Remove FunctionCallback deprecations
- Remove the super type FunctionCallingOptions from ToolCallingChatOptions
- Move toolContext builder methods into ToolCallingChatOptions
- Remove Model chat options' function specific usages
- Replace them with tooling:
FunctionCallback -> ToolCallback
functions -> toolNames
- Remove proxyToolCalls use
- Remove deprecated methods
- Update ChatClient methods
- Replace FunctionCallback -> ToolCallback
- Remove deprecated methods
- Update DefaultChatClient
- functionNames -> toolNames
- functionCallbacks -> toolCallbacks
- Update AdviseRequest
- functionNames -> toolNames
- functionCallbacks -> toolCallbacks
- Remove FunctionCallingOptions and replace it with ToolCallingOptions
- Remove FunctionCallingHelper
- Update DefaultToolCallingChatOptions, ToolCallbackResolvers, ToolCallbackProvider to use Tool calling types
- Update documentation
- Remove VertexAiGeminiChatModelFunctionCallingIT and adjust MistralAiApiToolFunctionCallIT
Resolves #2528
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
This commit is contained in:
Ilayaperumal Gopinathan
committed by
Christian Tzolov
Christian Tzolov
parent
3756e16526
commit
c0bc6231a5
@@ -107,7 +107,7 @@
|
||||
** xref:api/chat/prompt-engineering-patterns.adoc[]
|
||||
* xref:api/testing.adoc[AI Model Evaluation]
|
||||
* xref:api/functions.adoc[Function Calling (Deprecated)]
|
||||
** xref:api/function-callback.adoc[FunctionCallback API (Deprecated)]
|
||||
|
||||
|
||||
* Service Connections
|
||||
** xref:api/docker-compose.adoc[Docker Compose]
|
||||
|
||||
@@ -127,11 +127,10 @@ Another way to register a function is to create a `FunctionCallback` instance li
|
||||
static class Config {
|
||||
|
||||
@Bean
|
||||
public FunctionCallback weatherFunctionInfo() {
|
||||
public FunctionToolCallback weatherFunctionInfo() {
|
||||
|
||||
return FunctionCallback.builder()
|
||||
return FunctionToolCallback.builder("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
.description("Get the weather in location") // (2) function description
|
||||
.function("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
.inputType(MockWeatherService.Request.class) // (3) function signature
|
||||
.build();
|
||||
}
|
||||
@@ -144,7 +143,7 @@ It also provides a description (2) and input type (3) used to generate the JSON
|
||||
|
||||
NOTE: By default, the response converter does a JSON serialization of the Response object.
|
||||
|
||||
NOTE: The `FunctionCallback` internally resolves the function call signature based on the `MockWeatherService.Request` class.
|
||||
NOTE: The `FunctionToolCallback` internally resolves the function call signature based on the `MockWeatherService.Request` class.
|
||||
|
||||
=== Specifying functions in Chat Options
|
||||
|
||||
@@ -157,7 +156,7 @@ AnthropicChatModel chatModel = ...
|
||||
UserMessage userMessage = new UserMessage("What's the weather like in Paris?");
|
||||
|
||||
ChatResponse response = this.chatModel.call(new Prompt(List.of(this.userMessage),
|
||||
AnthropicChatOptions.builder().function("CurrentWeather").build())); // (1) Enable the function
|
||||
AnthropicChatOptions.builder().toolNames("CurrentWeather").build())); // (1) Enable the function
|
||||
|
||||
logger.info("Response: {}", response);
|
||||
----
|
||||
@@ -177,8 +176,7 @@ AnthropicChatModel chatModel = ...
