Implementation:Cohere ai Cohere python EmbedByTypeResponse Model

Knowledge Sources	Cohere Python SDK
Domains	SDK, Embeddings
Last Updated	2026-02-15 14:00 GMT

Overview

EmbedByTypeResponse is a Pydantic model representing the Cohere Embed API response when embeddings are returned in multiple numeric formats (float, int8, uint8, binary, ubinary, base64).

Description

The EmbedByTypeResponse class encapsulates the response from the Cohere Embed API when the embedding_types parameter is used to request embeddings in specific numeric formats. Instead of returning a flat list of float arrays, this response wraps an EmbedByTypeResponseEmbeddings object that contains separate arrays for each requested embedding type.

The response includes the unique request id, the embeddings object organized by type, the original texts that were embedded, any images that were embedded, optional response_type metadata, and an ApiMeta object with API usage information such as token counts and warnings.

The class extends UncheckedBaseModel and is auto-generated by the Fern API definition toolchain. It supports both Pydantic v1 and v2 through a compatibility layer.

Usage

Use EmbedByTypeResponse when calling the Embed API with the embedding_types parameter to receive embeddings in multiple numeric formats simultaneously. This is useful for applications that need quantized embeddings for efficient storage or specific numeric precision requirements.

Code Reference

Source Location

• Repository: Cohere Python SDK
• File: src/cohere/types/embed_by_type_response.py

Signature

class EmbedByTypeResponse(UncheckedBaseModel):
    response_type: typing.Optional[EmbedByTypeResponseResponseType] = None
    id: str
    embeddings: EmbedByTypeResponseEmbeddings
    texts: typing.Optional[typing.List[str]] = None
    images: typing.Optional[typing.List[Image]] = None
    meta: typing.Optional[ApiMeta] = None

Import

from cohere.types import EmbedByTypeResponse

I/O Contract

Fields

Field	Type	Required	Default	Description
response_type	Optional[EmbedByTypeResponseResponseType]	No	None	The response type indicator
id	str	Yes	--	Unique identifier for this embed request
embeddings	EmbedByTypeResponseEmbeddings	Yes	--	An object with different embedding types; array lengths match the original input length
texts	Optional[List[str]]	No	None	The text entries for which embeddings were returned
images	Optional[List[Image]]	No	None	The image entries for which embeddings were returned
meta	Optional[ApiMeta]	No	None	API metadata including token counts and warnings

Usage Examples

Accessing Typed Embeddings

import cohere

co = cohere.Client()

response = co.embed(
    texts=["Hello world", "Cohere embeddings"],
    model="embed-english-v3.0",
    input_type="search_document",
    embedding_types=["float", "int8", "uint8"],
)

# response is an EmbedByTypeResponse
print(response.id)

# Access float embeddings
if response.embeddings.float_:
    for embedding in response.embeddings.float_:
        print(f"Float embedding dimension: {len(embedding)}")

# Access int8 embeddings
if response.embeddings.int8:
    for embedding in response.embeddings.int8:
        print(f"Int8 embedding dimension: {len(embedding)}")

# Access the original texts
if response.texts:
    print(f"Embedded texts: {response.texts}")

Checking API Metadata

import cohere

co = cohere.Client()

response = co.embed(
    texts=["Sample text for embedding"],
    model="embed-english-v3.0",
    input_type="search_query",
    embedding_types=["float"],
)

if response.meta:
    print(f"API metadata: {response.meta}")

Related Pages

• Environment:Cohere_ai_Cohere_python_Python_SDK_Runtime