Skip to content

Lightweight Python library to add low-footprint (all-MiniLM-* equivalent) multilingual retrievers to your RAG and Search & Retrieval pipelines.

License

Notifications You must be signed in to change notification settings

PrithivirajDamodaran/flashembed

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

What is FlashEmbed?

Lightweight & Fast Python library to add low-footprint (all-MiniLM-* equivalent) multilingual retrievers to your RAG and Search & Retrieval pipelines. No heavy torch or transformer dependencies like it's Sister library FlashRank. FlashEmbed uses miniMiracle* series of models. Ofcourse we will be adding more retrievers in future.

📖 License & Terms

The library is licensed under Apache 2.0 but the weights are licensed differently see below for details. Note: The below license & terms apply ONLY for miniMiracle series models. Use responsibly.

🚀 Installation

pip install flashembed

Supported Models

📖 Usage

For Gated models login first

huggingface-cli login
from flashembed import Embedder
from typing import List

# Onetime Init and Load model.
embedder = Embedder('prithivida/miniMiracle_hi_v1')


passages = [
    'एक आदमी खाना खा रहा है।',
    'लोग ब्रेड का एक टुकड़ा खा रहे हैं।',
    'लड़की एक बच्चे को उठाए हुए है।',
    'एक आदमी घोड़े पर सवार है।',
    'एक महिला वायलिन बजा रही है।',
    'दो आदमी जंगल में गाड़ी धकेल रहे हैं।',
    'एक आदमी एक सफेद घोड़े पर एक बंद मैदान में सवारी कर रहा है।',
    'एक बंदर ड्रम बजा रहा है।',
    'एक चीता अपने शिकार के पीछे दौड़ रहा है।',
    'एक बड़ा डिनर है।'
]

# Get embeddings.
embeddings = embedder.encode(passages) 

About

Lightweight Python library to add low-footprint (all-MiniLM-* equivalent) multilingual retrievers to your RAG and Search & Retrieval pipelines.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages