Find similar images with CLIP
Build visual similarity search to find images that look alike using OpenAI's CLIP model.
Updated Open in Colab
Build semantic search for text
Create a searchable knowledge base that finds content by meaning, not just keywords.
Search & Embeddings · Notebook · Updated
Colab runs it in your browser. If it calls a model provider, it asks for that provider's API key in a cell.
How it works
You add an embedding index to your text column. Pixeltable automatically generates embeddings for each row and enables similarity search.
What it covers
- Create a text table with embeddings
- Search by semantic similarity
- Combine with metadata filters
What it uses
- Install
- terminalpip install pixeltable sentence-transformers
- Pixeltable calls
pxt.create_table()insert()add_embedding_index()similarity()
A look at the code
search-semantic-text.ipynb
# Add embedding indexkb.add_embedding_index(column='content',string_embed=sentence_transformer.using(model_id='all-MiniLM-L6-v2'),)
One cell of the notebook, copied as it is. Open it in Colab for the rest.
More in Search & Embeddings
Browse all 103Create text embeddings with OpenAI
Generate vector embeddings for text data to enable semantic search and similarity matching.
Updated Open in Colab