-
Notifications
You must be signed in to change notification settings - Fork 813
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
expectation error #1807
Comments
Based on the error codetype, it sounds like your embedding model is not the problem, but rather the context row in the new_ragas_dataset that makes up the textual data is not a List[str], so you should check the data type first. When you check the data once, if you load new_ragas_dataset['context'], |
thanks for helping out @hundredeuk2 🙂 ❤️ @amin-kh96 like Heondeuk suggest this is likely do to an inconsistency with how you have formatted the data, do check it out. |
@dosubot in my dataset, the context should be a list of lists like this. |
I found similar threads that might help you resolve the issue. In one closed issue, users encountered a similar # Assuming new_ragas_dataset is your dataset
new_ragas_dataset['contexts'] = [item for sublist in new_ragas_dataset['contexts'] for item in sublist] This transformation ensures that each entry in the "contexts" field is a single list of strings, which should resolve the error you're encountering [1]. To continue talking to Dosu, mention @dosu. Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other |
@dosu |
The error you're encountering is due to the fact that the # Assuming new_ragas_dataset is your dataset
def flatten_contexts(example):
example['contexts'] = [item for sublist in example['contexts'] for item in sublist]
return example
new_ragas_dataset = new_ragas_dataset.map(flatten_contexts) This approach uses the To continue talking to Dosu, mention @dosu. Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other |
@dosu |
The "Failed to parse output" message indicates that the Ragas framework is encountering issues when trying to parse the output generated by the language model. This could be due to the output not conforming to the expected format or schema. Here are some steps you can take to troubleshoot and resolve this issue:
By following these steps, you should be able to identify and address the cause of the output parsing errors. To continue talking to Dosu, mention @dosu. Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other |
i see this |
To resolve the "Failed to parse output. Returning None." error in the Ragas framework, you should handle the
By following these steps, you should be able to identify and address the cause of the output parsing errors. To continue talking to Dosu, mention @dosu. Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other |
I am working with ragas and I Have my own embeddings and textual data. i see this error what should I do?
The text was updated successfully, but these errors were encountered: