Embedding API Usage Guide

The Turing Platform's embedding models convert text into high-dimensional vector representations for use in semantic search, clustering, recommendation, and other tasks.

Notes:

• Multiple embedding models are supported, including text-embedding-ada-002
• A single request supports up to 8,192 tokens
• The vector dimensions returned depend on the model selected

Models and Dimensions

Model	Default Dimensions	Adjustable Dimension Range
turing/text-embedding-ada-002	1536	Not supported
turing/text-embedding-3-small	1536	512, 1536
turing/text-embedding-3-large	3072	256, 1024, 3072

Custom Dimensions

For models that support dimension adjustment, you can use the dimensions parameter to specify the output vector dimensions. Smaller dimensions can reduce cost and improve performance, but may affect embedding quality.

SDK

from openai import OpenAI

client = OpenAI()

response = client.embeddings.create(
  model="text-embedding-ada-002",
  input="The quick brown fox jumps over the lazy dog"
)

print(response.data[0].embedding)
print(f"Embedding dimension: {len(response.data[0].embedding)}")

# Batch processing multiple texts
texts = [
  "Hello world",
  "Python programming",
  "Machine learning"
]

response = client.embeddings.create(
  model="text-embedding-ada-002",
  input=texts
)

for i, embedding in enumerate(response.data):
  print(f"Text {i+1} embedding dimension: {len(embedding.embedding)}")

# Using custom dimensions (only applicable to text-embedding-3-small and text-embedding-3-large)
response = client.embeddings.create(
  model="text-embedding-3-small",
  input="Custom dimension example",
  dimensions=512  # Set dimensions to 512
)

print(f"Custom embedding dimension: {len(response.data[0].embedding)}")

CURL

curl $TURING_BASE_URL/embeddings \
  -H "Authorization: Bearer $TURING_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-ada-002",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

Batch Processing Example

curl $TURING_BASE_URL/embeddings \
  -H "Authorization: Bearer $TURING_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-ada-002",
    "input": [
      "Hello world",
      "Python programming", 
      "Machine learning"
    ]
  }'

Custom Dimensions Example

curl $TURING_BASE_URL/embeddings \
  -H "Authorization: Bearer $TURING_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "The quick brown fox jumps over the lazy dog",
    "dimensions": 512
  }'