fix(docker): added pgvector image to docker builds, modified push to migrate to ameliorate vector data type issue (#452)

* added pgvector image to docker builds, modified push to migrate to ameliorate vector data type issue

* added zod and t3-ss/env-nextjs to minimal set of dependencies for db image

* added healthcheck to docker services

Author: waleedlatif1

.devcontainer/docker-compose.yml

@@ -17,13 +17,33 @@ services:
     depends_on:
       db:
         condition: service_healthy
+      migrations:
+        condition: service_completed_successfully
     ports:
       - "3000:3000"
       - "3001:3001"
     working_dir: /workspace
+    healthcheck:
+      test: ['CMD', 'wget', '--spider', '--quiet', 'http://127.0.0.1:3000']
+      interval: 90s
+      timeout: 5s
+      retries: 3
+      start_period: 10s
+
+  migrations:
+    build:
+      context: ..
+      dockerfile: docker/db.Dockerfile
+    environment:
+      - DATABASE_URL=postgresql://postgres:postgres@db:5432/simstudio
+    depends_on:
+      db:
+        condition: service_healthy
+    command: ['bun', 'run', 'db:migrate']
+    restart: 'no'
 
   db:
-    image: postgres:17-alpine
+    image: pgvector/pgvector:pg17
     restart: unless-stopped
     volumes:
       - postgres-data:/var/lib/postgresql/data

apps/sim/db/migrations/0000_careless_black_knight.sql

@@ -1,6 +1,5 @@
 -- Current sql file was generated after introspecting the database
--- If you want to run this migration please uncomment this code before executing migrations
-/*
+
 CREATE TABLE "verification" (
 	"id" text PRIMARY KEY NOT NULL,
 	"identifier" text NOT NULL,
@@ -50,5 +49,4 @@ CREATE TABLE "session" (
 );
 --> statement-breakpoint
 ALTER TABLE "account" ADD CONSTRAINT "account_user_id_user_id_fk" FOREIGN KEY ("user_id") REFERENCES "public"."user"("id") ON DELETE cascade ON UPDATE no action;--> statement-breakpoint
-ALTER TABLE "session" ADD CONSTRAINT "session_user_id_user_id_fk" FOREIGN KEY ("user_id") REFERENCES "public"."user"("id") ON DELETE cascade ON UPDATE no action;
-*/
+ALTER TABLE "session" ADD CONSTRAINT "session_user_id_user_id_fk" FOREIGN KEY ("user_id") REFERENCES "public"."user"("id") ON DELETE cascade ON UPDATE no action;

apps/sim/db/migrations/0006_plain_zzzax.sql

@@ -29,7 +29,7 @@ ALTER TABLE "user_settings" DISABLE ROW LEVEL SECURITY;--> statement-breakpoint
 DROP TABLE "logs" CASCADE;--> statement-breakpoint
 DROP TABLE "user_environment" CASCADE;--> statement-breakpoint
 DROP TABLE "user_settings" CASCADE;--> statement-breakpoint
-ALTER TABLE "workflow" ALTER COLUMN "state" SET DATA TYPE json;--> statement-breakpoint
+ALTER TABLE "workflow" ALTER COLUMN "state" SET DATA TYPE json USING state::json;--> statement-breakpoint
 ALTER TABLE "workflow_logs" ADD CONSTRAINT "workflow_logs_workflow_id_workflow_id_fk" FOREIGN KEY ("workflow_id") REFERENCES "public"."workflow"("id") ON DELETE cascade ON UPDATE no action;--> statement-breakpoint
 ALTER TABLE "settings" ADD CONSTRAINT "settings_user_id_user_id_fk" FOREIGN KEY ("user_id") REFERENCES "public"."user"("id") ON DELETE cascade ON UPDATE no action;--> statement-breakpoint
 ALTER TABLE "environment" ADD CONSTRAINT "environment_user_id_user_id_fk" FOREIGN KEY ("user_id") REFERENCES "public"."user"("id") ON DELETE cascade ON UPDATE no action;

bun.lock

@@ -27,6 +27,12 @@ services:
         condition: service_healthy
       migrations:
         condition: service_completed_successfully
+    healthcheck:
+      test: ['CMD', 'wget', '--spider', '--quiet', 'http://127.0.0.1:3000']
+      interval: 90s
+      timeout: 5s
+      retries: 3
+      start_period: 10s
 
   migrations:
     build:
@@ -35,12 +41,13 @@ services:
     environment:
       - DATABASE_URL=postgresql://${POSTGRES_USER:-postgres}:${POSTGRES_PASSWORD:-postgres}@db:5432/${POSTGRES_DB:-simstudio}
     depends_on:
-      - db
-    command: ['bun', 'run', 'db:push']
+      db:
+        condition: service_healthy
+    command: ['bun', 'run', 'db:migrate']
     restart: 'no'
 
   db:
-    image: postgres:17-alpine
+    image: pgvector/pgvector:pg17
     restart: always
     ports:
       - '5432:5432'

docker-compose.local.yml

@@ -26,18 +26,25 @@ services:
         condition: service_healthy
       migrations:
         condition: service_completed_successfully
+    healthcheck:
+      test: ['CMD', 'wget', '--spider', '--quiet', 'http://127.0.0.1:3000']
+      interval: 90s
+      timeout: 5s
+      retries: 3
+      start_period: 10s
 
   migrations:
     image: ghcr.io/simstudioai/migrations:latest
     environment:
       - DATABASE_URL=postgresql://${POSTGRES_USER:-postgres}:${POSTGRES_PASSWORD:-postgres}@db:5432/${POSTGRES_DB:-simstudio}
     depends_on:
-      - db
-    command: ['bun', 'run', 'db:push']
+      db:
+        condition: service_healthy
+    command: ['bun', 'run', 'db:migrate']
     restart: 'no'
 
   db:
-    image: postgres:17-alpine
+    image: pgvector/pgvector:pg17
     restart: unless-stopped
     ports:
       - '5432:5432'

docker-compose.prod.yml

@@ -10,7 +10,7 @@ COPY apps/sim/package.json ./apps/sim/db/
 
 # Install minimal dependencies in one layer
 RUN bun install --omit dev --ignore-scripts && \
-    bun install --omit dev --ignore-scripts drizzle-kit drizzle-orm postgres next-runtime-env
+    bun install --omit dev --ignore-scripts drizzle-kit drizzle-orm postgres next-runtime-env zod @t3-oss/env-nextjs
 
 # ========================================
 # Runner Stage: Production Environment

docker/db.Dockerfile

@@ -1,6 +1,6 @@
 {
   "name": "simstudio",
-  "version": "0.1.17",
+  "version": "0.1.18",
   "description": "Sim Studio CLI - Run Sim Studio with a single command",
   "main": "dist/index.js",
   "bin": {

packages/simstudio/package.json

@@ -101,7 +101,7 @@ async function main() {
   if (options.pull) {
     await pullImage('ghcr.io/simstudioai/simstudio:latest')
     await pullImage('ghcr.io/simstudioai/migrations:latest')
-    await pullImage('postgres:17-alpine')
+    await pullImage('pgvector/pgvector:pg17')
   }
 
   // Ensure Docker network exists
@@ -144,7 +144,7 @@ async function main() {
     `${dataDir}/postgres:/var/lib/postgresql/data`,
     '-p',
     '5432:5432',
-    'postgres:17-alpine',
+    'pgvector/pgvector:pg17',
   ])
 
   if (!dbSuccess) {