# MLflow runtime for MLServer
This package provides a MLServer runtime compatible with [MLflow
models](https://www.mlflow.org/docs/latest/models.html).
## Usage
You can install the runtime, alongside `mlserver`, as:
```bash
pip install mlserver mlserver-mlflow
```
## Content Types
The MLflow inference runtime introduces a new `dict` content type, which
decodes an incoming V2 request as a [dictionary of
tensors](https://www.mlflow.org/docs/latest/models.html#deploy-mlflow-models).
This is useful for certain MLflow-serialised models, which will expect that the
model inputs are serialised in this format.
```{note}
The `dict` content type can be _stacked_ with other content types, like
[`np`](../../docs/user-guide/content-type).
This allows the user to use a different set of content types to decode each of
the dict entries.
```
Raw data
{
"_id": null,
"home_page": null,
"name": "mlserver-mlflow",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.12,>=3.9",
"maintainer_email": null,
"keywords": null,
"author": "Seldon Technologies Ltd.",
"author_email": "hello@seldon.io",
"download_url": "https://files.pythonhosted.org/packages/b0/1e/d9026530a03f2163dfc28512dbcb3523b9ba23e9fe649786c9406afc6f78/mlserver_mlflow-1.6.1.tar.gz",
"platform": null,
"description": "# MLflow runtime for MLServer\n\nThis package provides a MLServer runtime compatible with [MLflow\nmodels](https://www.mlflow.org/docs/latest/models.html).\n\n## Usage\n\nYou can install the runtime, alongside `mlserver`, as:\n\n```bash\npip install mlserver mlserver-mlflow\n```\n\n## Content Types\n\nThe MLflow inference runtime introduces a new `dict` content type, which\ndecodes an incoming V2 request as a [dictionary of\ntensors](https://www.mlflow.org/docs/latest/models.html#deploy-mlflow-models).\nThis is useful for certain MLflow-serialised models, which will expect that the\nmodel inputs are serialised in this format.\n\n```{note}\nThe `dict` content type can be _stacked_ with other content types, like\n[`np`](../../docs/user-guide/content-type).\nThis allows the user to use a different set of content types to decode each of\nthe dict entries.\n```\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "MLflow runtime for MLServer",
"version": "1.6.1",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "703e752f9405bd6f96171e83a5fa22e95a9c313ec697a2e6c00f3c380c62eeb5",
"md5": "c44066c9f94f30fbf91b33ab6ff4b377",
"sha256": "769c2f51c2f11d2bee7818432daa29ad9a71646c8ade35eb1135b4fc23b3d48b"
},
"downloads": -1,
"filename": "mlserver_mlflow-1.6.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "c44066c9f94f30fbf91b33ab6ff4b377",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.12,>=3.9",
"size": 10104,
"upload_time": "2024-09-10T15:11:02",
"upload_time_iso_8601": "2024-09-10T15:11:02.400615Z",
"url": "https://files.pythonhosted.org/packages/70/3e/752f9405bd6f96171e83a5fa22e95a9c313ec697a2e6c00f3c380c62eeb5/mlserver_mlflow-1.6.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "b01ed9026530a03f2163dfc28512dbcb3523b9ba23e9fe649786c9406afc6f78",
"md5": "7f67f67df1c164c20eb8531f94b85eb6",
"sha256": "f102bdb5dbe865a122aca0d9043e4d098cfdfc4a8d6a09f66ec26d7aae0b5e3f"
},
"downloads": -1,
"filename": "mlserver_mlflow-1.6.1.tar.gz",
"has_sig": false,
"md5_digest": "7f67f67df1c164c20eb8531f94b85eb6",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.12,>=3.9",
"size": 8572,
"upload_time": "2024-09-10T15:11:03",
"upload_time_iso_8601": "2024-09-10T15:11:03.341292Z",
"url": "https://files.pythonhosted.org/packages/b0/1e/d9026530a03f2163dfc28512dbcb3523b9ba23e9fe649786c9406afc6f78/mlserver_mlflow-1.6.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-10 15:11:03",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "mlserver-mlflow"
}
JSON