<div align="center">
<img src="docs_site/docs/images/logos/arize_toolkit_v2.png" alt="Arize Toolkit Logo" width="200"/>
</div>
<div align="center">
[](https://github.com/duncankmckinnon/arize_toolkit/actions/workflows/test.yml)
[](https://github.com/duncankmckinnon/arize_toolkit/actions/workflows/docs.yml)
[](https://github.com/duncankmckinnon/arize_toolkit/actions/workflows/publish.yml)
[](https://github.com/duncankmckinnon/arize_toolkit/actions/workflows/lint.yml)
[](https://www.python.org)
[](https://github.com/astral-sh/uv)
[](https://github.com/psf/black)
[](https://coverage.readthedocs.io)
</div>
## 📚 Documentation
### Quick Links
- [**Home**](https://duncankmckinnon.github.io/arize_toolkit) - Main documentation page
- [**Quickstart Guide**](https://duncankmckinnon.github.io/arize_toolkit/quickstart) - Get started quickly with Arize Toolkit
### Tools Documentation
| Tool Category | Description |
|--------------|-------------|
| [**Model Tools**](https://duncankmckinnon.github.io/arize_toolkit/model_tools) | Access and manage models, retrieve performance metrics and inference volumes |
| [**Monitor Tools**](https://duncankmckinnon.github.io/arize_toolkit/monitor_tools) | Create, copy, and manage monitors and alerting |
| [**Custom Metrics Tools**](https://duncankmckinnon.github.io/arize_toolkit/custom_metrics_tools) | Create and manage custom metrics |
| [**Language Model Tools**](https://duncankmckinnon.github.io/arize_toolkit/language_model_tools) | Work with prompts, annotations, and LLM features |
| [**Space & Organization Tools**](https://duncankmckinnon.github.io/arize_toolkit/space_and_organization_tools) | Navigate and manage spaces, organizations, and models |
| [**Data Import Tools**](https://duncankmckinnon.github.io/arize_toolkit/data_import_tools) | Import data from cloud storage and databases |
| [**Dashboard Tools**](https://duncankmckinnon.github.io/arize_toolkit/dashboard_tools) | Create and manage dashboards |
| [**Utility Tools**](https://duncankmckinnon.github.io/arize_toolkit/utility_tools) | Client configuration and utility functions |
### Extensions
| Extension | Description |
|-----------|-------------|
| [**Prompt Optimization**](https://duncankmckinnon.github.io/arize_toolkit/extensions/prompt_optimization) | Automated prompt improvement based on historical performance |
### For Developers
- [**Development Guide**](https://duncankmckinnon.github.io/arize_toolkit/developers/development) - Information about extending the toolkit
- [**Integration Tests**](https://duncankmckinnon.github.io/arize_toolkit/developers/integration_test) - Running integration tests
## Disclaimer
Although this package is used for development work with and within the Arize platform, it is not an Arize product.
It is a open source project developed and maintained by an Arize Engineer. Feel free to add issues or reach out for help in the Arize community Slack channel.
## Overview
Arize Toolkit is a set of tools packaged as a Python client that lets you easily interact with Arize AI APIs.
Here's a quick overview of the main features in the current release:
- Access and manage models
- Retrieve performance metrics over a time period
- Retrieve inference volume over a time period
- Create, copy, and manage custom metrics
- Create, copy, and manage monitors and alerting
- Work with LLM features like prompts and annotations
- Import data from cloud storage (S3, GCS, Azure) and databases (BigQuery, Snowflake, Databricks)
- Create, update, and delete data import jobs with full lifecycle management
- **Prompt Optimization Extension** (optional): Automatically optimize prompts using meta-prompt techniques with feedback from evaluators
## Installation
```bash
pip install arize_toolkit
```
### Optional Dependencies
#### Prompt Optimization Extension
For automated prompt optimization using meta-prompt techniques, install with the `prompt_optimizer` extras:
```bash
pip install arize_toolkit[prompt_optimizer]
```
## Client Setup
The `Client` class is the entrypoint for interacting with the toolkit. It provides maintains the connection information for making requests to the Arize APIs, and offers a wide range of operations for interacting with models, monitors, dashboards, and more.
### API Key
To create a client, you need to provide your Arize API key. Use this reference to [get your API key](https://docs.arize.com/arize/reference/authentication-and-security/api-keys) from the Arize UI.
