Metadata-Version: 2.3
Name: apophenia
Version: 0.1.1
Summary: Extract and structure all the data from a Git repository to make them usable in RAG.
Author-email: Hervé Beraud <herveberaud.pro@gmail.com>
License: MIT
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development
Classifier: Topic :: Utilities
Requires-Python: >=3.9
Requires-Dist: faiss-cpu
Requires-Dist: gitpython
Requires-Dist: numpy
Requires-Dist: sentence-transformers
Provides-Extra: dev
Requires-Dist: black; extra == 'dev'
Requires-Dist: build; extra == 'dev'
Requires-Dist: commitizen; extra == 'dev'
Requires-Dist: isort; extra == 'dev'
Requires-Dist: pip-tools; extra == 'dev'
Requires-Dist: pre-commit; extra == 'dev'
Requires-Dist: twine; extra == 'dev'
Description-Content-Type: text/markdown

# apophenia

![Build](https://github.com/4383/apophenia/actions/workflows/main.yml/badge.svg)
![PyPI](https://img.shields.io/pypi/v/apophenia.svg)
![PyPI - Python Version](https://img.shields.io/pypi/pyversions/apophenia.svg)
![PyPI - Status](https://img.shields.io/pypi/status/apophenia.svg)
[![Downloads](https://pepy.tech/badge/apophenia)](https://pepy.tech/project/apophenia)
[![Downloads](https://pepy.tech/badge/apophenia/month)](https://pepy.tech/project/apophenia/month)

Impose a meaningful interpretation on a nebulous stimulus (a Git repo).

Extract and structure all the data from a Git repository to make them usable
in RAG or in with AI agents.

## Usage

```bash
$ pip install apophenia
$ apophenia https://github.com/4383/niet \
  --faiss_path /tmp/faiss_result \
  --metadata_path /tmp/json_result
```

## About FAISS

You can use generated output FAISS with [langchain](
https://python.langchain.com/docs/integrations/vectorstores/faiss/)
or with any modern libraries like [llamaindex](
https://docs.llamaindex.ai/en/stable/api_reference/storage/vector_store/faiss/)

- https://github.com/facebookresearch/faiss
- https://pypi.org/project/faiss/
