Introduction

Voyage AI provides cutting-edge embedding/vectorizations models.

Embedding models are neural net models (e.g., transformers) that convert unstructured and complex data, such as documents, images, audios, videos, or tabular data, into numerical vectors that capture their semantic meanings. These vectors serve as representations/indices for datapoints and are an essential building blocks for semantic search and retrieval-augmented generation stack (RAG), which is the dominating approach for domain-specific or company-specific chatbots.

Voyage AI provides API endpoints for embedding models that take in your data (e.g., documents or queries) and return their embeddings. The embedding models are a modular component that can used with any other components in the RAG stack, such as any vectorDB and any generative LLM.

Voyage’s embedding models are state-of-the-art in retrieval accuracy. Please read our announcing blog post for details. Please also check out a high-level introduction of embedding models, semantic search, and RAG, and our step-by-step quickstart tutorial on implementing a minimalist RAG chatbot using Voyage embeddings.