Skip to main content

Comprehend code with AI

io.moderne.prethink.ComprehendCode

Use an LLM to generate descriptions for classes and methods in the codebase. Descriptions are cached based on source code checksums to avoid regenerating descriptions for unchanged code.

Recipe source​

GitHub: ComprehendCode.java, Issue Tracker, Maven Central

This recipe is available under the Moderne Source Available License.

Options​

TypeNameDescriptionExample
StringproviderOptional. LLM provider: openai, gemini, or poolside.poolside
StringapiKeyOptional. API key for the LLM provider.sk-...
StringmodelOptional. Model name to use.malibu
StringbaseUrlOptional. Custom base URL for the LLM provider (for self-hosted instances).https://divers.poolsi.de/openai/v1/
IntegerrequestsPerMinuteOptional. Rate limit for LLM requests.60

Used by​

This recipe is used as part of the following composite recipes:

Usage​

This recipe has no required configuration options. It can be activated by adding a dependency on org.openrewrite.recipe:rewrite-prethink in your build file or by running a shell command (in which case no build changes are needed):

  1. Add the following to your build.gradle file:
build.gradle
plugins {
    id("org.openrewrite.rewrite") version("latest.release")
}

rewrite {
    activeRecipe("io.moderne.prethink.ComprehendCode")
    setExportDatatables(true)
}

repositories {
    mavenCentral()
}

dependencies {
    rewrite("org.openrewrite.recipe:rewrite-prethink:0.2.2")
}
  1. Run gradle rewriteRun to run the recipe.

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​

Method descriptions​

io.moderne.prethink.table.MethodDescriptions

AI-generated descriptions of methods in the codebase with inference time and token usage metrics.

Column NameDescription
Source pathThe path to the source file containing the method.
Class nameThe fully qualified name of the class containing the method.
SignatureThe method signature including parameter types.
ChecksumSHA-256 checksum of the method source code for cache validation.
DescriptionAI-generated description of what the method does.
Return value descriptionAI-generated description of what the method returns.
Technique 1First programming technique or pattern used in the method.
Technique 2Second programming technique or pattern used in the method.
Technique 3Third programming technique or pattern used in the method.
Inference time (ms)Time taken for the LLM to generate the description, in milliseconds.
Input tokensNumber of tokens in the input prompt sent to the LLM.
Output tokensNumber of tokens in the response generated by the LLM.