All tips and important blocks to Starlight built-ins (#19885)

* All tips and important blocks to Starlight built-ins

* These all need to be MDX for the Aside tag to work.

Author: seldo

docs/docs/getting_started/concepts.md renamed to docs/docs/getting_started/concepts.mdx

@@ -62,7 +62,8 @@ A query engine is an end-to-end flow that allows you to ask questions over your
 [**Chat Engines**](/python/framework/module_guides/deploying/chat_engines):
 A chat engine is an end-to-end flow for having a conversation with your data (multiple back-and-forth instead of a single question-and-answer).
 
-!!! tip
-    * Tell me how to [customize things](/python/framework/getting_started/faq)
-    * Continue learning with our [understanding LlamaIndex](/python/framework/understanding) guide
-    * Ready to dig deep? Check out the [component guides](/python/framework/module_guides)
+<Aside type="tip">
+* Tell me how to [customize things](/python/framework/getting_started/faq)
+* Continue learning with our [understanding LlamaIndex](/python/framework/understanding) guide
+* Ready to dig deep? Check out the [component guides](/python/framework/module_guides)
+</Aside>

docs/docs/getting_started/faq.md renamed to docs/docs/getting_started/faq.mdx

@@ -4,8 +4,9 @@ sidebar:
 ---
 # Frequently Asked Questions (FAQ)
 
-!!! tip
-    If you haven't already, [install LlamaIndex](/python/framework/getting_started/installation) and complete the [starter tutorial](/python/framework/getting_started/starter_example). If you run into terms you don't recognize, check out the [high-level concepts](/python/framework/getting_started/concepts).
+<Aside type="tip">
+If you haven't already, [install LlamaIndex](/python/framework/getting_started/installation) and complete the [starter tutorial](/python/framework/getting_started/starter_example). If you run into terms you don't recognize, check out the [high-level concepts](/python/framework/getting_started/concepts).
+</Aside>
 
 In this section, we start with the code you wrote for the [starter example](/python/framework/getting_started/starter_example) and show you the most common ways you might want to customize it for your use case:
 

docs/docs/getting_started/installation.md renamed to docs/docs/getting_started/installation.mdx

@@ -33,8 +33,9 @@ This is a starter bundle of packages, containing
 By default, we use the OpenAI `gpt-3.5-turbo` model for text generation and `text-embedding-ada-002` for retrieval and embeddings. In order to use this, you must have an OPENAI_API_KEY set up as an environment variable.
 You can obtain an API key by logging into your OpenAI account and [creating a new API key](https://platform.openai.com/account/api-keys).
 
-!!! tip
-    You can also [use one of many other available LLMs](/python/framework/module_guides/models/llms/usage_custom). You may need additional environment keys + tokens setup depending on the LLM provider.
+<Aside type="tip">
+You can also [use one of many other available LLMs](/python/framework/module_guides/models/llms/usage_custom). You may need additional environment keys + tokens setup depending on the LLM provider.
+</Aside>
 
 [Check out our OpenAI Starter Example](/python/framework/getting_started/starter_example)
 

docs/docs/getting_started/starter_example.md renamed to docs/docs/getting_started/starter_example.mdx

@@ -6,12 +6,14 @@ sidebar:
 
 This tutorial will show you how to get started building agents with LlamaIndex. We'll start with a basic example and then show how to add RAG (Retrieval-Augmented Generation) capabilities.
 
-!!! tip
-    Make sure you've followed the [installation](/python/framework/getting_started/installation) steps first.
+<Aside type="tip">
+Make sure you've followed the [installation](/python/framework/getting_started/installation) steps first.
+</Aside>
 
-!!! tip
-    Want to use local models?
-    If you want to do our starter tutorial using only local models, [check out this tutorial instead](/python/framework/getting_started/starter_example_local).
+<Aside type="tip">
+Want to use local models?
+If you want to do our starter tutorial using only local models, [check out this tutorial instead](/python/framework/getting_started/starter_example_local).
+</Aside>
 
