feat(gemini): trace google gemini Integration #10503
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
|
![datadog-datadog-prod-us1[bot]](https://avatars.githubusercontent.com/u/365230?s=60&v=4){kind=small}
BenchmarksBenchmark execution time: 2024-09-11 20:02:53 Comparing candidate commit eecda47 in PR branch Found 0 performance improvements and 0 performance regressions! Performance is the same for 353 metrics, 47 unstable metrics. |
Datadog ReportBranch report: ✅ 0 Failed, 9717 Passed, 355 Skipped, 2h 9m 47.19s Total duration (1m 35.08s time saved) |
erikayasuda
approved these changes
Sep 10, 2024
lievan
reviewed
Sep 10, 2024
sabrenner
reviewed
Sep 11, 2024
lievan
approved these changes
Sep 11, 2024
github-actions bot
pushed a commit
that referenced
this pull request
Sep 11, 2024
Adds support for tracing Google's Gemini Python SDK `generate_content` and `generate_content_async` methods (also indirectly traces `send_message()`). This PR also moves `_get_attr()` convenience helper from the anthropic integration to the shared `ddtrace.llmobs._utils.py` module. ### Features: - Traces `generate_content/generate_content_async()` and indirectly `send_message/send_message_async()` which uses `generate_content` under the hood - Handles streamed responses - Captures input/outputs (truncation included, function call/response messages included), token usage, input configuration options, and model name. ### Testing: The Gemini Python SDK does not use requests/httpx to submit requests but instead via GRPC. The vcrpy testing framework does not capture this so I wrote a mock client to store/return mock responses instead of sending actual requests to Google. This testing framework was inspired by the [Gemini Python SDK's testing strategy](https://github.com/google-gemini/generative-ai-python/blob/9407dcde5666ba58831227d3acf8bd0e3f3b4f81/tests/test_generative_models.py#L41). ### Next steps (future PRs) - Wrap `send_message()` not to trace, but to attach a hash/session_id for all subsequent send_message calls - Integrate with LLMObs ## 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 c0fd013)
2 tasks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adds support for tracing Google's Gemini Python SDK
generate_contentandgenerate_content_asyncmethods (also indirectly tracessend_message()).This PR also moves
_get_attr()convenience helper from the anthropic integration to the sharedddtrace.llmobs._utils.pymodule.Features:
generate_content/generate_content_async()and indirectlysend_message/send_message_async()which usesgenerate_contentunder the hoodTesting:
The Gemini Python SDK does not use requests/httpx to submit requests but instead via GRPC. The vcrpy testing framework does not capture this so I wrote a mock client to store/return mock responses instead of sending actual requests to Google. This testing framework was inspired by the Gemini Python SDK's testing strategy.
Next steps (future PRs)
send_message()not to trace, but to attach a hash/session_id for all subsequent send_message callsChecklist
Reviewer Checklist