[chore] upgrade dependencies (pin transformers==4.31.0 to avoid llava error), remove already installed packages on colab from requirements_colab.txt

[refactor] transform model and utils in python packages

[build] update idea configs

[refactor] code cleaning

[test] rename old notebook to tests_saturncloud.ipynb, add tests_colab.ipynb, update requirements_colab.txt

[test] fix test.ipynb, add example1_mask_0_broken.png

[test] update inference function to return also output mask, useful for tests (now on saturncloud test.ipynb notebook)

[ci] add requirements_colab.txt

[refactor] renamed inference() argument, updated logs

[refactor] start reducing complexity of chat.py

[fix] use sys.exit() instead than exit()

[refactor] move routes to dedicated routes.py, move app helper functions to dedicated app_helpers.py

[refactor] move the app python scripts under the app package

[fix] fix wrong path for image placeholders folder

[refactor] add and use create_placeholder_variables() function

[feat] load LISA model in 4 bit to avoid Memory limit exceeded errors

[refactor] lisa app has back all its functionalities

[fix] rename app.py to main.py, use empty sys.argv to keep only defaults args

[refactor] minor updates to .gitignore, Dockerfile

[refactor] fix missing parse_args() functions, fix inference()

[refactor] update pycharm .idea configs

[refactor] start reverting to original app.py content/1

[refactor] try revert to nvidia pytorch docker based image, nvidia based entrypoint.sh with uvicorn command

[fix] fix missing imports, wrong path in entrypoint.sh

[ci] change Dockerfile base image

[feat] restart from an example app to check what's working

[refactor] try avoid using "if __name__ == '__main__'"

[refactor] add FASTAPI_STATIC folder under ${XDG_CACHE_HOME}/static

[refactor] try mount the gradio app within a fastapi to prepare logging the session id

[refactor] set image precision with an external function

[fix] fix missing import

[debug] add some logs

[fxi] get_inference_model_by_args: use args_to_parse argument

[refactor] return the inference function to inject the model

[refactor] try to wrap model generation code in a dedicated function

[refactor] more refactor app.py/1

[refactor] start refactor app.py

[fix] add missing example3.jpg

[feat] add option to expose inference app

[feat] add missing image

[chore] upgrade dependencies

[refactor] use nh3 instead than bleach to prepare input_str

[refactor] revert to not-modified repository with a working Dockerfile and entrypoint.sh

Merge branch 'main' into new_dockerfile

[feat] update .gitattributes to prepare merge

[feat] update README.md to prepare merge

[feat] add .idea files, update README.md

[feat] track images under resources/imgs with git-lfs, update .gitignore

[feat] use nvidia-smi, nvcc and python3 at runtime within entrypoint.sh

[feat] check for python3 executable