avenqor-ai 0.1.0__tar.gz

avenqor_ai-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Your Name
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

avenqor_ai-0.1.0/PKG-INFO

@@ -0,0 +1,60 @@
+Metadata-Version: 2.4
+Name: avenqor-ai
+Version: 0.1.0
+Summary: A simple utility package for text and AI-related helper functions
+Author-email: shubham kumar <shubhamk97251@gmail.com>
+License: MIT
+Project-URL: Homepage, https://github.com/yourusername/avenqor-ai
+Project-URL: Repository, https://github.com/yourusername/avenqor-ai
+Keywords: ai,nlp,text,utility
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# avenqor-ai
+
+A simple Python utility package for text processing and AI-related helper functions.
+
+## Installation
+
+```bash
+pip install avenqor-ai
+```
+
+## Usage
+
+```python
+from avenqor_ai import clean_text, count_tokens_approx, chunk_text, similarity_score
+
+# Clean messy text
+clean_text("Hello    World!!\n\n")
+# -> "Hello World!!"
+
+# Estimate token count
+count_tokens_approx("Hello world")
+# -> 2
+
+# Split long text into chunks (for LLM context windows)
+chunks = chunk_text("your very long document here...", chunk_size=500, overlap=50)
+
+# Compare similarity between two texts
+similarity_score("hello world", "hello there")
+# -> 0.33
+```
+
+## Functions
+
+| Function | Description |
+|---|---|
+| `clean_text(text)` | Normalizes whitespace and strips text |
+| `count_tokens_approx(text)` | Rough token count estimate |
+| `chunk_text(text, chunk_size, overlap)` | Splits text into overlapping chunks |
+| `similarity_score(text1, text2)` | Jaccard word-overlap similarity (0-1) |
+
+## License
+
+MIT

avenqor_ai-0.1.0/README.md

@@ -0,0 +1,43 @@
+# avenqor-ai
+
+A simple Python utility package for text processing and AI-related helper functions.
+
+## Installation
+
+```bash
+pip install avenqor-ai
+```
+
+## Usage
+
+```python
+from avenqor_ai import clean_text, count_tokens_approx, chunk_text, similarity_score
+
+# Clean messy text
+clean_text("Hello    World!!\n\n")
+# -> "Hello World!!"
+
+# Estimate token count
+count_tokens_approx("Hello world")
+# -> 2
+
+# Split long text into chunks (for LLM context windows)
+chunks = chunk_text("your very long document here...", chunk_size=500, overlap=50)
+
+# Compare similarity between two texts
+similarity_score("hello world", "hello there")
+# -> 0.33
+```
+
+## Functions
+
+| Function | Description |
+|---|---|
+| `clean_text(text)` | Normalizes whitespace and strips text |
+| `count_tokens_approx(text)` | Rough token count estimate |
+| `chunk_text(text, chunk_size, overlap)` | Splits text into overlapping chunks |
+| `similarity_score(text1, text2)` | Jaccard word-overlap similarity (0-1) |
+
+## License
+
+MIT

avenqor_ai-0.1.0/pyproject.toml

@@ -0,0 +1,28 @@
+[build-system]
+requires = ["setuptools>=68.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "avenqor-ai"
+version = "0.1.0"
+description = "A simple utility package for text and AI-related helper functions"
+readme = "README.md"
+requires-python = ">=3.8"
+license = {text = "MIT"}
+authors = [
+    {name = "shubham kumar", email = "shubhamk97251@gmail.com"}
+]
+keywords = ["ai", "nlp", "text", "utility"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+dependencies = []
+
+[project.urls]
+Homepage = "https://github.com/yourusername/avenqor-ai"
+Repository = "https://github.com/yourusername/avenqor-ai"
+
+[tool.setuptools.packages.find]
+where = ["src"]

avenqor_ai-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

avenqor_ai-0.1.0/src/avenqor_ai/__init__.py

@@ -0,0 +1,19 @@
+"""
+avenqor-ai
+A simple utility package for text and AI-related helper functions.
+"""
+
+from .core import (
+    clean_text,
+    count_tokens_approx,
+    chunk_text,
+    similarity_score,
+)
+
+__version__ = "0.1.0"
+__all__ = [
+    "clean_text",
+    "count_tokens_approx",
+    "chunk_text",
+    "similarity_score",
+]

