Gemini

Use Google Gemini API for text generation, vision, and multimodal tasks. Use when this capability is needed.

tomevault-io Updated

File contents

Gemini

Access Google's Gemini models via the API.

Text Generation

curl -s "https://generativelanguage.googleapis.com/v1/models/gemini-pro:generateContent?key=$GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents":[{"parts":[{"text":"Explain quantum computing"}]}]}'

Vision (Image Analysis)

# Base64 encode an image and send with prompt
IMAGE_B64=$(base64 -i image.jpg)
curl -s "https://generativelanguage.googleapis.com/v1/models/gemini-pro-vision:generateContent?key=$GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents":[{"parts":[
      {"text":"What is in this image?"},
      {"inlineData":{"mimeType":"image/jpeg","data":"'$IMAGE_B64'"}}
    ]}]
  }'

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

tomevault-io/skills-registry/tree/main/kody-w--openrappter--gemini commit 95e5b7bc60

Frequently asked questions

npx skillmds@latest add tomevault-io/gemini-13