Langflow
Stack
Visual builder for AI agents and workflows: drag together models, prompts, tools, vector stores and MCP servers on a canvas, chat with the result in a playground, then call it as an API or serve it as an MCP server. Source: https://github.com/langflow-ai/langflow
Source details
Configuration
TypeComposelinuxLANGFLOW_ADMIN_PASSWORD=''LANGFLOW_DB_PASSWORD=''LANGFLOW_PORT=7860unless-stoppedTemplate by NotAFlightRisk·Source
Report issueNotes
http://<your-host>:7860 (or whichever port you picked) and sign in as langflow with your admin password. Changing that password on the form later does nothing. Add your AI provider's key under Settings --> Model Providers (Ollama works too). The sign-up link makes accounts that stay locked until an admin switches them on, and the open-source version only does that through its API, so treat it as a one-person app. Any account can run its own Python on the server, so only switch on people you trust. Langflow sends anonymous usage stats to its makers. To stop it, add LANGFLOW_TELEMETRY_OFF set to true to the stack's environment variables and redeploy. Uploaded files and its generated keys live in the langflow-data volume, your flows and settings in postgres-data. Docs: docs.langflow.orgServices
langflow
Configuration
Imagelangflowai/langflow:latest${LANGFLOW_PORT:-7860}:7860/app/langflow : langflow-dataLANGFLOW_SUPERUSER_PASSWORD=${LANGFLOW_ADMIN_PASSWORD:?Set an admin password}LANGFLOW_DATABASE_URL=postgresql://langflow:${LANGFLOW_DB_PASSWORD:?Set a database password}@postgres:5432/langflowLANGFLOW_CONFIG_DIR=/app/langflowDO_NOT_TRACK=${LANGFLOW_TELEMETRY_OFF:-false}unless-stoppedImage details
postgres
Configuration
Imagepostgres:17-alpine/var/lib/postgresql/data : postgres-dataPOSTGRES_DB=langflowPOSTGRES_USER=langflowPOSTGRES_PASSWORD=${LANGFLOW_DB_PASSWORD:?Set a database password}unless-stoppedImage details
Standalone Install
Select an install method, to see config/commands for deploying Langflow
Install on Portainer
Import all app templates into your Portainer instance, for easy 1-click deploys
- Ensure both Docker and Portainer are installed, and up-to-date
- Log into your Portainer web UI
- Under Settings → App Templates, paste the below URL
- Head to Home → App Templates, and the list of apps will show up
- Select Langflow, fill in any config options, and hit Deploy
Template Import URL
https://raw.githubusercontent.com/Lissy93/portainer-templates/main/templates.json
Show Me
Original stackfile
The compose file this template deploys, straight from its repo:
services:
langflow:
image: langflowai/langflow:latest
restart: unless-stopped
ports:
- "${LANGFLOW_PORT:-7860}:7860"
environment:
LANGFLOW_SUPERUSER_PASSWORD: ${LANGFLOW_ADMIN_PASSWORD:?Set an admin password}
LANGFLOW_DATABASE_URL: postgresql://langflow:${LANGFLOW_DB_PASSWORD:?Set a database password}@postgres:5432/langflow
LANGFLOW_CONFIG_DIR: /app/langflow
DO_NOT_TRACK: ${LANGFLOW_TELEMETRY_OFF:-false}
volumes:
- langflow-data:/app/langflow
depends_on:
postgres:
condition: service_healthy
postgres:
image: postgres:17-alpine
restart: unless-stopped
environment:
POSTGRES_DB: langflow
POSTGRES_USER: langflow
POSTGRES_PASSWORD: ${LANGFLOW_DB_PASSWORD:?Set a database password}
volumes:
- postgres-data:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U langflow -d langflow"]
interval: 10s
timeout: 5s
retries: 5
volumes:
langflow-data:
postgres-data:
Or deploy it directly from the source:
git clone https://github.com/NotAFlightRisk/portainer-templates-extras
cd portainer-templates-extras
docker compose -f apps/langflow/compose.yml up -dMore install options in our documentation, or see langflow-ai/langflow for app-specific guidance.
