Skip to main content

No project description provided

Project description

Vellum Python Library

pypi license badge fern shield

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.

Installation

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.

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:

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:

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 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!

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vellum_ai-0.8.19.tar.gz (148.8 kB view details)

Uploaded Source

Built Distribution

vellum_ai-0.8.19-py3-none-any.whl (401.3 kB view details)

Uploaded Python 3

File details

Details for the file vellum_ai-0.8.19.tar.gz.

File metadata

  • Download URL: vellum_ai-0.8.19.tar.gz
  • Upload date:
  • Size: 148.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.5.1 CPython/3.8.18 Linux/5.15.0-1073-azure

File hashes

Hashes for vellum_ai-0.8.19.tar.gz
Algorithm Hash digest
SHA256 64c5a7d2fc28d5e74a52739efb0bb1e1e4ded2af925fcdf6f92f36f466432911
MD5 d5f290bb2bbbe8fc8559bea68366dba5
BLAKE2b-256 ab51024019cfa76eb7e9ba06f022e8e1a000b4fa2377b7eae73c2442161aba1e

See more details on using hashes here.

Provenance

File details

Details for the file vellum_ai-0.8.19-py3-none-any.whl.

File metadata

  • Download URL: vellum_ai-0.8.19-py3-none-any.whl
  • Upload date:
  • Size: 401.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.5.1 CPython/3.8.18 Linux/5.15.0-1073-azure

File hashes

Hashes for vellum_ai-0.8.19-py3-none-any.whl
Algorithm Hash digest
SHA256 1cfa42dfb792ad7e3e85a10d49561d742034002fa7ae77169dc6d7f1a6c96533
MD5 19fc6e5d22f4b7c46bf5e8cef11b8562
BLAKE2b-256 a3769f9f31160ffc4d96ceb012e66a01378efd8c0c016d7f25d697b65223c753

See more details on using hashes here.

Provenance

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page