docs: add deployment (#173)

www/pages/docs/_meta.json

@@ -12,24 +12,15 @@
   "faq": "FAQ",
   "-- Deploy This RAG": {
     "type": "separator",
-    "title": "Deploy this RAG",
-    "display": "hidden"
+    "title": "Deployment"
   },
+  "requirements": "Requirements",
   "deploy-with-docker": {
     "title": "Deploy with Docker",
     "display": "hidden"
   },
-  "deploy-to-vercel": {
-    "title": "Deploy to Vercel",
-    "display": "hidden"
-  },
-  "-- Usage": {
-    "type": "separator",
-    "title": "Usage",
-    "display": "hidden"
-  },
   "javascript": {
-    "title": "Embedable JS Code Snippet",
+    "title": "Deploy with JavaScript",
     "display": "hidden"
   },
   "README": {

www/pages/docs/requirements.mdx

@@ -0,0 +1,45 @@
+# Deployment Requirements
+In this section, we will cover the requirements for deploying the project.
+
+
+## Software Requirements
+* Python 3.11 or higher.
+* Node.js 18.17 or higher.
+* An [TiDB Serverless Vector](https://pingcap.com/ai) account.
+  * Currently only TiDB Serverless tier has the support for the Vector Search. You can use the free tier with 25GiB storage. We suggest to choose a nearby region to reduce the latency.
+  * TiDB will probably introduce the Vector Search feature to the open source version next quarter, so stay tuned.
+
+
+## GenAI Services / API Keys
+
+* An **OpenAI API key**, you can get it from [here](https://platform.openai.com/). It will be used for these purposes:
+  * LLM(Large Language Model) for knowledge graph extraction and chat engine.
+  * Embedding model for converting text into vectors.
+  * Chat Engine for generating the answer for the question asked by the user.
+
+* An **Jina AI API key**, you can get it from [here](https://jina.ai/reranker/), it is free for 1M tokens. It will be used for reranking the results retrieved from vector storage.
+
+
+## Web Hosting
+
+### Hardware
+You can use any of the following web hosting services to deploy the project:
+* Cloud server providers like [AWS](https://aws.amazon.com/), [Google Cloud](https://cloud.google.com/), [Azure](https://azure.microsoft.com/), etc.
+* Or your own server.
+
+We suggest the following configuration for the server:
+
+| Name                 | Value            |
+|----------------------|------------------|
+| Memory               | 8 GB RAM         |
+| CPU                  | 4 vCPUs          |
+| Disk                 | 100 GB SSD       |
+| Number of servers    | 1                |
+
+100 GB SSD is enough for most of the cases, but if your corpus is large then you may need more storage.
+
+### Domain name
+You need to have a domain name to deploy the project on the server. You can get a domain name from [GoDaddy](https://www.godaddy.com/), [Namecheap](https://www.namecheap.com/), [Google Domains](https://domains.google/), etc.
+
+### SSL certificate
+You need to have a domain name and SSL certificate to deploy the project on the server. You can get a free SSL certificate from [Let's Encrypt](https://letsencrypt.org/).