Dicklesworthstone/swiss_army_llama

A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.

34
/ 100
Emerging

This project helps you find specific information within your collection of documents and audio files using advanced search methods. You feed it various file types like PDFs, Word documents, images, and audio, and it processes them to extract text and generate numerical representations. These representations allow you to perform powerful semantic searches and retrieve relevant content, making it useful for researchers, analysts, or anyone needing to quickly sift through large datasets.

1,048 stars. No commits in the last 6 months.

Use this if you need to perform highly accurate and nuanced searches across a diverse collection of documents, images, and audio files, going beyond simple keyword matching.

Not ideal if you only need basic text search, have a very small collection of simple text files, or prefer a ready-to-use application rather than integrating with an API.

document-intelligence information-retrieval semantic-search content-analysis knowledge-management
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

1,048

Forks

65

Language

Python

License

Last pushed

Feb 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/Dicklesworthstone/swiss_army_llama"

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