SemanticOwl + LightOwl + LangOwl open-core
Project description
pipowl 🦉
Open Semantic Tools for Python
SemanticOwl + LightOwl + LangOwl Open-Core
pipowl 提供:
SemanticOwl:輕量語意編碼器(使用 SentenceTransformer)
LightOwl:基本文本清洗
LangOwl:語意搜尋(top-k + cosine similarity)
pip install:
pip install pipowl
使用:
① 先把 LangOwl 叫出來(像叫一隻貓頭鷹出來)
from pipowl.lang import LangOwl
lang = LangOwl()
② 準備一些句子(要比對的清單)
corpus = [ "我今天真的好累", "我覺得今天狀態不太好", "今天的天氣真的很好", ]
③ 比對:丟一句話進去,看哪句最像
results = lang.topk("我今天真的很想睡覺,因為工作太累了", corpus)
④ 把比對結果印出來(分數 + 句子)
for text, score in results: print(score, text)
總結: pipowl 是一個用來比較句子語意相似度的小工具。 你只要給它兩個東西:
- 你的句子(要查的)
- 你有的一堆句子(要比的)
它就會告訴你「哪一句最像」。
輸出示例:
0.903 我今天真的好累 0.882 我覺得今天狀態不太好 0.834 今天的天氣真的很好
請試試看(範例):
py -m quickstart
""" quickstart.py
from pipowl.lang import LangOwl
叫出語意偵探 LangOwl
lang = LangOwl()
準備一組你想比較的句子清單
corpus = [ "我今天真的好累", "我覺得今天狀態不太好", "今天的天氣真的很好", ]
print("模型載入完成!你可以開始輸入句子(Ctrl+C 結束)\n")
互動式輸入,讓你看到最快速的語意搜尋效果
while True: query = input("請輸入句子: ")
results = lang.topk(query, corpus)
print("\n相似結果:")
for text, score in results:
print(f"{score:.3f} | {text}")
print()
"""
""" minimal.py
from pipowl.lang import LangOwl
lang = LangOwl() results = lang.topk("我很累", ["我好累", "我想吃飯"]) print(results)
"""
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file pipowl-1.4.5.tar.gz.
File metadata
- Download URL: pipowl-1.4.5.tar.gz
- Upload date:
- Size: 5.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2f81276fd5b85d20b94d029c93183084fca4aaaf990a6d2ef108e41e479772d4
|
|
| MD5 |
76a216b1388431e2cfee2c0b38d13c1b
|
|
| BLAKE2b-256 |
e748355548f95360547a86299cc8a467c83c12a53c1847e2274f3315decb017e
|
File details
Details for the file pipowl-1.4.5-py3-none-any.whl.
File metadata
- Download URL: pipowl-1.4.5-py3-none-any.whl
- Upload date:
- Size: 4.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d331b5b1c26d962d598fd48a8dddc7ec47f6035e6b013adb50ae0a1e9d9ea723
|
|
| MD5 |
a470ddbbfbfcadefb891ca7d09c74b02
|
|
| BLAKE2b-256 |
12c85fa83f1a66fcc6ceab8dee090d89fcb2a0d06e6f8271c7724b3b5cd2a708
|