docs: update quickstart

docs/readme.md

@@ -84,7 +84,7 @@ Our API is composed of two main endpoints:
 
 - `/chat`: This endpoint receives a list of messages, the last being the user query and returns a response generated by the LLM. It uses the documents stored in the database to generate the response. We use LangChain.js components to connect to the database, load the documents and perform a vector search after vectorizing the user query. After that, the most relevant documents are injected into the prompt, and we generate the response. While this process seems complex, LangChain.js does all the heavy lifting for us so we can focus on the application flow.
 
-The `/documents` endpoint is used to ingest the documents after the application is deployed, using `curl` commands (have a look at the `postup` hook in the `azure.yaml` file).
+The `/documents` endpoint is used to ingest the documents after the application is deployed by uploading the PDFs, using either `curl` commands or the Node.js script we built (have a look at the `postup` hook in the `azure.yaml` file).
 
 The web app is a simple chat interface that sends the user queries to the `/chat` endpoint and displays the responses.
 We use the [HTTP protocol for AI chat apps](https://github.com/Azure-Samples/ai-chat-app-protocol) to communicate between the web app and the API.