Working with Together AI 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.

Prerequisites

• A Together AI account with an API key (https://api.together.ai/settings/api-keys)

Important Notes

• Together.ai usage may incur costs based on your Together.ai 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 Together API key.

%pip install -qU pixeltable together

import os
import getpass

if 'TOGETHER_API_KEY' not in os.environ:
    os.environ['TOGETHER_API_KEY'] = getpass.getpass('Together API Key: ')

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

import pixeltable as pxt

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

Connected to Pixeltable database at: postgresql+psycopg://postgres:@/pixeltable?host=/Users/asiegel/.pixeltable/pgdata
Created directory ‘together_demo’.
<pixeltable.catalog.dir.Dir at 0x14b3d16c0>

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 together

chat_t = pxt.create_table('together_demo.chat', {'input': pxt.String})

messages = [{'role': 'user', 'content': chat_t.input}]

chat_t.add_computed_column(output=together.chat_completions(
    messages=messages,
    model='meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo',
    model_kwargs={
        # Optional dict with parameters for the Together API
        'max_tokens': 300,
        'stop': ['\n'],
        'temperature': 0.7,
        'top_p': 0.9,
    }
))
chat_t.add_computed_column(response=chat_t.output.choices[0].message.content)

Created table `chat`.
Added 0 column values with 0 errors.
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
chat_t.insert([
    {'input': 'How many species of felids have been classified?'},
    {'input': 'Can you make me a coffee?'}
])
chat_t.select(chat_t.input, chat_t.response).head()

Inserting rows into `chat`: 2 rows [00:00, 221.12 rows/s]
Inserted 2 rows with 0 errors.

Embeddings

emb_t = pxt.create_table('together_demo.embeddings', {'input': pxt.String})
emb_t.add_computed_column(embedding=together.embeddings(
    input=emb_t.input,
    model='BAAI/bge-base-en-v1.5'
))

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': 'Together AI provides a variety of embeddings models.'}])

Inserting rows into `embeddings`: 1 rows [00:00, 135.03 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('together_demo.images', {'input': pxt.String})
image_t.add_computed_column(img=together.image_generations(
    image_t.input,
    model='black-forest-labs/FLUX.1-schnell',
    model_kwargs={'steps': 5}
))

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 friendly dinosaur playing tennis in a cornfield'}
])

Inserting rows into `images`: 1 rows [00:00, 204.46 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()

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.