| Name | vellum-ai JSON |
| Version |
0.8.25
JSON |
| download |
| home_page | None |
| Summary | None |
| upload_time | 2024-10-20 23:07:06 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | <4.0,>=3.8 |
| license | MIT |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Vellum Python Library
[](https://pypi.python.org/pypi/vellum-ai)
[](https://buildwithfern.com/?utm_source=vellum-ai/vellum-client-python/readme)
The Vellum Python SDK provides access to the Vellum API from python.
## API Docs
You can find Vellum's complete API docs at [docs.vellum.ai](https://docs.vellum.ai/api-reference/introduction/getting-started).
## Installation
```sh
pip install --upgrade vellum-ai
```
## Usage
Below is how you would invoke a deployed Prompt from the Vellum API. For a complete list of all APIs
that Vellum supports, check out our [API Reference](https://docs.vellum.ai/api-reference/introduction/getting-started).
```python
from vellum import (
StringInputRequest,
)
from vellum.client import Vellum
client = Vellum(
api_key="YOUR_API_KEY",
)
def execute() -> str:
result = client.execute_prompt(
prompt_deployment_name="<example-deployment-name>>",
release_tag="LATEST",
inputs=[
StringInputRequest(
name="input_a",
type="STRING",
value="Hello, world!",
)
],
)
if result.state == "REJECTED":
raise Exception(result.error.message)
return result.outputs[0].value
if __name__ == "__main__":
print(execute())
```
> [!TIP]
> You can set a system environment variable `VELLUM_API_KEY` to avoid writing your api key within your code. To do so, add `export VELLUM_API_KEY=<your-api-token>`
> to your ~/.zshrc or ~/.bashrc, open a new terminal, and then any code calling `vellum.Vellum()` will read this key.
## Async Client
This SDK has an async version. Here's how to use it:
```python
import asyncio
import vellum
from vellum.client import AsyncVellum
client = AsyncVellum(api_key="YOUR_API_KEY")
async def execute() -> str:
result = await client.execute_prompt(
prompt_deployment_name="<example-deployment-name>>",
release_tag="LATEST",
inputs=[
vellum.StringInputRequest(
name="input_a",
value="Hello, world!",
)
],
)
if result.state == "REJECTED":
raise Exception(result.error.message)
return result.outputs[0].value
if __name__ == "__main__":
print(asyncio.run(execute()))
```
## Contributing
While we value open-source contributions to this SDK, most of this library is generated programmatically.
Please feel free to make contributions to any of the directories or files below:
```plaintext
examples/*
src/vellum/lib/*
tests/*
README.md
```
Any additions made to files beyond those directories and files above would have to be moved over to our generation code
(found in the separate [vellum-client-generator](https://github.com/vellum-ai/vellum-client-generator) repo),
otherwise they would be overwritten upon the next generated release. Feel free to open a PR as a proof of concept,
but know that we will not be able to merge it as-is. We suggest opening an issue first to discuss with us!
