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

google.generativeai.types.generation_types.BlockedPromptException: prompt_feedback { block_reason: OTHER } #305

Open
xxl4 opened this issue Apr 27, 2024 · 3 comments
Labels
component:python sdk Issue/PR related to Python SDK status:awaiting user response Awaiting a response from the author status:stale Issue/PR will be closed automatically if there's no further activity type:bug Something isn't working

Comments

@xxl4
Copy link

xxl4 commented Apr 27, 2024

Description of the bug:

This is our model config and when have a few image don't work fine.

image

response

image

but when i use the same the image and content on google ai platform will give more info.

Thank you.

Actual vs expected behavior:

No response

Any other information you'd like to share?

No response

@xxl4 xxl4 added component:python sdk Issue/PR related to Python SDK type:bug Something isn't working labels Apr 27, 2024
@singhniraj08
Copy link

@xxl4,

There are some filters that can't be turn off, these all go into the "OTHER" finish reason. For example: one of the non-configurable filters is child safety, which is a legal requirement.

These filters are set at Gemini API and can't be configured from SDK. For issues related to Gemini, we would suggest you to use "Send Feedback" option in Gemini docs and provide example prompts which can be sent to owners as an example of False Positive. Ref: Screenshot below. Thank you!

image

@singhniraj08 singhniraj08 added the status:awaiting user response Awaiting a response from the author label Apr 29, 2024
@mm-khalil1
Copy link

mm-khalil1 commented May 2, 2024

I am receiving the same error, but with text generation.
My prompts are basically about asking the model to rate a video transcript according to couple of questions about credibility (aims, sources, dates, etc). Each question along with the transcript is sent as a single prompt.

Anyone was able to avoid this error?


Edit
I saw this in the documentation:

If you see BlockedReason.OTHER, the query or response may violate the terms of service or be otherwise unsupported.

Source:
https://ai.google.dev/gemini-api/docs/troubleshooting#safety-issues

Copy link

Marking this issue as stale since it has been open for 14 days with no activity. This issue will be closed if no further activity occurs.

@github-actions github-actions bot added the status:stale Issue/PR will be closed automatically if there's no further activity label May 18, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
component:python sdk Issue/PR related to Python SDK status:awaiting user response Awaiting a response from the author status:stale Issue/PR will be closed automatically if there's no further activity type:bug Something isn't working
Projects
None yet
Development

No branches or pull requests

3 participants