|
||||
UserMessage userMessage = new UserMessage("What's the weather like in Paris?");
|
||||
|
||||
var promptOptions = AnthropicChatOptions.builder()
|
||||
.functionCallbacks(List.of(FunctionCallback.builder()
|
||||
.function("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
.toolCallbacks(List.of(FunctionToolCallback.builder("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
.description("Get the weather in location") // (2) function description
|
||||
.inputType(MockWeatherService.Request.class) // (3) function signature
|
||||
.build())) // function code
|
||||
|
||||
@@ -123,10 +123,9 @@ Another way to register a function is to create a `FunctionCallback` instance li
|
||||
static class Config {
|
||||
|
||||
@Bean
|
||||
public FunctionCallback weatherFunctionInfo() {
|
||||
public FunctionToolCallback weatherFunctionInfo() {
|
||||
|
||||
return FunctionCallback.builder()
|
||||
.function("CurrentWeather", new MockWeatherService()) // (1) function name
|
||||
return FunctionToolCallback.builder("CurrentWeather", new MockWeatherService()) // (1) function name
|
||||
.description("Get the current weather in a given location") // (2) function description
|
||||
.inputType(MockWeatherService.Request.class) // (3) function input type
|
||||
.build();
|
||||
@@ -139,7 +138,7 @@ It wraps the 3rd party `MockWeatherService` function and registers it as a `Curr
|
||||
|
||||
NOTE: The default response converter does a JSON serialization of the Response object.
|
||||
|
||||
NOTE: The `FunctionCallback` internally resolves the function call signature based on the `MockWeatherService.Request` class and internally generates an JSON schema for the function call.
|
||||
NOTE: The `FunctionToolCallback` internally resolves the function call signature based on the `MockWeatherService.Request` class and internally generates an JSON schema for the function call.
|
||||
|
||||
=== Specifying functions in Chat Options
|
||||
|
||||
@@ -152,7 +151,7 @@ AzureOpenAiChatModel chatModel = ...
|
||||
UserMessage userMessage = new UserMessage("What's the weather like in San Francisco, Tokyo, and Paris?");
|
||||
|
||||
ChatResponse response = this.chatModel.call(new Prompt(List.of(this.userMessage),
|
||||
AzureOpenAiChatOptions.builder().function("CurrentWeather").build())); // (1) Enable the function
|
||||
AzureOpenAiChatOptions.builder().tools("CurrentWeather").build())); // (1) Enable the function
|
||||
|
||||
logger.info("Response: {}", response);
|
||||
----
|
||||
@@ -182,8 +181,7 @@ AzureOpenAiChatModel chatModel = ...
|
||||
UserMessage userMessage = new UserMessage("What's the weather like in San Francisco, Tokyo, and Paris? Use Multi-turn function calling.");
|
||||
|
||||
var promptOptions = AzureOpenAiChatOptions.builder()
|
||||
.functionCallbacks(List.of(FunctionCallback.builder()
|
||||
.function("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
.toolCallbacks(List.of(FunctionToolCallback.builder("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
.description("Get the current weather in a given location") // (2) function description
|
||||
.inputType(MockWeatherService.Request.class) // (3) function input type
|
||||
.build()))
|
||||
|
||||
@@ -117,7 +117,7 @@ Mistral AI is almost identical to OpenAI in this regard.
|
||||
|
||||
==== FunctionCallback Wrapper
|
||||
|
||||
Another way to register a function is to create a `FunctionCallback` like this:
|
||||
Another way to register a function is to create a `FunctionToolCallback` like this:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
@@ -125,10 +125,9 @@ Another way to register a function is to create a `FunctionCallback` like this:
|
||||
static class Config {
|
||||
|
||||
@Bean
|
||||
public FunctionCallback weatherFunctionInfo() {
|
||||
public FunctionToolCallback weatherFunctionInfo() {
|
||||
|
||||
return FunctionCallback.builder()
|
||||
.function("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
return FunctionToolCallback.builder("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
.description("Get the weather in location") // (2) function description
|
||||
.inputType(MockWeatherService.Request.class) // (3) function signature
|
||||
.build();
|
||||
@@ -155,7 +154,7 @@ MistralAiChatModel chatModel = ...
|
||||
UserMessage userMessage = new UserMessage("What's the weather like in Paris?");
|
||||
|
||||
ChatResponse response = this.chatModel.call(new Prompt(this.userMessage,
|
||||
MistralAiChatOptions.builder().function("CurrentWeather").build())); // Enable the function
|
||||
MistralAiChatOptions.builder().tools("CurrentWeather").build())); // Enable the function
|
||||
|
||||
logger.info("Response: {}", response);
|
||||
----
|
||||
@@ -175,8 +174,7 @@ MistralAiChatModel chatModel = ...
|
||||
UserMessage userMessage = new UserMessage("What's the weather like in Paris?");
|
||||
|
||||
var promptOptions = MistralAiChatOptions.builder()
|
||||
.functionCallbacks(List.of(FunctionCallback.builder()
|
||||
.function("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
.toolCallbacks(List.of(FunctionToolCallback.builder("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
.description("Get the weather in location") // (2) function description
|
||||
.inputType(MockWeatherService.Request.class) // (3) function signature
|
||||
.build())) // function code
|
||||
|
||||
@@ -127,10 +127,9 @@ Another way to register a function is to create a `FunctionCallback` like this:
|
||||
static class Config {
|
||||
|
||||
@Bean
|
||||
public FunctionCallback weatherFunctionInfo() {
|
||||
public FunctionToolCallback weatherFunctionInfo() {
|
||||
|
||||
return FunctionCallback.builder()
|
||||
.function("CurrentWeather", new MockWeatherService()) // (1) function name
|
||||
return FunctionToolCallback.builder("CurrentWeather", new MockWeatherService()) // (1) function name
|
||||
.description("Get the weather in location") // (2) function description
|
||||
.inputType(MockWeatherService.Request.class) // (3) function signature
|
||||
.build();
|
||||
@@ -144,7 +143,7 @@ It also provides a description (2) and the function signature (3) to let the mod
|
||||
|
||||
NOTE: By default, the response converter performs a JSON serialization of the Response object.
|
||||
|
||||
NOTE: The `FunctionCallback` internally resolves the function call signature based on the `MockWeatherService.Request` class.
|
||||
NOTE: The `FunctionToolCallback` internally resolves the function call signature based on the `MockWeatherService.Request` class.
|
||||
|
||||
=== Specifying functions in Chat Options
|
||||
|
||||
@@ -157,7 +156,7 @@ OllamaChatModel chatModel = ...
|
||||
UserMessage userMessage = new UserMessage("What's the weather like in San Francisco, Tokyo, and Paris?");
|
||||
|
||||
ChatResponse response = this.chatModel.call(new Prompt(this.userMessage,
|
||||
OllamaOptions.builder().function("CurrentWeather").build())); // Enable the function
|
||||
OllamaOptions.builder().tools("CurrentWeather").build())); // Enable the function
|
||||
|
||||
logger.info("Response: {}", response);
|
||||
----
|
||||
@@ -186,8 +185,7 @@ OllamaChatModel chatModel = ...
|
||||
UserMessage userMessage = new UserMessage("What's the weather like in San Francisco, Tokyo, and Paris?");
|
||||
|
||||
var promptOptions = OllamaOptions.builder()
|
||||
.functionCallbacks(List.of(FunctionCallback.builder()
|
||||
.function("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
.toolCallbacks(List.of(FunctionToolCallback.builder("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
.description("Get the weather in location") // (2) function description
|
||||
.inputType(MockWeatherService.Request.class) // (3) function signature
|
||||
.build())) // function code
|
||||
|
||||
@@ -122,10 +122,9 @@ Another way to register a function is to create a `FunctionCallback` like this:
|
||||
static class Config {
|
||||
|
||||
@Bean
|
||||
public FunctionCallback weatherFunctionInfo() {
|
||||
public FunctionToolCallback weatherFunctionInfo() {
|
||||
|
||||
return FunctionCallback.builder()
|
||||
.function("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
return FunctionToolCallback.builder("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
.description("Get the weather in location") // (2) function description
|
||||
.inputType(MockWeatherService.Request.class) // (3) function input type
|
||||
.build();
|
||||
@@ -139,7 +138,7 @@ It also provides a description (2) and an input type (3) used to generate the JS
|
||||
|
||||
NOTE: By default, the response converter performs a JSON serialization of the Response object.
|
||||
|
||||
NOTE: The `FunctionCallback` internally resolves the function call signature based on the `MockWeatherService.Request` class.
