'folder_id - UUID input should be a string, bytes or UUID object' when starting in backend mode with LANGFLOW_LOAD_FLOWS_PATH

[amomra]

Bug Description

I'm trying to start a pod in Kubernetes running the langflowai/langflow-backend:v1.1.1 image (also tested with langflowai/langflow:v1.1.1 image) with a flow that was exported from another langflow instance. I adjusted the LANGFLOW_LOAD_FLOWS_PATH to a path where I mounted a config map with the flow file. The pod starts but it keeps restarting because of the following error:

Traceback (most recent call last):
  File "/app/.venv/lib/python3.12/site-packages/starlette/routing.py", line 693, in lifespan
    async with self.lifespan_context(app) as maybe_state:
               ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/fastapi/routing.py", line 133, in merged_lifespan
    async with original_context(app) as maybe_original_state:
               ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/fastapi/routing.py", line 133, in merged_lifespan
    async with original_context(app) as maybe_original_state:
               ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/fastapi/routing.py", line 133, in merged_lifespan
    async with original_context(app) as maybe_original_state:
               ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/langflow/main.py", line 108, in lifespan
    await load_flows_from_directory()
  File "/app/.venv/lib/python3.12/site-packages/langflow/initial_setup/setup.py", line 587, in load_flows_from_directory
    flow = Flow.model_validate(flow, from_attributes=True)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/sqlmodel/main.py", line 760, in model_validate
    return sqlmodel_validate(
           ^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/sqlmodel/_compat.py", line 313, in sqlmodel_validate
    cls.__pydantic_validator__.validate_python(
pydantic_core._pydantic_core.ValidationError: 1 validation error for Flow
folder_id
  UUID input should be a string, bytes or UUID object [type=uuid_type, input_value=<coroutine object get_def...er_id at 0x7f02e0d0e4d0>, input_type=coroutine]
    For further information visit https://errors.pydantic.dev/2.7/v/uuid_type

The flow file was attached in this issue. This is the Kubernetes deployment file:

apiVersion: apps/v1
kind: Deployment
metadata:
  name: langflow-teste-backend
  namespace: langflow
spec:
  selector:
    matchLabels:
      app: langflow-teste-backend
  replicas: 1
  template:
    metadata:
      labels:
        app: langflow-teste-backend
    spec:
      containers:
      - name: langflow-teste-backend
        image: langflowai/langflow-backend:v1.1.1
        command:
        - /bin/bash
        args:
        - -c
        - langflow run --backend-only --host 0.0.0.0 --port 7860
        ports:
        - containerPort: 7860
          name: web
        resources: {}
        env:
        - name: COLUMNS
          value: "200"
        - name: LANGFLOW_VARIABLES_TO_GET_FROM_ENVIRONMENT
          value: AZURE_OPENAI_API_DEPLOYMENT_NAME,AZURE_OPENAI_API_EMBEDDINGS_DEPLOYMENT_NAME,AZURE_OPENAI_API_KEY,AZURE_OPENAI_API_VERSION,AZURE_OPENAI_API_ENDPOINT
        - name: LANGFLOW_LOAD_FLOWS_PATH
          value: /app/flows
        envFrom:
        - secretRef:
            name: openai-config
        volumeMounts:
        - name: teste-flows
          mountPath: /app/flows
        - name: data-volume
          mountPath: /app/data/
      volumes:
      - name: teste-flows
        configMap:
          name: teste-flows
      - name: data-volume
        emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
  name: langflow-teste-backend-service
  namespace: langflow
spec:
  selector:
    app: langflow-teste-backend
  ports:
  - port: 80
    targetPort: 7860

Reproduction

Steps to reproduce:

1. Create namespace langflow in the Kubernetes
2. Create the configmap as shown in the flow file section of this issue
3. Deploy the backend using the YAML in the bug description
4. Check the pod logs

Expected behavior

Backend started with the flow running.

Who can help?

