DocumentationNeuronDB Documentation
Documentation Branch: You are viewing documentation for the main branch (3.0.0-devel). Select a branch to view its documentation:

Embedding Generation

Embedding Generation

Generate embeddings from text, images, and multimodal data with intelligent caching.

Text Embeddings

Generate embeddings from text:

SELECT embed_text('Hello world') AS embedding;

Specify model:

SELECT embed_text('Hello world', 'all-MiniLM-L6-v2') AS embedding;

Batch Generation

Generate embeddings in batches:

SELECT embed_text_batch(ARRAY['First text', 'Second text']) AS embeddings;

Caching

Embeddings are automatically cached to improve performance:

SELECT * FROM neurondb.embedding_cache_stats;

Learn More

For detailed documentation on embedding models, providers, caching strategies, and multimodal embeddings, visit:

Embedding Generation Documentation