Add instructions to README for local development

README.md

@@ -6,11 +6,57 @@ kinds.
 Built using [MFNG](https://github.com/unstubbable/mfng/) — a minimal React
 Server Components (RSC) bundler & library — and the
 [Vercel AI SDK](https://sdk.vercel.ai/docs), this demo leverages RSCs to
-[seamlessly integrate text with UI](https://sdk.vercel.ai/docs/concepts/ai-rsc),
+[seamlessly integrate text with UI](https://sdk.vercel.ai/docs/concepts/ai-rsc)
 as generated by the LLM.
 
 The app is deployed on AWS Lambda & CloudFront. Due to cost considerations, it
 is heavily rate-limited, which may result in occasional error responses.
 
 You can try it out at
 [https://ai-demo.mfng.strict.software](https://ai-demo.mfng.strict.software).
+
+---
+
+## Run Locally
+
+### Prerequisites
+
+- Node.js 20+ installed on your local development machine.
+- An [OpenAI API key](https://platform.openai.com/account/api-keys).
+
+### Install
+
+To install the dependencies, run:
+
+```
+npm install
+```
+
+### Environment Variables
+
+Define the following environment variables, e.g., using
+[direnv](https://direnv.net):
+
+- `OPENAI_API_KEY`: Your OpenAI API key (**required**)
+- `GOOGLE_SEARCH_API_KEY`: Your Custom Search JSON API key (optional)
+- `GOOGLE_SEARCH_SEARCH_ENGINE_ID`: Your Custom Search JSON API Engine ID
+  (optional)
+
+**Note:** When the two Google Custom Search JSON API environment variables are
+not defined, the chat will still function properly; however, images will not be
+displayed, and error messages will be shown instead.
+
+For more information on the Custom Search JSON API, visit:
+[https://developers.google.com/custom-search/v1/introduction](https://developers.google.com/custom-search/v1/introduction)
+
+### Dev Server
+
+To start the development server (which watches for file changes), run:
+
+```
+npm run dev
+```
+
+### Browser
+
+Open [http://localhost:3000](http://localhost:3000) in your browser.