Upsert - Upstash Documentation

Methods

The upsert method enables you to insert or update vectors in the index. You can perform upsert operations in three ways: using a vector object, a tuple, or a dictionary.

Upsert Via Vector Object

import randomfrom upstash_vector import Index, Vectorindex = Index.from_env()dimension = 128  # Adjust based on your index's dimensionupsert_amount = 100vectors = [    Vector(        id=f"generated-id-{i}",        vector=[random.random() for _ in range(dimension)],        metadata={"some_field": f"some_value-{i}"},        data=f"some-unstructured-data-{i}",    )    for i in range(upsert_amount)]index.upsert(vectors=vectors)

Upsert Via Tuple

import randomfrom upstash_vector import Indexindex = Index.from_env()dimension = 128  # Adjust based on your index's dimensionupsert_amount = 100vectors = [    (        f"generated-id-{i}",        [random.random() for _ in range(dimension)],        {"some_field": f"some_value-{i}"},        f"some-unstructured-data-{i}",    )    for i in range(upsert_amount)]index.upsert(vectors=vectors)

Upsert Via Dictionary

import randomfrom upstash_vector import Indexindex = Index.from_env()dimension = 128  # Adjust based on your index's dimensionupsert_amount = 100vectors = [    {        "id": f"generated-id-{i}",        "vector": [random.random() for _ in range(dimension)],        "metadata": {"some_field": f"some_value-{i}"},        "data": f"some-unstructured-data-{i}",    }    for i in range(upsert_amount)]index.upsert(vectors=vectors)

Also, you can specify a namespace to operate on. When no namespace is provided, the default namespace will be used.

index.upsert(..., namespace="ns")