> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cyborg.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Create Index

Creates and returns a new encrypted index. CyborgDB v0.17 uses a single **DiskIVF** index type, so there is no longer an `index_config` parameter to choose between index variants.

```python theme={null}
def create_index(self,
                 index_name: str,
                 index_key: bytes,
                 *,
                 dimension: int | None = None,
                 storage_precision = None,
                 embedding_model: str | None = None,
                 metric: str | None = None,
                 logger: Logger | None = None) -> EncryptedIndex
```

<Note>All parameters after `index_key` are keyword-only.</Note>

### Parameters

| Parameter           | Type                         | Default       | Description                                                                                                                                                                                                 |
| ------------------- | ---------------------------- | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `index_name`        | `str`                        | -             | Name of the index to create. Must be unique.                                                                                                                                                                |
| `index_key`         | `bytes`                      | -             | 32-byte encryption key (KEK) for the index, used to secure the index data.                                                                                                                                  |
| `dimension`         | `int` \| `None`              | `None`        | *(Optional, keyword-only)* Dimensionality of vector embeddings. When `None`, auto-detected from the first upsert (or derived from `embedding_model`).                                                       |
| `storage_precision` | `np.float32` \| `np.float16` | `np.float32`  | *(Optional, keyword-only)* On-disk dtype for the rerank vectors. `np.float16` (or `"float16"`) halves the disk footprint with a slight precision loss. See [storage precision](../types#storage-precision). |
| `embedding_model`   | `str` \| `None`              | `None`        | *(Optional, keyword-only)* Name of the SentenceTransformer model to use for automatic text embeddings.                                                                                                      |
| `metric`            | `str` \| `None`              | `"euclidean"` | *(Optional, keyword-only)* Distance metric to use: `"euclidean"`, `"cosine"`, or `"squared_euclidean"`. See [`DistanceMetric`](../types#distancemetric).                                                    |
| `logger`            | [`Logger`](./logger)         | `None`        | *(Optional, keyword-only)* Logger instance for capturing operation logs.                                                                                                                                    |

<Note>For more info on auto-generating embeddings, refer to [Auto-Generate Embeddings](../../guides/data-operations/add-items#automatic-embedding-generation).</Note>

### Returns

`EncryptedIndex`: An instance of the newly created encrypted index.

### Exceptions

<AccordionGroup>
  <Accordion title="ValueError">
    * Throws if the index name is not unique.
    * Throws if the index configuration is invalid.
    * Throws if the index could not be created.
  </Accordion>
</AccordionGroup>

### Example Usage

#### Automatic Setup

```python theme={null}
import cyborgdb_core as cyborgdb
import secrets

api_key = "your_api_key_here"  # Replace with your CyborgDB API key

client = cyborgdb.Client(api_key, cyborgdb.StorageConfig.memory())

index_name = "my_index"
index_key = secrets.token_bytes(32)  # 32-byte index KEK — store securely

# Dimension auto-detected from the first upsert
index = client.create_index(index_name, index_key)
```

#### Explicit Setup

```python theme={null}
import cyborgdb_core as cyborgdb
import numpy as np
import secrets

api_key = "your_api_key_here"  # Replace with your CyborgDB API key

client = cyborgdb.Client(api_key, cyborgdb.StorageConfig.disk("/tmp/cyborgdb"))

index_name = "my_index"
index_key = secrets.token_bytes(32)  # 32-byte index KEK — store securely

# Optional: Set up logging
logger = cyborgdb.Logger.instance()
logger.configure(level="info", to_file=True, file_path="index_creation.log")

index = client.create_index(
    index_name,
    index_key,
    dimension=128,
    storage_precision=np.float16,  # halve on-disk rerank-vector footprint
    metric="cosine",
    logger=logger,
)
```