Let the model call your code safely
You wrap a host capability with a name, purpose, typed arguments, result, and handler. The model sees when and how to call it while your app keeps control of execution.
Worked example
See the idea in context
Tool search = Ax.fn("search")
.description("Search docs")
.arg("query", Ax.f().string("Search query"))
.handler(args -> List.of("hit for " + args.get("query")))
.build();- Explain when to call it
The name and description orient the model toward product documentation searches.
- Constrain the call
query must be a string and the result is declared as a string.
- Bind trusted code
searchDocs runs in your host environment when the tool is selected.
Run itIn your own project
// Gradle (build.gradle):
implementation 'dev.axllm:ax:24.0.15'
// Maven (pom.xml):
<dependency>
<groupId>dev.axllm</groupId>
<artifactId>ax</artifactId>
<version>24.0.15</version>
</dependency>
import dev.axllm.ax.Ax;
import java.util.Map;
public class QuickStart {
public static void main(String[] args) throws Exception {
var llm = Ax.ai("openai", Map.of("apiKey", System.getenv("OPENAI_API_KEY")));
var classify = Ax.ax("review:string -> sentiment:class \"positive, negative, neutral\"");
var result = classify.forward(llm, Map.of(
"review", "Useful and boring in the best way."
));
System.out.println("sentiment: " + result.get("sentiment"));
}
}Set OPENAI_APIKEY in your environment before running provider-backed code.
From a clone of the ax repo:
npm run example -- java src/examples/java/generation/BasicGenerationExample.javaActive practice
Answer 2 in a row to learn this · attempt 1