### Organization and Space
You will also need to provide an `organization` name and `space` name. To give some context, models are scoped to a space, and the space is scoped to an organization. These can be found by navigating to the Arize UI and looking at the upper left path in the `Projects & Models` page. They will be in the format `organization/space`.
For the example below, the organization is `Demo Models` and the space is `Demo Model Manager`.
### For On Prem deployments
For SaaS users, the default API endpoint is always going to be `https://api.arize.com`.
If you are using an on prem deployment of Arize, you will need to provide the `api_url` parameter.
This parameters should just be the base url of your Arize instance.
Raw data
{
"_id": null,
"home_page": null,
"name": "arize_toolkit",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.13,>=3.9",
"maintainer_email": null,
"keywords": "arize, graphql, monitoring, observability",
"author": null,
"author_email": "Duncan McKinnon <dmckinnon@arize.com>",
"download_url": "https://files.pythonhosted.org/packages/d9/b2/9378c8b95be4e23a65c1340f09a7daf9783d92d236f6d0d41e013544fe5c/arize_toolkit-1.0.6.tar.gz",
"platform": null,
"description": "<div align=\"center\">\n <img src=\"docs_site/docs/images/logos/arize_toolkit_v2.png\" alt=\"Arize Toolkit Logo\" width=\"200\"/>\n</div>\n\n<div align=\"center\">\n\n[](https://github.com/duncankmckinnon/arize_toolkit/actions/workflows/test.yml)\n[](https://github.com/duncankmckinnon/arize_toolkit/actions/workflows/docs.yml)\n[](https://github.com/duncankmckinnon/arize_toolkit/actions/workflows/publish.yml)\n[](https://github.com/duncankmckinnon/arize_toolkit/actions/workflows/lint.yml)\n[](https://www.python.org)\n[](https://github.com/astral-sh/uv)\n[](https://github.com/psf/black)\n[](https://coverage.readthedocs.io)\n\n</div>\n\n## \ud83d\udcda Documentation\n\n### Quick Links\n\n- [**Home**](https://duncankmckinnon.github.io/arize_toolkit) - Main documentation page\n- [**Quickstart Guide**](https://duncankmckinnon.github.io/arize_toolkit/quickstart) - Get started quickly with Arize Toolkit\n\n### Tools Documentation\n\n| Tool Category | Description |\n|--------------|-------------|\n| [**Model Tools**](https://duncankmckinnon.github.io/arize_toolkit/model_tools) | Access and manage models, retrieve performance metrics and inference volumes |\n| [**Monitor Tools**](https://duncankmckinnon.github.io/arize_toolkit/monitor_tools) | Create, copy, and manage monitors and alerting |\n| [**Custom Metrics Tools**](https://duncankmckinnon.github.io/arize_toolkit/custom_metrics_tools) | Create and manage custom metrics |\n| [**Language Model Tools**](https://duncankmckinnon.github.io/arize_toolkit/language_model_tools) | Work with prompts, annotations, and LLM features |\n| [**Space & Organization Tools**](https://duncankmckinnon.github.io/arize_toolkit/space_and_organization_tools) | Navigate and manage spaces, organizations, and models |\n| [**Data Import Tools**](https://duncankmckinnon.github.io/arize_toolkit/data_import_tools) | Import data from cloud storage and databases |\n| [**Dashboard Tools**](https://duncankmckinnon.github.io/arize_toolkit/dashboard_tools) | Create and manage dashboards |\n| [**Utility Tools**](https://duncankmckinnon.github.io/arize_toolkit/utility_tools) | Client configuration and utility functions |\n\n### Extensions\n\n| Extension | Description |\n|-----------|-------------|\n| [**Prompt Optimization**](https://duncankmckinnon.github.io/arize_toolkit/extensions/prompt_optimization) | Automated prompt improvement based on historical performance |\n\n### For Developers\n\n- [**Development Guide**](https://duncankmckinnon.github.io/arize_toolkit/developers/development) - Information about extending the toolkit\n- [**Integration Tests**](https://duncankmckinnon.github.io/arize_toolkit/developers/integration_test) - Running integration tests\n\n## Disclaimer\n\nAlthough this package is used for development work with and within the Arize platform, it is not an Arize product.\nIt is a open source project developed and maintained by an Arize Engineer. Feel free to add issues or reach out for help in the Arize community Slack channel.