Python Configuration Methods
Python Using Embeddings for Vectorization Embeddings API Guide# Overview# New model release# text-embedding-3-large Features: lower cost, better multilingual performance, controllable dimensions
Main use cases# 🔍 Search (relevance ranking)
📊 Clustering (similarity grouping)
Basic usage# Get embedding vectors# {
"object" : "list" ,
"data" : [
{
"object" : "embedding" ,
"index" : 0 ,
"embedding" : [
-0.006929283495992422 ,
-0.005336422007530928 ,
] ,
}
] ,
"model" : "text-embedding-3-small" ,
"usage" : {
"prompt_tokens" : 5 ,
"total_tokens" : 5
}
} Model comparison# Model Pages per dollar MTEB performance evaluation Maximum input text-embedding-3-small 62,500 62.3% 8191 text-embedding-3-large 9,615 64.6% 8191 text-embedding-ada-002 12,500 61.0% 8191
Practical application example# Processing review data# Technical details# Dimension description# text-embedding-3-small: default 1536 dimensions
text-embedding-3-large: default 3072 dimensions
The dimensions can be adjusted through the Dimensions parameter
Notes# Billing is based on the number of input tokens
About 800 tokens per page
The maximum input for all models is 8191 tokens
Modified at 2026-06-01 02:49:50