Embeddings

Generate vector embeddings from text using OpenAI’s embedding models through Portkey.

OpenAI’s embedding models transform text into lists of floating-point numbers (vectors). Smaller distances between vectors indicate higher semantic similarity, making them useful for semantic search, content clustering, recommendations, and anomaly detection.

Usage

Python

from portkey_ai import Portkey

client = Portkey(
    api_key="PORTKEY_API_KEY",
    provider="@OPENAI_PROVIDER"
)

response = client.embeddings.create(
    input="Your text string goes here",
    model="text-embedding-3-small"
)

print(response.data[0].embedding)

Supported Models

Model	Dimensions	Notes
text-embedding-3-small	1536	Best cost/performance ratio
text-embedding-3-large	3072	Highest accuracy
text-embedding-ada-002	1536	Legacy model

Supported Parameters

Parameter	Type	Description
model	string	Embedding model ID
input	string or array	Text to embed. Pass an array to embed multiple strings in one request
encoding_format	string	float (default) or base64
dimensions	integer	Reduce output dimensions (supported on v3 models only)
user	string	End-user ID for tracking

FAQs

How can I tell how many tokens a string has before I embed it?

Use OpenAI’s Tiktoken library to count tokens before making an embedding request.

How can I retrieve K nearest embedding vectors quickly?

Use a specialized vector database. See OpenAI’s vector database cookbook for options and examples.

Do V3 embedding models know about recent events?

The knowledge cutoff for text-embedding-3-large and text-embedding-3-small is September 2021.