The Embeddings API converts text into numerical vectors that capture semantic meaning — enabling similarity search, clustering, and RAG applications.

Creating Embeddings

response = client.embeddings.create(
    model="text-embedding-3-small",
    input="The quick brown fox"
)
vector = response.data[0].embedding
# Returns a list of 1536 floats

Embedding Models

• text-embedding-3-small: Best cost/performance ratio — use this
• text-embedding-3-large: Highest accuracy for demanding applications

Key Use Case

Find semantically similar documents without exact keyword matching — the core of every RAG application.

Reference:

Embeddings documentation

https://en.wikipedia.org/wiki/Special:Search?search=Embeddings