Skip to main content

Google GenAI backend adapter for the AccuralAI orchestration pipeline.

Project description

AccuralAI Google Backend

This package provides the Google GenAI backend adapter for the AccuralAI orchestration core. It wraps the official google-genai client so the orchestrator can target Gemini models with the same pipeline used for other local or remote backends.

Features

  • Async-compatible adapter that internally uses google-genai's synchronous client.
  • Configurable model, generation parameters, safety settings, and client options.
  • Pulls API keys from configuration or the GOOGLE_GENAI_API_KEY environment variable.
  • Converts Google usage metadata into AccuralAI's standard Usage payload.

Installation

pip install accuralai-google

Configuration

From accuralai-core, reference the backend ID you register under backends:

[backends.google]
plugin = "google"
[backends.google.options]
model = "gemini-1.5-pro"
generation_config = { temperature = 0.7 }

Provide an API key either in the options (api_key = "...") or via GOOGLE_GENAI_API_KEY.

Project details


Download files

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

Source Distribution

accuralai_google-0.2.0.tar.gz (12.0 kB view details)

Uploaded Source

Built Distribution

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

accuralai_google-0.2.0-py3-none-any.whl (9.1 kB view details)

Uploaded Python 3

File details

Details for the file accuralai_google-0.2.0.tar.gz.

File metadata

  • Download URL: accuralai_google-0.2.0.tar.gz
  • Upload date:
  • Size: 12.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.19

File hashes

Hashes for accuralai_google-0.2.0.tar.gz
Algorithm Hash digest
SHA256 69d623c8aafbf719b96ffc9a660d135e4269a37ecb9b9d3b2566e143c93b2c9d
MD5 2d2affffc22a7d5c66987aee374047bb
BLAKE2b-256 091dd350c32156fccdf596bcc0c50faa453a82ed97e4a4b2dc28e6eefd1e42e4

See more details on using hashes here.

File details

Details for the file accuralai_google-0.2.0-py3-none-any.whl.

File metadata

File hashes

Hashes for accuralai_google-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 325f1e40ac5e573c06e250a558a3774888f51f3387e6d6f048f7f51492659219
MD5 121de3827dc096948f9f972008f8c77e
BLAKE2b-256 ecaefe8d5a035957c60ea893ac09de1b59d89b3388f2e8d8c180017e42929f17

See more details on using hashes here.

Supported by

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