 ## Set your OpenAI API key
 
@@ -25,8 +27,9 @@ export OPENAI_API_KEY=XXXXX
 set OPENAI_API_KEY=XXXXX
 ```
 
-!!! tip
-    If you are using an OpenAI-Compatible API, you can use the `OpenAILike` LLM class. You can find more information in the [OpenAILike LLM](https://docs.llamaindex.ai/en/stable/api_reference/llms/openai_like/) integration and [OpenAILike Embeddings](https://docs.llamaindex.ai/en/stable/api_reference/embeddings/openai_like/) integration.
+<Aside type="tip">
+If you are using an OpenAI-Compatible API, you can use the `OpenAILike` LLM class. You can find more information in the [OpenAILike LLM](https://docs.llamaindex.ai/en/stable/api_reference/llms/openai_like/) integration and [OpenAILike Embeddings](https://docs.llamaindex.ai/en/stable/api_reference/embeddings/openai_like/) integration.
+</Aside>
 
 ## Basic Agent Example
 
@@ -72,8 +75,9 @@ What happened is:
 - The agent selected the `multiply` tool and wrote the arguments to the tool
 - The agent received the result from the tool and interpolated it into the final response
 
-!!! tip
-    As you can see, we are using `async` python functions. Many LLMs and models support async calls, and using async code is recommended to improve performance of your application. To learn more about async code and python, we recommend this [short section on async + python](/python/framework/getting_started/async_python).
+<Aside type="tip">
+As you can see, we are using `async` python functions. Many LLMs and models support async calls, and using async code is recommended to improve performance of your application. To learn more about async code and python, we recommend this [short section on async + python](/python/framework/getting_started/async_python).
+</Aside>
 
 ## Adding Chat History
 
@@ -177,8 +181,9 @@ index = load_index_from_storage(storage_context)
 query_engine = index.as_query_engine()
 ```
 
-!!! tip
-    If you used a [vector store integration](/python/framework/module_guides/storing/vector_stores) besides the default, chances are you can just reload from the vector store:
+<Aside type="tip">
+If you used a [vector store integration](/python/framework/module_guides/storing/vector_stores) besides the default, chances are you can just reload from the vector store:
+</Aside>
 
     ```python
     index = VectorStoreIndex.from_vector_store(vector_store)

docs/docs/getting_started/starter_example_local.md renamed to docs/docs/getting_started/starter_example_local.mdx

@@ -9,8 +9,9 @@ This tutorial will show you how to get started building agents with LlamaIndex.
 
 We will use [`BAAI/bge-base-en-v1.5`](https://huggingface.co/BAAI/bge-base-en-v1.5) as our embedding model and `llama3.1 8B` served through `Ollama`.
 
-!!! tip
-    Make sure you've followed the [installation](/python/framework/getting_started/installation) steps first.
+<Aside type="tip">
+Make sure you've followed the [installation](/python/framework/getting_started/installation) steps first.
+</Aside>
 
 ## Setup
 
@@ -86,8 +87,9 @@ What happened is:
 - The agent selected the `multiply` tool and wrote the arguments to the tool
 - The agent received the result from the tool and interpolated it into the final response
 
-!!! tip
-    As you can see, we are using `async` python functions. Many LLMs and models support async calls, and using async code is recommended to improve performance of your application. To learn more about async code and python, we recommend this [short section on async + python](/python/framework/getting_started/async_python).
+<Aside type="tip">
+As you can see, we are using `async` python functions. Many LLMs and models support async calls, and using async code is recommended to improve performance of your application. To learn more about async code and python, we recommend this [short section on async + python](/python/framework/getting_started/async_python).
+</Aside>
 
