99sbr/semantic-search-with-sbert

Build Semantic Search with S-BERT and Fine-tune your model in unsupervised way

35
/ 100
Emerging

Quickly find the most relevant documents in a large collection by understanding the meaning behind your search queries, rather than just keywords. You input a question or search term, and the system outputs a ranked list of documents that are semantically similar. This is for researchers, analysts, or anyone who needs to efficiently retrieve information from extensive text datasets like reports, articles, or customer feedback.

No commits in the last 6 months.

Use this if you need to find information based on the true meaning of your query, even if the exact keywords aren't present in the documents.

Not ideal if your search needs are simple keyword matching or if your document collection is very small and doesn't require deep semantic understanding.

information-retrieval document-search text-analysis knowledge-discovery content-discovery
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

59

Forks

21

Language

Jupyter Notebook

License

Last pushed

Apr 26, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/99sbr/semantic-search-with-sbert"

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