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

Add Spring Annotation for registerding Function Calling tools.

Browse Source 
- Built on top of the existing ToolFunctionCallback utilites.
 - Organized as part of auto-configuration project under the /common/function
   package to be reusable for different model implementations.
 - Add OpenAI support for the SpringAiFunction annotation.
 - Update the OpenAI function calling documentation.
 - Add ITs

Co-Authored-By: Christian Tzolov <ctzolov@vmware.com>
This commit is contained in:
Chris Smith
2023-09-06 17:05:50 -04:00
committed by Christian Tzolov
parent 57c66b91d7
commit b2a4f01761
6 changed files with 285 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
spring-ai-docs/src/main/antora/modules/ROOT/pages/api/clients/functions/openai-chat-functions.adoc
View File

@@ -64,16 +64,16 @@ The Spring AI auto-generates the JSON Scheme for the `MockWeatherService.Request
If you enable the link:../openai-chat.html#_auto_configuration[OpenAiChatClient Auto-Configuration], the easiest way to register a function is to created it as a bean in the Spring context:
[source,java,linenums]
[source,java]
----
@Configuration
static class Config {
@Bean
public WeatherFunctionCallback weatherFunctionInfo() {
return new WeatherFunctionCallback(
"CurrentWeather", // (1) name
"Get the weather in location", // (2) description
MockWeatherService.Request.class); // (3) signature
"CurrentWeather", // (1) function name
"Get the weather in location", // (2) function description
MockWeatherService.Request.class); // (3) function input signature
}
...
}
@@ -106,6 +106,35 @@ Here is the current weather for the requested cities:
The link:https://github.com/spring-projects/spring-ai/blob/main/spring-ai-spring-boot-autoconfigure/src/test/java/org/springframework/ai/autoconfigure/openai/tool/ToolCallWithBeanFunctionRegistrationIT.java[ToolCallWithBeanFunctionRegistrationIT.java] integration test provides a complete example of how to register a function with the `OpenAiChatClient` using the auto-configuration.
==== @SpringAiFunction
You can use the `SpringAiFunction` annotation cam be used to register a `java.util.Function<I,O>` as a `ToolFunctionCallback` bean:
[source,java]
----
@Configuration
static class Config {
@SpringAiFunction(
name = "CurrentWeather", // (1)
description = "Get the weather in location", // (2)
classType = MockWeatherService.Request.class) // (3)
public Function<Request, Response> weatherFunction() {
MockWeatherService weatherService = new MockWeatherService();
return (weatherService::apply);
}
...
}
----
The `@SpringAiFunction` annotation defines the function name (1), description (2), and input signature (3) and registers the function as a bean in the Spring context.
NOTE: The `SpringAiFunction` annotation supported only if the auto-configuration is enabled.
NOTE: The Function<I, O> implementation is responsible to convert the response into a text as expected by the model.
By default, the `AbstractToolFunctionCallback` provides a default converter that returns the `toString()` of the response object.
=== Register/Call Functions with Prompt Options
In addition to the auto-configuration you can register callback functions, dynamically, with your Prompt requests: