Concept · Building with AI

Embedding

Also called: embeddings, text embedding, semantic meaning

A way of turning a piece of text into a list of numbers that captures its meaning, so software can tell which pieces of text are about similar things.

For example: The sentences 'How do I get my money back?' and 'What is your refund policy?' share few words, but their embeddings are close because they mean nearly the same thing.

Connects to 14

• Vector database Concept
• RAG Concept
• LLM Concept
• Vector Concept
• Dimension Concept
• Similarity search Concept
• Chunking Concept
• Attention Concept
• Latent space Concept
• Knowledge graph Concept
• Recommendation engine Concept
• Cosine similarity Concept
• Tokenizer Concept
• ONNX Tool