Compare the Top Embedding Models that integrate with Elasticsearch as of July 2025

This a list of Embedding Models that integrate with Elasticsearch. Use the filters on the left to add additional filters for products that have integrations with Elasticsearch. View the products that work with Elasticsearch in the table below.

What are Embedding Models for Elasticsearch?

Embedding models, accessible via APIs, transform data such as text or images into numerical vector representations that capture semantic relationships. These vectors facilitate efficient similarity searches, clustering, and various AI-driven tasks by positioning related concepts closer together in a continuous space. By preserving contextual meaning, embedding models and embedding APIs help machines understand relationships between words, objects, or other entities. They play a crucial role in enhancing search relevance, recommendation systems, and natural language processing applications. Compare and read user reviews of the best Embedding Models for Elasticsearch currently available using the table below. This list is updated regularly.

  • 1
    voyage-code-3

    voyage-code-3

    Voyage AI

    Voyage AI introduces voyage-code-3, a next-generation embedding model optimized for code retrieval. It outperforms OpenAI-v3-large and CodeSage-large by an average of 13.80% and 16.81% on a suite of 32 code retrieval datasets, respectively. It supports embeddings of 2048, 1024, 512, and 256 dimensions and offers multiple embedding quantization options, including float (32-bit), int8 (8-bit signed integer), uint8 (8-bit unsigned integer), binary (bit-packed int8), and ubinary (bit-packed uint8). With a 32 K-token context length, it surpasses OpenAI's 8K and CodeSage Large's 1K context lengths. Voyage-code-3 employs Matryoshka learning to create embeddings with a nested family of various lengths within a single vector. This allows users to vectorize documents into a 2048-dimensional vector and later use shorter versions (e.g., 256, 512, or 1024 dimensions) without re-invoking the embedding model.
  • Previous
  • You're on page 1
  • Next