Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix(botocore): bedrock cross-region inference model name does not throw [backport 2.13] #10965

Open
wants to merge 2 commits into
base: 2.13
Choose a base branch
from

Conversation

github-actions[bot]
Copy link
Contributor

@github-actions github-actions bot commented Oct 7, 2024

Backport 80a3ee8 from #10949 to 2.13.

What does this PR do?

Fixes #10772

Model IDs with cross-region inference would throw because we assumed modelID would only have the provider and model_name, when it could have the region as well. This would result in:

File /python3.11/site-packages/ddtrace/contrib/internal/botocore/services/bedrock.py:321, in patched_bedrock_api_call(original_func, instance, args, kwargs, function_vars)
    319 params = function_vars.get("params")
    320 pin = function_vars.get("pin")
--> 321 model_provider, model_name = params.get("modelId").split(".")
    322 integration = function_vars.get("integration")
    323 submit_to_llmobs = integration.llmobs_enabled and "embed" not in model_name

ValueError: too many values to unpack (expected 2)

We are not tagging that cross-region inference in this PR, just resolving the error.

Testing

To test this change, a singular anthropic_message test case and corresponding cassette was modified. This had an unfortunate side effect of affecting an LLMObs test as well. I can add a different test instead, but I believe that would require an additional 60+ line cassette which isn't totally needed, so I opted for this instead.

Checklist

  • PR author has checked that all the criteria below are met
  • The PR description includes an overview of the change
  • The PR description articulates the motivation for the change
  • The change includes tests OR the PR description describes a testing strategy
  • The PR description notes risks associated with the change, if any
  • Newly-added code is easy to change
  • The change follows the library release note guidelines
  • The change includes or references documentation updates if necessary
  • Backport labels are set (if applicable)

Reviewer Checklist

  • Reviewer has checked that all the criteria below are met
  • Title is accurate
  • All changes are related to the pull request's stated goal
  • Avoids breaking API changes
  • Testing strategy adequately addresses listed risks
  • Newly-added code is easy to change
  • Release note makes sense to a user of the library
  • If necessary, author has acknowledged and discussed the performance implications of this PR as reported in the benchmarks PR comment
  • Backport labels are set in a manner that is consistent with the release branch maintenance policy

…ow (#10949)

## What does this PR do?
Fixes #10772

Model IDs with cross-region inference would throw because we assumed
`modelID` would only have the `provider` and `model_name`, when it could
have the region as well. This would result in:

```
File /python3.11/site-packages/ddtrace/contrib/internal/botocore/services/bedrock.py:321, in patched_bedrock_api_call(original_func, instance, args, kwargs, function_vars)
    319 params = function_vars.get("params")
    320 pin = function_vars.get("pin")
--> 321 model_provider, model_name = params.get("modelId").split(".")
    322 integration = function_vars.get("integration")
    323 submit_to_llmobs = integration.llmobs_enabled and "embed" not in model_name

ValueError: too many values to unpack (expected 2)
```

We are not tagging that cross-region inference in this PR, just
resolving the error.

### Testing
To test this change, a singular `anthropic_message` test case and
corresponding cassette was modified. This had an unfortunate side effect
of affecting an LLMObs test as well. I can add a different test instead,
but I believe that would require an additional 60+ line cassette which
isn't totally needed, so I opted for this instead.

## Checklist
- [x] PR author has checked that all the criteria below are met
- The PR description includes an overview of the change
- The PR description articulates the motivation for the change
- The change includes tests OR the PR description describes a testing
strategy
- The PR description notes risks associated with the change, if any
- Newly-added code is easy to change
- The change follows the [library release note
guidelines](https://ddtrace.readthedocs.io/en/stable/releasenotes.html)
- The change includes or references documentation updates if necessary
- Backport labels are set (if
[applicable](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting))

## Reviewer Checklist
- [x] Reviewer has checked that all the criteria below are met
- Title is accurate
- All changes are related to the pull request's stated goal
- Avoids breaking
[API](https://ddtrace.readthedocs.io/en/stable/versioning.html#interfaces)
changes
- Testing strategy adequately addresses listed risks
- Newly-added code is easy to change
- Release note makes sense to a user of the library
- If necessary, author has acknowledged and discussed the performance
implications of this PR as reported in the benchmarks PR comment
- Backport labels are set in a manner that is consistent with the
[release branch maintenance
policy](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting)

(cherry picked from commit 80a3ee8)
@github-actions github-actions bot requested review from a team as code owners October 7, 2024 15:21
@datadog-dd-trace-py-rkomorn
Copy link

datadog-dd-trace-py-rkomorn bot commented Oct 7, 2024

Datadog Report

Branch report: backport-10949-to-2.13
Commit report: 016f127
Test service: dd-trace-py

✅ 0 Failed, 3975 Passed, 5205 Skipped, 53m 53.95s Total duration (1h 11m 41.15s time saved)

@pr-commenter
Copy link

pr-commenter bot commented Oct 7, 2024

Benchmarks

Benchmark execution time: 2024-10-10 15:39:32

Comparing candidate commit 016f127 in PR branch backport-10949-to-2.13 with baseline commit a54549e in branch 2.13.

Found 0 performance improvements and 0 performance regressions! Performance is the same for 353 metrics, 47 unstable metrics.

@sabrenner sabrenner enabled auto-merge (squash) October 10, 2024 14:58
Copy link
Contributor Author

CODEOWNERS have been resolved as:

releasenotes/notes/botocore-bedrock-cross-region-inference-model-fix-179b7f1ddd6e8e02.yaml  @DataDog/apm-python
ddtrace/contrib/internal/botocore/services/bedrock.py                   @DataDog/ml-observability
tests/contrib/botocore/bedrock_cassettes/anthropic_message_invoke.yaml  @DataDog/ml-observability
tests/contrib/botocore/test_bedrock.py                                  @DataDog/ml-observability
tests/contrib/botocore/test_bedrock_llmobs.py                           @DataDog/ml-observability

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant