| Name | flashembed JSON |
| Version |
0.0.2
JSON |
| download |
| home_page | https://github.com/PrithivirajDamodaran/flashembed |
| Summary | Lightweight & Fast Python library to add low-footprint (all-MiniLM-* equivalent) multilingual retrievers to your RAG and Search & Retrieval pipelines. |
| upload_time | 2024-06-08 05:28:59 |
| maintainer | None |
| docs_url | None |
| author | Prithivi Da |
| requires_python | >=3.6 |
| license | Apache 2.0 |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
<center>
<h1> What is FlashEmbed? </h1>
</center>
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](https://github.com/PrithivirajDamodaran/FlashRank). FlashEmbed uses miniMiracle* series of models. Ofcourse we will be adding more retrievers in future.
<h2> ЁЯУЦ License & Terms </h2>
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.
<center>
<img src="./images/terms.png" width=80%>
</center>
<h2> ЁЯЪА Installation </h2>
```python
pip install flashembed
```
<h2> Supported Models </h2>
- [prithivida/miniMiracle_hi_v1](https://huggingface.co/prithivida/miniMiracle_hi_v1)
- [prithivida/miniMiracle_te_v1](https://huggingface.co/prithivida/miniMiracle_te_v1)
- [prithivida/miniMiracle_zh_v1](https://huggingface.co/prithivida/miniMiracle_zh_v1)
<h2> ЁЯУЦ Usage </h2>
```python
from flashembed import Embedder
from typing import List
passages = [
'рдПрдХ рдЖрджрдореА рдЦрд╛рдирд╛ рдЦрд╛ рд░рд╣рд╛ рд╣реИред',
'рд▓реЛрдЧ рдмреНрд░реЗрдб рдХрд╛ рдПрдХ рдЯреБрдХрдбрд╝рд╛ рдЦрд╛ рд░рд╣реЗ рд╣реИрдВред',
'рд▓рдбрд╝рдХреА рдПрдХ рдмрдЪреНрдЪреЗ рдХреЛ рдЙрдард╛рдП рд╣реБрдП рд╣реИред',
'рдПрдХ рдЖрджрдореА рдШреЛрдбрд╝реЗ рдкрд░ рд╕рд╡рд╛рд░ рд╣реИред',
'рдПрдХ рдорд╣рд┐рд▓рд╛ рд╡рд╛рдпрд▓рд┐рди рдмрдЬрд╛ рд░рд╣реА рд╣реИред',
'рджреЛ рдЖрджрдореА рдЬрдВрдЧрд▓ рдореЗрдВ рдЧрд╛рдбрд╝реА рдзрдХреЗрд▓ рд░рд╣реЗ рд╣реИрдВред',
'рдПрдХ рдЖрджрдореА рдПрдХ рд╕рдлреЗрдж рдШреЛрдбрд╝реЗ рдкрд░ рдПрдХ рдмрдВрдж рдореИрджрд╛рди рдореЗрдВ рд╕рд╡рд╛рд░реА рдХрд░ рд░рд╣рд╛ рд╣реИред',
'рдПрдХ рдмрдВрджрд░ рдбреНрд░рдо рдмрдЬрд╛ рд░рд╣рд╛ рд╣реИред',
'рдПрдХ рдЪреАрддрд╛ рдЕрдкрдиреЗ рд╢рд┐рдХрд╛рд░ рдХреЗ рдкреАрдЫреЗ рджреМрдбрд╝ рд░рд╣рд╛ рд╣реИред',
'рдПрдХ рдмрдбрд╝рд╛ рдбрд┐рдирд░ рд╣реИред'
]
# Onetime Init and Load model
embedder = Embedder('prithivida/miniMiracle_hi_v1')
embeddings = embedder.encode(passages)
Raw data
{
"_id": null,
"home_page": "https://github.com/PrithivirajDamodaran/flashembed",
"name": "flashembed",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": null,
"keywords": null,
"author": "Prithivi Da",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/cb/ef/0d5a27e515df21c21aee53cba6950b200fee1cfadb47231c47fba5dfe77b/flashembed-0.0.2.tar.gz",
"platform": null,
"description": "<center>\n<h1> What is FlashEmbed? </h1>\n</center>\n\nLightweight & 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](https://github.com/PrithivirajDamodaran/FlashRank). FlashEmbed uses miniMiracle* series of models. Ofcourse we will be adding more retrievers in future.\n\n<h2> \ud83d\udcd6 License & Terms </h2> \n\nThe 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.