|
||||
NOTE: The `FunctionToolCallback` internally resolves the function call signature based on the `MockWeatherService.Request` class.
|
||||
|
||||
=== Specifying functions in Chat Options
|
||||
|
||||
@@ -152,7 +151,7 @@ OpenAiChatModel chatModel = ...
|
||||
UserMessage userMessage = new UserMessage("What's the weather like in San Francisco, Tokyo, and Paris?");
|
||||
|
||||
ChatResponse response = this.chatModel.call(new Prompt(this.userMessage,
|
||||
OpenAiChatOptions.builder().function("CurrentWeather").build())); // Enable the function
|
||||
OpenAiChatOptions.builder().tools("CurrentWeather").build())); // Enable the function
|
||||
|
||||
logger.info("Response: {}", response);
|
||||
----
|
||||
@@ -181,8 +180,7 @@ OpenAiChatModel chatModel = ...
|
||||
UserMessage userMessage = new UserMessage("What's the weather like in San Francisco, Tokyo, and Paris?");
|
||||
|
||||
var promptOptions = OpenAiChatOptions.builder()
|
||||
.functionCallbacks(List.of(FunctionCallback.builder()
|
||||
.function("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
.toolCallbacks(List.of(FunctionToolCallback.builder("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
.description("Get the weather in location") // (2) function description
|
||||
.inputType(MockWeatherService.Request.class) // (3) function input type
|
||||
.build())) // function code
|
||||
@@ -232,8 +230,7 @@ BiFunction<MockWeatherService.Request, ToolContext, MockWeatherService.Response>
|
||||
|
||||
OpenAiChatOptions options = OpenAiChatOptions.builder()
|
||||
.model(OpenAiApi.ChatModel.GPT_4_O.getValue())
|
||||
.functionCallbacks(List.of(FunctionCallback.builder()
|
||||
.function("getCurrentWeather", this.weatherFunction)
|
||||
.toolCallbacks(List.of(FunctionToolCallback.builder("getCurrentWeather", this.weatherFunction)
|
||||
.description("Get the weather in location")
|
||||
.inputType(MockWeatherService.Request.class)
|
||||
.build()))
|
||||
|
||||
@@ -34,7 +34,7 @@ As a developer, you need to implement a function that takes the function call ar
|
||||
Spring AI makes this as easy as defining a `@Bean` definition that returns a `java.util.Function` and supplying the bean name as an option when invoking the `ChatClient` or registering the function dynamically in your prompt request.
|
||||
|
||||
Under the hood, Spring wraps your POJO (the function) with the appropriate adapter code that enables interaction with the AI Model, saving you from writing tedious boilerplate code.
|
||||
The basis of the underlying infrastructure is the link:https://github.com/spring-projects/spring-ai/blob/main/spring-ai-model/src/main/java/org/springframework/ai/model/function/FunctionCallback.java[FunctionCallback.java] interface and the companion Builder utility class to simplify the implementation and registration of Java callback functions.
|
||||
The basis of the underlying infrastructure is the link:https://github.com/spring-projects/spring-ai/blob/main/spring-ai-core/src/main/java/org/springframework/ai/tool/function/FunctionToolCallback.java[FunctionToolCallback.java] interface and the companion Builder utility class to simplify the implementation and registration of Java callback functions.
|
||||
|
||||
== How it works
|
||||
|
||||
@@ -110,7 +110,7 @@ We start by describing the most POJO-friendly options.
|
||||
|
||||
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 `FunctionCallback` that adds the logic for it being invoked via the AI model.
|
||||
Internally, Spring AI `ChatModel` will create an instance of a `FunctionToolCallback` that adds the logic for it being invoked via the AI model.
|
||||
The name of the `@Bean` is used function name.
|
||||
|
||||
--
|
||||
@@ -191,9 +191,9 @@ 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.
|
||||
|
||||
==== FunctionCallback
|
||||
==== FunctionToolCallback
|
||||
|
||||
Another way to register a function is to create a `FunctionCallback` like this:
|
||||
Another way to register a function is to create a `FunctionToolCallback` like this:
|
||||
|
||||
--
|
||||
[tabs]
|
||||
@@ -206,10 +206,9 @@ Java::
|
||||
static class Config {
|
||||
|
||||
@Bean
|
||||
public FunctionCallback weatherFunctionInfo() {
|
||||
public FunctionToolCallback weatherFunctionInfo() {
|
||||
|
||||
return FunctionCallback.builder()
|
||||
.function("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
return FunctionToolCallback.builder("CurrentWeather", new MockWeatherService()) // (1) function name and instance
|
||||
.description("Get the weather in location") // (2) function description
|
||||
.inputType(MockWeatherService.Request.class) // (3) input type to build the JSON schema
|
||||
.build();
|
||||
@@ -226,10 +225,9 @@ import org.springframework.ai.model.function.withInputType
|
||||
class Config {
|
||||
|
||||
@Bean
|
||||
fun weatherFunctionInfo(): FunctionCallback {
|
||||
fun weatherFunctionInfo(): FunctionToolCallback {
|
||||
|
||||
return FunctionCallback.builder()
|
||||
.function("CurrentWeather", MockWeatherService()) // (1) function name and instance
|
||||
return FunctionToolCallback.builder("CurrentWeather", MockWeatherService()) // (1) function name and instance
|
||||
.description("Get the weather in location") // (2) function description
|
||||
// (3) Required due to Kotlin SAM conversion being an opaque lambda
|
||||
.inputType<MockWeatherService.Request>()
|
||||
@@ -246,7 +244,7 @@ It also provides a description (2) and an optional response converter to convert
|
||||
|
||||
NOTE: By default, the response converter performs a JSON serialization of the Response object.
|
||||
|
||||
NOTE: The `FunctionCallback.Builder` internally resolves the function call signature based on the `MockWeatherService.Request` class.
|
||||
NOTE: The `FunctionToolCallback.Builder` internally resolves the function call signature based on the `MockWeatherService.Request` class.
|
||||
|
||||
=== Enable functions by bean name
|
||||
|
||||
@@ -257,7 +255,7 @@ To let the model know and call your `CurrentWeather` function you need to enable
|
||||
ChatClient chatClient = ...
|
||||
|
||||
ChatResponse response = this.chatClient.prompt("What's the weather like in San Francisco, Tokyo, and Paris?")
|
||||
.functions("CurrentWeather") // Enable the function
|
||||
.tools("CurrentWeather") // Enable the function
|
||||
.call().
|
||||
chatResponse();
|
||||
|
||||
@@ -289,8 +287,7 @@ The client-side registration enables you to register functions by default.
|
||||
ChatClient chatClient = ...
|
||||
|
||||
ChatResponse response = this.chatClient.prompt("What's the weather like in San Francisco, Tokyo, and Paris?")
|
||||
.functions(FunctionCallback.builder()
|
||||
.function("currentWeather", (Request request) -> new Response(30.0, Unit.C)) // (1) function name and instance
|
||||
.tools(FunctionToolCallback.builder("currentWeather", (Request request) -> new Response(30.0, Unit.C)) // (1) function name and instance
|
||||
.description("Get the weather in location") // (2) function description
|
||||
.inputType(MockWeatherService.Request.class) // (3) input type to build the JSON schema
|
||||
.build())
|
||||
@@ -317,7 +314,7 @@ The `MethodInvokingFunctionCallback` implements the `FunctionCallback` interface
|
||||
- Any parameter/return types (primitives, objects, collections)
|
||||
- Special handling for `ToolContext` parameters
|
||||
|
||||
You need the `FunctionCallback.Builder` to create `MethodInvokingFunctionCallback` like this:
|
||||
You need the `MethodToolCallback.Builder` to create `MethodInvokingFunctionCallback` like this:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
