Class TurRagContextBuilder

java.lang.Object

com.viglet.turing.genai.TurRagContextBuilder

@Component
public class TurRagContextBuilder
extends Object

Shared builder for RAG infrastructure (EmbeddingModel + VectorStore). Eliminates duplication between SN GenAI, Asset Training, and RAG Search Tool.

Since:

2026.1.14

Author:

Alexandre Oliveira

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static final record	TurRagContextBuilder.RagInfrastructure	Result of building RAG infrastructure.

Constructor Summary

Constructors

Constructor	Description
TurRagContextBuilder(TurGenAiLlmProviderFactory llmProviderFactory, TurGenAiStoreProviderFactory storeProviderFactory, TurSecretCryptoService secretCryptoService, TurGlobalSettingsService globalSettingsService, TurEmbeddingModelRepository embeddingModelRepository, TurStoreInstanceRepository storeInstanceRepository)

Method Summary

Modifier and Type	Method	Description
Optional<TurRagContextBuilder.RagInfrastructure>	build(TurEmbeddingModel embModel, TurStoreInstance storeInstance, String collectionNameOverride)	Builds the full RAG infrastructure from resolved entities with an optional collection name override.
Optional<TurRagContextBuilder.RagInfrastructure>	build(String embeddingModelId, String storeInstanceId)	Builds the full RAG infrastructure (EmbeddingModel + VectorStore) from explicit IDs.
Optional<TurRagContextBuilder.RagInfrastructure>	build(String embeddingModelId, String storeInstanceId, String collectionNameOverride)	Builds the full RAG infrastructure with an optional collection name override.
Optional<TurRagContextBuilder.RagInfrastructure>	buildFromGlobalSettings()	Builds RAG infrastructure using the Global Settings defaults.
Optional<TurRagContextBuilder.RagInfrastructure>	buildFromGlobalSettings(String collectionNameOverride)	Builds RAG infrastructure using the Global Settings defaults with a collection name override.
org.springframework.ai.embedding.EmbeddingModel	resolveEmbeddingModel(TurEmbeddingModel embModel)	Resolves a TurEmbeddingModel into a Spring AI EmbeddingModel.

Methods inherited from class Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

TurRagContextBuilder

public TurRagContextBuilder(TurGenAiLlmProviderFactory llmProviderFactory,
 TurGenAiStoreProviderFactory storeProviderFactory,
 TurSecretCryptoService secretCryptoService,
 TurGlobalSettingsService globalSettingsService,
 TurEmbeddingModelRepository embeddingModelRepository,
 TurStoreInstanceRepository storeInstanceRepository)

Method Details

resolveEmbeddingModel

public org.springframework.ai.embedding.EmbeddingModel resolveEmbeddingModel(TurEmbeddingModel embModel)

Resolves a TurEmbeddingModel into a Spring AI EmbeddingModel. Creates a detached LLM instance with the embedding model's reference overriding the modelName.

build

public Optional<TurRagContextBuilder.RagInfrastructure> build(String embeddingModelId,
 String storeInstanceId)

Builds the full RAG infrastructure (EmbeddingModel + VectorStore) from explicit IDs.

build

public Optional<TurRagContextBuilder.RagInfrastructure> build(String embeddingModelId,
 String storeInstanceId,
 String collectionNameOverride)

Builds the full RAG infrastructure with an optional collection name override.

build

public Optional<TurRagContextBuilder.RagInfrastructure> build(TurEmbeddingModel embModel,
 TurStoreInstance storeInstance,
 String collectionNameOverride)

Builds the full RAG infrastructure from resolved entities with an optional collection name override.

buildFromGlobalSettings

public Optional<TurRagContextBuilder.RagInfrastructure> buildFromGlobalSettings()

Builds RAG infrastructure using the Global Settings defaults.

buildFromGlobalSettings

public Optional<TurRagContextBuilder.RagInfrastructure> buildFromGlobalSettings(String collectionNameOverride)

Builds RAG infrastructure using the Global Settings defaults with a collection name override.