Skip to main content

No project description provided

Project description

Vellum Python Library

pypi fern shield

The Vellum Python Library 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

import vellum
from vellum.client import Vellum


client = Vellum(api_key="YOUR_API_KEY")

result = client.generate(
    deployment_name="my-deployment",
    requests=[
        vellum.GenerateRequest(
            input_values={"question": "Can I get a refund?"})]
    )

print(result.text)

Async Client

import vellum
from vellum.client import AsyncVellum

raven = AsyncVellum(api_key="YOUR_API_KEY")

async def generate() -> str:
  result = client.generate(
    deployment_name="my-deployment",
    requests=[
        vellum.GenerateRequest(
            input_values={"question": "Can I get a refund?"})]
    )
  
  return result.text

Uploading documents

Documents can be uploaded to Vellum via either the UI or this API. Once uploaded and indexed, Vellum's Search allows you to perform semantic searches against them.

from vellum.client import Vellum

client = Vellum(api_key="YOUR_API_KEY")

with open("/path/to/your/file.txt", "rb") as file:
    result = client.documents.upload(
        # File to upload
        contents=file,
        # Document label
        label="Human-friendly label for your document",
        # The names of indexes that you'd like this document to be added to.
        add_to_index_names=["<your-index-name>"],
        # Optionally include a unique ID from your system to this document later.
        #   Useful if you want to perform updates later
        external_id="<your-index-name>",
        # Optionally include keywords to associate with the document that can be used in hybrid search
        keywords=[],
    )

print(result)

Beta status

This SDK is in beta, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning the package version to a specific version in your pyproject.toml file. This way, you can install the same version each time without breaking changes unless you are intentionally looking for the latest version.

Contributing

While we value open-source contributions to this SDK, this library is generated programmatically. Additions made directly to this library would have to be moved over to our generation code, 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!

On the other hand, contributions to the README are always very welcome!

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-0.3.5.tar.gz (57.6 kB view details)

Uploaded Source

Built Distribution

vellum_ai-0.3.5-py3-none-any.whl (204.8 kB view details)

Uploaded Python 3

File details

Details for the file vellum_ai-0.3.5.tar.gz.

File metadata

  • Download URL: vellum_ai-0.3.5.tar.gz
  • Upload date:
  • Size: 57.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.5.1 CPython/3.7.17 Linux/5.15.0-1056-azure

File hashes

Hashes for vellum_ai-0.3.5.tar.gz
Algorithm Hash digest
SHA256 e12e159c0e8eb928b023cbbfe6b4413168ea22277383d392fe271969ffcf7551
MD5 20603da788ee87f73f5363533179a5d0
BLAKE2b-256 b7a3628781256d168b27cfca0f14c75fdf2022f8877f00eb4f3f57a2432633c6

See more details on using hashes here.

Provenance

File details

Details for the file vellum_ai-0.3.5-py3-none-any.whl.

File metadata

  • Download URL: vellum_ai-0.3.5-py3-none-any.whl
  • Upload date:
  • Size: 204.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.5.1 CPython/3.7.17 Linux/5.15.0-1056-azure

File hashes

Hashes for vellum_ai-0.3.5-py3-none-any.whl
Algorithm Hash digest
SHA256 6451c97f06118acca906933f65f23d544a03b1a684f98622105b476bfc1ed09a
MD5 3508cfb720b04e65d7b6fd73121a981f
BLAKE2b-256 db1c50e45c8fc6c75a88c505ac7c221062f9447f62cc83dd790b765337151a4f

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