Working with Gemini in Pixeltable

    

This documentation page is also available as an interactive notebook. You can launch the notebook in Kaggle or Colab, or download it for use with an IDE or local Jupyter installation, by clicking one of the above links.

Pixeltable’s Gemini integration supports two authentication methods:

• Google AI Studio: requires an API key from https://aistudio.google.com/app/apikey
• Vertex AI: uses Application Default Credentials via the Google Cloud SDK

Prerequisites

For Google AI Studio:

• A Google AI Studio account with an API key (https://aistudio.google.com/app/apikey)

For Vertex AI:

• A Google Cloud project with the Vertex AI API enabled
• The Google Cloud SDK installed and configured (gcloud auth application-default login)

Important notes

• Usage may incur costs based on your plan.
• Be mindful of sensitive data and consider security measures when integrating with external services.

%pip install -qU pixeltable google-genai

import os

vertex_enabled = (
    os.environ.get('GOOGLE_GENAI_USE_VERTEXAI', '').lower() == 'true'
)

# Option 1: Google AI Studio (API key)
# Set GEMINI_API_KEY or GOOGLE_API_KEY in your environment,
# or add api_key to the [gemini] section of $PIXELTABLE_HOME/config.toml

if (
    not vertex_enabled
    and 'GEMINI_API_KEY' not in os.environ
    and 'GOOGLE_API_KEY' not in os.environ
):
    import getpass

    os.environ['GEMINI_API_KEY'] = getpass.getpass(
        'Google AI Studio API Key:'
    )

# Option 2: Vertex AI (Application Default Credentials)
# Uncomment and set the following environment variables to use Vertex AI instead:
# os.environ['GOOGLE_GENAI_USE_VERTEXAI'] = 'true'
# os.environ['GOOGLE_CLOUD_PROJECT'] = 'your-project-id'
# os.environ['GOOGLE_CLOUD_LOCATION'] = 'us-central1'  # optional, defaults to us-central1
# Then authenticate via: gcloud auth application-default login

Now let’s create a Pixeltable directory to hold the tables for our demo.

import pixeltable as pxt

# Remove the 'gemini_demo' directory and its contents, if it exists
pxt.drop_dir('gemini_demo', force=True)
pxt.create_dir('gemini_demo')

Connected to Pixeltable database at: postgresql+psycopg://postgres:@/pixeltable?host=/Users/asiegel/.pixeltable/pgdata
Created directory ‘gemini_demo’.
<pixeltable.catalog.dir.Dir at 0x12fdde740>

Generate content

Create a Table: In Pixeltable, create a table with columns to represent your input data and the columns where you want to store the results from Gemini.

from google.genai.types import GenerateContentConfigDict
from pixeltable.functions import gemini

# Create a table in Pixeltable and pick a model hosted on Google AI Studio with some parameters

t = pxt.create_table('gemini_demo/text', {'input': pxt.String})

config = GenerateContentConfigDict(
    max_output_tokens=300, temperature=1.0, top_p=0.95, top_k=40
)
t.add_computed_column(
    output=gemini.generate_content(
        t.input, model='gemini-2.5-flash', config=config
    )
)

Created table ‘text’.
Added 0 column values with 0 errors in 0.01 s
No rows affected.

# Ask Gemini to generate some content based on the input
t.insert(
    [
        {'input': 'Write a story about a magic backpack.'},
        {'input': 'Tell me a science joke.'},
    ]
)

Inserted 2 rows with 0 errors in 4.96 s (0.40 rows/s)
2 rows inserted.

# Parse the response into a new column
t.add_computed_column(
    response=t.output['candidates'][0]['content']['parts'][0]['text']
)
t.select(t.input, t.response).head()

Generate images with Imagen

from google.genai.types import GenerateImagesConfigDict
from pixeltable.functions import gemini

images_t = pxt.create_table('gemini_demo/images', {'prompt': pxt.String})

config = GenerateImagesConfigDict(aspect_ratio='16:9')
images_t.add_computed_column(
    generated_image=gemini.generate_images(
        images_t.prompt, model='imagen-4.0-generate-001', config=config
    )
)

Created table ‘images’.
Added 0 column values with 0 errors in 0.02 s
No rows affected.

images_t.insert(
    [{'prompt': 'A friendly dinosaur playing tennis in a cornfield'}]
)

Inserted 1 row with 0 errors in 12.31 s (0.08 rows/s)
1 row inserted.

images_t.head()

Generate video with Veo

videos_t = pxt.create_table('gemini_demo/videos', {'prompt': pxt.String})

videos_t.add_computed_column(
    generated_video=gemini.generate_videos(
        videos_t.prompt, model='veo-2.0-generate-001'
    )
)

Created table ‘videos’.
Added 0 column values with 0 errors in 0.01 s
No rows affected.

videos_t.insert(
    [
        {
            'prompt': 'A giant pixel floating over the open ocean in a sea of data'
        }
    ]
)

Inserted 1 row with 0 errors in 40.06 s (0.02 rows/s)
1 row inserted.

videos_t.head()

Generate Video from an existing Image

We’ll add an additional computed column to our existing images_t to animate the generated images.

images_t.add_computed_column(
    generated_video=gemini.generate_videos(
        image=images_t.generated_image, model='veo-2.0-generate-001'
    )
)

Added 1 column value with 0 errors in 52.22 s (0.02 rows/s)
1 row updated.

images_t.head()

Learn more

To learn more about advanced techniques like RAG operations in Pixeltable, check out the RAG Operations in Pixeltable tutorial.

If you have any questions, don’t hesitate to reach out.