Embedding Models - Upstash Documentation

To store text in a vector database, it must first be converted into a vector, also known as an embedding. Typically, this vectorization is done by a third party. By selecting an embedding model when you create your Upstash Vector database, you can now upsert and query raw string data when using your database instead of converting your text to a vector first. The vectorization is done automatically by your selected model.

Models

Upstash Vector hosts the following embedding model for dense and hybrid indexes:

Name	Dimension	Sequence Length	MTEB
openai/text-embedding-3-small	1536	8191	62.3

The MTEB score is the average reported by OpenAI in its model announcement.

The sequence length is not a hard limit. The model truncates the input appropriately when given raw text that would result in more tokens than the given sequence length. However, we recommend not exceeding the sequence length to have more accurate results.

For sparse and hybrid indexes, the following model can be selected:

Name
BM25

See Creating Sparse Vectors for the details of the above model.

The BGE models (BAAI/bge-large-en-v1.5, BAAI/bge-base-en-v1.5, BAAI/bge-small-en-v1.5 and BAAI/bge-m3) are no longer available for new indexes. If you need a different model, you can generate the embeddings yourself and create the index with a custom dimension.

Using a Model

To start using embedding models, create the index with a model of your choice.

Create a Vector index with an embedding model

Then, you can start upserting and querying raw text data without any extra setup.

Python
JavaScript
Go
PHP
curl

from upstash_vector import Index

index = Index(
    url="UPSTASH_VECTOR_REST_URL",
    token="UPSTASH_VECTOR_REST_TOKEN",
)

index.upsert(
    [("id-0", "Upstash is a serverless data platform.", {"field": "value"})],
)

import { Index } from "@upstash/vector"

const index = new Index({
  url: "UPSTASH_VECTOR_REST_URL",
  token: "UPSTASH_VECTOR_REST_TOKEN",
})

await index.upsert({
  id: "id-0",
  data: "Upstash is a serverless data platform.",
  metadata: {
    field: "value",
  },
})

package main

import (
	"github.com/upstash/vector-go"
)

func main() {
	index := vector.NewIndex("UPSTASH_VECTOR_REST_URL", "UPSTASH_VECTOR_REST_TOKEN")

	index.UpsertData(vector.UpsertData{
		Id:       "id-0",
		Data:     "Upstash is a serverless data platform.",
		Metadata: map[string]any{"field": "value"},
	})
}

use Upstash\Vector\Index;
use Upstash\Vector\DataUpsert;

$index = new Index(
  url: 'UPSTASH_VECTOR_REST_URL',
  token: 'UPSTASH_VECTOR_REST_TOKEN',
);

$index->upsertData(new DataUpsert(
  id: 'id-0',
  data: 'Upstash is a serverless data platform.',
  metadata: [
    'field' => 'value',
  ],
));

curl $UPSTASH_VECTOR_REST_URL/upsert-data \
  -X POST \
  -H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
  -d '{"id": "1", "data": "Upstash is a serverless data platform.", "metadata": {"field": "value"}}'

Python
JavaScript
Go
PHP
curl

from upstash_vector import Index

index = Index(
    url="UPSTASH_VECTOR_REST_URL",
    token="UPSTASH_VECTOR_REST_TOKEN",
)

index.query(
    data="What is Upstash?",
    top_k=1,
    include_metadata=True,
)

import { Index } from "@upstash/vector"

const index = new Index({
  url: "UPSTASH_VECTOR_REST_URL",
  token: "UPSTASH_VECTOR_REST_TOKEN",
})

await index.query({
  data: "What is Upstash?",
  topK: 1,
  includeMetadata: true,
})

package main

import (
	"github.com/upstash/vector-go"
)

func main() {
	index := vector.NewIndex("UPSTASH_VECTOR_REST_URL", "UPSTASH_VECTOR_REST_TOKEN")

	index.QueryData(vector.QueryData{
		Data:            "What is Upstash?",
		TopK:            1,
		IncludeMetadata: true,
	})
}

use Upstash\Vector\Index;
use Upstash\Vector\DataQuery;

$index = new Index(
  url: 'UPSTASH_VECTOR_REST_URL',
  token: 'UPSTASH_VECTOR_REST_TOKEN',
);

$index->queryData(new DataQuery(
  data: 'What is Upstash?',
  topK: 1,
  includeMetadata: true,
));

curl $UPSTASH_VECTOR_REST_URL/query-data \
  -H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
  -d '{"data": "What is Upstash?", "topK": 1, "includeMetadata": "true"}'

​Models

​Using a Model

Models

Using a Model