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

Provides multi-format document ingestion (PDFs with OCR, Word docs, images, audio via Whisper transcription) with sentence-level embeddings cached in SQLite, eliminating redundant computation. Advanced semantic search combines FAISS cosine similarity filtering with sophisticated rank-correlation measures (Spearman's rho, Kendall's tau, Hoeffding's D) via a custom Rust library for refined result ranking. Supports multiple embedding pooling strategies (mean, SVD, ICA, factor analysis) to handle variable-length inputs and includes grammar-constrained text generation endpoints.

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

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.