Embeddings

Turn text into vectors for RAG, semantic search, clustering, and recommendations. The launch embedding model is text-embedding-3-large.

Supported models

Model	Dim	Ctx	Price / 1M	Best for
text-embedding-3-large	3072	8K	$0.13	General, English-leaning

Example

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.sealink.asia/v1",
    api_key="<your-sealink-key>",
)

# Single string
res = client.embeddings.create(
    model="text-embedding-3-large",
    input="SeaLink helps SEA developers ship AI faster."
)
vec = res.data[0].embedding   # 3072-dim vector

# Batch (recommended for performance)
texts = ["Doc 1 content", "Doc 2 content", "Doc 3 content"]
res = client.embeddings.create(model="text-embedding-3-large", input=texts)
vectors = [d.embedding for d in res.data]

Which one?

text-embedding-3-large: Industry standard from OpenAI. Most reliable for English. 3072-dim takes more storage.

Performance tips

Batch input (array form) is 5-10× faster than looping single calls.
L2-normalize before storing — cosine retrieval becomes a dot product, much faster.
Chunk size: 500-800 tokens with 50-100 token overlap is a safe default.
Want full RAG end-to-end? See the text-embedding-3-large + Qwen recipe in Cookbook.