Add arbitrary domain support + website hosting to onebox setup

backend/deployment/README.md

@@ -1,5 +0,0 @@
-This serves as an example for how to deploy everything in a single box. This is far
-from optimal, but can get you started easily and cheaply. To run:
-
-1. Set up a `.env` file in this directory with relevant environment variables (TODO: document)
-2. `docker compose up -d --build`

deployment/.gitignore

@@ -0,0 +1 @@
+.env*

deployment/README.md

@@ -0,0 +1,7 @@
+This serves as an example for how to deploy everything on a single machine. This is
+not optimal, but can get you started easily and cheaply. To run:
+
+1. Set up a `.env` + `.env.nginx` file in this directory with relevant environment variables
+  a. TODO: add description of required variables
+2. `chmod +x init-letsencrypt.sh` + `./init-letsencrypt.sh` to setup https certificate
+2. `docker compose up -d --build` to start nginx, postgres, web/api servers, and the background indexing job

deployment/data/nginx/app.conf.template

@@ -6,14 +6,20 @@ upstream app_server {
     #server unix:/tmp/gunicorn.sock fail_timeout=0;
 
     # for a TCP configuration
+    # TODO: use gunicorn to manage multiple processes
     server api:8080 fail_timeout=0;
 }
 
+upstream web_server {
+    server web:3000 fail_timeout=0;
+}
+
 server {
     listen 80;
-    server_name api.danswer.dev;
+    server_name ${DOMAIN};
 
-    location / {
+    location ~ ^/api(.*)$ {
+      rewrite ^/api(/.*)$ $1 break;
       proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
       proxy_set_header X-Forwarded-Proto $scheme;
       proxy_set_header Host $http_host;
@@ -23,6 +29,14 @@ server {
       proxy_pass http://app_server;
     }
 
+    location / {
+      proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+      proxy_set_header X-Forwarded-Proto $scheme;
+      proxy_set_header Host $http_host;
+      proxy_redirect off;
+      proxy_pass http://web_server;
+    }
+
     location /.well-known/acme-challenge/ {
         root /var/www/certbot;
     }
@@ -30,14 +44,14 @@ server {
 
 server {
     listen 443 ssl;
-    server_name api.danswer.dev;
+    server_name ${DOMAIN};
     
     location / {
-        proxy_pass http://api.danswer.dev;
+        proxy_pass http://${DOMAIN};
     }
 
-    ssl_certificate /etc/letsencrypt/live/api.danswer.dev/fullchain.pem;
-    ssl_certificate_key /etc/letsencrypt/live/api.danswer.dev/privkey.pem;
+    ssl_certificate /etc/letsencrypt/live/${DOMAIN}/fullchain.pem;
+    ssl_certificate_key /etc/letsencrypt/live/${DOMAIN}/privkey.pem;
     include /etc/letsencrypt/options-ssl-nginx.conf;
     ssl_dhparam /etc/letsencrypt/ssl-dhparams.pem;
 }

deployment/docker-compose.yml

@@ -3,13 +3,13 @@ version: '3'
 services:
   api:
     build:
-      context: ..
+      context: ../backend
       dockerfile: Dockerfile
     depends_on:
       - db
-    # just for local testing
-    ports:
-      - "8080:8080"
+    # uncomment for local testing
+    # ports:
+    #   - "8080:8080"
     env_file:
       - .env
     environment:
@@ -18,7 +18,7 @@ services:
       - local_dynamic_storage:/home/storage
   background:
     build:
-      context: ..
+      context: ../backend
       dockerfile: Dockerfile.background
     depends_on:
       - db
@@ -28,6 +28,14 @@ services:
       - POSTGRES_HOST=db
     volumes:
       - local_dynamic_storage:/home/storage
+  web:
+    build:
+      context: ../web
+      dockerfile: Dockerfile
+      args:
+        NEXT_PUBLIC_API_URL: /api
+    depends_on:
+      - api
   db:
     image: postgres:15.2-alpine
     restart: always
@@ -47,7 +55,11 @@ services:
       - ./data/nginx:/etc/nginx/conf.d
       - ./data/certbot/conf:/etc/letsencrypt
       - ./data/certbot/www:/var/www/certbot
-    command: "/bin/sh -c 'while :; do sleep 6h & wait $${!}; nginx -s reload; done & nginx -g \"daemon off;\"'"
+    command: > 
+      /bin/sh -c "envsubst '$$\{DOMAIN\}' < /etc/nginx/conf.d/app.conf.template > /etc/nginx/conf.d/app.conf 
+      && while :; do sleep 6h & wait $${!}; nginx -s reload; done & nginx -g \"daemon off;\""
+    env_file:
+      - .env.nginx
     depends_on:
       - api
   certbot:

deployment/init-letsencrypt.sh

@@ -1,14 +1,20 @@
 #!/bin/bash
 
+# .env.nginx file must be present in the same directory as this script and
+# must set DOMAIN (and optionally EMAIL)
+set -o allexport
+source .env.nginx
+set +o allexport
+
 if ! [ -x "$(command -v docker compose)" ]; then
   echo 'Error: docker compose is not installed.' >&2
   exit 1
 fi
 
