v3.4.5 - robust linux install

Expand the setup_linux.py script. If it doesn't work properly, Linux users can submit an "issue" and in the meantime use release 3.4.4 instead.

v3.4.4 - bug fixes

Refactor several scripts, offload verbose language to constants.py, hopefully fix once and for all copying pdf.py to the appropriate langchain source code directory on windows/linux/macos.

bitsandbytes-windows-0.41.2.post2-py3

bitsandbytes-win-0.41.2.post2-py3

add missing torch import

v3.4.2 - linux improv

Add additional script to streamline linux installation.
Minor changes such as revising requirements.txt to remove unnecessary imports, etc. that might have been causing some problems depending on a user's setup.
Minor refactoring.

v3.4.1 - bugs/refactor

Requirements.txt was installing langchain on linux when it should only be installed via replace_pdf.py to ensure that pdf.py is copied replaced within the langchain source code (otherwise pdf loader doesn't work).

Removed bitsandbytes macos install unless/until it's supported.

Removed Triton install from requirements.txt and put specific installation commands in github readme.

Refactors several scripts for manageability.

Revised setup.py to use tkinter for Windows users.

v3.4 - RIGHTEOUS SEARCH!

Finally caught a bug that for the last 6 months prevented the "similarity" search setting from working. Make sure and read the updated "tips" and "settings" portion of the user guide.

Refactored multiple scripts.
Specified utf-8 encoding throughout the program to fix bugs.
Consolidated the vision model loaders into new script named loader_images.py.

v3.3.2 - bug fix and refactor

Fix bug when trying to search by document type.

Refactor three scripts into loader_images.py.

v3.3 - POWER search!

Rearranged buttons.

Added the ability to filter chunks by keyword and search images, non-images or both.

Updated user Manual.

Updated readme installation instructions.

Linux and MacoS users, if the langchain library is not installed during the installation process you should install it manually using the typical install command. There might have been a typo in the requirements.txt file.

v3.2 - creature comforts

Add ability to stop LLM from responding midstream.

Add error handling for when server is not running and submit questions button is pressed.

Modify "chunk settings" parameter to be passed directly instead of via config.yaml file.

Consolidate and/or refactor certain scripts for efficiency and reduce number of scripts.

v3.1.1 - Better DB stuff!

View, add, and delete files from DB easier now.