Metadata-Version: 2.4
Name: corpus-engine_tanjha
Version: 0.1.1
Summary: A CLI tool meant for directory text querying VIA text embedding
Author: Tanush Ojha
Author-email: Tanush Ojha <tanushojha057@gmail.com>
License-Expression: MIT
License-File: LICENSE
Requires-Dist: einops>=0.8.2
Requires-Dist: langchain-text-splitters>=1.1.2
Requires-Dist: numpy>=2.4.6
Requires-Dist: scikit-learn>=1.9.0
Requires-Dist: sentence-transformers>=5.5.1
Requires-Dist: typer>=0.26.5
Requires-Python: >=3.11.9
Project-URL: Homepage, https://github.com/tanjha/corpus-engine
Project-URL: Issues, https://github.com/tanjha/corpus-engine/issues
Description-Content-Type: text/markdown

# Corpus Engine
Vector Embedding Powered Corpus Search Engine

# Use

```
engine <command>
```
## Example
```
engine init
rm -rf <example file>
engine update
engine query
engine remove
```

## Commands
- init
   - Initializes corpus engine into CWD and parses any current file inside of it

- query
    - Allows for user queries to search all supported files inside of CWD (and internal directories)

- update
    - Updates all changed, new, or removed files in database

- remove
    - Removes corpus engine from CWD

- reset
    - Performs remove and init actions sequentially


# Build

Build in project root using:
```
uv tool install .
```

Dev build using:
```
uv tool install -e .
```