Create embedding

Generate vector embeddings for one or more text inputs. Returns numerical arrays representing semantic meaning, useful for search, classification, and retrieval.

POST /embeddings

Python

Together AI SDK (v2)

# Docs for v1 can be found by changing the above selector ^
from together import Together
import os

client = Together(
    api_key=os.environ.get("TOGETHER_API_KEY"),
)

response = client.embeddings.create(
    model="BAAI/bge-large-en-v1.5",
    input="New York City",
)

print(response.data[0].embedding)

200

{
  "object": "<unknown>",
  "model": "<string>",
  "data": [
    {
      "object": "<unknown>",
      "embedding": [
        123
      ],
      "index": 123
    }
  ]
}

Authorizations

Authorization · string · header · default: default · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

model · enum<string> string · required

The name of the embedding model to use.

See all of Together AI's embedding models

Available options: WhereIsAI/UAE-Large-V1, BAAI/bge-large-en-v1.5, BAAI/bge-base-en-v1.5, togethercomputer/m2-bert-80M-8k-retrieval

Example:

"togethercomputer/m2-bert-80M-8k-retrieval"

input · string string[] · required

A string providing the text for the model to embed.

Example:

"Our solar system orbits the Milky Way galaxy at about 515,000 mph"

Response

200

application/json

200

object · any · required

The object type, which is always list.

model · string · required

data · object[] · required

Show child attributes