# Truss
**The simplest way to serve AI/ML models in production**
[](https://badge.fury.io/py/truss)
[](https://github.com/basetenlabs/truss/actions/workflows/release.yml)
## Why Truss?
* **Write once, run anywhere:** Package and test model code, weights, and dependencies with a model server that behaves the same in development and production.
* **Fast developer loop:** Implement your model with fast feedback from a live reload server, and skip Docker and Kubernetes configuration with a batteries-included model serving environment.
* **Support for all Python frameworks**: From `transformers` and `diffusers` to `PyTorch` and `TensorFlow` to `TensorRT` and `Triton`, Truss supports models created and served with any framework.
See Trusses for popular models including:
* 🦙 [Llama 2 7B](https://github.com/basetenlabs/truss-examples/tree/main/llama/llama-2-7b-chat) ([13B](https://github.com/basetenlabs/truss-examples/tree/main/llama/llama-2-13b-chat)) ([70B](https://github.com/basetenlabs/truss-examples/tree/main/llama/llama-2-70b-chat))
* 🎨 [Stable Diffusion XL](https://github.com/basetenlabs/truss-examples/tree/main/stable-diffusion/stable-diffusion-xl-1.0)
* 🗣 [Whisper](https://github.com/basetenlabs/truss-examples/tree/main/whisper/whisper-truss)
and [dozens more examples](https://github.com/basetenlabs/truss-examples/).
## Installation
Install Truss with:
```
pip install --upgrade truss
```
## Quickstart
As a quick example, we'll package a [text classification pipeline](https://huggingface.co/docs/transformers/main_classes/pipelines) from the open-source [`transformers` package](https://github.com/huggingface/transformers).
### Create a Truss
To get started, create a Truss with the following terminal command:
```sh
truss init text-classification
```
When prompted, give your Truss a name like `Text classification`.
Then, navigate to the newly created directory:
```sh
cd text-classification
```
### Implement the model
One of the two essential files in a Truss is `model/model.py`. In this file, you write a `Model` class: an interface between the ML model that you're packaging and the model server that you're running it on.
There are two member functions that you must implement in the `Model` class:
* `load()` loads the model onto the model server. It runs exactly once when the model server is spun up or patched.
* `predict()` handles model inference. It runs every time the model server is called.
Here's the complete `model/model.py` for the text classification model:
```python
from transformers import pipeline
class Model:
def __init__(self, **kwargs):
self._model = None
def load(self):
self._model = pipeline("text-classification")
def predict(self, model_input):
return self._model(model_input)
```
### Add model dependencies
The other essential file in a Truss is `config.yaml`, which configures the model serving environment. For a complete list of the config options, see [the config reference](https://truss.baseten.co/reference/config).
The pipeline model relies on [Transformers](https://huggingface.co/docs/transformers/index) and [PyTorch](https://pytorch.org/). These dependencies must be specified in the Truss config.
In `config.yaml`, find the line `requirements`. Replace the empty list with:
```yaml
requirements:
- torch==2.0.1
- transformers==4.30.0
```
No other configuration is needed.
## Deployment
Truss is maintained by [Baseten](https://baseten.co), which provides infrastructure for running ML models in production. We'll use Baseten as the remote host for your model.
Other remotes are coming soon, starting with AWS SageMaker.
### Get an API key
To set up the Baseten remote, you'll need a [Baseten API key](https://app.baseten.co/settings/account/api_keys). If you don't have a Baseten account, no worries, just [sign up for an account](https://app.baseten.co/signup/) and you'll be issued plenty of free credits to get you started.
### Run `truss push`
With your Baseten API key ready to paste when prompted, you can deploy your model:
```sh
truss push
```
You can monitor your model deployment from [your model dashboard on Baseten](https://app.baseten.co/models/).
### Invoke the model
After the model has finished deploying, you can invoke it from the terminal.
**Invocation**
```sh
truss predict -d '"Truss is awesome!"'
```
**Response**
```json
[
{
"label": "POSITIVE",
"score": 0.999873161315918
}
]
```
## Truss contributors
Truss is backed by Baseten and built in collaboration with ML engineers worldwide. Special thanks to [Stephan Auerhahn](https://github.com/palp) @ [stability.ai](https://stability.ai/) and [Daniel Sarfati](https://github.com/dsarfati) @ [Salad Technologies](https://salad.com/) for their contributions.
