Skip to main content
Open in Kaggle  Open in Colab  Download Notebook
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 OpenAI integration enables you to access OpenAI models via the OpenAI API.

​
Prerequisites

​
Important Notes

  • OpenAI usage may incur costs based on your OpenAI plan.
  • Be mindful of sensitive data and consider security measures when integrating with external services.
First you’ll need to install required libraries and enter your OpenAI API key. 
%pip install -qU pixeltable openai

import os
import getpass
if 'OPENAI_API_KEY' not in os.environ:
    os.environ['OPENAI_API_KEY'] = getpass.getpass('Enter your OpenAI API key:')
Now let’s create a Pixeltable directory to hold the tables for our demo. 
import pixeltable as pxt

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

Connected to Pixeltable database at: postgresql+psycopg://postgres:@/pixeltable?host=/Users/asiegel/.pixeltable/pgdata
Created directory ‘openai_demo’.
<pixeltable.catalog.dir.Dir at 0x32c099c30>

​
Chat Completions

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 OpenAI. 
from pixeltable.functions import openai

# Create a table in Pixeltable and add a computed column that calls OpenAI

t = pxt.create_table('openai_demo.chat', {'input': pxt.String})

messages = [{'role': 'user', 'content': t.input}]
t.add_computed_column(output=openai.chat_completions(
    messages=messages,
    model='gpt-4o-mini',
    model_kwargs={
        # Optional dict with parameters for the OpenAI API
        'max_tokens': 300,
        'top_p': 0.9,
        'temperature': 0.7
    }
))

Created table `chat`.
Added 0 column values with 0 errors.
UpdateStatus(num_rows=0, num_computed_values=0, num_excs=0, updated_cols=[], cols_with_excs=[])
# Parse the response into a new column
t.add_computed_column(response=t.output.choices[0].message.content)

Added 0 column values with 0 errors.
UpdateStatus(num_rows=0, num_computed_values=0, num_excs=0, updated_cols=[], cols_with_excs=[])
# Start a conversation
t.insert([{'input': 'How many islands are in the Aleutian island chain?'}])
t.select(t.input, t.response).head()

Inserting rows into `chat`: 1 rows [00:00, 106.84 rows/s]
Inserted 1 row with 0 errors.

​
Embeddings

Note: OpenAI Embeddings API is not available with free tier API keys 
emb_t = pxt.create_table('openai_demo.embeddings', {'input': pxt.String})
emb_t.add_computed_column(embedding=openai.embeddings(
    input=emb_t.input,
    model='text-embedding-3-small'
))

Created table `embeddings`.
Added 0 column values with 0 errors.
UpdateStatus(num_rows=0, num_computed_values=0, num_excs=0, updated_cols=[], cols_with_excs=[])
emb_t.insert([{'input': 'OpenAI provides a variety of embeddings models.'}])

Inserting rows into `embeddings`: 1 rows [00:00, 164.18 rows/s]
Inserted 1 row with 0 errors.
UpdateStatus(num_rows=1, num_computed_values=2, num_excs=0, updated_cols=[], cols_with_excs=[])
emb_t.head()

​
Image Generations

image_t = pxt.create_table('openai_demo.images', {'input': pxt.String})
image_t.add_computed_column(img=openai.image_generations(
    image_t.input,
    model='dall-e-2',
))

Created table `images`.
Added 0 column values with 0 errors.
UpdateStatus(num_rows=0, num_computed_values=0, num_excs=0, updated_cols=[], cols_with_excs=[])
image_t.insert([
    {'input': 'A giant Pixel floating in the open ocean in a sea of data'}
])

Inserting rows into `images`: 1 rows [00:00, 444.88 rows/s]
Inserted 1 row with 0 errors.
UpdateStatus(num_rows=1, num_computed_values=2, num_excs=0, updated_cols=[], cols_with_excs=[])
image_t

image_t.head()

​
Audio Transcription

audio_t = pxt.create_table('openai_demo.audio', {'input': pxt.Audio})
audio_t.add_computed_column(result=openai.transcriptions(
    audio_t.input,
    model='whisper-1',
    model_kwargs={
        'language': 'en',
        'prompt': 'Transcribe the contents of this recording.'
    },
))

Created table `audio`.
Added 0 column values with 0 errors.
UpdateStatus(num_rows=0, num_computed_values=0, num_excs=0, updated_cols=[], cols_with_excs=[])
url = (
    'https://github.com/pixeltable/pixeltable/raw/release/tests/data/audio/'
    'jfk_1961_0109_cityuponahill-excerpt.flac'
)
audio_t.insert([{'input': url}])

Inserting rows into `audio`: 1 rows [00:00, 160.69 rows/s]
Inserted 1 row with 0 errors.
UpdateStatus(num_rows=1, num_computed_values=3, num_excs=0, updated_cols=[], cols_with_excs=[])
audio_t.head()

audio_t.head()[0]['result']['text']

‘Allow me to illustrate. During the last 60 days, I have been at the task of constructing an administration. It has been a long and deliberate process. Some have counseled greater speed. Others have counseled more expedient tests. But I have been guided by the standard John Winthrop set before his shipmates on the flagship Arabella 331 years ago, as they too faced the task of building a new government on a perilous frontier. We must always consider, he said, that we shall be as a city upon a hill. The eyes of all peoples are upon us. Today, the eyes of all people are truly upon us. And our governments, in every branch, at every level,‘

​
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.