\n\n<center>\n<img src=\"./images/terms.png\" width=80%>\n</center>\n\n\n<h2> \ud83d\ude80 Installation </h2> \n\n```python \npip install flashembed\n```\n<h2> Supported Models </h2>\n\n- [prithivida/miniMiracle_hi_v1](https://huggingface.co/prithivida/miniMiracle_hi_v1)\n- [prithivida/miniMiracle_te_v1](https://huggingface.co/prithivida/miniMiracle_te_v1)\n- [prithivida/miniMiracle_zh_v1](https://huggingface.co/prithivida/miniMiracle_zh_v1)\n\n\n<h2> \ud83d\udcd6 Usage </h2> \n\n```python\nfrom flashembed import Embedder\nfrom typing import List\n\npassages = [\n '\u090f\u0915 \u0906\u0926\u092e\u0940 \u0916\u093e\u0928\u093e \u0916\u093e \u0930\u0939\u093e \u0939\u0948\u0964',\n '\u0932\u094b\u0917 \u092c\u094d\u0930\u0947\u0921 \u0915\u093e \u090f\u0915 \u091f\u0941\u0915\u0921\u093c\u093e \u0916\u093e \u0930\u0939\u0947 \u0939\u0948\u0902\u0964',\n '\u0932\u0921\u093c\u0915\u0940 \u090f\u0915 \u092c\u091a\u094d\u091a\u0947 \u0915\u094b \u0909\u0920\u093e\u090f \u0939\u0941\u090f \u0939\u0948\u0964',\n '\u090f\u0915 \u0906\u0926\u092e\u0940 \u0918\u094b\u0921\u093c\u0947 \u092a\u0930 \u0938\u0935\u093e\u0930 \u0939\u0948\u0964',\n '\u090f\u0915 \u092e\u0939\u093f\u0932\u093e \u0935\u093e\u092f\u0932\u093f\u0928 \u092c\u091c\u093e \u0930\u0939\u0940 \u0939\u0948\u0964',\n '\u0926\u094b \u0906\u0926\u092e\u0940 \u091c\u0902\u0917\u0932 \u092e\u0947\u0902 \u0917\u093e\u0921\u093c\u0940 \u0927\u0915\u0947\u0932 \u0930\u0939\u0947 \u0939\u0948\u0902\u0964',\n '\u090f\u0915 \u0906\u0926\u092e\u0940 \u090f\u0915 \u0938\u092b\u0947\u0926 \u0918\u094b\u0921\u093c\u0947 \u092a\u0930 \u090f\u0915 \u092c\u0902\u0926 \u092e\u0948\u0926\u093e\u0928 \u092e\u0947\u0902 \u0938\u0935\u093e\u0930\u0940 \u0915\u0930 \u0930\u0939\u093e \u0939\u0948\u0964',\n '\u090f\u0915 \u092c\u0902\u0926\u0930 \u0921\u094d\u0930\u092e \u092c\u091c\u093e \u0930\u0939\u093e \u0939\u0948\u0964',\n '\u090f\u0915 \u091a\u0940\u0924\u093e \u0905\u092a\u0928\u0947 \u0936\u093f\u0915\u093e\u0930 \u0915\u0947 \u092a\u0940\u091b\u0947 \u0926\u094c\u0921\u093c \u0930\u0939\u093e \u0939\u0948\u0964',\n '\u090f\u0915 \u092c\u0921\u093c\u093e \u0921\u093f\u0928\u0930 \u0939\u0948\u0964'\n]\n \n\n# Onetime Init and Load model\nembedder = Embedder('prithivida/miniMiracle_hi_v1')\n\nembeddings = embedder.encode(passages) \n\n",
"bugtrack_url": null,
"license": "Apache 2.0",
"summary": "Lightweight & Fast Python library to add low-footprint (all-MiniLM-* equivalent) multilingual retrievers to your RAG and Search & Retrieval pipelines.",
"version": "0.0.2",
"project_urls": {
"Homepage": "https://github.com/PrithivirajDamodaran/flashembed"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "7d769466463a525871a03a153198fb764cf57936af80040a3e3475fef81550e7",
"md5": "0ec9491df9e12e918d154aaba1c6d06a",
"sha256": "cdaf2c8bbf7260ffdfbff712fdbbb20e94e8f97cfd72a542c526342558159b63"
},
"downloads": -1,
"filename": "flashembed-0.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "0ec9491df9e12e918d154aaba1c6d06a",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 10856,
"upload_time": "2024-06-08T05:28:58",
"upload_time_iso_8601": "2024-06-08T05:28:58.383285Z",
"url": "https://files.pythonhosted.org/packages/7d/76/9466463a525871a03a153198fb764cf57936af80040a3e3475fef81550e7/flashembed-0.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "cbef0d5a27e515df21c21aee53cba6950b200fee1cfadb47231c47fba5dfe77b",
"md5": "c75885fa9543ea89b9e1419d7f223dec",
"sha256": "8062ba0eed13e2347e068cceef4f538d1428e4c062c00a81db0280fd17f95ba3"
},
"downloads": -1,
"filename": "flashembed-0.0.2.tar.gz",
"has_sig": false,
"md5_digest": "c75885fa9543ea89b9e1419d7f223dec",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 8843,
"upload_time": "2024-06-08T05:28:59",
"upload_time_iso_8601": "2024-06-08T05:28:59.311654Z",
"url": "https://files.pythonhosted.org/packages/cb/ef/0d5a27e515df21c21aee53cba6950b200fee1cfadb47231c47fba5dfe77b/flashembed-0.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-06-08 05:28:59",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "PrithivirajDamodaran",
"github_project": "flashembed",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "flashembed"
}
