Allow users to add LLM within the UI (#6)

* Rename AzureChatOpenAI to LCAzureChatOpenAI
* Provide vanilla ChatOpenAI and AzureChatOpenAI
* Remove the highest accuracy, lowest cost criteria

These criteria are unnecessary. The users, not pipeline creators, should choose
which LLM to use. Furthermore, it's cumbersome to input this information,
really degrades user experience.

* Remove the LLM selection in simple reasoning pipeline
* Provide a dedicated stream method to generate the output
* Return placeholder message to chat if the text is empty

docs/pages/app/customize-flows.md

@@ -193,7 +193,8 @@ information panel.
 You can access users' collections of LLMs and embedding models with:
 
 ```python
-from ktem.components import llms, embeddings
+from ktem.components import embeddings
+from ktem.llms.manager import llms
 
 
 llm = llms.get_default()
@@ -206,12 +207,12 @@ models they want to use through the settings.
 ```python
     @classmethod
     def get_user_settings(cls) -> dict:
-        from ktem.components import llms
+        from ktem.llms.manager import llms
 
         return {
             "citation_llm": {
                 "name": "LLM for citation",
-                "value": llms.get_lowest_cost_name(),
+                "value": llms.get_default(),
                 "component: "dropdown",
                 "choices": list(llms.options().keys()),
             },