Create Index

Creates and returns an EncryptedIndex instance based on the provided configuration.

client.create_index(
    index_name,
    index_key,
    index_config = None,
    embedding_model = None,
    metric = None,
)

Parameters

Parameter	Type	Default	Description
`index_name`	`str`	-	Unique name for the index
`index_key`	`bytes`	-	32-byte encryption key
`index_config`	`IndexIVFFlat \| IndexIVFPQ \| IndexIVFSQ`	`None`	(Optional) Index configuration object
`embedding_model`	`str`	`None`	(Optional) Embedding model identifier
`metric`	`str`	`None`	(Optional) Distance metric to use (`"euclidean"`, `"squared_euclidean"`, or `"cosine"`). When `None`, the server determines the default metric

Returns

An instance of EncryptedIndex configured with the provided parameters.

Exceptions

Error

Throws if the index name already exists on the server.
Throws if the index configuration is invalid or missing required parameters.
Throws if the encryption key is not exactly 32 bytes.
Throws if the embedding model is not supported by the server.

Service Errors

Throws if the CyborgDB service is unavailable or unreachable.
Throws if there are internal server errors on the CyborgDB service.

Example Usage

Automatic Index Config

from cyborgdb import Client

# Initialize client
client = Client(base_url='http://localhost:8000', api_key='your-api-key')

# Generate a secure encryption key
index_key = client.generate_key(save=True)

# Create an index
index = client.create_index('documents', index_key)

For more info on generate_key, refer to Generate Key.

IVFFlat Index

from cyborgdb import Client, IndexIVFFlat

# Initialize client
client = Client(base_url='http://localhost:8000', api_key='your-api-key')

# Generate a secure encryption key
index_key = client.generate_key(save=True)

# Create a basic IVFFlat index
config = IndexIVFFlat()
index = client.create_index('documents', index_key, config)

IVFPQ Index with Embedding Model

from cyborgdb import Client, IndexIVFPQ

# Initialize client
client = Client(base_url='http://localhost:8000', api_key='your-api-key')

# Generate a secure encryption key
index_key = client.generate_key(save=True)

# Create an IVFPQ index with automatic embedding generation
config = IndexIVFPQ(pq_dim=64, pq_bits=8)
index = client.create_index('documents', index_key, config, embedding_model='all-MiniLM-L6-v2')

For more info on auto-generating embeddings, refer to Auto-Generate Embeddings.

Introduction

Client

Encrypted Index

Types & Helpers

Parameters

Returns

Exceptions

Example Usage

Automatic Index Config

IVFFlat Index

IVFPQ Index with Embedding Model

​Parameters

​Returns

​Exceptions

​Example Usage

​Automatic Index Config

​IVFFlat Index

​IVFPQ Index with Embedding Model

Parameters

Returns

Exceptions

Example Usage

Automatic Index Config

IVFFlat Index

IVFPQ Index with Embedding Model