Notebooks
A
Arize AI
Intro Gemini 1 5 Flash

Intro Gemini 1 5 Flash

arize-tutorialstracingvertexaiLLMPython

arize logo
Docs | GitHub | Community

VertexAI Tracing

Learn how to instrument vertex ai with Arize. Learn more about Gemini 1.5 Flash.

Getting Started

In order to activate VertexAI, you must have an existing Google Cloud project and enable the Vertex AI API.

  1. Create a new Google Cloud project
  2. Create a billing account linked to this project
  3. Enable the Vertex API with the above link
  4. Save the project id to copy into the cell below

Learn more about setting up a project and a development environment.

Install dependencies

[ ]

Restart runtime

To use the newly installed packages in this Jupyter runtime, you must restart the runtime. You can do this by running the cell below, which restarts the current kernel.

[ ]
⚠️ The kernel is going to restart. Please wait until it is finished before continuing to the next step. ⚠️

Authenticate your notebook environment (Colab only)

If you are running this notebook on Google Colab, run the cell below to authenticate your environment.

[ ]

Setup Arize

[ ]
[ ]

Set Google Cloud project information and initialize Vertex AI SDK

To get started using Vertex AI, you must have an existing Google Cloud project and enable the Vertex AI API.

Learn more about setting up a project and a development environment.

[ ]

Import libraries

[ ]

Load the Gemini 1.5 Flash model

To learn more about all Gemini API models on Vertex AI.

[ ]
MODEL_ID

Vertex AI SDK basic usage

Below is a simple example that demonstrates how to prompt the Gemini 1.5 Flash model using the Vertex AI SDK. Learn more about the Gemini API parameters.

[ ]