mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00

Files

T

Eduard van Valkenburg 90a633967c Python: Fix Gemini client support for Gemini API and Vertex AI (#5258 )

* Add Gemini and Vertex AI client support

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address Gemini PR review feedback

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* removed sample run readme part

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com>

90a633967c · 2026-04-16 19:38:50 +00:00

History

__init__.py

Python: Fix Gemini client support for Gemini API and Vertex AI (#5258 )

2026-04-16 19:38:50 +00:00

gemini_advanced.py

Python: Fix Gemini client support for Gemini API and Vertex AI (#5258 )

2026-04-16 19:38:50 +00:00

gemini_basic.py

Python: Fix Gemini client support for Gemini API and Vertex AI (#5258 )

2026-04-16 19:38:50 +00:00

gemini_with_code_execution.py

Python: Fix Gemini client support for Gemini API and Vertex AI (#5258 )

2026-04-16 19:38:50 +00:00

gemini_with_google_maps.py

Python: Fix Gemini client support for Gemini API and Vertex AI (#5258 )

2026-04-16 19:38:50 +00:00

gemini_with_google_search.py

Python: Fix Gemini client support for Gemini API and Vertex AI (#5258 )

2026-04-16 19:38:50 +00:00

README.md

Python: Fix Gemini client support for Gemini API and Vertex AI (#5258 )

2026-04-16 19:38:50 +00:00

README.md

Google Gemini Examples

This folder contains examples demonstrating how to use Google Gemini models with the Agent Framework.

Examples

File	Description
`gemini_basic.py`	Basic agent with a weather tool, demonstrating both streaming and non-streaming responses.
`gemini_advanced.py`	Extended thinking via `ThinkingConfig` for reasoning-heavy questions (Gemini 2.5+).
`gemini_with_google_search.py`	Google Search grounding for up-to-date answers.
`gemini_with_google_maps.py`	Google Maps grounding for location and mapping information.
`gemini_with_code_execution.py`	Built-in code execution tool for computing precise answers in a sandboxed environment.

Environment Variables

GOOGLE_MODEL or GEMINI_MODEL: The Gemini model to use (for example, gemini-2.5-flash-lite or gemini-2.5-pro)
For Gemini Developer API: GEMINI_API_KEY or GOOGLE_API_KEY
For Vertex AI: GOOGLE_GENAI_USE_VERTEXAI=true, GOOGLE_CLOUD_PROJECT, and GOOGLE_CLOUD_LOCATION