Table of Content

Introduction and Key Concepts

Welcome to Orca! This guide explains how to use Orca’s intuitive tools to create, manage, and optimize memory-augmented AI models tailored to your specific needs.

Key Concepts

Before you begin, familiarize yourself with the following core concepts to streamline your experience:

Memory-Augmented Models: Orca's proprietary models use external, human-readable data to enhance their knowledge and performance. When Orca trains these models, they learn to leverage this external data instead of memorizing their training data. Memory-augmented models consist of two components:

• The foundation model: The underlying AI
• Embeddings database: The integrated database the model leverages for each inference. The data stored in this database provides the model’s “knowledge,” and this knowledge can be updated without retraining.

Memories: Discrete, unique pieces of information saved as embeddings, that the model uses for each inference

Memoryset: A complete collection of memories.

Memory management: The practice of determining which data points ("memories") positively or negatively impact model performance, enabling informed adjustments.

Contacting Orca

If you become stuck at any point, or you run into an unexpected error in the software, please contact an Orca representative at [email protected] and we will help resolve this issue.

Getting Started