Dense vector

Elastic Stack Serverless

Dense neural embeddings capture semantic meaning by translating content into fixed-length vectors of floating-point numbers. Similar content maps to nearby points in the vector space, making them ideal for:

• Finding semantically similar content
• Matching questions with answers
• Image similarity search
• Content-based recommendations

Dense vector search requires both index configuration and a strategy for generating embeddings. To use dense vectors in Elasticsearch:

1. Index documents with embeddings

• You can generate embeddings within Elasticsearch
  • Refer to this overview of the main options
• You can also bring your own embeddings
  • Use the dense_vector field type

2. Query the index using the knn search