No response

Operating System

Kubernetes

Langflow Version

1.1.1

Python Version

None

Screenshot

No response

Flow File

flow.json

To create the config map:

kubectl create configmap teste-flows -n langflow --from-file=flow.json

[dosubot[bot]]

The error you're encountering, "UUID input should be a string, bytes or UUID object," suggests that the folder_id field in your flow file is not being correctly interpreted as a UUID. This issue typically arises when the folder_id is not properly formatted or is being processed incorrectly.

Here are a few steps you can take to resolve this issue:

1. Check the Flow File: Ensure that the folder_id in your flow file is a valid UUID string. It should be a properly formatted UUID, like 123e4567-e89b-12d3-a456-426614174000.

2. Flow File Structure: Verify that the flow file's structure is correct and that all fields are properly defined. The folder_id should be a string representing a UUID.

3. Default Folder Handling: If the folder_id is not specified or is None, Langflow should automatically assign it to a default folder. Ensure that this logic is correctly implemented in your setup. You might want to check if the default folder exists and is correctly configured in your database.

4. Environment Configuration: Double-check your Kubernetes configuration to ensure that the flow file is correctly mounted and accessible at the path specified by LANGFLOW_LOAD_FLOWS_PATH.

5. Debugging: Add logging or print statements in the code where the flow is loaded and validated to see the exact value of folder_id being processed. This can help identify if the value is being altered or not set correctly.

By ensuring that the folder_id is a valid UUID and that your environment is correctly configured, you should be able to resolve this error. If the issue persists, consider reviewing the flow file and the logic that handles the folder_id assignment in the Langflow codebase.

To continue talking to Dosu, mention @dosu.

[tssantos]

This is happening to me as well

[roman-shakudo]

Is it going to be fixed by? https://github.com/langflow-ai/langflow/pull/4891

[elolivier]

Hi @amomra / @tssantos did you manage to solve it? I'm facing this issue too. The issue mentioned by @roman-shakudo is merged but no new version is been released yet and we are not sure if this will solve it.

[HaloWorld]

This issue occurs because get_default_folder_id was not properly awaited. Since get_default_folder_id is an async def function, its invocation within the load_flows_from_directory function lacks the await keyword. As a result, folder_id becomes a coroutine object, which ultimately disrupts Pydantic’s validation process.

A temporary workaround is as follows:

async def load_flows_from_directory() -> None:
    ...

    async with async_session_scope() as session:

        ...

        for f in files:

            ...

            if existing:
                
                ...

                if existing.folder_id is None:
                    folder_id = await get_default_folder_id(session, user_id)
                    
                ...

            else:

                ...

                folder_id = await get_default_folder_id(session, user_id)

                ...

[HaloWorld]

I believe this issue has already been resolved in #4893.

[roman-shakudo]

@elolivier @HaloWorld Thanks for heads up. I did not test the fixes. I wait for a new version to be release. Till then I use LangFlow Runtime 1.1.0 and LangFlow Ide 1.1.1

[dosubot[bot]]

Hi, @amomra. I'm Dosu, and I'm helping the langflow team manage their backlog. I'm marking this issue as stale.

Issue Summary:

• The issue involves a Kubernetes pod restarting due to an invalid folder_id UUID with the langflowai/langflow-backend:v1.1.1 image.
• A missing await in the get_default_folder_id function was identified as the root cause.
• A workaround was provided, and the issue was resolved in pull request #4893.
• A new version release is awaited to confirm the fix by other users experiencing the same issue.

Next Steps:

• Please confirm if this issue is still relevant with the latest version of the langflow repository. If so, you can keep the discussion open by commenting here.
• If there is no further activity, this issue will be automatically closed in 7 days.

Thank you for your understanding and contribution!

[amomra]

I've tested and the issue was solved. Thanks!

[dosubot[bot]]

Thank you for closing the issue, amomra! We appreciate your contribution to Langflow!