Gemini

Uses Google's Gemini LLM, which accepts natural language text prompts and image files as input, then outputs the text result to the output.txt file in the working directory.

API Key

Go to Google AI Studio ( https://aistudio.google.com/ ) to apply for an API Key.

MODEL

The default model is gemini-1.5-flash. In the future, it can be replaced with a newer model when available.

IMAGE

You can select an image file for the Gemini model to analyze.

OUTPUT

The output format can be plain text or JSON.

TEMPERATURE(0~1.0)

The response randomness can be adjusted:

  • 0 = Lowest randomness, most stable responses.

  • 1.0 = Highest randomness, most diverse responses.

MAX TOKENS

The maximum response word count can be set. A higher value usually requires more time to generate a response. Please refer to the limitations and cost calculations for detail.

SYSTEM PROMPT

Specify the role or overall function for the model, such as: "Translate the user's provided text into Traditional Chinese."

USER PROMPT

User prompt, for example: "A prompt is a natural language request submitted to a language model to receive a response back."

Last updated