{"id":24809,"library":"vellum-ai","title":"Vellum AI Python SDK","description":"Vellum is an AI workflow platform that allows you to build, deploy, and manage AI applications. The Python SDK provides programmatic access to Vellum's APIs for workflow execution, prompt management, and model deployment. Current stable version is 1.14.7, with active development and frequent releases.","status":"active","version":"1.14.7","language":"python","source_language":"en","source_url":"https://github.com/vellum-ai/vellum-python-sdks","tags":["vellum","ai","workflow","ml-model","api-client"],"install":[{"cmd":"pip install vellum-ai","lang":"bash","label":"Install from PyPI"}],"dependencies":[{"reason":"HTTP client for API calls","package":"requests","optional":false},{"reason":"Data validation and settings management","package":"pydantic","optional":false}],"imports":[{"note":"Main client class","symbol":"VellumClient","correct":"from vellum import VellumClient"},{"note":"Environment configuration","symbol":"VellumEnvironment","correct":"from vellum import VellumEnvironment"},{"note":"Workflow execution class","symbol":"WorkflowExecution","correct":"from vellum.workflows import WorkflowExecution"},{"note":"Old package name was vellum-ai, but actual module is vellum","wrong":"from vellum_ai import Vellum","symbol":"Vellum","correct":"from vellum import Vellum"}],"quickstart":{"code":"import os\nfrom vellum import VellumClient\n\nclient = VellumClient(api_key=os.environ.get('VELLUM_API_KEY', ''))\n# Execute a workflow\nresult = client.execute_workflow(\n    workflow_deployment_name=\"my_workflow\",\n    inputs={\"question\": \"What is the capital of France?\"}\n)\nprint(result)","lang":"python","description":"Initialize the client with API key and execute a workflow deployment."},"warnings":[{"fix":"Use 'import vellum' or 'from vellum import ...'","message":"The pip package is 'vellum-ai', but the Python module is just 'vellum'. Many users incorrectly import from 'vellum_ai' which does not exist.","severity":"gotcha","affected_versions":"all"},{"fix":"Review port usage if using >> operator with Port objects.","message":"In version 1.14.0, the Port class added __rrshift__ method which changes how ports behave with operators. If you were using manual port assignments, this may cause unexpected behavior.","severity":"breaking","affected_versions":">=1.14.0"},{"fix":"Check release notes for deprecated fields.","message":"The 'hosted_by' field has been added to ML Model responses. Deprecations may apply to older model fields.","severity":"deprecated","affected_versions":">=1.14.2"}],"env_vars":null,"last_verified":"2026-05-01T00:00:00.000Z","next_check":"2026-07-30T00:00:00.000Z","problems":[{"fix":"Use 'import vellum' or 'from vellum import ...'","cause":"Attempting to import from the incorrect module name","error":"ModuleNotFoundError: No module named 'vellum_ai'"},{"fix":"Set VELLUM_API_KEY environment variable or pass api_key argument to VellumClient","cause":"Missing or incorrect VELLUM_API_KEY environment variable","error":"vellum.exceptions.InvalidApiKeyError: API key is invalid or missing"}],"ecosystem":"pypi","meta_description":null,"install_score":null,"install_tag":null,"quickstart_score":null,"quickstart_tag":null}