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(llmobs): correctly cast bedrock token/temperature parameters #8790

Merged
merged 3 commits into from
Mar 27, 2024

Conversation

Yun-Kim
Copy link
Contributor

@Yun-Kim Yun-Kim commented Mar 26, 2024

This PR fixes the AWS bedrock integration to default tag an empty string if an input parameter is not provided (preivously we defaulted to "None"), as that led to casting errors on the LLMObs integration side when we try to cast the span tag value to an int/float.

Now, we default tag to an empty string, which avoids the casting errors we had previously, and only add the max_tokens parameter to the LLMObs span event if it is a non-null value.

Checklist

  • Change(s) are motivated and described in the PR description
  • Testing strategy is described if automated tests are not included in the PR
  • Risks are described (performance impact, potential for breakage, maintainability)
  • Change is maintainable (easy to change, telemetry, documentation)
  • Library release note guidelines are followed or label changelog/no-changelog is set
  • Documentation is included (in-code, generated user docs, public corp docs)
  • Backport labels are set (if applicable)
  • If this PR changes the public interface, I've notified @DataDog/apm-tees.
  • If change touches code that signs or publishes builds or packages, or handles credentials of any kind, I've requested a review from @DataDog/security-design-and-guidance.

Reviewer Checklist

  • Title is accurate
  • All changes are related to the pull request's stated goal
  • Description motivates each change
  • Avoids breaking API changes
  • Testing strategy adequately addresses listed risks
  • Change is maintainable (easy to change, telemetry, documentation)
  • Release note makes sense to a user of the library
  • 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

@Yun-Kim Yun-Kim added changelog/no-changelog A changelog entry is not required for this PR. MLObs ML Observability (LLMObs) labels Mar 26, 2024
@Yun-Kim Yun-Kim requested a review from a team as a code owner March 26, 2024 23:47
@datadog-dd-trace-py-rkomorn
Copy link

datadog-dd-trace-py-rkomorn bot commented Mar 27, 2024

Datadog Report

Branch report: yunkim/llmobs-fix-bedrock-token
Commit report: 6a2dbbd
Test service: dd-trace-py

✅ 0 Failed, 288 Passed, 647 Skipped, 7m 1.87s Total duration (32m 56.59s time saved)

@pr-commenter
Copy link

pr-commenter bot commented Mar 27, 2024

Benchmarks

Benchmark execution time: 2024-03-27 16:38:09

Comparing candidate commit 6a2dbbd in PR branch yunkim/llmobs-fix-bedrock-token with baseline commit fedf88e in branch main.

Found 5 performance improvements and 2 performance regressions! Performance is the same for 194 metrics, 9 unstable metrics.

scenario:httppropagationextract-large_header_no_matches

  • 🟩 max_rss_usage [-783.828KB; -702.611KB] or [-3.581%; -3.210%]

scenario:httppropagationextract-medium_header_no_matches

  • 🟩 max_rss_usage [-731.438KB; -655.058KB] or [-3.346%; -2.996%]

scenario:httppropagationextract-none_propagation_style

  • 🟩 max_rss_usage [-1044.377KB; -781.211KB] or [-4.770%; -3.568%]

scenario:httppropagationextract-wsgi_invalid_trace_id_header

  • 🟥 max_rss_usage [+661.108KB; +740.133KB] or [+3.129%; +3.503%]

scenario:httppropagationextract-wsgi_large_header_no_matches

  • 🟩 max_rss_usage [-780.119KB; -706.729KB] or [-3.563%; -3.228%]

scenario:httppropagationextract-wsgi_medium_header_no_matches

  • 🟩 max_rss_usage [-792.186KB; -708.588KB] or [-3.617%; -3.236%]

scenario:sethttpmeta-all-enabled

  • 🟥 max_rss_usage [+445.669KB; +711.861KB] or [+2.069%; +3.305%]

@Yun-Kim Yun-Kim changed the title fix(llmobs): correctly cast token/temperature parameters fix(llmobs): correctly cast token/temperature parameters for bedrock Mar 27, 2024
@Yun-Kim Yun-Kim changed the title fix(llmobs): correctly cast token/temperature parameters for bedrock fix(llmobs): correctly cast bedrock token/temperature parameters Mar 27, 2024
Copy link
Contributor

@lievan lievan left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I also see in line 234

n = int(span.get_tag("bedrock.request.n"))

Might want to change to

n = int(span.get_tag("bedrock.request.n") or 0)

@Yun-Kim Yun-Kim enabled auto-merge (squash) March 27, 2024 15:46
@Yun-Kim Yun-Kim merged commit 141b09b into main Mar 27, 2024
68 of 69 checks passed
@Yun-Kim Yun-Kim deleted the yunkim/llmobs-fix-bedrock-token branch March 27, 2024 17:31
christophe-papazian pushed a commit that referenced this pull request Mar 29, 2024
This PR fixes the AWS bedrock integration to default tag an empty string
if an input parameter is not provided (preivously we defaulted to
`"None"`), as that led to casting errors on the LLMObs integration side
when we try to cast the span tag value to an int/float.

Now, we default tag to an empty string, which avoids the casting errors
we had previously, and only add the `max_tokens` parameter to the LLMObs
span event if it is a non-null value.

## Checklist

- [x] Change(s) are motivated and described in the PR description
- [x] Testing strategy is described if automated tests are not included
in the PR
- [x] Risks are described (performance impact, potential for breakage,
maintainability)
- [x] Change is maintainable (easy to change, telemetry, documentation)
- [X] [Library release note
guidelines](https://ddtrace.readthedocs.io/en/stable/releasenotes.html)
are followed or label `changelog/no-changelog` is set
- [x] Documentation is included (in-code, generated user docs, [public
corp docs](https://github.com/DataDog/documentation/))
- [X] Backport labels are set (if
[applicable](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting))
- [x] If this PR changes the public interface, I've notified
`@DataDog/apm-tees`.
- [x] If change touches code that signs or publishes builds or packages,
or handles credentials of any kind, I've requested a review from
`@DataDog/security-design-and-guidance`.

## Reviewer Checklist

- [x] Title is accurate
- [x] All changes are related to the pull request's stated goal
- [x] Description motivates each change
- [x] Avoids breaking
[API](https://ddtrace.readthedocs.io/en/stable/versioning.html#interfaces)
changes
- [x] Testing strategy adequately addresses listed risks
- [x] Change is maintainable (easy to change, telemetry, documentation)
- [x] Release note makes sense to a user of the library
- [x] Author has acknowledged and discussed the performance implications
of this PR as reported in the benchmarks PR comment
- [x] 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)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
changelog/no-changelog A changelog entry is not required for this PR. MLObs ML Observability (LLMObs)
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants