langchain4j-tool-function-calling-patterns

Name: langchain4j-tool-function-calling-patterns
Author: giuseppe-trisciuoglio

1.6kinstalls36forks

How to install langchain4j-tool-function-calling-patterns?

giuseppe-trisciuoglio/developer-kit/langchain4j-tool-function-calling-patterns

$npx -y skills add giuseppe-trisciuoglio/developer-kit --skill langchain4j-tool-function-calling-patterns

Installs into the current project.

Summary

Provides and generates LangChain4j tool and function calling patterns: annotates methods as tools with @Tool, configures tool executors, registers tools with AiServices, validates tool parameters, and handles tool execution errors. Use when building AI agents that call tools, def

Files · 1

View on GitHub

SKILL.md

1	# LangChain4j Tool & Function Calling Patterns
2
3	Provides patterns for annotating methods as tools, configuring tool executors, registering tools with AI services, validating parameters, and handling tool execution errors in LangChain4j applications.
4
5	## Overview
6
7	LangChain4j uses the `@Tool` annotation to expose Java methods as callable functions for AI agents. The `AiServices` builder registers tools with a chat model, enabling LLMs to perform actions beyond text generation: database queries, API calls, calculations, and business system integrations. Parameters use `@P` for descriptions that guide the LLM.
8
9	## When to Use
10
11	- Building AI agents that call external tools (weather, stocks, database queries)
12	- Defining function specifications for LLM tool use (`@Tool`, `@P` annotations)
13	- Registering and managing tool sets with `AiServices.builder().tools()`
14	- Handling tool execution errors, timeouts, and hallucinated tool names
15	- Implementing context-aware tools that inject user state via `@ToolMemoryId`
16	- Configuring dynamic tool providers for large or conditional tool sets
17
18	## Instructions
19
20	### 1. Annotate Methods with `@Tool`
21
22	Define a tool class with methods annotated `@Tool`. Provide a description as the first parameter. Use `@P` for each parameter description.
23
24	```java
25	public class WeatherTools {
26	private final WeatherService weatherService;
27
28	public WeatherTools(WeatherService weatherService) {
29	this.weatherService = weatherService;
30	}
31
32	@Tool("Get current weather for a city")
33	public String getWeather(
34	@P("City name") String city,
35	@P("Temperature unit: celsius or fahrenheit") String unit) {
36	return weatherService.getWeather(city, unit);
37	}
38	}
39	```
40
41	Validate: Create an instance and confirm the class loads without errors.
42
43	### 2. Register Tools with AiServices
44
45	Use `AiServices.builder()` to register tool instances with the chat model.
46
47	```java
48	MathAssistant assistant = AiServices.builder(MathAssistant.class)
49	.chatModel(chatModel)
50	.tools(new Calculator(), new WeatherTools(weatherService))
51	.build();
52	```
53
54	Validate: Call `assistant.chat("What is 2 + 2?")` and verify the LLM responds without throwing.
55
56	### 3. Test Tool Invocation End-to-End
57
58	Send a prompt that triggers tool usage and verify the tool executes and its result is incorporated.
59
60	```java
61	String response = assistant.chat("What is the weather in Rome?");
62	System.out.println(response);
63	```
64
65	Validate: Check logs for tool invocation and confirm the response uses the tool output.
66
67	### 4. Handle Tool Execution Errors
68
69	Add error handlers to gracefully manage failures without exposing stack traces.
70
71	```java
72	AiServices.builder(Assistant.class)
73	.chatModel(chatModel)
74	.tools(new ExternalServiceTools())
75	.toolExecutionErrorHandler((request, exception) -> {
76	logger.error("Tool '{}' failed: {}", request.name(), exception.getMessage());
77	return "An error occurred while processing your request";
78	})
79	.hallucinatedToolNameStrategy(request ->
80	ToolExecutionResultMessage.from(request,
81	"Error: tool '" + request.name() + "' does not exist"))
82	.toolArgumentsErrorHandler((error, context) ->
83	ToolErrorHandlerResult.text("Invalid arguments: " + error.getMessage()))
84	.build();
85	```
86
87	Validate: Trigger an error condition and confirm the LLM receives a safe error message.
88
89	### 5. Optimize for Performance and Scale
90
91	Enable concurrent tool execution and set timeouts for long-running tools.
92
93	```java
94	AiServices.builder(Assistant.class)
95	.chatModel(chatModel)
96	.tools(new DbTools(), new HttpTools())
97	.executeToolsConcurrently(Executors.newFixedThreadPool(5))
98	.toolExecutionTimeout(Duration.ofSeconds(30))
99	.build();
100	```
101
102	Validate: Run concurrent requests and confirm no thread contention or deadlocks.
103
104	## Examples
105
106	### Calculator Tool with Full Class
107
108	```java
109	public class Calculator {
110	@Tool("Perform basic arithmetic")
111	public double calculate(
112	@P("Expression like 2+2 or 10*5") String expression) {
113	// Parse and evaluate expression
114	return eval(expression);
115	}
116	}
117
118	Assistant assistant = AiServices.builder(Assistant.class)
119	.chatModel(ChatModel.builder()
120	.apiKey(System.getenv("API_KEY"))
121	.model("gpt-4o")
122	.build())
123	.tools(new Calculator())
124	.build();
125	```
126
127	### Immediate Return Tool (No LLM Response)
128
129	```java
130	@Tool(value = "Send email notification", ret

giuseppe-trisciuoglioPublisher · 122 listings

Preview

giuseppe-trisciuoglio/developer-kit

Repogiuseppe-trisciuoglio/developer-kit

LicenseMIT

TypeSkills

CategorySearch & RAG

UpdatedJun 2026

Repo stars310

First seenJul 22, 2026

People who liked this also viewed

6 picks

Type

langchain4j-tool-function-calling-patterns

1.6kinstalls36forks

View on GitHub

How to install langchain4j-tool-function-calling-patterns?

giuseppe-trisciuoglio/developer-kit/langchain4j-tool-function-calling-patterns

$npx -y skills add giuseppe-trisciuoglio/developer-kit --skill langchain4j-tool-function-calling-patterns

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# LangChain4j Tool & Function Calling Patterns
2
3	Provides patterns for annotating methods as tools, configuring tool executors, registering tools with AI services, validating parameters, and handling tool execution errors in LangChain4j applications.
4
5	## Overview
6
7	LangChain4j uses the `@Tool` annotation to expose Java methods as callable functions for AI agents. The `AiServices` builder registers tools with a chat model, enabling LLMs to perform actions beyond text generation: database queries, API calls, calculations, and business system integrations. Parameters use `@P` for descriptions that guide the LLM.
8
9	## When to Use
10
11	- Building AI agents that call external tools (weather, stocks, database queries)
12	- Defining function specifications for LLM tool use (`@Tool`, `@P` annotations)
13	- Registering and managing tool sets with `AiServices.builder().tools()`
14	- Handling tool execution errors, timeouts, and hallucinated tool names
15	- Implementing context-aware tools that inject user state via `@ToolMemoryId`
16	- Configuring dynamic tool providers for large or conditional tool sets
17
18	## Instructions
19
20	### 1. Annotate Methods with `@Tool`
21
22	Define a tool class with methods annotated `@Tool`. Provide a description as the first parameter. Use `@P` for each parameter description.
23
24	```java
25	public class WeatherTools {
26	private final WeatherService weatherService;
27
28	public WeatherTools(WeatherService weatherService) {
29	this.weatherService = weatherService;
30	}
31
32	@Tool("Get current weather for a city")
33	public String getWeather(
34	@P("City name") String city,
35	@P("Temperature unit: celsius or fahrenheit") String unit) {
36	return weatherService.getWeather(city, unit);
37	}
38	}
39	```
40
41	Validate: Create an instance and confirm the class loads without errors.
42
43	### 2. Register Tools with AiServices
44
45	Use `AiServices.builder()` to register tool instances with the chat model.
46
47	```java
48	MathAssistant assistant = AiServices.builder(MathAssistant.class)
49	.chatModel(chatModel)
50	.tools(new Calculator(), new WeatherTools(weatherService))
51	.build();
52	```
53
54	Validate: Call `assistant.chat("What is 2 + 2?")` and verify the LLM responds without throwing.
55
56	### 3. Test Tool Invocation End-to-End
57
58	Send a prompt that triggers tool usage and verify the tool executes and its result is incorporated.
59
60	```java
61	String response = assistant.chat("What is the weather in Rome?");
62	System.out.println(response);
63	```
64
65	Validate: Check logs for tool invocation and confirm the response uses the tool output.
66
67	### 4. Handle Tool Execution Errors
68
69	Add error handlers to gracefully manage failures without exposing stack traces.
70
71	```java
72	AiServices.builder(Assistant.class)
73	.chatModel(chatModel)
74	.tools(new ExternalServiceTools())
75	.toolExecutionErrorHandler((request, exception) -> {
76	logger.error("Tool '{}' failed: {}", request.name(), exception.getMessage());
77	return "An error occurred while processing your request";
78	})
79	.hallucinatedToolNameStrategy(request ->
80	ToolExecutionResultMessage.from(request,
81	"Error: tool '" + request.name() + "' does not exist"))
82	.toolArgumentsErrorHandler((error, context) ->
83	ToolErrorHandlerResult.text("Invalid arguments: " + error.getMessage()))
84	.build();
85	```
86
87	Validate: Trigger an error condition and confirm the LLM receives a safe error message.
88
89	### 5. Optimize for Performance and Scale
90
91	Enable concurrent tool execution and set timeouts for long-running tools.
92
93	```java
94	AiServices.builder(Assistant.class)
95	.chatModel(chatModel)
96	.tools(new DbTools(), new HttpTools())
97	.executeToolsConcurrently(Executors.newFixedThreadPool(5))
98	.toolExecutionTimeout(Duration.ofSeconds(30))
99	.build();
100	```
101
102	Validate: Run concurrent requests and confirm no thread contention or deadlocks.
103
104	## Examples
105
106	### Calculator Tool with Full Class
107
108	```java
109	public class Calculator {
110	@Tool("Perform basic arithmetic")
111	public double calculate(
112	@P("Expression like 2+2 or 10*5") String expression) {
113	// Parse and evaluate expression
114	return eval(expression);
115	}
116	}
117
118	Assistant assistant = AiServices.builder(Assistant.class)
119	.chatModel(ChatModel.builder()
120	.apiKey(System.getenv("API_KEY"))
121	.model("gpt-4o")
122	.build())
123	.tools(new Calculator())
124	.build();
125	```
126
127	### Immediate Return Tool (No LLM Response)
128
129	```java
130	@Tool(value = "Send email notification", ret

giuseppe-trisciuoglioPublisher · 122 listings

Preview

giuseppe-trisciuoglio/developer-kit

Repogiuseppe-trisciuoglio/developer-kit

LicenseMIT

TypeSkills

CategorySearch & RAG

UpdatedJun 2026

Repo stars310

First seenJul 22, 2026

People who liked this also viewed

6 picks

Type