Is is possible to fully run on docker compose?

[HeMuling]

I tried:

services:
  open-canvas:
    build: .
    env_file: .env
    ports:
      - "3000:3000"
    depends_on:
      - langgraph
      - db
      - redis
    environment:
      - LANGCHAIN_TRACING_V2=${LANGCHAIN_TRACING_V2}
      - LANGCHAIN_API_KEY=${LANGCHAIN_API_KEY}
      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
      - OPENAI_API_KEY=${OPENAI_API_KEY}
      - GOOGLE_API_KEY=${GOOGLE_API_KEY}
      - FIREWORKS_API_KEY=${FIREWORKS_API_KEY}
      - NEXT_PUBLIC_FIREWORKS_ENABLED=${NEXT_PUBLIC_FIREWORKS_ENABLED}
      - NEXT_PUBLIC_GEMINI_ENABLED=${NEXT_PUBLIC_GEMINI_ENABLED}
      - NEXT_PUBLIC_ANTHROPIC_ENABLED=${NEXT_PUBLIC_ANTHROPIC_ENABLED}
      - NEXT_PUBLIC_OPENAI_ENABLED=${NEXT_PUBLIC_OPENAI_ENABLED}
      - NEXT_PUBLIC_AZURE_ENABLED=${NEXT_PUBLIC_AZURE_ENABLED}
      - LANGGRAPH_API_URL=${LANGGRAPH_API_URL}
      - NEXT_PUBLIC_SUPABASE_URL=${NEXT_PUBLIC_SUPABASE_URL}
      - NEXT_PUBLIC_SUPABASE_ANON_KEY=${NEXT_PUBLIC_SUPABASE_ANON_KEY}
      - _AZURE_OPENAI_API_KEY=${_AZURE_OPENAI_API_KEY}
      - _AZURE_OPENAI_API_INSTANCE_NAME=${_AZURE_OPENAI_API_INSTANCE_NAME}
      - _AZURE_OPENAI_API_DEPLOYMENT_NAME=${_AZURE_OPENAI_API_DEPLOYMENT_NAME}
      - _AZURE_OPENAI_API_VERSION=${_AZURE_OPENAI_API_VERSION}

  langgraph:
    image: langchain/langgraphjs-api:20
    command: LANGSMITH_API_KEY=${LANGCHAIN_API_KEY} langgraph up --watch --port 54367
    environment:
      - LANGSMITH_API_KEY=${LANGCHAIN_API_KEY}
      - DATABASE_URI=postgresql://user:password@db:5432/mydatabase
      - REDIS_URI=redis://redis:6379
      - PORT=54367
    ports:
      - "54367:54367"

  db:
    image: postgres:15
    environment:
      - POSTGRES_USER=user
      - POSTGRES_PASSWORD=password
      - POSTGRES_DB=mydatabase
    ports:
      - "5432:5432"

  redis:
    image: redis:7
    ports:
      - "6379:6379"

and for dockerfile:

FROM node:20

WORKDIR /app

COPY package*.json ./
RUN yarn install

COPY . .

ENV NODE_ENV development
ENV LANGGRAPH_API_URL=http://langgraph:54367
ENV NEXT_PUBLIC_LANGGRAPH_API_URL=http://langgraph:54367
ENV NEXT_PUBLIC_BASE_URL=http://langgraph:54367/api

EXPOSE 3000

CMD ["yarn", "dev"]

But it always fail with log:

yarn run v1.22.22
$ next dev
  ▲ Next.js 14.2.10
  - Local:        http://localhost:3000
  - Environments: .env

 ✓ Starting...
 ✓ Ready in 4.2s
 ✓ Compiled /src/middleware in 119ms
 ✓ Compiled (143 modules)
 ○ Compiling / ...
 ✓ Compiled /_not-found in 59.7s (10419 modules)
 GET /sw.js 404 in 31605ms
 GET / 200 in 61873ms
 GET / 200 in 120ms
 GET /sw.js 404 in 22ms
 ○ Compiling /api/[..._path] ...
 ✓ Compiled /api/[..._path] in 1988ms (4629 modules)
ERROR IN PROXY 404 Not Found
 GET /api/threads/5b796332-7638-48cc-9a50-8a784145df04 404 in 3545ms
 POST /api/threads/search 200 in 3592ms
 POST /api/threads/search 200 in 4331ms
ERROR IN PROXY 404 Not Found
 POST /api/assistants/search 404 in 3570ms
ERROR IN PROXY 404 Not Found
 POST /api/assistants 404 in 226ms
ERROR IN PROXY 404 Not Found
 GET /api/threads/5b796332-7638-48cc-9a50-8a784145df04 404 in 160ms
 POST /api/threads 200 in 288ms
 POST /api/threads 200 in 213ms
 POST /api/threads/search 200 in 195ms
 POST /api/threads/search 200 in 177ms
 GET /sw.js 404 in 130ms

so I'm wondering if it is possible to run on docker compose?

[HARISH-VARMA-GIT]

@HeMuling
It is possible to run fully on docker compose
I got the same erorr before (ERROR IN PROXY 404 Not Found) .I think this error occurs when there is an issue with the Langgraph server.
It worked for me when I used this Dockerfile for the Langgraph server:

FROM langchain/langgraphjs-api:20
ADD . /deps/open-canvas

RUN cd /deps/open-canvas && yarn install --frozen-lockfile

ENV LANGSERVE_GRAPHS='{
    "agent": "./src/agent/open-canvas/index.ts:graph",
    "reflection": "./src/agent/reflection/index.ts:graph",
    "thread_title": "./src/agent/thread-title/index.ts:graph"
}'

WORKDIR /deps/open-canvas

RUN (test ! -f /api/langgraph_api/js/build.mts && echo "Prebuild script not found, skipping") || tsx /api/langgraph_api/js/build.mts

This Dockerfile is generated from the langgraph.json file located in the root directory of open-canvas. Ensure that you build it before running the docker-compose command.

Docker Compose File

volumes:
  langgraph-data:
    driver: local

services:
  langgraph-redis:
    image: redis:6
    healthcheck:
      test: redis-cli ping
      interval: 5s
      timeout: 1s
      retries: 5

  langgraph-postgres:
    image: postgres:16
    ports:
      - "5433:5432"
    environment:
      POSTGRES_DB: postgres
      POSTGRES_USER: postgres
      POSTGRES_PASSWORD: postgres
    volumes:
      - langgraph-data:/var/lib/postgresql/data
    healthcheck:
      test: pg_isready -U postgres
      start_period: 10s
      timeout: 1s
      retries: 5
      interval: 5s

  langgraph-api:
    image: open-canvas:latest
    ports:
      - "57318:8000"
    depends_on:
      langgraph-redis:
        condition: service_healthy
      langgraph-postgres:
        condition: service_healthy
    env_file:
      - .env
    environment:
      REDIS_URI: redis://langgraph-redis:6379
      LANGSMITH_API_KEY: YOUR_API_KEY
      POSTGRES_URI: postgres://postgres:postgres@langgraph-postgres:5432/postgres?sslmode=disable

[tisDDM]

No need to write the Dockerfile on your own. Just use langgraph build or langgraph dockerfile
https://langchain-ai.github.io/langgraph/cloud/reference/cli/#build