docs: improve faq and docs (#99)

* docs: add possible solutions when hitting a quota issue

* docs: add link to learn doc

* docs: add details about ai search

README.md

@@ -6,6 +6,7 @@
 # Serverless AI Chat with RAG using LangChain.js
 
 [![Open project in GitHub Codespaces](https://img.shields.io/badge/Codespaces-Open-blue?style=flat-square&logo=github)](https://codespaces.new/Azure-Samples/serverless-chat-langchainjs?hide_repo_select=true&ref=main&quickstart=true)
+[![Official Learn documentation](https://img.shields.io/badge/Documentation-00a3ee?style=flat-square)](https://learn.microsoft.com/azure/developer/javascript/ai/get-started-app-chat-template-langchainjs)
 [![dev.to blog post walkthrough](https://img.shields.io/badge/Blog%20post-black?style=flat-square&logo=dev.to)](https://dev.to/azure/build-a-serverless-chatgpt-with-rag-using-langchainjs-3487)
 [![Build Status](https://img.shields.io/github/actions/workflow/status/Azure-Samples/serverless-chat-langchainjs/build-test.yaml?style=flat-square&label=Build)](https://github.com/Azure-Samples/serverless-chat-langchainjs/actions)
 ![Node version](https://img.shields.io/badge/Node.js->=20-3c873a?style=flat-square)

docs/faq.md

@@ -122,6 +122,17 @@ Related commands are `azd provision` for just provisioning (if infra files chang
 
 </details>
 
+<details>
+<summary><b>Why using Azure Cosmos DB for vector search? What about Azure AI Search?</b></summary><br>
+
+There are multiple Azure services that implement vector search capabilities, including Azure Cosmos DB. In this sample, we use Azure Cosmos DB for vector search because it's also a regular NoSQL database that can store any of your regular data workloads in addition to the vector search data. This makes it a versatile choice for a wide range of applications, all while keeping costs low by using a serverless tier.
+
+Azure AI Search is another option for vector search, but it's more focused on search capabilities: it provides more advanced vector search and hybrid search options, though it doesn't provide the same flexibility as Azure Cosmos DB. We also have a version of this sample that uses Azure AI Search, which you can find [here](https://github.com/Azure-Samples/serverless-chat-langchainjs/tree/ai-search).
+
+For more information about Azure vector search options, you can check out [this architecture guide](https://learn.microsoft.com/azure/architecture/guide/technology-choices/vector-search).
+
+</details>
+
 <!-- TODO: implement this in the code
 <details>
 <summary><b>I don't have access to Azure OpenAI, can I use the regular OpenAI API?</b></summary><br>

docs/troubleshooting.md

@@ -6,7 +6,12 @@ Here are the most common failure scenarios and solutions:
 
 1. You're attempting to create resources in regions not enabled for Azure OpenAI (e.g. East US 2 instead of East US), or where the model you're trying to use isn't enabled. See [this matrix of model availability](https://aka.ms/oai/models).
 
-1. You've exceeded a quota, most often number of resources per region. See [this article on quotas and limits](https://aka.ms/oai/quotas).
+1. You've exceeded a quota, most often number of resources per region. See [this article on quotas and limits](https://aka.ms/oai/quotas). If this happens, you have a few options:
+
+   - Delete other unused resources in the region you're trying to deploy to.
+   - Deploy to a different region.
+   - Try to use a different model or adjust the capacity in `infra/main.bicep` (see [the FAQ](faq.md)).
+   - Request a quota increase.
 
 1. You're getting "same resource name not allowed" conflicts. That's likely because you've run the sample multiple times and deleted the resources you've been creating each time, but are forgetting to purge them. Azure keeps resources for 48 hours unless you purge from soft delete. See [this article on purging resources](https://learn.microsoft.com/azure/ai-services/recover-purge-resources?tabs=azure-portal#purge-a-deleted-resource).