Ekiya and LLMs

Ekiya is not yet another effort to build a LLM or a foundation model.

The main strengths of Large Language Models (LLMs) is their increasing ability to act as general reasoning engines. Therefore, they are very good at tasks like translating, summarizing or generating text that seems like written by humans. Their large size enables them to capture intricate language patterns, making them versatile for a wide range of natural language processing applications. However, it's important to be aware of their limitations, such as potential biases and hallucinations that require careful handling to avoid misuse.

At Ekiya, we use available LLMs, either locally installed or through APIs in our own Graph-of-Thoughts to solve very specific domain problems. We connect them to other forms of AI in order to validate their outcome against domain knowledge and rules.