[BUG]: Could not respond to message. #3000

New issue

Closed

opened 2026-02-28 06:26:41 -05:00 by deekerman · 1 comment

deekerman commented

2026-02-28 06:26:41 -05:00

Owner

Originally created by @foundanand on GitHub (Nov 26, 2025).

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

AWSBedrock::streamGetChatCompletion failed during setup. Invocation of model ID meta.llama4-maverick-17b-instruct-v1:0 with on-demand throughput isn’t supported. Retry your request with the ID or ARN of an inference profile that contains this model.

I keep getting this issue, I have tried many thing, including following:

https://docs.anythingllm.com/setup/llm-configuration/cloud/aws-bedrock

Are there known steps to reproduce?

No response

Originally created by @foundanand on GitHub (Nov 26, 2025). ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? <img width="834" height="115" alt="Image" src="https://github.com/user-attachments/assets/72db596b-150e-4de1-950f-21bdd337e080" /> AWSBedrock::streamGetChatCompletion failed during setup. Invocation of model ID meta.llama4-maverick-17b-instruct-v1:0 with on-demand throughput isn’t supported. Retry your request with the ID or ARN of an inference profile that contains this model. I keep getting this issue, I have tried many thing, including following: https://docs.anythingllm.com/setup/llm-configuration/cloud/aws-bedrock ### Are there known steps to reproduce? _No response_

deekerman

2026-02-28 06:26:41 -05:00

closed this issue
added the
possible bug
label

deekerman commented

2026-02-28 06:26:45 -05:00

Author

Owner

@timothycarambat commented on GitHub (Nov 26, 2025):

The error message says all there is to know about this error. It is not related to AnythingLLM. You cannot use the llama4 maverick model for serverless/on-demand via bedrock. Thats it

@timothycarambat commented on GitHub (Nov 26, 2025): The error message says all there is to know about this error. It is not related to AnythingLLM. You cannot use the llama4 maverick model for serverless/on-demand via bedrock. Thats it

deekerman referenced this issue

2026-02-28 06:33:16 -05:00

[FEAT]: remote mcp server support for docker AnythingLLM #3198

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

starred/anything-llm#3000

No description provided.

Rows
Columns