is superior at responding to a customer's mood and responding appropriately, LLM-based interfaces can still lean in that direction; the more comprehensively they do so, the fewer support requests need to be served by a human agent.

Orchestrating LLMs for Product Recommendations

This recipe demonstrates the manual orchestration of three different LLM product recommendation models. Executing this recipe grants the business user the decision-making power to determine in which circumstances each recommendation model should be used.

Polling Third-Party Endpoints with a Microservice

A lightweight, task-specific microservice can extend the capabilities of Conscia's low-code platform tremendously, and allow for a streamlined and clear business user experience despite complex programmed functions being executed in the workflow. This recipe demonstrates one such microservice.