[NL-to-ESQL] refactor and improve the task's workflow #192850
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
|
Great to see you dumb this down for the mere mortals @pgayvallet !!! |
|
/ci |
|
/ci |
pgayvallet
added
release_note:skip
|
/ci |
|
Pinging @elastic/appex-ai-infra (Team:AI Infra) |
botelastic
bot
added
ci:project-deploy-observability
pgayvallet
changed the title
dgieselaar
approved these changes
Sep 17, 2024
|
@elasticmachine merge upstream |
💛 Build succeeded, but was flaky
Failed CI StepsTest FailuresMetrics [docs]Public APIs missing exports
History
To update your PR or re-run it, just comment with: |
kibanamachine
pushed a commit
to kibanamachine/kibana
that referenced
this pull request
Sep 17, 2024
## Summary Some cleanup and minor enhancements, just to get my hands on that part of the code. evaluation framework was run against gemini1.5, claude-sonnet and GPT-4, with a few improvements ### Cleanup - Refactor the code to improve readability and maintainability ### Improvements - Add support for keyword aliases (turns out, some models asks for `STATS...BY` and not `STATS`) - Add (naive for now) support for suggestion (to try to influence the model on using some function instead of others, e.g group by time with BUCKET instead of DATE_TRUNC) - Generate "this command does not exist" documentation when the model request a missing command (help making it understand it shouldn't use the command, e.g gpt-4 was hallucinating a `REVERSE` command) --------- Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com> (cherry picked from commit 0fc191a)
💔 Some backports could not be created
Note: Successful backport PRs will be merged automatically after passing CI. Manual backportTo create the backport manually run: Questions ?Please refer to the Backport tool documentation |
kibanamachine
added a commit
that referenced
this pull request
Sep 17, 2024
…2850) (#193207) # Backport This will backport the following commits from `main` to `8.x`: - [[NL-to-ESQL] refactor and improve the task's workflow (#192850)](#192850) <!--- Backport version: 9.4.3 --> ### Questions ? Please refer to the [Backport tool documentation](https://github.com/sqren/backport) <!--BACKPORT [{"author":{"name":"Pierre Gayvallet","email":"pierre.gayvallet@elastic.co"},"sourceCommit":{"committedDate":"2024-09-17T16:54:36Z","message":"[NL-to-ESQL] refactor and improve the task's workflow (#192850)\n\n## Summary\r\n\r\nSome cleanup and minor enhancements, just to get my hands on that part\r\nof the code.\r\n\r\nevaluation framework was run against gemini1.5, claude-sonnet and GPT-4,\r\nwith a few improvements\r\n\r\n### Cleanup\r\n\r\n- Refactor the code to improve readability and maintainability\r\n\r\n### Improvements\r\n\r\n- Add support for keyword aliases (turns out, some models asks for\r\n`STATS...BY` and not `STATS`)\r\n- Add (naive for now) support for suggestion (to try to influence the\r\nmodel on using some function instead of others, e.g group by time with\r\nBUCKET instead of DATE_TRUNC)\r\n- Generate \"this command does not exist\" documentation when the model\r\nrequest a missing command (help making it understand it shouldn't use\r\nthe command, e.g gpt-4 was hallucinating a `REVERSE` command)\r\n\r\n---------\r\n\r\nCo-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com>","sha":"0fc191aa320db4b7949f1c2d47a273a5362029c8","branchLabelMapping":{"^v9.0.0$":"main","^v8.16.0$":"8.x","^v(\\d+).(\\d+).\\d+$":"$1.$2"}},"sourcePullRequest":{"labels":["release_note:skip","v9.0.0","backport:prev-major","Team:Obs AI Assistant","ci:project-deploy-observability","v8.16.0","Team:AI Infra"],"title":"[NL-to-ESQL] refactor and improve the task's workflow","number":192850,"url":"https://github.com/elastic/kibana/pull/192850","mergeCommit":{"message":"[NL-to-ESQL] refactor and improve the task's workflow (#192850)\n\n## Summary\r\n\r\nSome cleanup and minor enhancements, just to get my hands on that part\r\nof the code.\r\n\r\nevaluation framework was run against gemini1.5, claude-sonnet and GPT-4,\r\nwith a few improvements\r\n\r\n### Cleanup\r\n\r\n- Refactor the code to improve readability and maintainability\r\n\r\n### Improvements\r\n\r\n- Add support for keyword aliases (turns out, some models asks for\r\n`STATS...BY` and not `STATS`)\r\n- Add (naive for now) support for suggestion (to try to influence the\r\nmodel on using some function instead of others, e.g group by time with\r\nBUCKET instead of DATE_TRUNC)\r\n- Generate \"this command does not exist\" documentation when the model\r\nrequest a missing command (help making it understand it shouldn't use\r\nthe command, e.g gpt-4 was hallucinating a `REVERSE` command)\r\n\r\n---------\r\n\r\nCo-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com>","sha":"0fc191aa320db4b7949f1c2d47a273a5362029c8"}},"sourceBranch":"main","suggestedTargetBranches":["8.x"],"targetPullRequestStates":[{"branch":"main","label":"v9.0.0","branchLabelMappingKey":"^v9.0.0$","isSourceBranch":true,"state":"MERGED","url":"https://github.com/elastic/kibana/pull/192850","number":192850,"mergeCommit":{"message":"[NL-to-ESQL] refactor and improve the task's workflow (#192850)\n\n## Summary\r\n\r\nSome cleanup and minor enhancements, just to get my hands on that part\r\nof the code.\r\n\r\nevaluation framework was run against gemini1.5, claude-sonnet and GPT-4,\r\nwith a few improvements\r\n\r\n### Cleanup\r\n\r\n- Refactor the code to improve readability and maintainability\r\n\r\n### Improvements\r\n\r\n- Add support for keyword aliases (turns out, some models asks for\r\n`STATS...BY` and not `STATS`)\r\n- Add (naive for now) support for suggestion (to try to influence the\r\nmodel on using some function instead of others, e.g group by time with\r\nBUCKET instead of DATE_TRUNC)\r\n- Generate \"this command does not exist\" documentation when the model\r\nrequest a missing command (help making it understand it shouldn't use\r\nthe command, e.g gpt-4 was hallucinating a `REVERSE` command)\r\n\r\n---------\r\n\r\nCo-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com>","sha":"0fc191aa320db4b7949f1c2d47a273a5362029c8"}},{"branch":"8.x","label":"v8.16.0","branchLabelMappingKey":"^v8.16.0$","isSourceBranch":false,"state":"NOT_CREATED"}]}] BACKPORT--> Co-authored-by: Pierre Gayvallet <pierre.gayvallet@elastic.co>
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
Some cleanup and minor enhancements, just to get my hands on that part of the code.
evaluation framework was run against gemini1.5, claude-sonnet and GPT-4, with a few improvements
Cleanup
Improvements
STATS...BYand notSTATS)REVERSEcommand)