Add Support for Annotating Embedding and Retrieval Documents - #12149
Add Support for Annotating Embedding and Retrieval Documents#12149sabrenner wants to merge 3 commits into
Conversation
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b4184fb6d5
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
This comment has been minimized.
This comment has been minimized.
🟡 Java Benchmark SLOs — Performance SLO warning (near threshold)
PR vs. master results
Commit: Load and DaCapo benchmarks can be triggered manually in the GitLab pipeline. Results will appear in the Benchmarking Platform UI after completion. |
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 2c241d4eb5
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
|
@codex review |
|
Codex Review: Didn't find any major issues. Swish! Reviewed commit: ℹ️ About Codex in GitHubCodex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback". |
There was a problem hiding this comment.
More details
The embedding and retrieval document paths preserve legacy string behavior while emitting the new document shape, including optional name, id, and score fields. Focused domain and mapper tests passed across legacy, metadata-rich, partial, empty, and invalid-value scenarios; no diff-attributable behavioral regression was found.
📊 Validated against 8 scenarios · Open Bits AI session
🤖 Datadog Autotest · Commit 27cb607 · What is Autotest? · @DataDog review to ask questions · Any feedback? Reach out in #autotest
ygree
left a comment
There was a problem hiding this comment.
AnnotateIO taking two arguments does not seem to be a flexible API design. Since we need to add more combinations of different types, we might want to consider splitting it into two separate methods, at least for new methods. WDYT?
What Does This Do
Adds proper support for annotating embedding and retrieval documents for LLM Observability spans by adding two new
annotateEmbeddingIO(List<LLMObs.Document>, String)andannotateRetrievalIO(String, List<LLMObs.Document>)functions for embedding and retrieval spans respectively.Motivation
In-parity support with Node.js and Python. Additionally, unblocks proper span processing support in #12112
Additional Notes
Contributor Checklist
type:and (comp:orinst:) labels in addition to any other useful labelsclose,fix, or any linking keywords when referencing an issueUse
solvesinstead, and assign the PR milestone to the issueJira ticket: MLOB-7937