[Doc] Introduce LLM App in doc

README.md

@@ -6,7 +6,17 @@
 
 Parrot is a distributed serving system for LLM-based Applications. The Parrot API w/ Semantic Variable is served by a centralized cluster manager called `ServeCore`, which manages many `Engine` instances. Each Parrot `Engine` runs a single LLM model and communicates with `ServeCore` by contextual Fill/Gen APIs. Note that each `Engine` is capable of providing language model services independently, therefore the system is horizontally scalable and many types of `Engine`s can be integrated into Parrot (e.g., vLLM, FasterTransformer, etc.).
 
-![](assets/arch_paper_ver.png)
+<div align="center">
+  <img src="assets/arch_paper_ver.png" width="500px" />
+</div>
+
+## LLM Applications
+
+The powerful language understanding capability of large language models (LLMs) has enabled a new application paradigm, where one or multiple application entities, known as AI agents or co-pilots, communicate with LLMs via natural language, known as “prompts”, to accomplish a task collaboratively. Parrot is designed to serve these LLM-based applications efficiently by adding `Semantic Variable` in current OpenAI-style API, exposing richer application-level knowledge to backend systems and engines for better optimization.
+
+<div align="center">
+  <img src="assets/app_examples.png" width="500px" />
+</div>
 
 ## Install
 
@@ -54,6 +64,7 @@ If you find Parrot useful or relevant to your research, please cite our paper as
     year = {2024},
     address = {Santa Clara, CA},
     publisher = {USENIX Association},
+    url = {https://www.usenix.org/conference/osdi24/presentation/lin-chaofan},
     month = jul
 }
 ```