google-cloud-aiplatform
Vertex AI API client library
Decision gist · record as of 2026-08-14
Yes, if you are building AI agents or generative AI applications on Google Cloud. The SDK is actively maintained, has no known vulnerabilities, and offers comprehensive features for agent development and deployment. Be aware that major API reorganization is planned before 7/31/2026—pin to version < 2.0.0 if you need stability. Requires Google Cloud credentials and an active project.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Google Cloud credentials (service account or user authentication) and an active Google Cloud project with Vertex AI APIs enabled.
- Low friction: pure Python wheel with no compiled dependencies.
- Actively maintained with a release 2 days old.
License · maintenance · safety
Apache 2.0 (permissive) — Apache 2.0 permissive license allows commercial and private use with minimal restrictions—suitable for most production deployments.
last release 2026-08-12 (2 days) · last repo commit 2026-08-14 · 903 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 174,186,530 downloads/mo, #243 on PyPI
Alternatives
Verify before relying
pip install google-cloud-aiplatform
from google_cloud_aiplatform import client
client = client.Client(project='my-project', location='us-central1')
inference_results = client.evals.run_inference(
model="gemini-2.5-flash-preview-05-20",
src=prompts_df
)- Whether the upcoming rebranding (agent_engines → runtimes, module relocations) will break existing code before the 7/31/2026 deadline.
- Performance characteristics and rate limits for concurrent agent queries at scale.
- Cost implications of using different model variants and inference methods.
What it is and what it does
google-cloud-aiplatform is the official Python client library for Google's Gemini Enterprise Agent Platform, a managed service for building and deploying AI agents. It provides high-level APIs for defining agents with tools, running inference and evaluation against generative models, optimizing prompts, and managing agent deployments on Google Cloud infrastructure. The SDK abstracts away underlying complexity, offering Pythonic interfaces for common tasks like creating agents, streaming query results, and running batch evaluations with metrics.
The package is tightly integrated with Google Cloud services through dependencies on google-cloud-storage, google-cloud-bigquery, and google-cloud-resource-manager for data handling, and on google-genai and google-auth for authentication and model access. It targets developers building production AI applications who want to leverage Google's infrastructure without managing deployment or scaling themselves. The library is in active development and supports modern Python versions (3.10–3.14), though the documentation warns of significant API reorganization coming in a future major release.
Use it for
- Build and test an AI agent locally, then deploy it to Agent Engine for production queries.
- Run batch inference on a dataset of prompts using a specified Gemini model, then evaluate outputs with multiple metrics.
- Optimize system prompts using zero-shot or data-driven methods to improve agent or model performance.
- Manage agent sandboxes, sessions, and memory banks for multi-turn conversations and stateful interactions.
- Integrate custom tools into agents so they can call external APIs or perform domain-specific logic.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building AI agents or generative AI applications on Google Cloud.
The SDK is actively maintained, has no known vulnerabilities, and offers comprehensive features for agent development and deployment. Be aware that major API reorganization is planned before 7/31/2026—pin to version < 2.0.0 if you need stability. Requires Google Cloud credentials and an active project.
Install
google-cloud-aiplatform on PyPI
Before you install
Low friction: pure Python wheel with no compiled dependencies. Actively maintained with a release 2 days old. Supports Python 3.10 through 3.14. Depends on 13 runtime packages including google-auth, protobuf, and google-cloud-storage.
Requires Google Cloud credentials (service account or user authentication) and an active Google Cloud project with Vertex AI APIs enabled.
License in practice
Apache 2.0 permissive license allows commercial and private use with minimal restrictions—suitable for most production deployments.
Quickstart
pip install google-cloud-aiplatform
from google_cloud_aiplatform import client
client = client.Client(project='my-project', location='us-central1')
inference_results = client.evals.run_inference(
model="gemini-2.5-flash-preview-05-20",
src=prompts_df
)Verify before relying
- Whether the upcoming rebranding (agent_engines → runtimes, module relocations) will break existing code before the 7/31/2026 deadline.
- Performance characteristics and rate limits for concurrent agent queries at scale.
- Cost implications of using different model variants and inference methods.
Package facts
| License | Apache 2.0 permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 13 packagesgoogle-api-coregoogle-authcertifiproto-plusprotobufpackaginggoogle-cloud-storagegoogle-cloud-bigquerygoogle-cloud-resource-managergoogle-genaipydantictyping_extensionsdocstring_parser |
| Maintenance | Actively maintained 2 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 174,186,530 / month, #243 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersOperating System :: OS IndependentProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: InternetTopic :: Software Development :: Libraries :: Python Modules |
Evidence: google_cloud_aiplatform-1.164.0-py2.py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
An agent finds packages by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language. Give your agent the search over MCP.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also google-antigravity · vertexai · google-agents-cli · google-genai · google-adk · google-generativeai · livekit-plugins-google · plato-sdk · notebooklm-py · google-ai-generativelanguage