feature: AI generated evaluations #407
Open
+456
−136
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
geclos
force-pushed
the
feature/automatically_generate_suggestions
branch
from
a4a69f7
to
3394d11
Compare
Helps people get started with evaluations!
geclos
force-pushed
the
feature/automatically_generate_suggestions
branch
from
3394d11
to
367501a
Compare
geclos
commented
Oct 11, 2024
| return ( | ||
| <DocumentContext.Provider value={document}> | ||
| <DocumentContext.Provider value={document || fallbackDocument}> | ||
| {children} | ||
| </DocumentContext.Provider> | ||
| ) |
There was a problem hiding this comment.
this makes this hook work properly with frontend state, finally
| input.type === 'number' | ||
| ? EvaluationResultableType.Number | ||
| : EvaluationResultableType.Boolean, | ||
| detail: input.type === 'number' ? input.metadata : undefined, |
There was a problem hiding this comment.
All this could be validated inside zod so this checks are not needed. refine is what you're looking for
There was a problem hiding this comment.
const allowedTypesSchema = z.enum([
EvaluationResultableType.Number,
EvaluationResultableType.Boolean,
]);
const inputSchema = z
.object({
name: z.string(),
prompt: z.string(),
type: allowedTypesSchema, // Using the restricted enum values
metadata: z
.object({
range: z.object({
from: z.number(),
to: z.number(),
}),
})
.optional(),
})
.refine((data) => {
// If type is 'Number', metadata must be present
if (data.type === EvaluationResultableType.Number && !data.metadata) {
return false;
}
return true;
}, {
message: "Metadata is required when type is 'Number'",
path: ['metadata'],
})There was a problem hiding this comment.
Also instead of metadata call it configDetail
|
|
||
| const suggestedEvaluations = res.object[0] as SuggestedEvaluation[] | ||
| const suggestedEvaluation = res.object | ||
| console.log('suggested eval: ', suggestedEvaluation) |
| const { execute: generateEvaluation, isPending: isGenerating } = | ||
| useLatitudeAction(generateSuggestedEvaluationsAction, { | ||
| onSuccess: () => { | ||
| // do nothing |
| ) | ||
| } | ||
|
|
||
| export default TypewriterText |
There was a problem hiding this comment.
This is an atom. Please keep having things organized
| description: string | ||
| eval_name: string | ||
| eval_type: 'number' | 'boolean' | ||
| eval_prompt: string |
| const evaluation = result[0]! | ||
|
|
||
| // If projectId and documentUuid are provided, connect the evaluation | ||
| if (projectId && documentUuid) { |
| NEXT_PUBLIC_POSTHOG_KEY: '', | ||
| NEXT_PUBLIC_POSTHOG_HOST: '', | ||
| DATASET_GENERATOR_WORKSPACE_APIKEY: | ||
| 'e2c21df6-4e2d-4703-9b65-5f4dee0add23', // fake |
There was a problem hiding this comment.
:ecce_homo: I really hate all this not working by default dev setup
There was a problem hiding this comment.
Also we should unifiy under 1 unique project Copilot all prompts used for suggestions and copilots to simplify the setup and the amount of env vars
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.
Helps people get started with evaluations!