langchain4j-rag-implementation-patterns

Name: langchain4j-rag-implementation-patterns
Author: giuseppe-trisciuoglio

1.6kinstalls36forks

How to install langchain4j-rag-implementation-patterns?

giuseppe-trisciuoglio/developer-kit/langchain4j-rag-implementation-patterns

$npx -y skills add giuseppe-trisciuoglio/developer-kit --skill langchain4j-rag-implementation-patterns

Installs into the current project.

Summary

Provides Retrieval-Augmented Generation (RAG) implementation patterns with LangChain4j for Java. Generates document ingestion pipelines, embedding stores, vector search, and semantic search capabilities. Use when building chat-with-documents systems, document Q&A over PDFs or tex

Files · 1

View on GitHub

SKILL.md

1	# LangChain4j RAG Implementation Patterns
2
3	## Overview
4
5	Implements RAG systems with LangChain4j: document ingestion pipelines, embedding stores, and vector search for chat-with-documents and knowledge-enhanced AI applications.
6
7	## When to Use This Skill
8
9	- Building chat-with-documents systems or document Q&A over PDFs, text files, or web pages
10	- Creating AI assistants with access to company knowledge bases or external sources
11	- Implementing semantic search or hybrid search over document repositories
12	- Building domain-specific AI with curated knowledge and source attribution
13
14	## Instructions
15
16	### Initialize RAG Project
17
18	Create a new Spring Boot project with required dependencies:
19
20	pom.xml:
21	```xml
22	<dependency>
23	<groupId>dev.langchain4j</groupId>
24	<artifactId>langchain4j-spring-boot-starter</artifactId>
25	<version>1.8.0</version>
26	</dependency>
27	<dependency>
28	<groupId>dev.langchain4j</groupId>
29	<artifactId>langchain4j-open-ai</artifactId>
30	<version>1.8.0</version>
31	</dependency>
32	```
33
34	### Setup Document Ingestion
35
36	Configure document loading and processing with validation:
37
38	Validation Checkpoint: After ingestion, verify embedding count matches segment count and test retrieval with a sample query.
39
40	```java
41	@Configuration
42	public class RAGConfiguration {
43
44	@Bean
45	public EmbeddingModel embeddingModel() {
46	return OpenAiEmbeddingModel.builder()
47	.apiKey(System.getenv("OPENAI_API_KEY"))
48	.modelName("text-embedding-3-small")
49	.build();
50	}
51
52	@Bean
53	public EmbeddingStore<TextSegment> embeddingStore() {
54	return new InMemoryEmbeddingStore<>();
55	}
56	}
57	```
58
59	Create document ingestion service:
60
61	```java
62	@Service
63	@RequiredArgsConstructor
64	public class DocumentIngestionService {
65
66	private final EmbeddingModel embeddingModel;
67	private final EmbeddingStore<TextSegment> embeddingStore;
68
69	public void ingestDocument(String filePath, Map<String, Object> metadata) {
70	Document document = FileSystemDocumentLoader.loadDocument(filePath);
71	document.metadata().putAll(metadata);
72
73	DocumentSplitter splitter = DocumentSplitters.recursive(
74	500, 50, new OpenAiTokenCountEstimator("text-embedding-3-small")
75	);
76
77	List<TextSegment> segments = splitter.split(document);
78	List<Embedding> embeddings = embeddingModel.embedAll(segments).content();
79	embeddingStore.addAll(embeddings, segments);
80
81	// Validation: verify embedding count matches segments
82	if (embeddings.size() != segments.size()) {
83	throw new IllegalStateException("Embedding count mismatch: expected " + segments.size() + ", got " + embeddings.size());
84	}
85	}
86
87	public boolean validateIngestion(String testQuery) {
88	// Validation: test retrieval with sample query
89	Embedding queryEmbedding = embeddingModel.embed(testQuery).content();
90	List<EmbeddingMatch<TextSegment>> results = embeddingStore.search(
91	EmbeddingSearchRequest.builder()
92	.queryEmbedding(queryEmbedding)
93	.maxResults(1)
94	.build()
95	).matches();
96	return !results.isEmpty();
97	}
98	}
99	```
100
101	### Configure Content Retrieval
102
103	Setup content retrieval with filtering:
104
105	Validation Checkpoint: After configuration, test retrieval with a known query to verify embeddings are searchable.
106
107	```java
108	@Configuration
109	public class ContentRetrieverConfiguration {
110
111	@Bean
112	public ContentRetriever contentRetriever(
113	EmbeddingStore<TextSegment> embeddingStore,
114	EmbeddingModel embeddingModel) {
115
116	return EmbeddingStoreContentRetriever.builder()
117	.embeddingStore(embeddingStore)
118	.embeddingModel(embeddingModel)
119	.maxResults(5)
120	.minScore(0.7)
121	.build();
122	}
123	}
124	```
125
126	### Create RAG-Enabled AI Service
127
128	Define AI service with context retrieval:
129
130	```java
131	interface KnowledgeAssistant {
132	@SystemMessage("""
133	You are a knowledgeable assistant with access to a comprehensive knowledge base.
134
135	When answering questions:
136	1. Use the provided context from the knowledge base
137	2. If information is not in the context, clearly state this
138	3. Provide accurate, helpful responses
139	4. When possible, reference specific sources
140	5. If the context is insufficient, ask for clarification
141	""")
142	String answerQuestion(String question);
143	}
144
145	@Service

