Google GenAI Plugin

This Genkit plugin provides a unified interface for Google AI (Gemini) and Vertex AI models, embedding, and other services.

Setup environment

uv venv
source .venv/bin/activate
pip install genkit-plugins-google-genai

Configuration

Google AI (AI Studio)

To use Google AI models, obtain an API key from Google AI Studio and set it in your environment:

export GEMINI_API_KEY='<your-api-key>'

Vertex AI (Google Cloud)

To use Vertex AI models, ensure you have a Google Cloud project and Application Default Credentials (ADC) set up:

gcloud auth application-default login

Features

Dynamic Models

The plugin automatically discovers available models from the API upon initialization. You can use any model name supported by the API (e.g., googleai/gemini-2.0-flash-exp, vertexai/gemini-1.5-pro).

Dynamic Configuration

New or experimental parameters can be passed flexibly using model_validate to bypass strict schema checks:

from genkit_google_genai import GeminiConfigSchema

config = GeminiConfigSchema.model_validate({
    'temperature': 1.0,
    'response_modalities': ['TEXT', 'IMAGE'],
})

Vertex AI Rerankers

The VertexAI plugin provides semantic rerankers for improving RAG quality by re-scoring documents based on relevance:

from genkit import Genkit
from genkit_google_genai import VertexAI

ai = Genkit(plugins=[VertexAI(project='my-project')])

# Rerank documents after retrieval
ranked_docs = await ai.rerank(
    reranker='vertexai/semantic-ranker-default@latest',
    query='What is machine learning?',
    documents=retrieved_docs,
    options={'top_n': 5},
)

Supported Models:

Model Description
semantic-ranker-default@latest Latest default semantic ranker
semantic-ranker-default-004 Semantic ranker version 004
semantic-ranker-fast-004 Fast variant (lower latency)

Vertex AI Evaluators

Built-in evaluators for assessing model output quality. Evaluators are automatically registered when using the VertexAI plugin and are accessed via ai.evaluate():

from genkit import Genkit
from genkit._core.typing import BaseDataPoint
from genkit_google_genai import VertexAI

ai = Genkit(plugins=[VertexAI(project='my-project')])

# Prepare test dataset
dataset = [
    BaseDataPoint(
        input='Write about AI.',
        output='AI is transforming industries through intelligent automation.',
    ),
]

# Evaluate fluency (scores 1-5)
results = await ai.evaluate(
    evaluator='vertexai/fluency',
    dataset=dataset,
)

for result in results.root:
    print(f'Score: {result.evaluation.score}')

Supported Metrics:

Metric Description
BLEU Translation quality (compare to reference)
ROUGE Summarization quality
FLUENCY Language mastery and readability
SAFETY Harmful/inappropriate content detection
GROUNDEDNESS Hallucination detection
SUMMARIZATION_QUALITY Overall summarization ability

Examples

For comprehensive usage examples, see:

Project links

Data verified by PyPI on Jul 31, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.11.0)

Owner

PyPI data
Data sourced directly from PyPI's database.

Credits

Author: Google

GitHub Statistics

Data verified by PyPI on Jul 31, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License expression

Apache-2.0
View SPDX License List

Requires

Python >=3.10

Tags

ai artificial-intelligence gemini generative-ai genkit google imagen llm machine-learning vertex-ai

Classifiers

Report project as malware

Download files

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

Source Distribution

genkit_google_genai-0.9.0.tar.gz (83.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

genkit_google_genai-0.9.0-py3-none-any.whl (68.3 kB view details)

Uploaded Python 3

File details

Details for the file genkit_google_genai-0.9.0.tar.gz.

File metadata

  • Download URL: genkit_google_genai-0.9.0.tar.gz
  • Upload date:
  • Size: 83.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for genkit_google_genai-0.9.0.tar.gz
Algorithm Hash digest
SHA256 c902ce7587f0b9ac5c1290fc24077017ff2c5ea2b544cb775a017715ea0d1036
MD5 6d14caea46453e6e975bc6d9e76f1464
BLAKE2b-256 230ee65ca6acd08cb175c26a3cb9a2b9504af54530135d70e3154502e8f35cdb

See more details on using hashes here.

Provenance

The following attestation bundles were made for genkit_google_genai-0.9.0.tar.gz:

Publisher: publish_python.yml on genkit-ai/genkit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file genkit_google_genai-0.9.0-py3-none-any.whl.

File metadata

File hashes

Hashes for genkit_google_genai-0.9.0-py3-none-any.whl
Algorithm Hash digest
SHA256 49eaa0b49eedb35b9dddaad3f86f8a2c9cbe875aadf48018b4f233267d334e06
MD5 dd2c55842dc73fe89a76018eea2936b4
BLAKE2b-256 2ce76be3ea1bd63c48acf25bd5f3f44e03c2f13c97cf3215b0fc8fbe1b820feb

See more details on using hashes here.

Provenance

The following attestation bundles were made for genkit_google_genai-0.9.0-py3-none-any.whl:

Publisher: publish_python.yml on genkit-ai/genkit

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

0.11.0

2 files

0.10.0

2 files

This release

0.9.0 This release

2 files

0.8.1

2 files

0.8.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page