Add docs for writing custom evaluators #14
Merged
Conversation
This file contains hidden or 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
schnecle
force-pushed
the
schnecle-custom-evaluator-docs
branch
from
2020b3f to
20ae1ea
Compare
pavelgj
reviewed
May 2, 2024
tagboola
reviewed
May 2, 2024
| async (datapoint: BaseDataPoint) => { | ||
| const score = await deliciousnessScore(judge, datapoint, judgeConfig); | ||
| return { | ||
| testCaseId: datapoint.testCaseId, |
Contributor
There was a problem hiding this comment.
Thought: Can we avoid requiring the plugin writer to have to write this boilerplate testCaseId: datapoint.testCaseId?
Contributor
Author
There was a problem hiding this comment.
I don't know if we can at the moment because it's the way that we map all the additional metadata from the input dataset into the final scored result.
ssbushi
reviewed
May 2, 2024
ssbushi
reviewed
May 2, 2024
|
|
||
| Now, define the function that will take an example which includes `output` as is required by the prompt and score the result. Genkit test cases include `input` and `output` as required fields, with optional fields for `context`. It is the responsibility of the evaluator to validate that all fields required for evaluation are present. | ||
|
|
||
| This example leverages `handlebars` to hydrate the prompt and `zod` to format and validate the response. |
Contributor
There was a problem hiding this comment.
We should probably update the evaluators to use dotprompt instead.
ssbushi
reviewed
May 2, 2024
kevinthecheung
approved these changes
May 2, 2024
ssbushi
approved these changes
May 3, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
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Outdated suggestions cannot be applied.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.
No description provided.