Implementation:Mistralai Client python EmbeddingResponse

Knowledge Sources	Mistral Client Python Mistral AI Embeddings
Domains	NLP, Embeddings
Last Updated	2026-02-15 14:00 GMT

Overview

Concrete tool for extracting embedding vectors and usage metadata from API responses provided by the EmbeddingResponse model.

Description

The EmbeddingResponse Pydantic model encapsulates the embedding API response. It contains data (a list of EmbeddingResponseData objects, each with an embedding vector and index), model name, and usage statistics. Access individual vectors via response.data[i].embedding.

Usage

Access the EmbeddingResponse returned by client.embeddings.create(). Iterate over response.data to get each embedding vector.

Code Reference

Source Location

• Repository: client-python
• File: src/mistralai/client/models/embeddingresponse.py (L1-30), embeddingresponsedata.py (L1-25)

Signature

class EmbeddingResponseData(BaseModel):
    embedding: List[float]
    index: int
    object: str

class EmbeddingResponse(BaseModel):
    id: str
    object: str
    data: List[EmbeddingResponseData]
    model: str
    usage: UsageInfo

Import

from mistralai.models import EmbeddingResponse
# Typically received as return value from client.embeddings.create()

I/O Contract

Inputs

Name	Type	Required	Description
response	EmbeddingResponse	Yes	Return value from embeddings.create()

Outputs

Name	Type	Description
embeddings	List[List[float]]	Vector representations, one per input text
usage	UsageInfo	Token consumption (prompt_tokens, total_tokens)

Usage Examples

Extract Vectors

response = client.embeddings.create(
    model="mistral-embed",
    inputs=["Hello world", "Goodbye world"],
)

# Get all vectors
vectors = [item.embedding for item in response.data]
print(f"Number of vectors: {len(vectors)}")
print(f"Vector dimension: {len(vectors[0])}")

# Usage statistics
print(f"Tokens used: {response.usage.total_tokens}")

Related Pages

Implements Principle

• Principle:Mistralai_Client_python_Embedding_Response_Processing