Issue Station
Sign In
Tools hereToolbox

litellm - 💡(How to fix) Fix [Bug]: bedrock reranker using litellm proxy [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
BerriAI/litellm#25417•Fetched 2026-04-10 03:41:15
View on GitHub
Comments
0
Participants
1
Timeline
4
Reactions
0
Author
mmg10mmg10
Participants
mmg10mmg10
Timeline (top)
labeled ×3renamed ×1

Error Message

I am trying to use bedrock reranker. But it gives an error. 3. read the error from the CLI :-)

Code Example

model_list: 
  - model_name: bedrock-rerank
    litellm_params:
        model: bedrock/arn:aws:bedrock:us-east-1::foundation-model/amazon.rerank-v1:0
        #api_key: "os.environ/AWS_BEARER_TOKEN_BEDROCK"
        #model: bedrock/amazon.rerank-v1:0
        aws_region_name: "us-east-1"
        aws_access_key_id: "123"
        aws_secret_access_key: "123"
        
litellm_settings:
    drop_params: true

---

please see the screenshot
RAW_BUFFERClick to expand / collapse

Check for existing issues

  • I have searched the existing issues and checked that my issue is not a duplicate.

What happened?

I am trying to use bedrock reranker. But it gives an error.

Here is my proxy config (for use with docker images

model_list: 
  - model_name: bedrock-rerank
    litellm_params:
        model: bedrock/arn:aws:bedrock:us-east-1::foundation-model/amazon.rerank-v1:0
        #api_key: "os.environ/AWS_BEARER_TOKEN_BEDROCK"
        #model: bedrock/amazon.rerank-v1:0
        aws_region_name: "us-east-1"
        aws_access_key_id: "123"
        aws_secret_access_key: "123"
        
litellm_settings:
    drop_params: true

Note i also use text and emebd models - not shown in the config but they work fine. The text/embed model wven work with the bedrock api key but that fails with the rernker model. even the sccess key methid (shown above fails). Also note that litllm is running on port 4001.

<img width="1835" height="352" alt="Image" src="https://github.com/user-attachments/assets/c2529a1b-8906-45be-8350-ee9738dce181" />

Steps to Reproduce

  1. add reranker to config file
  2. make curl request as shown in the docs
  3. read the error from the CLI :-)

Relevant log output

please see the screenshot

What part of LiteLLM is this about?

Proxy

What LiteLLM version are you on ?

v1.82.3

Twitter / LinkedIn details

No response

extent analysis

TL;DR

  • Verify the AWS credentials and region configuration for the bedrock-rerank model to ensure they match the requirements for accessing the Amazon Rerank API.

Guidance

  • Check that the aws_access_key_id and aws_secret_access_key are correctly set and valid for the specified aws_region_name.
  • Ensure the model parameter in litellm_params is correctly formatted and points to the right model version.
  • Test the AWS credentials with a different model or a direct API call to isolate the issue.
  • Review the screenshot of the error message for any specific details about the authentication or configuration failure.

Example

  • No code example is provided due to the lack of specific details about the error message or the exact configuration issue.

Notes

  • The issue might be related to the specific configuration of the bedrock-rerank model or the AWS credentials, which are not fully detailed in the provided information.
  • The fact that other models work with the same API key or access key method suggests the issue is specific to the reranker model configuration.

Recommendation

  • Apply workaround: Verify and correct the AWS credentials and model configuration to match the requirements for the Amazon Rerank API, as the issue seems to be related to authentication or configuration rather than a version problem.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#model save/load#optimization#mixed precision#training loop

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING