Not able to use AWS AI service comprehend

Cloud AWS
#1

image
image1895×926 124 KB

Hi,

Need assistant as im not able to AWS AI service comprehend, which says user is not authorized to perform action.

Thanks

#2

It’s because SCP (Service Control Policy) is implemented to block Comprehend:DetectDominantLanguage in your environment and it’s applicable to your username. Please talk to platform engineering team, they might help you!

#3

Looks like @devops-vin is right, without that access right, AWS Comprehend no comprende nada, as it were. I’'ve written this up for engineering to fix.

#4

Just an FYI,

It is happening for all AWS AI services, Comprehend, Transcribe, Textract, Translate, Rekognition.

image
image1897×377 84.6 KB

#5

Noted. I’ve added Transcribe to the same issue.

#6

Kindly add Textract, Translate, Rekognition these too.

#7

Hi KodeKloud Team,
Hope you had a good week! Just checking in on this issue.
Since I have to practice AWS AI services.
Thank You

#8

Hi Karmitesh
Could you please check again?
And let me know, have enabled it from our side

#9

Hi
Thank You. Kodekloud Team.

#10

@rob_kodekloud / @TanishkaMarrott, relatedly, I am not able to use models permitted under Services on AWS AI Playground | KodeKloud

I am getting this error in my localhost terminal:

return new AuthenticationError(status, error, message, headers);
             ^


AuthenticationError: 401 User: arn:aws:iam::822233328238:user/kk_labs_user_504951 is not authorized to perform: bedrock-mantle:CreateInference on resource: arn:aws:bedrock-mantle:us-east-1:822233328238:project/default because no identity-based policy allows the bedrock-mantle:CreateInference action
    at Function.generate (/Users/t25/Downloads/genai/node_modules/openai/src/core/error.ts:76:14)
    at OpenAI.makeStatusError (/Users/t25/Downloads/genai/node_modules/openai/src/client.ts:494:28)
    at OpenAI.makeRequest (/Users/t25/Downloads/genai/node_modules/openai/src/client.ts:745:24)
    at process.processTicksAndRejections (node:internal/process/task_queues:105:5)
    at async <anonymous> (/Users/taran/Downloads/genai/src/index.ts:11:18) {
  status: 401,
  headers: Headers {},
  requestID: 'req_lskvufom64ftqfqvz7zef37mieeqgdxnuls3w77jtqm4k7xfitva',
  error: {
    code: 'access_denied',
    message: 'User: arn:aws:iam::822233328238:user/kk_labs_user_504951 is not authorized to perform: bedrock-mantle:CreateInference on resource: arn:aws:bedrock-mantle:us-east-1:822233328238:project/default because no identity-based policy allows the bedrock-mantle:CreateInference action',
    param: null,
    type: 'permission_denied_error'
  },
  code: 'access_denied',
  param: null,
  type: 'permission_denied_error'
}
#11

What were you doing when you got this error message? It’s not clear what was not permitted or blocked in this case.

#12

This was my index.ts file content:

I was just trying to see how llm responds

import dotenv from 'dotenv';
import OpenAI from 'openai';

dotenv.config();
const client = new OpenAI({
    apiKey: process.env.OPENAI_API_KEY,
    baseURL: process.env.OPENAI_BASE_URL,
});
const response = await client.chat.completions.create({
    model: 'meta.llama3-2-3b-instruct-v1:0',
    messages: [
        {
            role: 'user',
            content:
                'In a single sentence, why should someone choose KodeKloud over other platforms to learn DevOps?',
        },
    ],
});
console.log(response.choices[0]?.message.content);

image
image1920×2221 187 KB

AWS AI Playground | KodeKloud mentions:

  • Models Permitted in Bedrock:
    ‍
    1. ‍[Llama 3.2 1B Instruct]
    2. ‍[Llama 3.2 3B Instruct]
    3. [Titan Embeddings G1 - Text]
#13

First of all, this thread was concerning AWS Comprehend, and you’re having problems with Bedrock – this should have been its own post, to prevent confusing folks with a question on a new topic. :angry: PLEASE DO NOT DO THIS.

I’ll need to ask engineering what exactly they’re blocking here, since I’m seeing a similar error now that I get what you’re asking here :frowning:

#14

Comprehend and Bedrock were part of the same AWS AI playground

image
image999×1155 107 KB

Got it, I’ll keep that in mind moving forward. As a new user who joined KodeKloud community a few hours ago, I’m still getting a feel for the community guidelines, though the ‘angry’ emoji was a bit of a surprising welcome.
Thanks for looking into the engineering side for me.

#15

Sorry about the emoji – keeping topics separate saves time both for support people and for people looking for relevant topics, and while it’s the same playground, it’s a pretty different thing to debug. So avoiding posts that mix very different stuff is a very good thing :slight_smile:

Once I knew what you were talking about, I needed to come up with an example for the engineers. Which wasn’t too bad, again, once I had a clue what your problem was.

#16

No worries at all Rob, I’ll be more mindful moving forward :slight_smile:
Thanks for taking a look, I really appreciate it!
Please let me know when the engineering team responds.