Container Documentation
langflow Documentation
Langflow is a low-code app builder for RAG and multi-agent AI applications.
postgres Documentation
The PostgreSQL object-relational database system provides reliability and data integrity.
Check the logs first
Nine times out of ten the logs tell you exactly what went wrong.
- In Portainer, go to Containers, click the container, then Logs. Or run
docker logs <container> - Exit codes help too:
137means killed, usually out of memory.126or127means the command inside the image is broken.
Image won't pull
Test the pull directly on the host: docker pull langflowai/langflow:latest
- "manifest unknown" means the tag no longer exists. This template uses
latest, so try pinning a specific version instead. - "toomanyrequests" is the Docker Hub rate limit. Log in with
docker loginto raise it. - "no space left on device" means a full disk. Reclaim space with
docker system prune
"exec format error"
This means the image was built for a different CPU architecture than your server.
- Check yours with
uname -m: x86_64 is amd64, aarch64 is arm64. Raspberry Pi and other ARM boards are the usual culprits.
Container keeps restarting
The unless-stopped restart policy relaunches the app after every crash, so the real error can scroll past.
- Check the logs right after a restart, the last few lines before it died are the useful ones.
- Get the exit code with
docker inspect <container> --format '{{.State.ExitCode}}' - Still stuck? Redeploy once with the restart policy set to
noso the failure stays visible.
Stack won't deploy
Compose stacks fail fast on small mistakes, and Portainer shows the reason just above the editor.
- YAML only accepts spaces for indentation, a single tab breaks the whole file.
Raise an issue
Found something which isn't working as it should? Here's how to report it.
- Bug within the app: Open an issue on langflow-ai/langflow
- Template not working: Open an issue on NotAFlightRisk/portainer-templates-extras
- This website not working: Open an issue on lissy93/portainer-templates
A Compose stack
Langflow is a Compose stack, a set of containers (2 of them) defined in one file and brought up together by Portainer, then started and stopped as a single app.
The services
This stack is built from 2 containers that run side by side. Here's each one, with the image it runs and anything it waits for first:
langflowrunslangflowai/langflow:latest, starts after postgrespostgresrunspostgres:17-alpine
Volumes
A volume is where Langflow keeps its files so they survive an update or a restart. Without one, anything it saves would sit inside the container and vanish the moment it's recreated. This template mounts:
/app/langflowkept in thelangflow-datavolume Docker manages/var/lib/postgresql/datakept in thepostgres-datavolume Docker manages
Environment variables
Environment variables are the settings you hand over when you deploy, things like a password or a timezone. Langflow takes 7 of them, and 2 need a value before it'll start properly:
LANGFLOW_SUPERUSER_PASSWORD, needs a valueLANGFLOW_DATABASE_URL, defaults topostgresql://langflow:@postgres:5432/langflowLANGFLOW_CONFIG_DIR, defaults to/app/langflowDO_NOT_TRACK, defaults tofalsePOSTGRES_DB, defaults tolangflowPOSTGRES_USER, defaults tolangflowPOSTGRES_PASSWORD, needs a value
Restart policy
The restart policy here is unless-stopped, so Docker restarts Langflow after a crash or reboot, but leaves it off when you stop it on purpose. You can change this on the deploy screen. The choices are no (never restart), on-failure (only after a crash), unless-stopped (restart unless you stop it), and always (bring it back no matter what).
Networking
Portainer puts these services on one shared private network, so they can find each other by name (like langflow) while only the ports above are open to you.
Platform
The platform is linux, the kind of system the container is built to run on. Docker and Portainer handle this on a normal Linux server.
Open source license
Langflow is open source, released under the MIT license. In plain terms the code is out in the open, so you're free to run it and change it to fit what you need.
Portainer app templates
Zooming out, this whole page comes from a Portainer app template: a short recipe telling Portainer how to set Langflow up. Add the template list to Portainer once, then deploying Langflow is a click rather than a wall of config.