Skip to main content
The generate_content method is the primary way to interact with Gemini models for text generation. This guide covers different ways to structure your inputs and handle responses.

​
Basic Text Generation

The simplest way to generate content is to pass a string prompt: 
from google import genai

client = genai.Client(api_key='your-api-key')

response = client.models.generate_content(
    model='gemini-2.5-flash',
    contents='Why is the sky blue?'
)
print(response.text)

​
Understanding the Contents Parameter

The SDK converts all inputs to the contents parameter into list[types.Content]. You can structure your inputs in several ways:
The simplest format - SDK converts it to a text part:
contents = 'Why is the sky blue?'
The SDK converts this to:
[
    types.UserContent(
        parts=[
            types.Part.from_text(text='Why is the sky blue?')
        ]
    )
]
Where types.UserContent is a subclass of types.Content with role='user'.

​
Working with Parts

Parts are the building blocks of content. You can mix different types:

​
Text Parts

from google.genai import types

contents = types.Part.from_text('Why is the sky blue?')
The SDK converts non-function-call parts into types.UserContent: 
[
    types.UserContent(parts=[
        types.Part.from_text('Why is the sky blue?')
    ])
]

​
List of Parts

from google.genai import types

contents = [
    types.Part.from_text('What is this image about?'),
    types.Part.from_uri(
        file_uri='gs://generativeai-downloads/images/scones.jpg',
        mime_type='image/jpeg',
    )
]
The SDK groups them into a single types.UserContent: 
[
    types.UserContent(
        parts=[
            types.Part.from_text('What is this image about?'),
            types.Part.from_uri(
                file_uri='gs://generativeai-downloads/images/scones.jpg',
                mime_type='image/jpeg',
            )
        ]
    )
]

​
Response Handling

The response object provides several ways to access the generated content: 
response = client.models.generate_content(
    model='gemini-2.5-flash',
    contents='Tell me a story'
)

# Get the text content
print(response.text)

# Access individual parts
for part in response.parts:
    if part.text:
        print(part.text)

# Access candidates and their content
for candidate in response.candidates:
    print(candidate.content.parts[0].text)

​
Image Output Generation

Some models like gemini-2.5-flash-image can generate images: 
from google.genai import types

response = client.models.generate_content(
    model='gemini-2.5-flash-image',
    contents='A cartoon infographic for flying sneakers',
    config=types.GenerateContentConfig(
        response_modalities=["IMAGE"],
        image_config=types.ImageConfig(
            aspect_ratio="9:16",
        ),
    ),
)

for part in response.parts:
    if part.inline_data:
        generated_image = part.as_image()
        generated_image.show()

​
Using Uploaded Files

You can reference uploaded files in your prompts (Gemini Developer API only): 
# Upload a file first
file = client.files.upload(file='a11.txt')

# Use it in generate_content
response = client.models.generate_content(
    model='gemini-2.5-flash',
    contents=['Could you summarize this file?', file]
)
print(response.text)

​
Mixed Content Types

You can mix different content types in a single request: 
from google.genai import types

contents = [
    types.Content(
        role='user',
        parts=[types.Part.from_text(text='Previous question')]
    ),
    types.Content(
        role='model',
        parts=[types.Part.from_text(text='Previous answer')]
    ),
    # Inner list becomes a single UserContent
    [
        types.Part.from_text('What is this?'),
        types.Part.from_uri(
            file_uri='gs://generativeai-downloads/images/scones.jpg',
            mime_type='image/jpeg',
        )
    ]
]
The SDK groups consecutive non-function-call parts into types.UserContent and consecutive function-call parts into types.ModelContent.

​
Use Cases

Q&A Systems

Generate answers to user questions with context

Content Creation

Generate blog posts, articles, or creative writing

Summarization

Summarize documents, articles, or conversations

Translation

Translate text between languages

​
Best Practices

  • Use simple string inputs for basic prompts
  • Use types.Content objects when you need explicit role control
  • Combine text and other modalities (images, files) in the same request
  • Access response.text for simple text responses
  • Iterate over response.parts for multimodal responses
  • Check response.candidates for multiple response options

Build docs developers (and LLMs) love

Get started for freeTalk to us