@@ -344,11 +341,14 @@ public class WeatherService {
|
||||
}
|
||||
|
||||
// Usage
|
||||
FunctionCallback callback = FunctionCallback.builder()
|
||||
.method("getWeather", String.class, TemperatureUnit.class)
|
||||
.description("Get weather information for a city")
|
||||
.targetClass(WeatherService.class)
|
||||
.build();
|
||||
var toolMethod = ReflectionUtils.findMethod(WeatherService.class, "getWeather", String.class, TemperatureUnit.class);
|
||||
MethodToolCallback callback = MethodToolCallback.builder()
|
||||
.toolDefinition(ToolDefinition.builder(toolMethod)
|
||||
.description("Get the weather in location")
|
||||
.build())
|
||||
.toolMethod(toolMethod)
|
||||
.toolObject(targetObject)
|
||||
.build();
|
||||
----
|
||||
Instance Method with ToolContext::
|
||||
+
|
||||
@@ -363,19 +363,21 @@ public class DeviceController {
|
||||
|
||||
// Usage
|
||||
DeviceController controller = new DeviceController();
|
||||
|
||||
var toolMethod = ReflectionUtils.findMethod(
|
||||
DeviceController.class, "setDeviceState", String.class, Boolean.class, ToolContext.class);
|
||||
String response = ChatClient.create(chatModel).prompt()
|
||||
.user("Turn on the living room lights")
|
||||
.functions(FunctionCallback.builder()
|
||||
.method("setDeviceState", String.class,boolean.class,ToolContext.class)
|
||||
.description("Control device state")
|
||||
.targetObject(controller)
|
||||
.build())
|
||||
.toolContext(Map.of("location", "home"))
|
||||
.call()
|
||||
.content();
|
||||
.user("Turn on the living room lights")
|
||||
.tools(MethodToolCallback.builder()
|
||||
.toolDefinition(ToolDefinition.builder(toolMethod)
|
||||
.description("Control device state")
|
||||
.build())
|
||||
.toolMethod(toolMethod)
|
||||
.toolObject(controller)
|
||||
.build())
|
||||
.toolContext(Map.of("location", "home"))
|
||||
.call()
|
||||
.content();
|
||||
----
|
||||
|
||||
======
|
||||
|
||||
The https://github.com/spring-projects/spring-ai/blob/main/models/spring-ai-openai/src/test/java/org/springframework/ai/openai/chat/client/OpenAiChatClientMethodInvokingFunctionCallbackIT.java[OpenAiChatClientMethodInvokingFunctionCallbackIT]
|
||||
@@ -425,8 +427,7 @@ BiFunction<MockWeatherService.Request, ToolContext, MockWeatherService.Response>
|
||||
|
||||
|
||||
ChatResponse response = chatClient.prompt("What's the weather like in San Francisco, Tokyo, and Paris?")
|
||||
.functions(FunctionCallback.builder()
|
||||
.function("getCurrentWeather", this.weatherFunction)
|
||||
.tools(FunctionToolCallback.builder("getCurrentWeather", this.weatherFunction)
|
||||
.description("Get the weather in location")
|
||||
.inputType(MockWeatherService.Request.class)
|
||||
.build())
|
||||
@@ -452,15 +453,18 @@ public class DeviceController {
|
||||
|
||||
// Usage
|
||||
DeviceController controller = new DeviceController();
|
||||
|
||||
var toolMethod = ReflectionUtils.findMethod(
|
||||
DeviceController.class, "setDeviceState", String.class, Boolean.class, ToolContext.class);
|
||||
String response = ChatClient.create(chatModel).prompt()
|
||||
.user("Turn on the living room lights")
|
||||
.functions(FunctionCallback.builder()
|
||||
.method("setDeviceState", String.class,boolean.class,ToolContext.class)
|
||||
.description("Control device state")
|
||||
.targetObject(controller)
|
||||
.build())
|
||||
.toolContext(Map.of("location", "home"))
|
||||
.call()
|
||||
.content();
|
||||
.user("Turn on the living room lights")
|
||||
.tools(MethodToolCallback.builder()
|
||||
.toolDefinition(ToolDefinition.builder(toolMethod)
|
||||
.description("Control device state")
|
||||
.build())
|
||||
.toolMethod(toolMethod)
|
||||
.toolObject(controller)
|
||||
.build())
|
||||
.toolContext(Map.of("location", "home"))
|
||||
.call()
|
||||
.content();
|
||||
----
|
||||
|
||||
Reference in New Issue
Block a user