Skip to main content

Google AI

Google AI provides advanced capabilities for generating content using text, images, and code execution. It leverages the Google Generative Language API to produce creative and informative outputs based on user inputs.

Generate Content with Text and Image input​

Generate content using text and image inputs with the Google Generative Language API.

Fields​

  • Text Input: The text prompt to guide the content generation. This is the main input for the model to generate content. You can enter any descriptive text or question that you want the model to respond to. For example, "Tell me about this instrument."

  • Image Data: Base64 encoded image data to be used as part of the content generation. Ensure the image is encoded in base64 format. You can use online tools or programming libraries to convert your image to base64.

  • Temperature: Controls the randomness of the output. Use higher values for more creative responses, and lower values for more deterministic responses. Values can range from 0.0 to 2.0. For example, a value of 1.0 is a balanced choice.

  • Max Output Tokens: The maximum number of tokens to generate in the output. This limits the length of the generated content. For instance, setting it to 800 will allow the model to generate up to 800 tokens.

  • Top P: Changes how the model selects tokens for output. Tokens are selected from the most to least probable until the sum of their probabilities equals the topP value. A typical value is 0.8.

  • Top K: Changes how the model selects tokens for output. A topK of 1 means the selected token is the most probable among all the tokens in the model's vocabulary. A common setting is 10.

Output​

The output will be a generated content that combines both the text and image inputs, providing a creative and informative response based on the provided parameters.

Generate Text Content​

Generate text content using the Google Generative Language API with customizable parameters.

Fields​

  • Text Input: The text prompt you want the model to generate content for. This is the main input for the content generation. For example, "Explain how AI works."

  • Temperature: Controls the randomness of the output. Use higher values for more creative responses, and lower values for more deterministic responses. Values can range from 0.0 to 2.0. A typical value is 1.0.

  • Max Output Tokens: The maximum number of tokens to generate in the output. This limits the length of the generated content. For example, setting it to 800 will allow the model to generate up to 800 tokens.

  • Top P: Changes how the model selects tokens for output. Tokens are selected from the most to least probable until the sum of their probabilities equals the topP value. The default topP value is 0.95, but you can set it to 0.8 for a more focused output.

  • Top K: Changes how the model selects tokens for output. A topK of 1 means the selected token is the most probable among all the tokens in the model's vocabulary. A common setting is 10.

Output​

The output will be a text-based content generated by the model, providing a detailed and informative response to the input prompt.

Generate Content with Code Execution​

This action generates content using the Gemini API with code execution capabilities.

Fields​

  • Text for Code Execution: Enter the text or question for which you want the Gemini API to generate and execute code. For example, you can ask it to calculate the sum of the first 50 prime numbers.

Output​

The output will include the generated content along with the results of any code execution performed by the model, providing both a narrative and computational response to the input query.