Embeddings

POST /v1/embeddings

{
  "model": "text-embedding-3-small",
  "input": "Parel provides one API for many model types."
}

Python

response = client.embeddings.create(
    model="text-embedding-3-small",
    input="Parel provides one API for many model types.",
)

vector = response.data[0].embedding

Key fields

Field	Type	Required	Description
model	string	yes	Embedding model ID
input	string or array	yes	Text to embed
encoding_format	string	no	float or base64 when supported

RAG pattern

1. Embed the query.
2. Search your vector database.
3. Optionally rerank candidate documents.
4. Send the top context to chat completions.