avenqor_ai-0.1.0/src/avenqor_ai/core.py

@@ -0,0 +1,89 @@
+"""Core functions for avenqor_ai."""
+
+import re
+
+
+def clean_text(text: str) -> str:
+    """
+    Clean text by removing extra whitespace, special characters noise,
+    and normalizing spacing. Useful before feeding text to an LLM.
+
+    Example:
+        >>> clean_text("Hello   World!!\\n\\n")
+        'Hello World!!'
+    """
+    if not isinstance(text, str):
+        raise TypeError("clean_text expects a string")
+
+    text = text.strip()
+    text = re.sub(r"\s+", " ", text)
+    return text
+
+
+def count_tokens_approx(text: str) -> int:
+    """
+    Roughly estimate token count (approx 1 token ≈ 4 characters,
+    a common rule of thumb for English text with GPT/Claude-like models).
+
+    Example:
+        >>> count_tokens_approx("Hello world")
+        3
+    """
+    if not isinstance(text, str):
+        raise TypeError("count_tokens_approx expects a string")
+
+    return max(1, len(text) // 4)
+
+
+def chunk_text(text: str, chunk_size: int = 500, overlap: int = 50) -> list[str]:
+    """
+    Split long text into overlapping chunks — useful for feeding
+    long documents into an LLM with a limited context window.
+
+    Args:
+        text: input text
+        chunk_size: max characters per chunk
+        overlap: number of overlapping characters between chunks
+
+    Example:
+        >>> chunks = chunk_text("a" * 1000, chunk_size=400, overlap=50)
+        >>> len(chunks)
+        3
+    """
+    if not isinstance(text, str):
+        raise TypeError("chunk_text expects a string")
+    if chunk_size <= 0:
+        raise ValueError("chunk_size must be positive")
+    if overlap >= chunk_size:
+        raise ValueError("overlap must be smaller than chunk_size")
+
+    chunks = []
+    start = 0
+    while start < len(text):
+        end = start + chunk_size
+        chunks.append(text[start:end])
+        start += chunk_size - overlap
+    return chunks
+
+
+def similarity_score(text1: str, text2: str) -> float:
+    """
+    Compute a simple word-overlap similarity score (Jaccard similarity)
+    between two texts. Returns a float between 0 and 1.
+
+    Example:
+        >>> similarity_score("hello world", "hello there")
+        0.33
+    """
+    if not isinstance(text1, str) or not isinstance(text2, str):
+        raise TypeError("similarity_score expects two strings")
+
+    set1 = set(text1.lower().split())
+    set2 = set(text2.lower().split())
+
+    if not set1 or not set2:
+        return 0.0
+
+    intersection = set1 & set2
+    union = set1 | set2
+    return round(len(intersection) / len(union), 2)

avenqor_ai-0.1.0/src/avenqor_ai.egg-info/PKG-INFO

@@ -0,0 +1,60 @@
+Metadata-Version: 2.4
+Name: avenqor-ai
+Version: 0.1.0
+Summary: A simple utility package for text and AI-related helper functions
+Author-email: shubham kumar <shubhamk97251@gmail.com>
+License: MIT
+Project-URL: Homepage, https://github.com/yourusername/avenqor-ai
+Project-URL: Repository, https://github.com/yourusername/avenqor-ai
+Keywords: ai,nlp,text,utility
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# avenqor-ai
+
+A simple Python utility package for text processing and AI-related helper functions.
+
+## Installation
+
+```bash
+pip install avenqor-ai
+```
+
+## Usage
+
+```python
+from avenqor_ai import clean_text, count_tokens_approx, chunk_text, similarity_score
+
+# Clean messy text
+clean_text("Hello    World!!\n\n")
+# -> "Hello World!!"
+
+# Estimate token count
+count_tokens_approx("Hello world")
+# -> 2
+
+# Split long text into chunks (for LLM context windows)
+chunks = chunk_text("your very long document here...", chunk_size=500, overlap=50)
+
+# Compare similarity between two texts
+similarity_score("hello world", "hello there")
+# -> 0.33
+```
+
+## Functions
+
+| Function | Description |
+|---|---|
+| `clean_text(text)` | Normalizes whitespace and strips text |
+| `count_tokens_approx(text)` | Rough token count estimate |
+| `chunk_text(text, chunk_size, overlap)` | Splits text into overlapping chunks |
+| `similarity_score(text1, text2)` | Jaccard word-overlap similarity (0-1) |
+
+## License
+
+MIT

avenqor_ai-0.1.0/src/avenqor_ai.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+LICENSE
+README.md
+pyproject.toml
+src/avenqor_ai/__init__.py
+src/avenqor_ai/core.py
+src/avenqor_ai.egg-info/PKG-INFO
+src/avenqor_ai.egg-info/SOURCES.txt
+src/avenqor_ai.egg-info/dependency_links.txt
+src/avenqor_ai.egg-info/top_level.txt
+tests/test_core.py

avenqor_ai-0.1.0/src/avenqor_ai.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

avenqor_ai-0.1.0/src/avenqor_ai.egg-info/top_level.txt

@@ -0,0 +1 @@
+avenqor_ai

avenqor_ai-0.1.0/tests/test_core.py

@@ -0,0 +1,20 @@
+from avenqor_ai import clean_text, count_tokens_approx, chunk_text, similarity_score
+
+
+def test_clean_text():
+    assert clean_text("Hello   World!!\n\n") == "Hello World!!"
+
+
+def test_count_tokens_approx():
+    assert count_tokens_approx("Hello world") == 2
+
+
+def test_chunk_text():
+    chunks = chunk_text("a" * 1000, chunk_size=400, overlap=50)
+    assert len(chunks) == 3
+    assert all(len(c) <= 400 for c in chunks)
+
+
+def test_similarity_score():
+    score = similarity_score("hello world", "hello there")
+    assert 0 <= score <= 1