Raw data
{
"_id": null,
"home_page": null,
"name": "vellum-ai",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.8",
"maintainer_email": null,
"keywords": null,
"author": null,
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/cd/d8/352c1c7a7acd712782bb9f41964456e164a7484d1728af15f052906b2efa/vellum_ai-0.8.25.tar.gz",
"platform": null,
"description": "# Vellum Python Library\n\n[](https://pypi.python.org/pypi/vellum-ai)\n\n[](https://buildwithfern.com/?utm_source=vellum-ai/vellum-client-python/readme)\n\nThe Vellum Python SDK provides access to the Vellum API from python.\n\n\n## API Docs\nYou can find Vellum's complete API docs at [docs.vellum.ai](https://docs.vellum.ai/api-reference/introduction/getting-started).\n\n## Installation\n\n```sh\npip install --upgrade vellum-ai\n```\n\n## Usage\nBelow is how you would invoke a deployed Prompt from the Vellum API. For a complete list of all APIs\nthat Vellum supports, check out our [API Reference](https://docs.vellum.ai/api-reference/introduction/getting-started).\n\n```python\nfrom vellum import (\n StringInputRequest,\n)\nfrom vellum.client import Vellum\n\nclient = Vellum(\n api_key=\"YOUR_API_KEY\",\n)\n\ndef execute() -> str:\n result = client.execute_prompt(\n prompt_deployment_name=\"<example-deployment-name>>\",\n release_tag=\"LATEST\",\n inputs=[\n StringInputRequest(\n name=\"input_a\",\n type=\"STRING\",\n value=\"Hello, world!\",\n )\n ],\n )\n \n if result.state == \"REJECTED\":\n raise Exception(result.error.message)\n\n return result.outputs[0].value\n\nif __name__ == \"__main__\":\n print(execute())\n```\n\n> [!TIP]\n> You can set a system environment variable `VELLUM_API_KEY` to avoid writing your api key within your code. To do so, add `export VELLUM_API_KEY=<your-api-token>`\n> to your ~/.zshrc or ~/.bashrc, open a new terminal, and then any code calling `vellum.Vellum()` will read this key.\n\n## Async Client\nThis SDK has an async version. Here's how to use it:\n\n\n\n```python\nimport asyncio\n\nimport vellum\nfrom vellum.client import AsyncVellum\n\nclient = AsyncVellum(api_key=\"YOUR_API_KEY\")\n\nasync def execute() -> str:\n result = await client.execute_prompt(\n prompt_deployment_name=\"<example-deployment-name>>\",\n release_tag=\"LATEST\",\n inputs=[\n vellum.StringInputRequest(\n name=\"input_a\",\n value=\"Hello, world!\",\n )\n ],\n )\n\n if result.state == \"REJECTED\":\n raise Exception(result.error.message)\n \n return result.outputs[0].value\n\nif __name__ == \"__main__\":\n print(asyncio.run(execute()))\n```\n\n## Contributing\n\nWhile we value open-source contributions to this SDK, most of this library is generated programmatically.\n\nPlease feel free to make contributions to any of the directories or files below:\n```plaintext\nexamples/*\nsrc/vellum/lib/*\ntests/*\nREADME.md\n```\n\nAny additions made to files beyond those directories and files above would have to be moved over to our generation code\n(found in the separate [vellum-client-generator](https://github.com/vellum-ai/vellum-client-generator) repo),\notherwise they would be overwritten upon the next generated release. Feel free to open a PR as a proof of concept,\nbut know that we will not be able to merge it as-is. We suggest opening an issue first to discuss with us!\n",
"bugtrack_url": null,
"license": "MIT",
"summary": null,
"version": "0.8.25",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "53ecdb05d876b69a83b485634a8427228db6599c312cb5ac01720c2233c036b8",
"md5": "e4a48f0ba679df705080841ed840c403",
"sha256": "0fe89ee254016d53656762ede1f7d6c9b0bcac8912fedf98ea29044a24391d85"
},
"downloads": -1,
"filename": "vellum_ai-0.8.25-py3-none-any.whl",
"has_sig": false,
"md5_digest": "e4a48f0ba679df705080841ed840c403",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.8",
"size": 412820,
"upload_time": "2024-10-20T23:07:04",
"upload_time_iso_8601": "2024-10-20T23:07:04.890626Z",
"url": "https://files.pythonhosted.org/packages/53/ec/db05d876b69a83b485634a8427228db6599c312cb5ac01720c2233c036b8/vellum_ai-0.8.25-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "cdd8352c1c7a7acd712782bb9f41964456e164a7484d1728af15f052906b2efa",
"md5": "719bf1e6b455f14724e0533df9250682",
"sha256": "2e3d0471a992520d74d676022b11c94db7f65d3b67a522c92e469221fe869072"
},
"downloads": -1,
"filename": "vellum_ai-0.8.25.tar.gz",
"has_sig": false,
"md5_digest": "719bf1e6b455f14724e0533df9250682",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.8",
"size": 151565,
"upload_time": "2024-10-20T23:07:06",
"upload_time_iso_8601": "2024-10-20T23:07:06.704772Z",
"url": "https://files.pythonhosted.org/packages/cd/d8/352c1c7a7acd712782bb9f41964456e164a7484d1728af15f052906b2efa/vellum_ai-0.8.25.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-20 23:07:06",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "vellum-ai"
}
