Gemini 1.5 pro v1beta chat-api Response was blocked due to OTHER

[zakcali]

Expected Behavior

I setup all 4 safety settings to HarmBlockThreshold.BLOCK_NONE, I'm expecting a valid response

Actual Behavior

I got error:

sendMessage() was unsuccessful. Response was blocked due to OTHER. Inspect response object for details.
response: { promptFeedback: { blockReason: 'OTHER' }, text: [Function (anonymous)], functionCall: [Function (anonymous)], functionCalls: [Function (anonymous)] }

I'm getting same error both in Google AI Studio, and in my nodejs program using api

note, api call thinks that parameter is illegal, even though I see that category is defined in source code:
{ category: HarmCategory.HARM_CATEGORY_UNSPECIFIED, threshold: HarmBlockThreshold.BLOCK_NONE, },

Steps to Reproduce the Problem

1. const safetySettings = [ { category: HarmCategory.HARM_CATEGORY_HARASSMENT, threshold: HarmBlockThreshold.BLOCK_NONE, }, { category: HarmCategory.HARM_CATEGORY_HATE_SPEECH, threshold: HarmBlockThreshold.BLOCK_NONE, }, { category: HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT, threshold: HarmBlockThreshold.BLOCK_NONE, }, { category: HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT, threshold: HarmBlockThreshold.BLOCK_NONE, }, ];
2. const apiVersion = 'v1beta';
3. const generationConfig = { temperature: 0.9,};

4. `const model = genAI.getGenerativeModel({ model: "gemini-1.5-pro-latest" , generationConfig, safetySettings }, {apiVersion});`
   

5. `const result = await chat.sendMessage("translate following to English: Opere meme Ca tanısıyla izlenen hastada sağ meme mastektomizedir. Mastektomi lojunda belirgin kitle lezyonu saptanmadı.");`
   

Specifications

• Version: "@google/generative-ai": "^0.7.1",
• Platform: Windows 10, nodejs v20.12.2 (LTS)

[caliburn420]

Yes, also have this Blocked Reason other. Wonder if that's just Google controlling stuff :/

[singhniraj08]

@zakcali

Thank you reporting this issue. This issues look like more on the API side rather than SDK. For issues related to Gemini API, we would suggest you to use "Send Feedback" option in Gemini docs. Ref: Screenshot below.

[zakcali]

I send a feedback in Gemini docs

[singhniraj08]

@zakcali,
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.

Closing this issue as you have already sent feedback in Gemini Docs. Please reopen this issue with comments or open a new issue if the problem persists. Thank you

[sayhicoelho]

@singhniraj08 The Gemini API is completly useless since we can't use it to detect and block such contents in our applications. I'm trying to detect sexual content and hate speech in my chat application using Gemini API and it is useless even if I configure the safety filters.