skyvern
skyvern copied to clipboard
Skyvern-AI
BUG: Skyvern sensitive to port change
When I changed ports in docker-compose file to others , then Skyvern UI create new task started returning "network error" box .
However, after reverting this change and restarting, skyvern was working back again on default ports.
still not working, example port change:
diff --git a/docker-compose.yml b/docker-compose.yml
index a94b875..8e0ce9a 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -3,8 +3,8 @@ services:
image: postgres:14-alpine
restart: always
# comment out if you want to externally connect DB
- # ports:
- # - 5432:5432
+ ports:
+ - 5048:5432
volumes:
- ./postgres-data:/var/lib/postgresql/data
environment:
@@ -23,7 +23,7 @@ services:
restart: on-failure
# comment out if you want to externally call skyvern API
ports:
- - 8000:8000
+ - 5049:8000
volumes:
- ./artifacts:/data/artifacts
- ./videos:/data/videos
@@ -59,8 +59,8 @@ services:
image: public.ecr.aws/skyvern/skyvern-ui:latest
restart: on-failure
ports:
- - 8080:8080
- - 9090:9090
+ - 5050:8080
+ - 5051:9090
volumes:
- ./artifacts:/data/artifacts
- ./videos:/data/videos
To resolve the issue caused by changing ports in the docker-compose.yml file, ensure that all related environment variables, such as VITE_WSS_BASE_URL, are updated to reflect the new ports. For example, if the Skyvern API port changes to 5049, set VITE_WSS_BASE_URL=ws://localhost:5049/api/v1. After updating the configuration, rebuild and restart the containers using docker-compose down and docker-compose up --build. Clear your browser cache or perform a hard refresh (Ctrl+Shift+R) to load the updated settings. Additionally, verify service communication by checking the logs (docker-compose logs -f). Ensuring consistency across port configurations should resolve the "network error" issue.
docker-compose(dot)yml.txt After rebuilding with 'docker-compose up -build' , i launch the navigation panel on 192.168.1.32:8080 , works fine ...but when i try 'new task' i have : unexpected application error! 404 not found . The second error is when i try from prompt : 'error creating task from prompt : request failed with status error 400' . ??? thx
docker-compose(dot)yml.txt After rebuilding with 'docker-compose up -build' , i launch the navigation panel on 192.168.1.32:8080 , works fine ...but when i try 'new task' i have : unexpected application error! 404 not found . The second error is when i try from prompt : 'error creating task from prompt : request failed with status error 400' . ??? thx
Same. Bare 404's. Nothing works! If running without docker, you get a whole different set of errors with the "secondary LLM" or w.e
Same issue. Even when I re-map. I get: "Error creating workflow run from prompt Request failed with status code 401"
Here is my docker-compose:
services:
postgres:
image: postgres:14-alpine
restart: always
# comment out if you want to externally connect DB
# ports:
# - 5432:5432
volumes:
- ./postgres-data:/var/lib/postgresql/data
environment:
- PGDATA=/var/lib/postgresql/data/pgdata
- POSTGRES_USER=skyvern
- POSTGRES_PASSWORD=skyvern
- POSTGRES_DB=skyvern
healthcheck:
test: ["CMD-SHELL", "pg_isready -U skyvern"]
interval: 5s
timeout: 5s
retries: 5
skyvern:
image: public.ecr.aws/skyvern/skyvern:latest
restart: on-failure
# comment out if you want to externally call skyvern API
ports:
- 8011:8000
volumes:
- ./artifacts:/data/artifacts
- ./videos:/data/videos
- ./har:/data/har
- ./log:/data/log
- ./.streamlit:/app/.streamlit
# Uncomment the following two lines if you want to connect to any local changes
# - ./skyvern:/app/skyvern
# - ./alembic:/app/alembic
environment:
- DATABASE_STRING=postgresql+psycopg://skyvern:skyvern@postgres:5432/skyvern
- BROWSER_TYPE=chromium-headful
- ENABLE_OPENAI=true
- LLM_KEY=OPENAI_GPT4O
- OPENAI_API_KEY=XXXXXXXX
# If you want to use other LLM provider, like azure and anthropic:
# - ENABLE_ANTHROPIC=true
# - LLM_KEY=ANTHROPIC_CLAUDE3.5_SONNET
# - ANTHROPIC_API_KEY=<your_anthropic_key>
# Microsoft Azure OpenAI support:
# If you'd like to use Microsoft Azure OpenAI as your managed LLM service integration with Skyvern, use the environment variables below.
# In your Microsoft Azure subscription, you will need to provision the OpenAI service and deploy a model, in order to utilize it.
# 1. Login to the Azure Portal
# 2. Create an Azure Resource Group
# 3. Create an OpenAI resource in the Resource Group (choose a region and pricing tier)
# 4. From the OpenAI resource's Overview page, open the "Azure AI Foundry" portal (click the "Explore Azure AI Foundry Portal" button)
# 5. In Azure AI Foundry, click "Shared Resources" --> "Deployments"
# 6. Click "Deploy Model" --> "Deploy Base Model" --> select a model (specify this model "Deployment Name" value for the AZURE_DEPLOYMENT variable below)
# - ENABLE_AZURE=true
# - LLM_KEY=AZURE_OPENAI # Leave this value static, don't change it
# - AZURE_DEPLOYMENT=<your_azure_deployment> # Use the OpenAI model "Deployment Name" that you deployed, using the steps above
# - AZURE_API_KEY=<your_azure_api_key> # Copy and paste Key1 or Key2 from the OpenAI resource in Azure Portal
# - AZURE_API_BASE=<your_azure_api_base> # Copy and paste the "Endpoint" from the OpenAI resource in Azure Portal (eg. https://xyzxyzxyz.openai.azure.com/)
# - AZURE_API_VERSION=<your_azure_api_version> # Specify a valid Azure OpenAI data-plane API version (eg. 2024-08-01-preview) Docs: https://learn.microsoft.com/en-us/azure/ai-services/openai/reference
# Amazon Bedrock Support:
# Amazon Bedrock is a managed service that enables you to invoke LLMs and bill them through your AWS account.
# To use Amazon Bedrock as the LLM provider for Skyvern, specify the following environment variables.
# 1. In the AWS IAM console, create a new AWS IAM User (name it whatever you want)
# 2. Assign the "AmazonBedrockFullAccess" policy to the user
# 3. Generate an IAM Access Key under the IAM User's Security Credentials tab
# 4. In the Amazon Bedrock console, go to "Model Access"
# 5. Click Modify Model Access button
# 6. Enable "Claude 3.5 Sonnet v2" and save changes
# - ENABLE_BEDROCK=true
# - LLM_KEY=BEDROCK_ANTHROPIC_CLAUDE3.5_SONNET # This is the Claude 3.5 Sonnet "V2" model. Change to BEDROCK_ANTHROPIC_CLAUDE3.5_SONNET_V1 for the non-v2 version.
# - AWS_REGION=us-west-2 # Replace this with a different AWS region, if you desire
# - AWS_ACCESS_KEY_ID=FILL_ME_IN_PLEASE
# - AWS_SECRET_ACCESS_KEY=FILL_ME_IN_PLEASE
depends_on:
postgres:
condition: service_healthy
healthcheck:
test: ["CMD", "test", "-f", "/app/.streamlit/secrets.toml"]
interval: 5s
timeout: 5s
retries: 5
skyvern-ui:
image: public.ecr.aws/skyvern/skyvern-ui:latest
restart: on-failure
ports:
- 8081:8080
- 9090:9090
volumes:
- ./artifacts:/data/artifacts
- ./videos:/data/videos
- ./har:/data/har
- ./.streamlit:/app/.streamlit
environment:
# if you want to run skyvern on a remote server,
# you need to change the host in VITE_WSS_BASE_URL and VITE_API_BASE_URL to match your server ip
# If you're self-hosting this behind a dns, you'll want to set:
# A route for the API: api.yourdomain.com -> localhost:8000
# A route for the UI: yourdomain.com -> localhost:8080
# A route for the artifact API: artifact.yourdomain.com -> localhost:9090 (maybe not needed)
- VITE_WSS_BASE_URL=ws://localhost:8011/api/v1
# - VITE_ARTIFACT_API_BASE_URL=http://localhost:9090
# - VITE_API_BASE_URL=http://localhost:8000/api/v1
# - VITE_SKYVERN_API_KEY=<get this from "settings" in the Skyvern UI>
depends_on:
skyvern:
condition: service_healthy
