Implementation:Openai Openai python Embedding Create Params

Knowledge Sources	openai-python OpenAI Embeddings API
Domains	NLP, Embeddings
Last Updated	2026-02-15 00:00 GMT

Overview

Concrete TypedDict parameter type for configuring embedding generation requests provided by the OpenAI Python SDK.

Description

EmbeddingCreateParams defines the valid input format for embedding requests. It accepts text strings, string lists, token integer arrays, or batches of token arrays. The model parameter selects the embedding model, and optional dimensions parameter enables output truncation for newer models.

Usage

Parameters are passed as keyword arguments to client.embeddings.create().

Code Reference

Source Location

• Repository: openai-python
• File: src/openai/types/embedding_create_params.py
• Lines: L1-55

Signature

class EmbeddingCreateParams(TypedDict, total=False):
    input: Required[Union[str, List[str], Iterable[int], Iterable[Iterable[int]]]]
    model: Required[Union[str, EmbeddingModel]]
    dimensions: int
    encoding_format: Literal["float", "base64"]
    user: str

Import

from openai.types import EmbeddingCreateParams

I/O Contract

Inputs

Name	Type	Required	Description
input	str, list[str], Iterable[int], Iterable[Iterable[int]]	Yes	Text or token input
model	str	Yes	Embedding model ID
dimensions	int	No	Output vector dimensions (text-embedding-3-* only)
encoding_format	str	No	"float" or "base64"

Outputs

Name	Type	Description
params	TypedDict	Configuration for embeddings.create()

Usage Examples

Single Text

from openai import OpenAI

client = OpenAI()
response = client.embeddings.create(
    input="The quick brown fox",
    model="text-embedding-3-small",
)

Batch Text

response = client.embeddings.create(
    input=["Text one", "Text two", "Text three"],
    model="text-embedding-3-small",
)

With Dimension Truncation

response = client.embeddings.create(
    input="Some text to embed",
    model="text-embedding-3-large",
    dimensions=256,  # Truncate from 3072 to 256 dimensions
)

Related Pages

Implements Principle

• Principle:Openai_Openai_python_Embedding_Input_Preparation