---
title: "Working with Bedrock in Pixeltable"
description: "Pixeltable's Bedrock integration enables you to access AWS Bedrock foundation models directly from your tables."
url: "https://www.pixeltable.com/notebooks/working-with-bedrock"
updated: "2026-10-07"
---

# Working with Bedrock in Pixeltable

Pixeltable's Bedrock integration enables you to access AWS Bedrock foundation models directly from your tables.

- **Type:** Notebook
- **Group:** Providers

## What it uses

- **Install:** `pip install pixeltable`
- **Environment variables it names:** `BEDROCK_API_KEY`
- **Pixeltable calls:** `bedrock.converse()`, `pxt.create_table()`, `add_computed_column()`, `insert()`

## A look at the code

```python
from pixeltable.functions import bedrock

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

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

t.add_computed_column(
    output=bedrock.converse(
        model_id='amazon.nova-pro-v1:0',
        messages=[{'role': 'user', 'content': [{'text': t.input}]}],
    )
)
```

## Open it

- **Open in Colab:** https://colab.research.google.com/github/pixeltable/pixeltable/blob/release/docs/release/howto/providers/working-with-bedrock.ipynb
- **Docs page:** https://docs.pixeltable.com/howto/providers/working-with-bedrock
- **Source on GitHub:** https://github.com/pixeltable/pixeltable/blob/release/docs/release/howto/providers/working-with-bedrock.ipynb