Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.together.ai/llms.txt

Use this file to discover all available pages before exploring further.

Using a coding agent? Install the together-embeddings skill to let your agent write correct embeddings code automatically. Learn more.
The embeddings API turns an input string into a vector of numbers. You can compare two vectors to measure how closely related the source texts are. Common use cases include search, classification, recommendations, and retrieval-augmented generation (RAG). For long-term retrieval, store embeddings in a vector database and query by similarity. For the full parameter list, see the Create embedding reference. To browse available models, see serverless models.

​
Generate an embedding

Call client.embeddings.create with a model and an input string. 
from together import Together

client = Together()

response = client.embeddings.create(
    model="intfloat/multilingual-e5-large-instruct",
    input="Our solar system orbits the Milky Way galaxy at about 515,000 mph",
)
The response contains the embedding under data, along with metadata.
JSON
{
  "model": "intfloat/multilingual-e5-large-instruct",
  "object": "list",
  "data": [
    {
      "index": 0,
      "object": "embedding",
      "embedding": [0.2633975, 0.13856208, 0.04331574]
    }
  ]
}

​
Generate multiple embeddings

Pass an array of strings to input to embed several texts in one call. 
from together import Together

client = Together()

response = client.embeddings.create(
    model="intfloat/multilingual-e5-large-instruct",
    input=[
        "Our solar system orbits the Milky Way galaxy at about 515,000 mph",
        "Jupiter's Great Red Spot is a storm that has been raging for at least 350 years.",
    ],
)
response.data contains one object per input, each with the matching index.
JSON
{
  "model": "intfloat/multilingual-e5-large-instruct",
  "object": "list",
  "data": [
    {
      "index": 0,
      "object": "embedding",
      "embedding": [0.2633975, 0.13856208, 0.04331574]
    },
    {
      "index": 1,
      "object": "embedding",
      "embedding": [-0.14496337, 0.21044481, -0.16187587]
    }
  ]
}

​
Next steps