-domains=(api.danswer.dev www.api.danswer.dev)
+domains=("$DOMAIN" "www.$DOMAIN")
 rsa_key_size=4096
 data_path="./data/certbot"
-email="" # Adding a valid address is strongly recommended
+email="$EMAIL" # Adding a valid address is strongly recommended
 staging=0 # Set to 1 if you're testing your setup to avoid hitting request limits
 
 if [ -d "$data_path" ]; then

web/Dockerfile

@@ -0,0 +1,55 @@
+FROM node:18-alpine AS base
+
+# Step 1. Install dependencies only when needed
+FROM base AS deps
+# Check https://github.com/nodejs/docker-node/tree/b4117f9333da4138b03a546ec926ef50a31506c3#nodealpine to understand why libc6-compat might be needed.
+RUN apk add --no-cache libc6-compat
+WORKDIR /app
+
+# Install dependencies based on the preferred package manager
+COPY package.json yarn.lock* package-lock.json* pnpm-lock.yaml* ./
+RUN \
+  if [ -f yarn.lock ]; then yarn --frozen-lockfile; \
+  elif [ -f package-lock.json ]; then npm ci; \
+  elif [ -f pnpm-lock.yaml ]; then yarn global add pnpm && pnpm i --frozen-lockfile; \
+  else echo "Lockfile not found." && exit 1; \
+  fi
+
+
+# Step 2. Rebuild the source code only when needed
+FROM base AS builder
+WORKDIR /app
+COPY --from=deps /app/node_modules ./node_modules
+COPY . .
+
+# Disable automatic telemetry collection
+ENV NEXT_TELEMETRY_DISABLED 1
+
+RUN npm run build
+
+# Step 3. Production image, copy all the files and run next
+FROM base AS runner
+WORKDIR /app
+
+ENV NODE_ENV production
+# Disable automatic telemetry collection
+ENV NEXT_TELEMETRY_DISABLED 1
+
+# Don't run production as root
+RUN addgroup --system --gid 1001 nodejs
+RUN adduser --system --uid 1001 nextjs
+USER nextjs
+
+# Add back in if we add anything to `public`
+# COPY --from=builder /app/public ./public
+
+# Automatically leverage output traces to reduce image size
+# https://nextjs.org/docs/advanced-features/output-file-tracing
+COPY --from=builder --chown=nextjs:nodejs /app/.next/standalone ./
+COPY --from=builder --chown=nextjs:nodejs /app/.next/static ./.next/static
+
+# Note: Don't expose ports here, Compose will handle that for us if necessary. 
+# If you want to run this without compose, specify the ports to 
+# expose via cli
+
+CMD ["node", "server.js"]

web/next.config.js

@@ -3,6 +3,23 @@ const nextConfig = {
   experimental: {
     appDir: true,
   },
+  output: "standalone",
+  redirects: async () => {
+    // In production, something else (nginx in the one box setup) takes care
+    // of this redirect
+    // NOTE: this may get adjusted later if we want to support hosting of the
+    // API server on a different domain without requring some kind of proxy
+    if (process.env.NODE_ENV === "development") {
+      return [
+        {
+          source: "/api/:path*",
+          destination: "http://localhost:8080/:path*", // Proxy to Backend
+          permanent: true,
+        },
+      ];
+    }
+    return [];
+  },
 };
 
 module.exports = nextConfig;

web/src/components/SearchBar.tsx

@@ -6,11 +6,8 @@ import "tailwindcss/tailwind.css";
 import { SearchResultsDisplay } from "./SearchResultsDisplay";
 import { SearchResponse } from "./types";
 
-const BACKEND_URL =
-  process.env.NEXT_PUBLIC_BACKEND_URL || "http://localhost:8080"; // "http://servi-lb8a1-jhqpsz92kbm2-1605938866.us-east-2.elb.amazonaws.com/direct-qa";
-
 const searchRequest = async (query: string): Promise<SearchResponse> => {
-  const response = await fetch(BACKEND_URL + "/direct-qa", {
+  const response = await fetch("/api/direct-qa", {
     method: "POST",
     headers: { "Content-Type": "application/json" },
     body: JSON.stringify({

web/src/components/admin/connectors/SlackForm.tsx

@@ -1,7 +1,6 @@
 import React, { useEffect, useState } from "react";
 import { Formik, Form, Field, ErrorMessage, FormikHelpers } from "formik";
 import * as Yup from "yup";
-import { BACKEND_URL } from "@/lib/constants";
 import { Popup } from "./Popup";
 
 interface FormData {
@@ -18,7 +17,7 @@ const validationSchema = Yup.object().shape({
 });
 
 const getConfig = async (): Promise<FormData> => {
-  const response = await fetch(BACKEND_URL + "/admin/slack_connector_config");
+  const response = await fetch("/api/admin/slack_connector_config");
   return response.json();
 };
 
@@ -31,17 +30,13 @@ const handleSubmit = async (
 ) => {
   setSubmitting(true);
   try {
-    // Replace this with your actual API call
-    const response = await fetch(
-      BACKEND_URL + "/admin/slack_connector_config",
-      {
-        method: "POST",
-        headers: {
-          "Content-Type": "application/json",
-        },
-        body: JSON.stringify(values),
-      }
-    );
+    const response = await fetch("/api/admin/slack_connector_config", {
+      method: "POST",
+      headers: {
+        "Content-Type": "application/json",
+      },
+      body: JSON.stringify(values),
+    });
 
     if (response.ok) {
       setPopup({ message: "Success!", type: "success" });

web/src/lib/constants.ts

@@ -1,2 +0,0 @@
-export const BACKEND_URL =
-  process.env.NEXT_PUBLIC_BACKEND_URL || "http://localhost:8080"; // "http://servi-lb8a1-jhqpsz92kbm2-1605938866.us-east-2.elb.amazonaws.com/direct-qa";