 ## Adding Chat History
 
@@ -216,8 +218,9 @@ query_engine = index.as_query_engine(
 )
 ```
 
-!!! tip
-    If you used a [vector store integration](/python/framework/module_guides/storing/vector_stores) besides the default, chances are you can just reload from the vector store:
+<Aside type="tip">
+If you used a [vector store integration](/python/framework/module_guides/storing/vector_stores) besides the default, chances are you can just reload from the vector store:
+</Aside>
 
     ```python
     index = VectorStoreIndex.from_vector_store(

docs/docs/module_guides/deploying/agents/index.md renamed to docs/docs/module_guides/deploying/agents/index.mdx

@@ -48,8 +48,9 @@ The `FunctionAgent` is a type of agent that uses an LLM provider's function/tool
 
 You can visit [the agents guide](/python/framework/understanding/agent) to learn more about agents and their capabilities.
 
-!!! tip
-    Some models might not support streaming LLM output. While streaming is enabled by default, if you encounter an error, you can always set `FunctionAgent(..., streaming=False)` to disable streaming.
+<Aside type="tip">
+Some models might not support streaming LLM output. While streaming is enabled by default, if you encounter an error, you can always set `FunctionAgent(..., streaming=False)` to disable streaming.
+</Aside>
 
 ## Tools
 

docs/docs/module_guides/deploying/agents/memory.md renamed to docs/docs/module_guides/deploying/agents/memory.mdx

@@ -168,8 +168,9 @@ As the memory is used, the short-term memory will fill up. Once the short-term m
 
 When memory is retrieved, the short-term and long-term memories are merged together. The `Memory` object will ensure that the short-term memory + long-term memory content is less than or equal to the `token_limit`. If it is longer, the `.truncate()` method will be called on the memory blocks, using the `priority` to determine the truncation order.
 
-!!! tip
-    By default, tokens are counted using tiktoken. To customize this, you can set the `tokenizer_fn` argument to a custom callable that given a string, returns a list. The length of the list is then used to determine the token count.
+<Aside type="tip">
+By default, tokens are counted using tiktoken. To customize this, you can set the `tokenizer_fn` argument to a custom callable that given a string, returns a list. The length of the list is then used to determine the token count.
+</Aside>
 
 Once the memory has collected enough information, we might see something like this from the memory:
 

docs/docs/module_guides/deploying/chat_engines/index.md renamed to docs/docs/module_guides/deploying/chat_engines/index.mdx

@@ -9,8 +9,9 @@ Think ChatGPT, but augmented with your knowledge base.
 Conceptually, it is a **stateful** analogy of a [Query Engine](/python/framework/module_guides/deploying/query_engine).
 By keeping track of the conversation history, it can answer questions with past context in mind.
 
-!!! tip
-    If you want to ask standalone question over your data (i.e. without keeping track of conversation history), use [Query Engine](/python/framework/module_guides/deploying/query_engine) instead.
+<Aside type="tip">
+If you want to ask standalone question over your data (i.e. without keeping track of conversation history), use [Query Engine](/python/framework/module_guides/deploying/query_engine) instead.
+</Aside>
 
 ## Usage Pattern
 

docs/docs/module_guides/deploying/chat_engines/usage_pattern.md renamed to docs/docs/module_guides/deploying/chat_engines/usage_pattern.mdx

@@ -8,8 +8,9 @@ Build a chat engine from index:
 chat_engine = index.as_chat_engine()
 ```
 
-!!! tip
-    To learn how to build an index, see [Indexing](/python/framework/module_guides/indexing/index_guide)
+<Aside type="tip">
+To learn how to build an index, see [Indexing](/python/framework/module_guides/indexing/index_guide)
+</Aside>
 
 Have a conversation with your data:
 

docs/docs/module_guides/deploying/query_engine/index.md renamed to docs/docs/module_guides/deploying/query_engine/index.mdx

@@ -8,8 +8,9 @@ A query engine takes in a natural language query, and returns a rich response.
 It is most often (but not always) built on one or many [indexes](/python/framework/module_guides/indexing) via [retrievers](/python/framework/module_guides/querying/retriever).
 You can compose multiple query engines to achieve more advanced capability.
 
-!!! tip
-    If you want to have a conversation with your data (multiple back-and-forth instead of a single question & answer), take a look at [Chat Engine](/python/framework/module_guides/deploying/chat_engines)
+<Aside type="tip">
+If you want to have a conversation with your data (multiple back-and-forth instead of a single question & answer), take a look at [Chat Engine](/python/framework/module_guides/deploying/chat_engines)
+</Aside>
 
 ## Usage Pattern