readme update

README.md

@@ -3,8 +3,15 @@
 
 The FrugalGPT framework offers a collection of techniques for _building LLM applications with budget constraints_.
 
+## 🚀 Getting Started
+
+You can directly run the  [Google Colab Notebook](https://colab.research.google.com/drive/1LM-Wq-u87VI4TKM4thpnwepnOxTAtWaM?authuser=1#scrollTo=a95a1eec) to experience FrugalGPT. You don't even need API keys to get started with it.
+
+Once you go through the notebook, you'll be ready to build your own LLM applcations with FrugalGPT! 
+
+
 ## 🔧 Installation
-To install FrugalGPT, run the following commands:
+You can also install FrugalGPT locally by running the following commands:
 
 ```
 git clone https://github.com/stanford-futuredata/FrugalGPT
@@ -18,16 +25,8 @@ wget -P db/ https://github.com/lchen001/DataHolder/releases/download/v0.0.1/qa_c
 ```
 
 
+Now you are ready to use the [local intro notebook](intro.ipynb)!
 
-Now you are ready to use the [intro notebook](intro.ipynb)!
-
-## 🚀 Getting Started
-
-Our [intro notebook](intro.ipynb) provides examples of using FrugalGPT in a few different applications.
-
-You can also directly start with the  [Google Colab Notebook](https://colab.research.google.com/drive/1LM-Wq-u87VI4TKM4thpnwepnOxTAtWaM?authuser=1#scrollTo=a95a1eec). You don't even need API keys to get started with it.
-
-Once you go through the notebook, you'll be ready to build your own LLM applcations with FrugalGPT! 
 
 
 ## 📚 Read More