preprocess-co fef907779e Adding PreprocessReader for LlamaHub (#773) ...

* Adding PreprocessReader files.

* Update library.json to add PreprocessReader into the list of available readers.

* Fix, set the filepath on initialise in case it's been passed to avoid raising an error.

* Add an end-to-end test in tests folder.

* Update PreprocessReader add a new method to get directly the nodes from the chunks.

* Add new test case to check the result from get_node method.

* Separate the imports for make format and lint.

* Handled format from make.

* Add flag to return whole chunks in one Document object or return each chunk as a Document.

* Update README.md

* Add Preprocess SDK to poetry to be installed.

* Remove Preprocess SDK from main project's list of deps.

* move import under __init__

---------

Co-authored-by: Andrei Fajardo <92402603+nerdai@users.noreply.github.com>

2023-12-20 16:53:22 -05:00

..

__init__.py

Adding PreprocessReader for LlamaHub (#773)

2023-12-20 16:53:22 -05:00

preprocess_test.pdf

Adding PreprocessReader for LlamaHub (#773)

2023-12-20 16:53:22 -05:00

test_preprocess.py

Adding PreprocessReader for LlamaHub (#773)

2023-12-20 16:53:22 -05:00