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

templates/project-default/{{cookiecutter.project_name}}/{{cookiecutter.project_name}}/pipeline.py

@@ -5,7 +5,7 @@ from kotaemon.base import BaseComponent, Document, LLMInterface, Node, Param, la
 from kotaemon.contribs.promptui.logs import ResultLog
 from kotaemon.embeddings import AzureOpenAIEmbeddings
 from kotaemon.indices import VectorIndexing, VectorRetrieval
-from kotaemon.llms import AzureChatOpenAI
+from kotaemon.llms import LCAzureChatOpenAI
 from kotaemon.storages import ChromaVectorStore, SimpleFileDocumentStore
 
 
@@ -34,7 +34,7 @@ class QuestionAnsweringPipeline(BaseComponent):
     ]
 
     retrieval_top_k: int = 1
-    llm: AzureChatOpenAI = AzureChatOpenAI.withx(
+    llm: LCAzureChatOpenAI = LCAzureChatOpenAI.withx(
         azure_endpoint="https://bleh-dummy-2.openai.azure.com/",
         openai_api_key=os.environ.get("OPENAI_API_KEY", "default-key"),
         openai_api_version="2023-03-15-preview",