I am using the sample tutorial from GCP Vertex AI API docs:

const {VertexAI} = require('@google-cloud/vertexai');

/**
 * TODO(developer): Update these variables before running the sample.
 */
async function analyze_pdf(projectId = 'PROJECT_ID') {
  const vertexAI = new VertexAI({project: projectId, location: 'us-central1'});

  const generativeModel = vertexAI.getGenerativeModel({
    model: 'gemini-1.5-flash-001',
  });

  const filePart = {
    file_data: {
      file_uri: 'gs://cloud-samples-data/generative-ai/pdf/2403.05530.pdf',
      mime_type: 'application/pdf',
    },
  };
  const textPart = {
    text: `
    You are a very professional document summarization specialist.
    Please summarize the given document.`,
  };

  const request = {
    contents: [{role: 'user', parts: [filePart, textPart]}],
  };

  const resp = await generativeModel.generateContent(request);
  const contentResponse = await resp.response;
  console.log(JSON.stringify(contentResponse));
}

When calling generativeModel.generateContent({…}) I am getting the error,

"Error: GoogleGenerativeAIError: [VertexAI.GoogleGenerativeAIError]: got status: 500 Internal Server Error. {"error":{"code":500,"message":"Internal error encountered.","status":"INTERNAL"}}"
Is there a way to receive a more descriptive reason for the error from the Client API, or is there a known troubleshoot available?

I am able to upload to successfully Google Cloud Storage before this logic using ADC authentication, so I don’t think authentication is the issue. I also temporarily allowed the storage bucket public access, so I don’t think the issue is permission related(?)

I have tried to remove the filePart from the request, so that the call is:

const request = {
    contents: [{role: 'user', parts: [textPart]}],
  };

This works, so it must have something to do with retrieving the file from Cloud Storage, but I can’t figure out what that might be since I have allowed public access and have checked to make sure I am below the 30mb file limit.