[Security Assistant] Add support for manually entering eval datasets #194072
+17
−1
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
spong
added
release_note:skip
...es/kbn-elastic-assistant/impl/assistant/settings/evaluation_settings/evaluation_settings.tsx
Outdated
Show resolved
Hide resolved
andrew-goldstein
approved these changes
Sep 26, 2024
💛 Build succeeded, but was flaky
Failed CI StepsMetrics [docs]Async chunks
History
To update your PR or re-run it, just comment with: cc @spong |
kibanamachine
pushed a commit
to kibanamachine/kibana
that referenced
this pull request
Sep 26, 2024
…lastic#194072) ## Summary On cloud environments we don't send the LangSmith credentials through the `GET /evaluate` route which returns available datasets for selection, so the datasets are never populated. Since the Dataset field didn't allow custom options, this means you couldn't perform evals in cloud environments. This PR updates the Dataset field to take custom options so that you can manually enter the dataset name in cloud environments: <p align="center"> <img width="500" src="https://github.com/user-attachments/assets/4828e085-180c-42bb-9656-34bda57b74b5" /> </p> To test, enable the below feature flag to show the evaluation tab under settings: ``` xpack.securitySolution.enableExperimental: - "assistantModelEvaluation" ``` (cherry picked from commit 1c0ec85)
💚 All backports created successfully
Note: Successful backport PRs will be merged automatically after passing CI. Questions ?Please refer to the Backport tool documentation |
kibanamachine
added a commit
that referenced
this pull request
Sep 26, 2024
…asets (#194072) (#194207) # Backport This will backport the following commits from `main` to `8.x`: - [[Security Assistant] Add support for manually entering eval datasets (#194072)](#194072) <!--- Backport version: 9.4.3 --> ### Questions ? Please refer to the [Backport tool documentation](https://github.com/sqren/backport) <!--BACKPORT [{"author":{"name":"Garrett Spong","email":"[email protected]"},"sourceCommit":{"committedDate":"2024-09-26T18:17:50Z","message":"[Security Assistant] Add support for manually entering eval datasets (#194072)\n\n## Summary\r\n\r\nOn cloud environments we don't send the LangSmith credentials through\r\nthe `GET /evaluate` route which returns available datasets for\r\nselection, so the datasets are never populated. Since the Dataset field\r\ndidn't allow custom options, this means you couldn't perform evals in\r\ncloud environments.\r\n\r\nThis PR updates the Dataset field to take custom options so that you can\r\nmanually enter the dataset name in cloud environments:\r\n\r\n<p align=\"center\">\r\n<img width=\"500\"\r\nsrc=\"https://github.com/user-attachments/assets/4828e085-180c-42bb-9656-34bda57b74b5\"\r\n/>\r\n</p> \r\n\r\n\r\nTo test, enable the below feature flag to show the evaluation tab under\r\nsettings:\r\n\r\n```\r\nxpack.securitySolution.enableExperimental:\r\n - \"assistantModelEvaluation\"\r\n```","sha":"1c0ec85b740789ba99c30f09a5b56bc66a9de897","branchLabelMapping":{"^v9.0.0$":"main","^v8.16.0$":"8.x","^v(\\d+).(\\d+).\\d+$":"$1.$2"}},"sourcePullRequest":{"labels":["release_note:skip","v9.0.0","Feature:Security Assistant","Team:Security Generative AI","Feature:Assistant Evaluation","v8.16.0","backport:version"],"title":"[Security Assistant] Add support for manually entering eval datasets","number":194072,"url":"https://github.com/elastic/kibana/pull/194072","mergeCommit":{"message":"[Security Assistant] Add support for manually entering eval datasets (#194072)\n\n## Summary\r\n\r\nOn cloud environments we don't send the LangSmith credentials through\r\nthe `GET /evaluate` route which returns available datasets for\r\nselection, so the datasets are never populated. Since the Dataset field\r\ndidn't allow custom options, this means you couldn't perform evals in\r\ncloud environments.\r\n\r\nThis PR updates the Dataset field to take custom options so that you can\r\nmanually enter the dataset name in cloud environments:\r\n\r\n<p align=\"center\">\r\n<img width=\"500\"\r\nsrc=\"https://github.com/user-attachments/assets/4828e085-180c-42bb-9656-34bda57b74b5\"\r\n/>\r\n</p> \r\n\r\n\r\nTo test, enable the below feature flag to show the evaluation tab under\r\nsettings:\r\n\r\n```\r\nxpack.securitySolution.enableExperimental:\r\n - \"assistantModelEvaluation\"\r\n```","sha":"1c0ec85b740789ba99c30f09a5b56bc66a9de897"}},"sourceBranch":"main","suggestedTargetBranches":["8.x"],"targetPullRequestStates":[{"branch":"main","label":"v9.0.0","branchLabelMappingKey":"^v9.0.0$","isSourceBranch":true,"state":"MERGED","url":"https://github.com/elastic/kibana/pull/194072","number":194072,"mergeCommit":{"message":"[Security Assistant] Add support for manually entering eval datasets (#194072)\n\n## Summary\r\n\r\nOn cloud environments we don't send the LangSmith credentials through\r\nthe `GET /evaluate` route which returns available datasets for\r\nselection, so the datasets are never populated. Since the Dataset field\r\ndidn't allow custom options, this means you couldn't perform evals in\r\ncloud environments.\r\n\r\nThis PR updates the Dataset field to take custom options so that you can\r\nmanually enter the dataset name in cloud environments:\r\n\r\n<p align=\"center\">\r\n<img width=\"500\"\r\nsrc=\"https://github.com/user-attachments/assets/4828e085-180c-42bb-9656-34bda57b74b5\"\r\n/>\r\n</p> \r\n\r\n\r\nTo test, enable the below feature flag to show the evaluation tab under\r\nsettings:\r\n\r\n```\r\nxpack.securitySolution.enableExperimental:\r\n - \"assistantModelEvaluation\"\r\n```","sha":"1c0ec85b740789ba99c30f09a5b56bc66a9de897"}},{"branch":"8.x","label":"v8.16.0","branchLabelMappingKey":"^v8.16.0$","isSourceBranch":false,"state":"NOT_CREATED"}]}] BACKPORT--> Co-authored-by: Garrett Spong <[email protected]>
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.
Summary
On cloud environments we don't send the LangSmith credentials through the
GET /evaluateroute which returns available datasets for selection, so the datasets are never populated. Since the Dataset field didn't allow custom options, this means you couldn't perform evals in cloud environments.This PR updates the Dataset field to take custom options so that you can manually enter the dataset name in cloud environments:
To test, enable the below feature flag to show the evaluation tab under settings: