<div align="center">
<h1>RunPod | Python Library </h1>
[](https://badge.fury.io/py/runpod)
[](https://pepy.tech/project/runpod)
[](https://github.com/runpod/runpod-python/actions/workflows/CI-e2e.yml)
[](https://github.com/runpod/runpod-python/actions/workflows/CI-pylint.yml)
[](https://github.com/runpod/runpod-python/actions/workflows/CI-pytests.yml)
[](https://github.com/runpod/runpod-python/actions/workflows/CI-codeql.yml)
</div>
Welcome to the official Python library for RunPod API & SDK.
## Table of Contents
- [Table of Contents](#table-of-contents)
- [💻 | Installation](#--installation)
- [⚡ | Serverless Worker (SDK)](#--serverless-worker-sdk)
- [Quick Start](#quick-start)
- [Local Test Worker](#local-test-worker)
- [📚 | API Language Library (GraphQL Wrapper)](#--api-language-library-graphql-wrapper)
- [Endpoints](#endpoints)
- [GPU Cloud (Pods)](#gpu-cloud-pods)
- [📁 | Directory](#--directory)
- [🤝 | Community and Contributing](#--community-and-contributing)
## 💻 | Installation
```bash
# Install the latest release version
pip install runpod
# or
# Install the latest development version (main branch)
pip install git+https://github.com/runpod/runpod-python.git
```
*Python 3.8 or higher is required to use the latest version of this package.*
## ⚡ | Serverless Worker (SDK)
This python package can also be used to create a serverless worker that can be deployed to RunPod as a custom endpoint API.
### Quick Start
Create a python script in your project that contains your model definition and the RunPod worker start code. Run this python code as your default container start command:
```python
# my_worker.py
import runpod
def is_even(job):
job_input = job["input"]
the_number = job_input["number"]
if not isinstance(the_number, int):
return {"error": "Silly human, you need to pass an integer."}
if the_number % 2 == 0:
return True
return False
runpod.serverless.start({"handler": is_even})
```
Make sure that this file is ran when your container starts. This can be accomplished by calling it in the docker command when you set up a template at [runpod.io/console/serverless/user/templates](https://www.runpod.io/console/serverless/user/templates) or by setting it as the default command in your Dockerfile.
See our [blog post](https://www.runpod.io/blog/serverless-create-a-basic-api) for creating a basic Serverless API, or view the [details docs](https://docs.runpod.io/serverless-ai/custom-apis) for more information.
### Local Test Worker
You can also test your worker locally before deploying it to RunPod. This is useful for debugging and testing.
```bash
python my_worker.py --rp_serve_api
```
## 📚 | API Language Library (GraphQL Wrapper)
When interacting with the RunPod API you can use this library to make requests to the API.
```python
import runpod
runpod.api_key = "your_runpod_api_key_found_under_settings"
```
### Endpoints
You can interact with RunPod endpoints via a `run` or `run_sync` method.
```python
endpoint = runpod.Endpoint("ENDPOINT_ID")
run_request = endpoint.run(
{"your_model_input_key": "your_model_input_value"}
)
# Check the status of the endpoint run request
print(run_request.status())
# Get the output of the endpoint run request, blocking until the endpoint run is complete.
print(run_request.output())
```
```python
endpoint = runpod.Endpoint("ENDPOINT_ID")
run_request = endpoint.run_sync(
{"your_model_input_key": "your_model_input_value"}
)
# Returns the job results if completed within 90 seconds, otherwise, returns the job status.
print(run_request )
```
### GPU Cloud (Pods)
```python
import runpod
runpod.api_key = "your_runpod_api_key_found_under_settings"
# Get all my pods
pods = runpod.get_pods()
# Get a specific pod
pod = runpod.get_pod(pod.id)
# Create a pod
pod = runpod.create_pod("test", "runpod/stack", "NVIDIA GeForce RTX 3070")
# Stop the pod
runpod.stop_pod(pod.id)
# Resume the pod
runpod.resume_pod(pod.id)
# Terminate the pod
runpod.terminate_pod(pod.id)
```
## 📁 | Directory
```BASH
.
├── docs # Documentation
├── examples # Examples
├── runpod # Package source code
│ ├── api_wrapper # Language library - API (GraphQL)
│ ├── cli # Command Line Interface Functions
│ ├── endpoint # Language library - Endpoints
│ └── serverless # SDK - Serverless Worker
└── tests # Package tests
```
## 🤝 | Community and Contributing
We welcome both pull requests and issues on [GitHub](https://github.com/runpod/runpod-python). Bug fixes and new features are encouraged, but please read our [contributing guide](CONTRIBUTING.md) first.
<div align="center">
<a target="_blank" href="https://discord.gg/pJ3P2DbUUq"></a>
</div>
Raw data
{
"_id": null,
"home_page": "https://runpod.io",
"name": "runpod",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "runpod, ai, gpu, serverless, SDK, API, python, library",
"author": "RunPod",
"author_email": "RunPod <engineer@runpod.io>, Justin Merrell <justin.merrell@runpod.io>",
"download_url": "https://files.pythonhosted.org/packages/7a/52/f76a33feba67e6cd43479049e09208a56e03425ae7e7c84866e489d09ea9/runpod-1.7.7.tar.gz",
"platform": null,
"description": "<div align=\"center\">\n<h1>RunPod | Python Library </h1>\n\n[](https://badge.fury.io/py/runpod)\n \n[](https://pepy.tech/project/runpod)\n\n[](https://github.com/runpod/runpod-python/actions/workflows/CI-e2e.yml)\n\n[](https://github.com/runpod/runpod-python/actions/workflows/CI-pylint.yml)\n \n[](https://github.com/runpod/runpod-python/actions/workflows/CI-pytests.yml)\n \n[](https://github.com/runpod/runpod-python/actions/workflows/CI-codeql.yml)\n\n</div>\n\nWelcome to the official Python library for RunPod API & SDK.\n\n## Table of Contents\n\n- [Table of Contents](#table-of-contents)\n- [\ud83d\udcbb | Installation](#--installation)\n- [\u26a1 | Serverless Worker (SDK)](#--serverless-worker-sdk)\n - [Quick Start](#quick-start)\n - [Local Test Worker](#local-test-worker)\n- [\ud83d\udcda | API Language Library (GraphQL Wrapper)](#--api-language-library-graphql-wrapper)\n - [Endpoints](#endpoints)\n - [GPU Cloud (Pods)](#gpu-cloud-pods)\n- [\ud83d\udcc1 | Directory](#--directory)\n- [\ud83e\udd1d | Community and Contributing](#--community-and-contributing)\n\n## \ud83d\udcbb | Installation\n\n```bash\n# Install the latest release version\npip install runpod\n\n# or\n\n# Install the latest development version (main branch)\npip install git+https://github.com/runpod/runpod-python.git\n```\n\n*Python 3.8 or higher is required to use the latest version of this package.*\n\n## \u26a1 | Serverless Worker (SDK)\n\nThis python package can also be used to create a serverless worker that can be deployed to RunPod as a custom endpoint API.\n\n### Quick Start\n\nCreate a python script in your project that contains your model definition and the RunPod worker start code. Run this python code as your default container start command:\n\n```python\n# my_worker.py\n\nimport runpod\n\ndef is_even(job):\n\n job_input = job[\"input\"]\n the_number = job_input[\"number\"]\n\n if not isinstance(the_number, int):\n return {\"error\": \"Silly human, you need to pass an integer.\"}\n\n if the_number % 2 == 0:\n return True\n\n return False\n\nrunpod.serverless.start({\"handler\": is_even})\n```\n\nMake sure that this file is ran when your container starts. This can be accomplished by calling it in the docker command when you set up a template at [runpod.io/console/serverless/user/templates](https://www.runpod.io/console/serverless/user/templates) or by setting it as the default command in your Dockerfile.\n\nSee our [blog post](https://www.runpod.io/blog/serverless-create-a-basic-api) for creating a basic Serverless API, or view the [details docs](https://docs.runpod.io/serverless-ai/custom-apis) for more information.\n\n### Local Test Worker\n\nYou can also test your worker locally before deploying it to RunPod. This is useful for debugging and testing.\n\n```bash\npython my_worker.py --rp_serve_api\n```\n\n## \ud83d\udcda | API Language Library (GraphQL Wrapper)\n\nWhen interacting with the RunPod API you can use this library to make requests to the API.\n\n```python\nimport runpod\n\nrunpod.api_key = \"your_runpod_api_key_found_under_settings\"\n```\n\n### Endpoints\n\nYou can interact with RunPod endpoints via a `run` or `run_sync` method.\n\n```python\nendpoint = runpod.Endpoint(\"ENDPOINT_ID\")\n\nrun_request = endpoint.run(\n {\"your_model_input_key\": \"your_model_input_value\"}\n)\n\n# Check the status of the endpoint run request\nprint(run_request.status())\n\n# Get the output of the endpoint run request, blocking until the endpoint run is complete.\nprint(run_request.output())\n```\n\n```python\nendpoint = runpod.Endpoint(\"ENDPOINT_ID\")\n\nrun_request = endpoint.run_sync(\n {\"your_model_input_key\": \"your_model_input_value\"}\n)\n\n# Returns the job results if completed within 90 seconds, otherwise, returns the job status.