langchain4j-ai-services-patterns

Name: langchain4j-ai-services-patterns
Author: giuseppe-trisciuoglio

1.6kinstalls36forks

How to install langchain4j-ai-services-patterns?

giuseppe-trisciuoglio/developer-kit/langchain4j-ai-services-patterns

$npx -y skills add giuseppe-trisciuoglio/developer-kit --skill langchain4j-ai-services-patterns

Installs into the current project.

Summary

Provides patterns to build declarative AI Services with LangChain4j for LLM integration, chatbot development, AI agent implementation, and conversational AI in Java. Generates type-safe AI services using interface-based patterns, annotations, memory management, and tools integrat

Files · 1

View on GitHub

SKILL.md

1	# LangChain4j AI Services Patterns
2
3	This skill provides guidance for building declarative AI Services with LangChain4j using interface-based patterns, annotations for system and user messages, memory management, tools integration, and advanced AI application patterns that abstract away low-level LLM interactions.
4
5	## Overview
6
7	LangChain4j AI Services define AI functionality using Java interfaces with annotations, providing type-safe, declarative AI with minimal boilerplate.
8
9	## When to Use
10
11	Use this skill when:
12	- Building declarative AI services with minimal boilerplate using Java interfaces
13	- Creating type-safe conversational AI with memory management
14	- Implementing AI agents with function/tool calling capabilities
15	- Designing AI services returning structured data (enums, POJOs, lists)
16	- Integrating RAG patterns declaratively
17
18	## Instructions
19
20	Follow these steps to create declarative AI Services with LangChain4j:
21
22	### 1. Define AI Service Interface
23
24	Create a Java interface with method signatures for AI interactions:
25
26	```java
27	interface Assistant {
28	String chat(String userMessage);
29	}
30	```
31
32	### 2. Add Annotations for System and User Messages
33
34	Use `@SystemMessage` and `@UserMessage` annotations to define prompts:
35
36	```java
37	interface CustomerSupportBot {
38	@SystemMessage("You are a helpful customer support agent for TechCorp")
39	String handleInquiry(String customerMessage);
40
41	@UserMessage("Analyze sentiment: {{it}}")
42	Sentiment analyzeSentiment(String feedback);
43	}
44	```
45
46	### 3. Create AI Service Instance
47
48	Use `AiServices` builder or create to instantiate the service:
49
50	```java
51	// Simple creation
52	Assistant assistant = AiServices.create(Assistant.class, chatModel);
53
54	// Or with builder for advanced configuration
55	Assistant assistant = AiServices.builder(Assistant.class)
56	.chatModel(chatModel)
57	.build();
58	```
59
60	### 4. Configure Memory for Multi-turn Conversations
61
62	Add memory management using `@MemoryId` for multi-user scenarios:
63
64	```java
65	interface MultiUserAssistant {
66	String chat(@MemoryId String userId, String userMessage);
67	}
68
69	Assistant assistant = AiServices.builder(MultiUserAssistant.class)
70	.chatModel(model)
71	.chatMemoryProvider(userId -> MessageWindowChatMemory.withMaxMessages(10))
72	.build();
73	```
74
75	### 5. Integrate Tools for Function Calling
76
77	Register tools using `@Tool` annotation to enable AI function execution:
78
79	```java
80	class Calculator {
81	@Tool("Add two numbers") double add(double a, double b) { return a + b; }
82	}
83
84	interface MathGenius {
85	String ask(String question);
86	}
87
88	MathGenius mathGenius = AiServices.builder(MathGenius.class)
89	.chatModel(model)
90	.tools(new Calculator())
91	.build();
92	```
93
94	### 6. Validate and Test
95
96	Test AI services with concrete validation patterns:
97
98	```java
99	// 1. Test with sample inputs
100	String response = assistant.chat("Hello, how are you?");
101	assert response != null && !response.isEmpty();
102
103	// 2. Validate structured outputs with assertions
104	Sentiment result = bot.analyzeSentiment("Great product!");
105	assert result == Sentiment.POSITIVE;
106
107	// 3. Log tool calls with side effects for audit
108	MathGenius math = AiServices.builder(MathGenius.class)
109	.chatModel(model)
110	.tools(new Calculator())
111	.build();
112
113	// 4. Test memory isolation between users
114	String userA = assistant.chat("User A message", "session-a");
115	String userB = assistant.chat("User B message", "session-b");
116	assert !userA.equals(userB); // Verify memory isolation
117	```
118
119	## Examples
120
121	See [examples.md](references/examples.md) for comprehensive practical examples including:
122	- Basic chat interfaces
123	- Stateful assistants with memory
124	- Multi-user scenarios
125	- Structured output extraction
126	- Tool calling and function execution
127	- Streaming responses
128	- Error handling
129	- RAG integration
130	- Production patterns
131
132	## API Reference
133
134	Complete API documentation, annotations, interfaces, and configuration patterns are available in [references.md](references/references.md).
135
136	## Best Practices
137
138	1. Use type-safe interfaces instead of string-based prompts
139	2. Implement proper memory management with appropriate limits
140	3. Design clear tool descriptions with parameter documentation
141	4. Handle errors gracefully with custom error handlers
142	5. Use structured output for predictable responses
143	6. Implement validation for user inputs
144	7. Monitor performance for production deployments
145
146	## Dependencies
147
148	```xml
149	<!-- Maven -->
150	<dependency>
151	<groupId>dev.langchain

People who liked this also viewed

6 picks

Type

langchain4j-ai-services-patterns

1.6kinstalls36forks

View on GitHub

How to install langchain4j-ai-services-patterns?

giuseppe-trisciuoglio/developer-kit/langchain4j-ai-services-patterns

$npx -y skills add giuseppe-trisciuoglio/developer-kit --skill langchain4j-ai-services-patterns

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# LangChain4j AI Services Patterns
2
3	This skill provides guidance for building declarative AI Services with LangChain4j using interface-based patterns, annotations for system and user messages, memory management, tools integration, and advanced AI application patterns that abstract away low-level LLM interactions.
4
5	## Overview
6
7	LangChain4j AI Services define AI functionality using Java interfaces with annotations, providing type-safe, declarative AI with minimal boilerplate.
8
9	## When to Use
10
11	Use this skill when:
12	- Building declarative AI services with minimal boilerplate using Java interfaces
13	- Creating type-safe conversational AI with memory management
14	- Implementing AI agents with function/tool calling capabilities
15	- Designing AI services returning structured data (enums, POJOs, lists)
16	- Integrating RAG patterns declaratively
17
18	## Instructions
19
20	Follow these steps to create declarative AI Services with LangChain4j:
21
22	### 1. Define AI Service Interface
23
24	Create a Java interface with method signatures for AI interactions:
25
26	```java
27	interface Assistant {
28	String chat(String userMessage);
29	}
30	```
31
32	### 2. Add Annotations for System and User Messages
33
34	Use `@SystemMessage` and `@UserMessage` annotations to define prompts:
35
36	```java
37	interface CustomerSupportBot {
38	@SystemMessage("You are a helpful customer support agent for TechCorp")
39	String handleInquiry(String customerMessage);
40
41	@UserMessage("Analyze sentiment: {{it}}")
42	Sentiment analyzeSentiment(String feedback);
43	}
44	```
45
46	### 3. Create AI Service Instance
47
48	Use `AiServices` builder or create to instantiate the service:
49
50	```java
51	// Simple creation
52	Assistant assistant = AiServices.create(Assistant.class, chatModel);
53
54	// Or with builder for advanced configuration
55	Assistant assistant = AiServices.builder(Assistant.class)
56	.chatModel(chatModel)
57	.build();
58	```
59
60	### 4. Configure Memory for Multi-turn Conversations
61
62	Add memory management using `@MemoryId` for multi-user scenarios:
63
64	```java
65	interface MultiUserAssistant {
66	String chat(@MemoryId String userId, String userMessage);
67	}
68
69	Assistant assistant = AiServices.builder(MultiUserAssistant.class)
70	.chatModel(model)
71	.chatMemoryProvider(userId -> MessageWindowChatMemory.withMaxMessages(10))
72	.build();
73	```
74
75	### 5. Integrate Tools for Function Calling
76
77	Register tools using `@Tool` annotation to enable AI function execution:
78
79	```java
80	class Calculator {
81	@Tool("Add two numbers") double add(double a, double b) { return a + b; }
82	}
83
84	interface MathGenius {
85	String ask(String question);
86	}
87
88	MathGenius mathGenius = AiServices.builder(MathGenius.class)
89	.chatModel(model)
90	.tools(new Calculator())
91	.build();
92	```
93
94	### 6. Validate and Test
95
96	Test AI services with concrete validation patterns:
97
98	```java
99	// 1. Test with sample inputs
100	String response = assistant.chat("Hello, how are you?");
101	assert response != null && !response.isEmpty();
102
103	// 2. Validate structured outputs with assertions
104	Sentiment result = bot.analyzeSentiment("Great product!");
105	assert result == Sentiment.POSITIVE;
106
107	// 3. Log tool calls with side effects for audit
108	MathGenius math = AiServices.builder(MathGenius.class)
109	.chatModel(model)
110	.tools(new Calculator())
111	.build();
112
113	// 4. Test memory isolation between users
114	String userA = assistant.chat("User A message", "session-a");
115	String userB = assistant.chat("User B message", "session-b");
116	assert !userA.equals(userB); // Verify memory isolation
117	```
118
119	## Examples
120
121	See [examples.md](references/examples.md) for comprehensive practical examples including:
122	- Basic chat interfaces
123	- Stateful assistants with memory
124	- Multi-user scenarios
125	- Structured output extraction
126	- Tool calling and function execution
127	- Streaming responses
128	- Error handling
129	- RAG integration
130	- Production patterns
131
132	## API Reference
133
134	Complete API documentation, annotations, interfaces, and configuration patterns are available in [references.md](references/references.md).
135
136	## Best Practices
137
138	1. Use type-safe interfaces instead of string-based prompts
139	2. Implement proper memory management with appropriate limits
140	3. Design clear tool descriptions with parameter documentation
141	4. Handle errors gracefully with custom error handlers
142	5. Use structured output for predictable responses
143	6. Implement validation for user inputs
144	7. Monitor performance for production deployments
145
146	## Dependencies
147
148	```xml
149	<!-- Maven -->
150	<dependency>
151	<groupId>dev.langchain

People who liked this also viewed

6 picks

Type