\n\n## Overview\n\nArize Toolkit is a set of tools packaged as a Python client that lets you easily interact with Arize AI APIs.\nHere's a quick overview of the main features in the current release:\n\n- Access and manage models\n- Retrieve performance metrics over a time period\n- Retrieve inference volume over a time period\n- Create, copy, and manage custom metrics\n- Create, copy, and manage monitors and alerting\n- Work with LLM features like prompts and annotations\n- Import data from cloud storage (S3, GCS, Azure) and databases (BigQuery, Snowflake, Databricks)\n- Create, update, and delete data import jobs with full lifecycle management\n- **Prompt Optimization Extension** (optional): Automatically optimize prompts using meta-prompt techniques with feedback from evaluators\n\n## Installation\n\n```bash\npip install arize_toolkit\n```\n\n### Optional Dependencies\n\n#### Prompt Optimization Extension\n\nFor automated prompt optimization using meta-prompt techniques, install with the `prompt_optimizer` extras:\n\n```bash\npip install arize_toolkit[prompt_optimizer]\n```\n\n## Client Setup\n\nThe `Client` class is the entrypoint for interacting with the toolkit. It provides maintains the connection information for making requests to the Arize APIs, and offers a wide range of operations for interacting with models, monitors, dashboards, and more.\n\n### API Key\n\nTo create a client, you need to provide your Arize API key. Use this reference to [get your API key](https://docs.arize.com/arize/reference/authentication-and-security/api-keys) from the Arize UI.\n\n\n\n### Organization and Space\n\nYou will also need to provide an `organization` name and `space` name. To give some context, models are scoped to a space, and the space is scoped to an organization. These can be found by navigating to the Arize UI and looking at the upper left path in the `Projects & Models` page. They will be in the format `organization/space`.\n\nFor the example below, the organization is `Demo Models` and the space is `Demo Model Manager`.\n\n\n\n### For On Prem deployments\n\nFor SaaS users, the default API endpoint is always going to be `https://api.arize.com`.\nIf you are using an on prem deployment of Arize, you will need to provide the `api_url` parameter.\nThis parameters should just be the base url of your Arize instance.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A library to interact with Arize AI APIs",
"version": "1.0.6",
"project_urls": null,
"split_keywords": [
"arize",
" graphql",
" monitoring",
" observability"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "a73fd00daa93887e402fc3ef23ba64944b926149d36a029a44804526640b2d32",
"md5": "7492f8760ba612ee4c1e5cb143b91b3b",
"sha256": "5704c00f90e3c2665afc9ce574bb677e816534842183b5d546c57e996633c572"
},
"downloads": -1,
"filename": "arize_toolkit-1.0.6-py3-none-any.whl",
"has_sig": false,
"md5_digest": "7492f8760ba612ee4c1e5cb143b91b3b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.13,>=3.9",
"size": 68731,
"upload_time": "2025-07-16T19:33:01",
"upload_time_iso_8601": "2025-07-16T19:33:01.589833Z",
"url": "https://files.pythonhosted.org/packages/a7/3f/d00daa93887e402fc3ef23ba64944b926149d36a029a44804526640b2d32/arize_toolkit-1.0.6-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "d9b29378c8b95be4e23a65c1340f09a7daf9783d92d236f6d0d41e013544fe5c",
"md5": "75d2e0d363f355140c18ac8dffe11528",
"sha256": "ced14b3f757ae998cefc002eb5d8df26194634a8d284da202d1daa7053127c1e"
},
"downloads": -1,
"filename": "arize_toolkit-1.0.6.tar.gz",
"has_sig": false,
"md5_digest": "75d2e0d363f355140c18ac8dffe11528",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.13,>=3.9",
"size": 3776121,
"upload_time": "2025-07-16T19:33:02",
"upload_time_iso_8601": "2025-07-16T19:33:02.738978Z",
"url": "https://files.pythonhosted.org/packages/d9/b2/9378c8b95be4e23a65c1340f09a7daf9783d92d236f6d0d41e013544fe5c/arize_toolkit-1.0.6.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-16 19:33:02",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "arize_toolkit"
}
JSON