\nprint(run_request )\n```\n\n### GPU Cloud (Pods)\n\n```python\nimport runpod\n\nrunpod.api_key = \"your_runpod_api_key_found_under_settings\"\n\n# Get all my pods\npods = runpod.get_pods()\n\n# Get a specific pod\npod = runpod.get_pod(pod.id)\n\n# Create a pod\npod = runpod.create_pod(\"test\", \"runpod/stack\", \"NVIDIA GeForce RTX 3070\")\n\n# Stop the pod\nrunpod.stop_pod(pod.id)\n\n# Resume the pod\nrunpod.resume_pod(pod.id)\n\n# Terminate the pod\nrunpod.terminate_pod(pod.id)\n```\n\n## \ud83d\udcc1 | Directory\n\n```BASH\n.\n\u251c\u2500\u2500 docs # Documentation\n\u251c\u2500\u2500 examples # Examples\n\u251c\u2500\u2500 runpod # Package source code\n\u2502 \u251c\u2500\u2500 api_wrapper # Language library - API (GraphQL)\n\u2502 \u251c\u2500\u2500 cli # Command Line Interface Functions\n\u2502 \u251c\u2500\u2500 endpoint # Language library - Endpoints\n\u2502 \u2514\u2500\u2500 serverless # SDK - Serverless Worker\n\u2514\u2500\u2500 tests # Package tests\n```\n\n## \ud83e\udd1d | Community and Contributing\n\nWe welcome both pull requests and issues on [GitHub](https://github.com/runpod/runpod-python). Bug fixes and new features are encouraged, but please read our [contributing guide](CONTRIBUTING.md) first.\n\n<div align=\"center\">\n\n<a target=\"_blank\" href=\"https://discord.gg/pJ3P2DbUUq\"></a>\n\n</div>\n",
"bugtrack_url": null,
"license": "MIT License",
"summary": "\ud83d\udc0d | Python library for RunPod API and serverless worker SDK.",
"version": "1.7.7",
"project_urls": {
"Bug Tracker": "https://github.com/runpod/runpod-python/issues",
"Changelog": "https://github.com/runpod/runpod-python/blob/main/CHANGELOG.md",
"Documentation": "https://docs.runpod.io",
"Homepage": "https://runpod.io",
"Repository": "https://github.com/runpod/runpod-python"
},
"split_keywords": [
"runpod",
" ai",
" gpu",
" serverless",
" sdk",
" api",
" python",
" library"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "e076745eba1b9fccbaaf9ffa43c754e707c2098ddac1b8ab309a45c2d1c5b0a1",
"md5": "8586825bc012f62f57f6efa3da2c044a",
"sha256": "898a8e1ac99f840e6b2a07a90269501e8d4275773e823f6a58e97919e2820976"
},
"downloads": -1,
"filename": "runpod-1.7.7-py3-none-any.whl",
"has_sig": false,
"md5_digest": "8586825bc012f62f57f6efa3da2c044a",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 3975162,
"upload_time": "2024-12-10T21:50:39",
"upload_time_iso_8601": "2024-12-10T21:50:39.651095Z",
"url": "https://files.pythonhosted.org/packages/e0/76/745eba1b9fccbaaf9ffa43c754e707c2098ddac1b8ab309a45c2d1c5b0a1/runpod-1.7.7-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "7a52f76a33feba67e6cd43479049e09208a56e03425ae7e7c84866e489d09ea9",
"md5": "eb8b2e248044e847e9dd035385b5fbcd",
"sha256": "edcf1426afc03e8560633c4956ad859810c89e543bf86114503ddd9c5be6916d"
},
"downloads": -1,
"filename": "runpod-1.7.7.tar.gz",
"has_sig": false,
"md5_digest": "eb8b2e248044e847e9dd035385b5fbcd",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 4080363,
"upload_time": "2024-12-10T21:50:41",
"upload_time_iso_8601": "2024-12-10T21:50:41.689269Z",
"url": "https://files.pythonhosted.org/packages/7a/52/f76a33feba67e6cd43479049e09208a56e03425ae7e7c84866e489d09ea9/runpod-1.7.7.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-12-10 21:50:41",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "runpod",
"github_project": "runpod-python",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "aiohttp",
"specs": [
[
">=",
"3.9.3"
]
]
},
{
"name": "aiohttp-retry",
"specs": [
[
">=",
"2.8.3"
]
]
},
{
"name": "backoff",
"specs": [
[
">=",
"2.2.1"
]
]
},
{
"name": "boto3",
"specs": [
[
">=",
"1.26.165"
]
]
},
{
"name": "click",
"specs": [
[
">=",
"8.1.7"
]
]
},
{
"name": "colorama",
"specs": [
[
"<",
"0.4.7"
],
[
">=",
"0.2.5"
]
]
},
{
"name": "cryptography",
"specs": [
[
"<",
"45.0.0"
]
]
},
{
"name": "fastapi",
"specs": [
[
">=",
"0.94.0"
]
]
},
{
"name": "paramiko",
"specs": [
[
">=",
"3.3.1"
]
]
},
{
"name": "prettytable",
"specs": [
[
">=",
"3.9.0"
]
]
},
{
"name": "py-cpuinfo",
"specs": [
[
">=",
"9.0.0"
]
]
},
{
"name": "inquirerpy",
"specs": [
[
"==",
"0.3.4"
]
]
},
{
"name": "requests",
"specs": [
[
">=",
"2.31.0"
]
]
},
{
"name": "tomli",
"specs": [
[
">=",
"2.0.1"
]
]
},
{
"name": "tomlkit",
"specs": [
[
">=",
"0.12.2"
]
]
},
{
"name": "tqdm-loggable",
"specs": [
[
">=",
"0.1.4"
]
]
},
{
"name": "urllib3",
"specs": [
[
">=",
"1.26.6"
]
]
},
{
"name": "watchdog",
"specs": [
[
">=",
"3.0.0"
]
]
}
],
"lcname": "runpod"
}
JSON
