Skip to main content

Get recommendations

io.moderne.ai.research.GetRecommendations

This recipe calls an AI model to get recommendations for modernizing the code base by looking at a sample of method declarations.

Recipe source

This recipe is only available to users of Moderne.

This recipe is available under the Moderne Proprietary License.

Options

TypeNameDescriptionExample
BooleanrandomSamplingDo random sampling or use clusters based on embeddings to sample.
intnumberOfCentersOptional. Number of diverse centers to sample if you don't do random sampling per repository.3

Usage

This recipe has required configuration parameters and can only be run by users of Moderne. To run this recipe, you will need to provide the Moderne CLI run command with the required options. Or, if you'd like to create a declarative recipe, please see the below example of a rewrite.yml file:

rewrite.yml
---
type: specs.openrewrite.org/v1beta/recipe
name: com.yourorg.GetRecommendationsExample
displayName: Get recommendations example
recipeList:
- io.moderne.ai.research.GetRecommendations:
randomSampling: null
numberOfCenters: 3

You will need to have configured the Moderne CLI on your machine before you can run the following command.

shell
mod run . --recipe GetRecommendations --recipe-option "randomSampling=null" --recipe-option "numberOfCenters=3"

If the recipe is not available locally, then you can install it using:

mod config recipes jar install org.openrewrite.recipe:rewrite-ai-search:0.27.0

See how this recipe works across multiple open-source repositories

Run this recipe on OSS repos at scale with the Moderne SaaS.

The community edition of the Moderne platform enables you to easily run recipes across thousands of open-source repositories.

Please contact Moderne for more information about safely running the recipes on your own codebase in a private SaaS.

Data Tables

Recommendations

io.moderne.ai.table.Recommendations

Collects the recommendations based on sampled methods.

Column NameDescription
NameName of the class or method
LantencyLatency in seconds to get recommendations
Token sizeEstimated token size for input and output
RecommendationThe recommendations based on the method