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/ktem/flowsettings.py

@@ -124,6 +124,11 @@ if config("LOCAL_MODEL", default=""):
 
 
 KH_REASONINGS = ["ktem.reasoning.simple.FullQAPipeline"]
+KH_VLM_ENDPOINT = "{0}/openai/deployments/{1}/chat/completions?api-version={2}".format(
+    config("AZURE_OPENAI_ENDPOINT", default=""),
+    config("OPENAI_VISION_DEPLOYMENT_NAME", default="gpt-4-vision"),
+    config("OPENAI_API_VERSION", default=""),
+)
 
 
 SETTINGS_APP = {