We enthusiastically welcome contributions in accordance with our [contributors' guide](CONTRIBUTING.md) and [code of conduct](CODE_OF_CONDUCT.md).
Raw data
{
"_id": null,
"home_page": null,
"name": "truss",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.14,>=3.9",
"maintainer_email": null,
"keywords": "AI, MLOps, Machine Learning, Model Deployment, Model Serving",
"author": null,
"author_email": "Pankaj Gupta <no-reply@baseten.co>, Phil Howes <no-reply@baseten.co>",
"download_url": "https://files.pythonhosted.org/packages/09/18/021c9ce38d8d1c624a42c8768b1b27ebdb425811f240922bee903eac4c7e/truss-0.11.1.tar.gz",
"platform": null,
"description": "# Truss\n\n**The simplest way to serve AI/ML models in production**\n\n[](https://badge.fury.io/py/truss)\n[](https://github.com/basetenlabs/truss/actions/workflows/release.yml)\n\n## Why Truss?\n\n* **Write once, run anywhere:** Package and test model code, weights, and dependencies with a model server that behaves the same in development and production.\n* **Fast developer loop:** Implement your model with fast feedback from a live reload server, and skip Docker and Kubernetes configuration with a batteries-included model serving environment.\n* **Support for all Python frameworks**: From `transformers` and `diffusers` to `PyTorch` and `TensorFlow` to `TensorRT` and `Triton`, Truss supports models created and served with any framework.\n\nSee Trusses for popular models including:\n\n* \ud83e\udd99 [Llama 2 7B](https://github.com/basetenlabs/truss-examples/tree/main/llama/llama-2-7b-chat) ([13B](https://github.com/basetenlabs/truss-examples/tree/main/llama/llama-2-13b-chat)) ([70B](https://github.com/basetenlabs/truss-examples/tree/main/llama/llama-2-70b-chat))\n* \ud83c\udfa8 [Stable Diffusion XL](https://github.com/basetenlabs/truss-examples/tree/main/stable-diffusion/stable-diffusion-xl-1.0)\n* \ud83d\udde3 [Whisper](https://github.com/basetenlabs/truss-examples/tree/main/whisper/whisper-truss)\n\nand [dozens more examples](https://github.com/basetenlabs/truss-examples/).\n\n## Installation\n\nInstall Truss with:\n\n```\npip install --upgrade truss\n```\n\n## Quickstart\n\nAs a quick example, we'll package a [text classification pipeline](https://huggingface.co/docs/transformers/main_classes/pipelines) from the open-source [`transformers` package](https://github.com/huggingface/transformers).\n\n### Create a Truss\n\nTo get started, create a Truss with the following terminal command:\n\n```sh\ntruss init text-classification\n```\n\nWhen prompted, give your Truss a name like `Text classification`.\n\nThen, navigate to the newly created directory:\n\n```sh\ncd text-classification\n```\n\n### Implement the model\n\nOne of the two essential files in a Truss is `model/model.py`. In this file, you write a `Model` class: an interface between the ML model that you're packaging and the model server that you're running it on.\n\nThere are two member functions that you must implement in the `Model` class:\n\n* `load()` loads the model onto the model server. It runs exactly once when the model server is spun up or patched.\n* `predict()` handles model inference. It runs every time the model server is called.\n\nHere's the complete `model/model.py` for the text classification model:\n\n```python\nfrom transformers import pipeline\n\n\nclass Model:\n def __init__(self, **kwargs):\n self._model = None\n\n def load(self):\n self._model = pipeline(\"text-classification\")\n\n def predict(self, model_input):\n return self._model(model_input)\n```\n\n### Add model dependencies\n\nThe other essential file in a Truss is `config.yaml`, which configures the model serving environment. For a complete list of the config options, see [the config reference](https://truss.baseten.co/reference/config).\n\nThe pipeline model relies on [Transformers](https://huggingface.co/docs/transformers/index) and [PyTorch](https://pytorch.org/). These dependencies must be specified in the Truss config.