Embeddings

Reference

OpenAI Embedding Model

Cohere Embedding Models

AI21 Embeddings

AWS Titan for Embeddings

AWS Blog : Select the right algorithm

HuggingFace MTEB

Ragas

Basic terms

Corpus

In the context of an enterprise, a corpus refers to a structured collection of textual data, documents, or communications gathered from various sources within the organization.

This corpus serves as a valuable resource for conducting linguistic analysis, natural language processing tasks, and extracting insights to inform business decisions, improve processes, and enhance communication strategies within the organization.

Enterprise Knowledgebase

An enterprise knowledge base is a centralized repository or database that contains a wide range of information, data, documents, and resources relevant to an organization’s operations, products, services, policies, procedures, and expertise. It serves as a comprehensive source of knowledge and expertise that employees, customers, and stakeholders can access to find information, answer questions, solve problems, and make informed decisions.

The knowledge base may include various types of content, such as articles, manuals, FAQs, best practices, tutorials, training materials, case studies, and troubleshooting guides. It is typically organized and searchable, making it easy for users to locate relevant information efficiently.

The primary goal of an enterprise knowledge base is to facilitate knowledge sharing, collaboration, and learning within the organization, ultimately improving productivity, efficiency, and decision-making.

Vectors & Vector Space

Embeddings

How are embeddings created?

How are embeddings used?