v1

latestOpenAPI 3.0.3Apache 2.02026-07-2685172326.0 KB

Inference

Generate vectors

Generate vector embeddings for input data. This endpoint uses Pinecone's hosted embedding models.

post/embed

Headers

X-Pinecone-Api-Versionstring required

Required date-based version header

Request body

modelstring required

The model to use for embedding generation.

parametersobject

Additional model-specific parameters. Refer to the model guide for available model parameters.

Example request

{
  "model": "multilingual-e5-large",
  "parameters": {
    "input_type": "passage",
    "truncate": "END"
  },
  "inputs": [
    {
      "text": "The quick brown fox jumps over the lazy dog."
    }
  ]
}

Response

modelstring required

The model used to generate the embeddings

vector_typestring required

Indicates whether the response data contains 'dense' or 'sparse' embeddings.

Example response

{
  "model": "multilingual-e5-large",
  "vector_type": "dense",
  "data": [
    {
      "values": [
        0.1,
        0.2,
        0.3
      ]
    }
  ],
  "usage": {
    "total_tokens": 205
  }
}