\n\nIn `config.yaml`, find the line `requirements`. Replace the empty list with:\n\n```yaml\nrequirements:\n - torch==2.0.1\n - transformers==4.30.0\n```\n\nNo other configuration is needed.\n\n## Deployment\n\nTruss is maintained by [Baseten](https://baseten.co), which provides infrastructure for running ML models in production. We'll use Baseten as the remote host for your model.\n\nOther remotes are coming soon, starting with AWS SageMaker.\n\n### Get an API key\n\nTo set up the Baseten remote, you'll need a [Baseten API key](https://app.baseten.co/settings/account/api_keys). If you don't have a Baseten account, no worries, just [sign up for an account](https://app.baseten.co/signup/) and you'll be issued plenty of free credits to get you started.\n\n### Run `truss push`\n\nWith your Baseten API key ready to paste when prompted, you can deploy your model:\n\n```sh\ntruss push\n```\n\nYou can monitor your model deployment from [your model dashboard on Baseten](https://app.baseten.co/models/).\n\n### Invoke the model\n\nAfter the model has finished deploying, you can invoke it from the terminal.\n\n**Invocation**\n\n```sh\ntruss predict -d '\"Truss is awesome!\"'\n```\n\n**Response**\n\n```json\n[\n {\n \"label\": \"POSITIVE\",\n \"score\": 0.999873161315918\n }\n]\n```\n\n## Truss contributors\n\nTruss is backed by Baseten and built in collaboration with ML engineers worldwide. Special thanks to [Stephan Auerhahn](https://github.com/palp) @ [stability.ai](https://stability.ai/) and [Daniel Sarfati](https://github.com/dsarfati) @ [Salad Technologies](https://salad.com/) for their contributions.\n\nWe enthusiastically welcome contributions in accordance with our [contributors' guide](CONTRIBUTING.md) and [code of conduct](CODE_OF_CONDUCT.md).\n",
"bugtrack_url": null,
"license": null,
"summary": "A seamless bridge from model development to model delivery",
"version": "0.11.1",
"project_urls": {
"Baseten": "https://baseten.co",
"Bug Reports": "https://github.com/basetenlabs/truss/issues",
"Documentation": "https://truss.baseten.co",
"Homepage": "https://truss.baseten.co",
"Repository": "https://github.com/basetenlabs/truss"
},
"split_keywords": [
"ai",
" mlops",
" machine learning",
" model deployment",
" model serving"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "d2448efbc77b48128ecc221d56f52b48ca24fdd88f20c85d8497bea65fe88017",
"md5": "7048f18fbc4839fdd45363468e0be328",
"sha256": "503954459e82a8818a8aab43d87cd4b72d7c92f628c0a53e9b7afddc96862d88"
},
"downloads": -1,
"filename": "truss-0.11.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "7048f18fbc4839fdd45363468e0be328",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.14,>=3.9",
"size": 491878,
"upload_time": "2025-09-10T18:55:38",
"upload_time_iso_8601": "2025-09-10T18:55:38.337404Z",
"url": "https://files.pythonhosted.org/packages/d2/44/8efbc77b48128ecc221d56f52b48ca24fdd88f20c85d8497bea65fe88017/truss-0.11.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "0918021c9ce38d8d1c624a42c8768b1b27ebdb425811f240922bee903eac4c7e",
"md5": "32570d6b8f30c1ed5f73062ad536b6df",
"sha256": "b79714470251ce7f53df8dd3ecaef7f553605bdf3d047a1966db2c4c760ef295"
},
"downloads": -1,
"filename": "truss-0.11.1.tar.gz",
"has_sig": false,
"md5_digest": "32570d6b8f30c1ed5f73062ad536b6df",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.14,>=3.9",
"size": 384441,
"upload_time": "2025-09-10T18:55:39",
"upload_time_iso_8601": "2025-09-10T18:55:39.981866Z",
"url": "https://files.pythonhosted.org/packages/09/18/021c9ce38d8d1c624a42c8768b1b27ebdb425811f240922bee903eac4c7e/truss-0.11.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-09-10 18:55:39",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "basetenlabs",
"github_project": "truss",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "truss"
}
JSON
