Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Structured Output doesn't Open Output Schema Table #5577

Open
matthsena opened this issue Jan 7, 2025 · 4 comments
Open

Structured Output doesn't Open Output Schema Table #5577

matthsena opened this issue Jan 7, 2025 · 4 comments
Labels
bug Something isn't working

Comments

@matthsena
Copy link

Bug Description

When using the "Structured Output" component and clicking on "Output Schema Table", the message "loading" appears and it never stops loading

Reproduction

  1. Adicione o componente Structured Output
  2. Click "Open Table" in the Output Schema field

Expected behavior

Open the table to define the Structured Output fields

Who can help?

@anovazzi1
@ogabrielluiz

Operating System

Ubuntu Linux 24.04

Langflow Version

1.1.1

Python Version

None

Screenshot

image

Flow File

No response

@matthsena matthsena added the bug Something isn't working label Jan 7, 2025
Copy link

dosubot bot commented Jan 7, 2025

Olá @matthsena! Eu sou Dosu, um bot aqui para ajudar a resolver bugs, responder perguntas e ajudar você a se tornar um colaborador. Estou aqui para ajudar enquanto você espera por um mantenedor humano. Vamos resolver esse problema juntos! 🤖

The issue you're experiencing with the "Structured Output" component, where the "Output Schema Table" remains in a loading state, could be related to how the loading state is managed in the Langflow UI. The loading state is controlled by a status variable, which transitions from "loading" to "loaded" after processing the data. If the data isn't correctly parsed or if there's an error, the status might not change, causing the table to remain in a loading state indefinitely [1].

Here are a few things you might want to check or try:

  1. Data Parsing: Ensure that the data being processed is correctly formatted and that there are no errors in parsing. Any issues in data conversion could prevent the status from updating to "loaded".

  2. Error Handling: Check if there are any error messages in the console that might indicate issues with data parsing or other related processes.

  3. Timeout Settings: The default timeout for loading components is 60 seconds. If the process takes longer, it might be worth investigating if there's a delay in data retrieval or processing [2].

  4. Dependencies: Ensure that all necessary dependencies, such as Pydantic and Langflow custom inputs, are correctly installed and configured [3].

If these steps don't resolve the issue, further investigation into the specific implementation details or recent changes in the codebase might be necessary.

To continue talking to Dosu, mention @dosu.


Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other

@matthsena
Copy link
Author

@dosu I have tried all these 4 items but nothing works

Copy link

dosubot bot commented Jan 10, 2025

If the previous steps didn't resolve the issue, consider the following additional points:

  1. Check for Recent Changes: Review any recent commits or changes in the Langflow codebase that might affect the 'Structured Output' component. Sometimes, recent updates can introduce bugs or alter functionality.

  2. Inspect the convertCSVToData Function: Ensure that the convertCSVToData function is correctly returning rowData and colDefs. Any issues in this function could prevent the data from being processed correctly, keeping the status in "loading" [1].

  3. Verify the Separator: The default separator for CSV parsing is a comma. If your data uses a different delimiter, it could cause parsing issues. Make sure the separator is correctly set in the csvNode data [2].

  4. Console Errors: Double-check the browser console for any errors or warnings that might provide more insight into what's going wrong.

  5. Debugging: Add some debugging logs in the code to trace where the process might be failing. This can help identify if the issue is with data fetching, parsing, or rendering.

If none of these steps help, it might be necessary to dive deeper into the code or reach out to the maintainers for more specific guidance.

To continue talking to Dosu, mention @dosu.


Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other

@ogabrielluiz
Copy link
Contributor

Hey @matthsena

Have you tried clicking on the + button?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

2 participants