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

# Constructor

> Call `new Arize()` to initialize the Arize client prior to publishing prediction and actual records

## Overview

<Warning>
  If using version \< 1.0.0, the space\_key argument is called`organization_key`
</Warning>

Instantiating the client with `Arize(API_KEY, SPACE_KEY)` returns a client object you can use to log individual records [`arize.log()`](/ax/machine-learning/machine-learning/api-reference-ml/java-sdk/log), records in bulk [`arize.logBulk()`](/ax/machine-learning/machine-learning/api-reference-ml/java-sdk/bulklog) , validation records [`arize.logValidationRecords()`](/ax/machine-learning/machine-learning/api-reference-ml/java-sdk/logvalidationrecords), and training records [`arize.logTrainingRecords()`](/ax/machine-learning/machine-learning/api-reference-ml/java-sdk/logtrainingrecords) to Arize. You need only instantiate the client once to initialize a session. Sessions are tied to a specific space, however, you can log records to any model ID and version in your space.

## Instantiation Arguments

|            |        |                                                           |
| ---------- | ------ | --------------------------------------------------------- |
| Argument   | Type   | Description                                               |
| api\_key   | String | Arize-provided api key associated with your service/space |
| space\_key | String | Arize-provided identifier for relating records to a space |

## Code Example

```java theme={null}
import com.arize.ArizeClient;

ArizeClient arize = new ArizeClient("ARIZE_API_KEY", "SPACE_KEY");
```

<Info>
  Questions? Email us at [support@arize.com](mailto::support@arize.com) or [Slack us](https://arize-ai.slack.com/) in the #arize-support channel
</Info>