---
title: "Working with Jina AI in Pixeltable"
description: "Pixeltable's Jina AI integration enables you to access state-of-the-art embedding and reranker models via the Jina AI API."
url: "https://www.pixeltable.com/notebooks/working-with-jina"
updated: "2026-04-10"
---

# Working with Jina AI in Pixeltable

Pixeltable's Jina AI integration enables you to access state-of-the-art embedding and reranker models via the Jina AI API.

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

## What it covers

- Text Embeddings
- Multilingual Embeddings
- Embedding Index for Similarity Search
- Reranking
- Learn More

## What it uses

- **Install:** `pip install pixeltable`
- **Environment variables it names:** `JINA_API_KEY`
- **Pixeltable calls:** `jina.embeddings()`, `jina.rerank()`, `pxt.create_table()`, `add_computed_column()`, `insert()`, `add_embedding_index()`, `similarity()`

## A look at the code

```python
from pixeltable.functions import jina

# Create a table for document embeddings
docs_t = pxt.create_table('jina_demo.documents', {'text': pxt.String})

# Add computed column with Jina embeddings
# task='retrieval.passage' optimizes embeddings for documents to be searched
docs_t.add_computed_column(
    embedding=jina.embeddings(
        docs_t.text, model='jina-embeddings-v3', task='retrieval.passage'
    )
)
```

## Open it

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