Spring/spring-ai
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Revert "Add support for Kotlin functions"

Browse Source 
This reverts commit 9cf66333b5.
This commit is contained in:
Mark Pollack
2024-11-06 12:58:52 -05:00
parent 3fbc310ff4
commit f111aaea04
13 changed files with 119 additions and 721 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
spring-ai-docs/src/main/antora/modules/ROOT/pages/api/chat/openai-chat.adoc
View File

@@ -270,11 +270,6 @@ NOTE: Adhere to the OpenAI link:https://platform.openai.com/docs/guides/structur
You can leverage existing xref::api/structured-output-converter.adoc#_bean_output_converter[BeanOutputConverter] utilities to automatically generate the JSON Schema from your domain objects and later convert the structured response into domain-specific instances:
--
[tabs]
======
Java::
+
[source,java]
----
record MathReasoning(
@@ -306,41 +301,8 @@ String content = this.response.getResult().getOutput().getContent();
MathReasoning mathReasoning = this.outputConverter.convert(this.content);
----
Kotlin::
+
[source,kotlin]
----
data class MathReasoning(
@get:JsonProperty(required = true, value = "steps") val steps: Steps,
@get:JsonProperty(required = true, value = "final_answer") val finalAnswer: String) {
data class Steps(@get:JsonProperty(required = true, value = "items") val items: Array<Items>) {
data class Items(
@get:JsonProperty(required = true, value = "explanation") val explanation: String,
@get:JsonProperty(required = true, value = "output") val output: String)
}
}
val outputConverter = BeanOutputConverter(MathReasoning::class.java)
val jsonSchema = outputConverter.jsonSchema;
val prompt = Prompt("how can I solve 8x + 7 = -23",
OpenAiChatOptions.builder()
.withModel(ChatModel.GPT_4_O_MINI)
.withResponseFormat(ResponseFormat(ResponseFormat.Type.JSON_SCHEMA, jsonSchema))
.build())
val response = openAiChatModel.call(prompt)
val content = response.getResult().getOutput().getContent()
val mathReasoning = outputConverter.convert(content)
----
======
--
NOTE: Ensure you use the `@JsonProperty(required = true,...)` annotation (`@get:JsonProperty(required = true,...)` with Kotlin in order to generate the annotation on the related getters, see link:https://kotlinlang.org/docs/annotations.html#annotation-use-site-targets[related documentation]).
NOTE: Ensure you use the `@JsonProperty(required = true,...)` annotation.
This is crucial for generating a schema that accurately marks fields as `required`.
Although this is optional for JSON Schema, OpenAI link:https://platform.openai.com/docs/guides/structured-outputs/all-fields-must-be-required[mandates] it for the structured response to function correctly.

98
spring-ai-docs/src/main/antora/modules/ROOT/pages/api/functions.adoc
View File

@@ -56,13 +56,8 @@ When the model needs to answer a question such as `"What’s the weather like in
Our function calls some SaaS-based weather service API and returns the weather response back to the model to complete the conversation. In this example, we will use a simple implementation named `MockWeatherService` that hard-codes the temperature for various locations.
The following `MockWeatherService` class represents the weather service API:
The following `MockWeatherService.java` represents the weather service API:
--
[tabs]
======
Java::
+
[source,java]
----
public class MockWeatherService implements Function<Request, Response> {
@@ -76,20 +71,6 @@ public class MockWeatherService implements Function<Request, Response> {
}
}
----
Kotlin::
+
[source,kotlin]
----
class MockWeatherService : Function1<Request, Response> {
override fun invoke(request: Request) = Response(30.0, Unit.C)
}
enum class Unit { C, F }
data class Request(val location: String, val unit: Unit) {}
data class Response(val temp: Double, val unit: Unit) {}
----
======
--
=== Registering Functions as Beans
@@ -97,18 +78,13 @@ Spring AI provides multiple ways to register custom functions as beans in the Sp
We start by describing the most POJO-friendly options.
==== Plain Functions
==== Plain Java Functions
In this approach, you define a `@Bean` in your application context as you would any other Spring managed object.
Internally, Spring AI `ChatModel` will create an instance of a `FunctionCallbackWrapper` that adds the logic for it being invoked via the AI model.
The name of the `@Bean` is used function name.
--
[tabs]
======
Java::
+
[source,java]
----
@Configuration
@@ -122,63 +98,24 @@ static class Config {
}
----
Kotlin::
+
[source,kotlin]
----
@Configuration
class Config {
@Bean
@Description("Get the weather in location") // function description
fun currentWeather(): (Request) -> Response = MockWeatherService()
}
----
======
--
The `@Description` annotation is optional and provides a function description that helps the model understand when to call the function. It is an important property to set to help the AI model determine what client side function to invoke.
Another option for providing the description of the function is to use the `@JsonClassDescription` annotation on the `MockWeatherService.Request`:
--
[tabs]
======
Java::
+
[source,java]
----
@Configuration
static class Config {
@Bean
public Function<Request, Response> currentWeather() { // bean name as function name
return new MockWeatherService();
}
}
@JsonClassDescription("Get the weather in location") // function description
@JsonClassDescription("Get the weather in location") // // function description
public record Request(String location, Unit unit) {}
----
Kotlin::
+
[source,kotlin]
----
@Configuration
class Config {
@Bean
fun currentWeather(): (Request) -> Response { // bean name as function name
return MockWeatherService()
}
}
@JsonClassDescription("Get the weather in location") // function description
data class Request(val location: String, val unit: Unit)
----
======
--
It is a best practice to annotate the request object with information such that the generated JSON schema of that function is as descriptive as possible to help the AI model pick the correct function to invoke.
@@ -186,11 +123,6 @@ It is a best practice to annotate the request object with information such that
Another way to register a function is to create a `FunctionCallbackWrapper` like this:
--
[tabs]
======
Java::
+
[source,java]
----
@Configuration
@@ -206,30 +138,6 @@ static class Config {
}
}
----
Kotlin::
+
[source,kotlin]
----
import org.springframework.ai.model.function.withInputType
@Configuration
class Config {
@Bean
fun weatherFunctionInfo(): FunctionCallback {
return FunctionCallbackWrapper.builder(MockWeatherService())
.withName("CurrentWeather") // (1) function name
.withDescription("Get the weather in location") // (2) function description
// (3) Required due to Kotlin SAM conversion beeing an opaque lambda
.withInputType<MockWeatherService.Request>()
.build();
}
}
----
======
--
It wraps the 3rd party `MockWeatherService` function and registers it as a `CurrentWeather` function with the `ChatClient`.
It also provides a description (2) and an optional response converter to convert the response into a text as expected by the model.