Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/mscraftsman/gemini-playground
Playground to explore Google Gemini using various REST clients
https://github.com/mscraftsman/gemini-playground
Last synced: 2 days ago
JSON representation
Playground to explore Google Gemini using various REST clients
- Host: GitHub
- URL: https://github.com/mscraftsman/gemini-playground
- Owner: mscraftsman
- License: apache-2.0
- Created: 2024-02-22T08:39:20.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2024-02-23T09:12:28.000Z (9 months ago)
- Last Synced: 2024-02-23T11:28:41.176Z (9 months ago)
- Size: 360 KB
- Stars: 0
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Gemini Playground
Playground to explore Google Gemini using various REST clients. The repository contains different approaches using the REST API of Google Gemini.
## Use .http files in Visual Studio 2022
While using Visual Studio one can use the .http file editor as a convenient way to explore an API. More information about .http files can be found in the official documentation [Use .http files in Visual Studio 2022](https://learn.microsoft.com/en-us/aspnet/core/test/http-files).
Open the project GeminiPlayground.csproj in Visual Studio 2022. The .http files contain HTTP calls to send requests to the different models provided by the Gemini API.
- gemini-pro.http contains requests using the Gemini Pro 1.0 model.
- gemini-pro-vision.http has requests against the Gemini Pro Vision 1.0 endpoints.
- vertex-gemini-pro.http contains requests using the Gemini Pro 1.0 model.
- vertex-gemini-pro-vision.http has requests against the Gemini Pro Vision 1.0 endpoints.
The .http files are using file-based environment variables. To get started you have to create a .env file in the project folder and add the following content to it. More details are described in the [.env files](https://learn.microsoft.com/en-us/aspnet/core/test/http-files?view=aspnetcore-8.0#env-files) paragraph.
## Google AI Gemini API
Using Google AI Studio allows you to generate an API key that is used to access the Gemini API programmatically.
```
API_KEY=
```
All Google AI Gemini API requests are based on the [Quickstart: Get started with Gemini using the REST API](https://ai.google.dev/tutorials/rest_quickstart).
## Vertex AI Gemini API
Vertex AI is a service provided by Google Cloud and access to the API requires a cloud project with billing and Vertex AI API enabled.
```
PROJECT_ID=
ACCESS_TOKEN=
```
The region is specified in the .http files directly.
All Vertex AI Gemini API calls are based on the Jupyter notebook [Getting Started with the Vertex AI Gemini API with cURL](https://github.com/GoogleCloudPlatform/generative-ai/blob/main/gemini/getting-started/intro_gemini_curl.ipynb).