---
title: "Find similar images with CLIP"
description: "Build visual similarity search to find images that look alike using OpenAI's CLIP model."
url: "https://www.pixeltable.com/notebooks/search-similar-images"
updated: "2026-04-10"
---

# Find similar images with CLIP

Build visual similarity search to find images that look alike using OpenAI's CLIP model.

- **Type:** Notebook
- **Group:** Search & Embeddings

## How it works

You add an embedding index using CLIP, which understands both images and text. This enables finding similar images or searching images by text description.

## What it covers

- Create image embeddings with CLIP
- Search by image similarity
- Search by text description (cross-modal)

## What it uses

- **Install:** `pip install pixeltable sentence-transformers torch`
- **Pixeltable calls:** `pxt.create_table()`, `insert()`, `add_embedding_index()`, `similarity()`

## A look at the code

```python
# Add CLIP embedding index (supports both image and text queries)
images.add_embedding_index(
    'image', embedding=clip.using(model_id='openai/clip-vit-base-patch32')
)
```

## Open it

- **Open in Colab:** https://colab.research.google.com/github/pixeltable/pixeltable/blob/release/docs/release/howto/cookbooks/search/search-similar-images.ipynb
- **Docs page:** https://docs.pixeltable.com/howto/cookbooks/search/search-similar-images
- **Source on GitHub:** https://github.com/pixeltable/pixeltable/blob/release/docs/release/howto/cookbooks/search/search-similar-images.ipynb