People who liked this also viewed

6 picks

Type

langchain4j-rag-implementation-patterns

1.6kinstalls36forks

View on GitHub

How to install langchain4j-rag-implementation-patterns?

giuseppe-trisciuoglio/developer-kit/langchain4j-rag-implementation-patterns

$npx -y skills add giuseppe-trisciuoglio/developer-kit --skill langchain4j-rag-implementation-patterns

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# LangChain4j RAG Implementation Patterns
2
3	## Overview
4
5	Implements RAG systems with LangChain4j: document ingestion pipelines, embedding stores, and vector search for chat-with-documents and knowledge-enhanced AI applications.
6
7	## When to Use This Skill
8
9	- Building chat-with-documents systems or document Q&A over PDFs, text files, or web pages
10	- Creating AI assistants with access to company knowledge bases or external sources
11	- Implementing semantic search or hybrid search over document repositories
12	- Building domain-specific AI with curated knowledge and source attribution
13
14	## Instructions
15
16	### Initialize RAG Project
17
18	Create a new Spring Boot project with required dependencies:
19
20	pom.xml:
21	```xml
22	<dependency>
23	<groupId>dev.langchain4j</groupId>
24	<artifactId>langchain4j-spring-boot-starter</artifactId>
25	<version>1.8.0</version>
26	</dependency>
27	<dependency>
28	<groupId>dev.langchain4j</groupId>
29	<artifactId>langchain4j-open-ai</artifactId>
30	<version>1.8.0</version>
31	</dependency>
32	```
33
34	### Setup Document Ingestion
35
36	Configure document loading and processing with validation:
37
38	Validation Checkpoint: After ingestion, verify embedding count matches segment count and test retrieval with a sample query.
39
40	```java
41	@Configuration
42	public class RAGConfiguration {
43
44	@Bean
45	public EmbeddingModel embeddingModel() {
46	return OpenAiEmbeddingModel.builder()
47	.apiKey(System.getenv("OPENAI_API_KEY"))
48	.modelName("text-embedding-3-small")
49	.build();
50	}
51
52	@Bean
53	public EmbeddingStore<TextSegment> embeddingStore() {
54	return new InMemoryEmbeddingStore<>();
55	}
56	}
57	```
58
59	Create document ingestion service:
60
61	```java
62	@Service
63	@RequiredArgsConstructor
64	public class DocumentIngestionService {
65
66	private final EmbeddingModel embeddingModel;
67	private final EmbeddingStore<TextSegment> embeddingStore;
68
69	public void ingestDocument(String filePath, Map<String, Object> metadata) {
70	Document document = FileSystemDocumentLoader.loadDocument(filePath);
71	document.metadata().putAll(metadata);
72
73	DocumentSplitter splitter = DocumentSplitters.recursive(
74	500, 50, new OpenAiTokenCountEstimator("text-embedding-3-small")
75	);
76
77	List<TextSegment> segments = splitter.split(document);
78	List<Embedding> embeddings = embeddingModel.embedAll(segments).content();
79	embeddingStore.addAll(embeddings, segments);
80
81	// Validation: verify embedding count matches segments
82	if (embeddings.size() != segments.size()) {
83	throw new IllegalStateException("Embedding count mismatch: expected " + segments.size() + ", got " + embeddings.size());
84	}
85	}
86
87	public boolean validateIngestion(String testQuery) {
88	// Validation: test retrieval with sample query
89	Embedding queryEmbedding = embeddingModel.embed(testQuery).content();
90	List<EmbeddingMatch<TextSegment>> results = embeddingStore.search(
91	EmbeddingSearchRequest.builder()
92	.queryEmbedding(queryEmbedding)
93	.maxResults(1)
94	.build()
95	).matches();
96	return !results.isEmpty();
97	}
98	}
99	```
100
101	### Configure Content Retrieval
102
103	Setup content retrieval with filtering:
104
105	Validation Checkpoint: After configuration, test retrieval with a known query to verify embeddings are searchable.
106
107	```java
108	@Configuration
109	public class ContentRetrieverConfiguration {
110
111	@Bean
112	public ContentRetriever contentRetriever(
113	EmbeddingStore<TextSegment> embeddingStore,
114	EmbeddingModel embeddingModel) {
115
116	return EmbeddingStoreContentRetriever.builder()
117	.embeddingStore(embeddingStore)
118	.embeddingModel(embeddingModel)
119	.maxResults(5)
120	.minScore(0.7)
121	.build();
122	}
123	}
124	```
125
126	### Create RAG-Enabled AI Service
127
128	Define AI service with context retrieval:
129
130	```java
131	interface KnowledgeAssistant {
132	@SystemMessage("""
133	You are a knowledgeable assistant with access to a comprehensive knowledge base.
134
135	When answering questions:
136	1. Use the provided context from the knowledge base
137	2. If information is not in the context, clearly state this
138	3. Provide accurate, helpful responses
139	4. When possible, reference specific sources
140	5. If the context is insufficient, ask for clarification
141	""")
142	String answerQuestion(String question);
143	}
144
145	@Service

People who liked this also viewed

6 picks

Type