decodingai-magazine/tabular-semantic-search-tutorial

📚 Tutorial on building a modern search app for Amazon e-commerce products leveraging tabular semantic search and natural language queries.

46
/ 100
Emerging

Implements multi-attribute vector indexing via Superlinked to encode structured product data into dense embeddings, then queries them with OpenAI LLMs through MongoDB Atlas Vector Search—avoiding the brittleness of text-to-SQL approaches. Provides a complete stack with FastAPI backend and Streamlit frontend, plus comparative notebooks demonstrating tabular semantic search versus SQL generation on the ESCI Amazon product dataset (4,400 samples from ~1.8M products).

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

89

Forks

21

Language

Jupyter Notebook

License

MIT

Last pushed

Apr 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/decodingai-magazine/tabular-semantic-search-tutorial"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.