Refactor the index component and update the MVP insurance accordingly (#90)

Refactor the `kotaemon/pipelines` module to `kotaemon/indices`. Create the VectorIndex.

Note: currently I place `qa` to be inside `kotaemon/indices` since at the moment we only have `qa` in RAG. At the same time, I think `qa` can be an independent module in `kotaemon/qa`. Since this can be changed later, I still go at the 1st option for now to observe if we can change it later.

knowledgehub/llms/__init__.py

@@ -1,3 +1,5 @@
+from typing import Union
+
 from kotaemon.base.schema import AIMessage, BaseMessage, HumanMessage, SystemMessage
 
 from .branching import GatedBranchingPipeline, SimpleBranchingPipeline
@@ -6,7 +8,11 @@ from .completions import LLM, AzureOpenAI, OpenAI
 from .linear import GatedLinearPipeline, SimpleLinearPipeline
 from .prompts import BasePromptComponent, PromptTemplate
 
+BaseLLM = Union[ChatLLM, LLM]
+
+
 __all__ = [
+    "BaseLLM",
     # chat-specific components
     "ChatLLM",
     "BaseMessage",