💬Text generation

Generate text from text-only input

The simplest way to generate text using the Gemini API is to provide the model with a single text-only input, as shown in this example:

C#

using Glitch9.AIDevKit.Google.GenerativeAI;

// Choose a model that's appropriate for your use case.
var model = new GenerativeModel(GeminiModel.Gemini15Flash);

var prompt = "Write a story about a magic backpack.";

var response = await model.GenerateContentAsync(prompt);

Debug.Log(response.Text);

Python (Official SDK)

import os
import google.generativeai as genai

# Access your API key as an environment variable.
genai.configure(api_key=os.environ['API_KEY'])
# Choose a model that's appropriate for your use case.
model = genai.GenerativeModel('gemini-1.5-flash')

prompt = "Write a story about a magic backpack."

response = model.generate_content(prompt)

print(response.text)

In this case, the prompt ("Write a story about a magic backpack") doesn't include any output examples, system instructions, or formatting information. It's a zero-shot approach. For some use cases, a one-shot or few-shot prompt might produce output that's more aligned with user expectations. In some cases, you might also want to provide system instructions to help the model understand the task or follow specific guidelines.

Generate text from text-and-image input

The Gemini API supports multimodal inputs that combine text with media files. The following example shows how to generate text from text-and-image input:

C#

using Glitch9.AIDevKit.Google.GenerativeAI;

// Choose a model that's appropriate for your use case.
var model = new GenerativeModel(GeminiModel.Gemini15Flash);

var image1 = new ImageResource("Assets/image1.jpg");
var image2 = new ImageResource("Assets/image2.jpg");

var prompt = "What's different between these pictures?";

var response = await model.GenerateContentAsync(
    prompt, 
    images: new List<ImageResource> { image1, image2 });
    
Debug.Log(response.GetOutputText());

Python (Official SDK)

message = "hello world"
print(message)

As with text-only prompting, multimodal prompting can involve various approaches and refinements. Depending on the output from this example, you might want to add steps to the prompt or be more specific in your instructions. To learn more, see File prompting strategies.

Generate a text stream

By default, the model returns a response after completing the entire text generation process. You can achieve faster interactions by not waiting for the entire result, and instead use streaming to handle partial results.

The following example shows how to implement streaming using the streamGenerateContent method to generate text from a text-only input prompt.

C#

using Glitch9.AIDevKit.Google.GenerativeAI;

// Choose a model that's appropriate for your use case.
var model = new GenerativeModel(GeminiModel.Gemini15Flash);

var prompt = "Write a story about a magic backpack.";

var streamHandler = new StreamHandler();
streamHandler.OnStream += OnStream;

var response = await model.GenerateContentAsync(
    prompt, 
    streamHandler: streamHandler);
    
return;

void OnStream(object sender, string chunk)
{
    Debug.Log(chunk);
}

Python (Official SDK)

import os
import google.generativeai as genai

# Access your API key as an environment variable.
genai.configure(api_key=os.environ['API_KEY'])
# Choose a model that's appropriate for your use case.
model = genai.GenerativeModel('gemini-1.5-flash')

prompt = "Write a story about a magic backpack."

response = model.generate_content(prompt, stream=True)

for chunk in response:
  print(chunk.text)
  print("_"*80)

What's next

This guide shows how to use generateContent and streamGenerateContent to generate text outputs from text-only and text-and-image inputs. To learn more about generating text using the Gemini API, see the following resources:

• Prompting with media files: The Gemini API supports prompting with text, image, audio, and video data, also known as multimodal prompting.

• System instructions: System instructions let you steer the behavior of the model based on your specific needs and use cases.

• Safety guidance: Sometimes generative AI models produce unexpected outputs, such as outputs that are inaccurate, biased, or offensive. Post-processing and human evaluation are essential to limit the risk of harm from such outputs.

Generate text using the Gemini API  |  Google for DevelopersGoogle for Developers

Google official document