Skip to main content

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

Project description

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

from flashembed import Embedder
from typing import List

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।'
]
    

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

embeddings = embedder.encode(passages) 

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

flashembed-0.0.2.tar.gz (8.8 kB view details)

Uploaded Source

Built Distribution

flashembed-0.0.2-py3-none-any.whl (10.9 kB view details)

Uploaded Python 3

File details

Details for the file flashembed-0.0.2.tar.gz.

File metadata

  • Download URL: flashembed-0.0.2.tar.gz
  • Upload date:
  • Size: 8.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.4

File hashes

Hashes for flashembed-0.0.2.tar.gz
Algorithm Hash digest
SHA256 8062ba0eed13e2347e068cceef4f538d1428e4c062c00a81db0280fd17f95ba3
MD5 c75885fa9543ea89b9e1419d7f223dec
BLAKE2b-256 cbef0d5a27e515df21c21aee53cba6950b200fee1cfadb47231c47fba5dfe77b

See more details on using hashes here.

File details

Details for the file flashembed-0.0.2-py3-none-any.whl.

File metadata

  • Download URL: flashembed-0.0.2-py3-none-any.whl
  • Upload date:
  • Size: 10.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.4

File hashes

Hashes for flashembed-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 cdaf2c8bbf7260ffdfbff712fdbbb20e94e8f97cfd72a542c526342558159b63
MD5 0ec9491df9e12e918d154aaba1c6d06a
BLAKE2b-256 7d769466463a525871a03a153198fb764cf57936af80040a3e3475fef81550e7

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page