Feat/add multimodal loader (#5)

* Add Adobe reader as the multimodal loader

* Allow FullQAPipeline to reasoning on figures

* fix: move the adobe import to avoid ImportError, notify users whenever they run the AdobeReader

---------

Co-authored-by: cin-albert <albert@cinnamon.is>

libs/kotaemon/pyproject.toml

@@ -60,6 +60,7 @@ adv = [
     "cohere",
     "elasticsearch",
     "llama-cpp-python",
+    "pdfservices-sdk @  git+https://github.com/niallcm/pdfservices-python-sdk.git@bump-and-unfreeze-requirements",
 ]
 dev = [
     "ipython",
@@ -69,6 +70,7 @@ dev = [
     "flake8",
     "sphinx",
     "coverage",
+    "python-decouple"
 ]
 all = ["kotaemon[adv,dev]"]