Facing error while using a Video as an input to gemini android sdk

Gemini API
1

Getting error:

com.google.ai.client.generativeai.type.ServerException: An internal error has occurred. Please retry or report in https://developers.generativeai.google/guide/troubleshooting
                                                                                                    	at com.google.ai.client.generativeai.type.GoogleGenerativeAIException$Companion.from(Exceptions.kt:43)
                                                                                                    	at com.google.ai.client.generativeai.GenerativeModel.generateContent(GenerativeModel.kt:115)
                                                                                                    	at com.google.ai.client.generativeai.GenerativeModel$generateContent$1.invokeSuspend(Unknown Source:15)
                                                                                                    	at kotlin.coroutines.jvm.internal.BaseContinuationImpl.resumeWith(ContinuationImpl.kt:33)
                                                                                                    	at kotlinx.coroutines.DispatchedTask.run(DispatchedTask.kt:108)
                                                                                                    	at kotlinx.coroutines.internal.LimitedDispatcher$Worker.run(LimitedDispatcher.kt:115)
                                                                                                    	at kotlinx.coroutines.scheduling.TaskImpl.run(Tasks.kt:103)
                                                                                                    	at kotlinx.coroutines.scheduling.CoroutineScheduler.runSafely(CoroutineScheduler.kt:584)
                                                                                                    	at kotlinx.coroutines.scheduling.CoroutineScheduler$Worker.executeTask(CoroutineScheduler.kt:793)
                                                                                                    	at kotlinx.coroutines.scheduling.CoroutineScheduler$Worker.runWorker(CoroutineScheduler.kt:697)
                                                                                                    	at kotlinx.coroutines.scheduling.CoroutineScheduler$Worker.run(CoroutineScheduler.kt:684)
                                                                                                    	Suppressed: kotlinx.coroutines.internal.DiagnosticCoroutineContextException: [StandaloneCoroutine{Cancelling}@3e71807, Dispatchers.IO]

Here is my configuration:

    private val config by lazy {
        generationConfig {
            temperature = 0.7f
        }
    }
    private val generativeModel by lazy {
        GenerativeModel(
            modelName = "gemini-1.5-pro-latest",
            apiKey = "",
            generationConfig = config
        )
    }

val input = content {
            blob(
                mimeType,
                file.readBytes())
            text(message)
        }
        val resp =generativeModel.generateContent(input)

mimeType is video/mp4
video link: drive

2

I have the same issue
image

3

Welcome to the forums!

For videos, you need to use the File API to upload the video first for processing before you can generate content based on that video.

1 Like
4

Allen is spot on. It would be helpful if someone in Google would address this issue (also reported here Video content supplied *inline* causes server fault)