IndexProps

Properties for defining a Index.

See https://www.alibabacloud.com/help/ros/developer-reference/aliyun-bailian-index

Initializer

import com.aliyun.ros.cdk.bailian.IndexProps;
IndexProps.builder()
    .name(java.lang.String)
    .name(IResolvable)
    .sourceType(java.lang.String)
    .sourceType(IResolvable)
    .structureType(java.lang.String)
    .structureType(IResolvable)
    .workspaceId(java.lang.String)
    .workspaceId(IResolvable)
//  .categoryIds(IResolvable)
//  .categoryIds(java.util.List<java.lang.String)
//  .categoryIds(IResolvable>)
//  .chunkMode(java.lang.String)
//  .chunkMode(IResolvable)
//  .chunkSize(java.lang.Number)
//  .chunkSize(IResolvable)
//  .connectId(java.lang.String)
//  .connectId(IResolvable)
//  .database(java.lang.String)
//  .database(IResolvable)
//  .denseSimilarityTopK(java.lang.Number)
//  .denseSimilarityTopK(IResolvable)
//  .description(java.lang.String)
//  .description(IResolvable)
//  .documentIds(IResolvable)
//  .documentIds(java.util.List<java.lang.String)
//  .documentIds(IResolvable>)
//  .embeddingModelName(java.lang.String)
//  .embeddingModelName(IResolvable)
//  .enableHeaders(java.lang.Boolean)
//  .enableHeaders(IResolvable)
//  .enableRewrite(java.lang.Boolean)
//  .enableRewrite(IResolvable)
//  .knowledgeScene(java.lang.String)
//  .knowledgeScene(IResolvable)
//  .knowledgeType(java.lang.String)
//  .knowledgeType(IResolvable)
//  .metaExtractColumns(IResolvable)
//  .metaExtractColumns(java.util.List<IResolvable)
//  .metaExtractColumns(MetaExtractColumnsProperty>)
//  .overlapSize(java.lang.Number)
//  .overlapSize(IResolvable)
//  .pipelineCommercialCu(java.lang.Number)
//  .pipelineCommercialCu(IResolvable)
//  .pipelineCommercialType(java.lang.String)
//  .pipelineCommercialType(IResolvable)
//  .pipelineRetrieveRateLimitStrategy(java.lang.String)
//  .pipelineRetrieveRateLimitStrategy(IResolvable)
//  .rerankInstruct(java.lang.String)
//  .rerankInstruct(IResolvable)
//  .rerankMinScore(java.lang.Number)
//  .rerankMinScore(IResolvable)
//  .rerankMode(java.lang.String)
//  .rerankMode(IResolvable)
//  .rerankModelName(java.lang.String)
//  .rerankModelName(IResolvable)
//  .separator(java.lang.String)
//  .separator(IResolvable)
//  .sinkInstanceId(java.lang.String)
//  .sinkInstanceId(IResolvable)
//  .sinkRegion(java.lang.String)
//  .sinkRegion(IResolvable)
//  .sinkType(java.lang.String)
//  .sinkType(IResolvable)
//  .sparseSimilarityTopK(java.lang.Number)
//  .sparseSimilarityTopK(IResolvable)
//  .table(java.lang.String)
//  .table(IResolvable)
//  .tableIds(IResolvable)
//  .tableIds(java.util.List<java.lang.String)
//  .tableIds(IResolvable>)
    .build();

Properties

name^Required

public java.lang.Object getName();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property name: Knowledge base name.

1-20 characters. Supports Chinese, English, numbers, underscores (_), hyphens (-), periods (.) and colons (:).

sourceType^Required

public java.lang.Object getSourceType();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property sourceType: Data source type.

DATA_CENTER_CATEGORY: import files from specified categories. DATA_CENTER_FILE: import specified files.

structureType^Required

public java.lang.Object getStructureType();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property structureType: Knowledge base type.

unstructured: document search or audio/video knowledge base. structured: data query or image Q&A knowledge base.

workspaceId^Required

public java.lang.Object getWorkspaceId();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property workspaceId: Workspace ID.

The knowledge base will be created in this workspace.

categoryIds^Optional

public java.lang.Object getCategoryIds();

• Type: com.aliyun.ros.cdk.core.IResolvable OR java.util.List

Property categoryIds: Category IDs to import when creating the knowledge base.

Required when SourceType is DATA_CENTER_CATEGORY.

chunkMode^Optional

public java.lang.Object getChunkMode();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property chunkMode: Chunk strategy.

If not specified, smart chunking is used. When set to regex, Separator must also be provided.

chunkSize^Optional

public java.lang.Object getChunkSize();

• Type: java.lang.Number OR com.aliyun.ros.cdk.core.IResolvable

Property chunkSize: Chunk size, the maximum number of characters per text slice.

Range [1-6000]. Defaults to 500. If ChunkSize is less than 100, OverlapSize must also be set.

connectId^Optional

public java.lang.Object getConnectId();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property connectId: Connection ID.

Replaces the deprecated datasourceCode parameter.

database^Optional

public java.lang.Object getDatabase();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property database: Database name for structured knowledge base.

denseSimilarityTopK^Optional

public java.lang.Object getDenseSimilarityTopK();

• Type: java.lang.Number OR com.aliyun.ros.cdk.core.IResolvable

Property denseSimilarityTopK: Vector retrieval Top K.

Retrieves the K most similar text slices by vector similarity. Range [0-100]. Defaults to 100. DenseSimilarityTopK + SparseSimilarityTopK must be <= 200. Only supported in UpdateIndex, not in CreateIndex.

description^Optional

public java.lang.Object getDescription();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property description: Knowledge base description.

0-1000 characters.

documentIds^Optional

public java.lang.Object getDocumentIds();

• Type: com.aliyun.ros.cdk.core.IResolvable OR java.util.List

Property documentIds: Document IDs to import when creating the knowledge base.

Required when SourceType is DATA_CENTER_FILE.

embeddingModelName^Optional

public java.lang.Object getEmbeddingModelName();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property embeddingModelName: Embedding model used by the knowledge base.

Defaults to text-embedding-v3.

enableHeaders^Optional

public java.lang.Object getEnableHeaders();

• Type: java.lang.Boolean OR com.aliyun.ros.cdk.core.IResolvable

Property enableHeaders: Whether to enable headers for document parsing.

Defaults to false.

enableRewrite^Optional

public java.lang.Object getEnableRewrite();

• Type: java.lang.Boolean OR com.aliyun.ros.cdk.core.IResolvable

Property enableRewrite: Whether to enable multi-turn dialogue rewriting.

Defaults to true.

knowledgeScene^Optional

public java.lang.Object getKnowledgeScene();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property knowledgeScene: Knowledge base scene.

Must be provided together with KnowledgeType. The valid values depend on KnowledgeType.

knowledgeType^Optional

public java.lang.Object getKnowledgeType();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property knowledgeType: Knowledge base type classification.

Must be provided together with KnowledgeScene. If both are omitted, the system uses default based on StructureType.

metaExtractColumns^Optional

public java.lang.Object getMetaExtractColumns();

• Type: com.aliyun.ros.cdk.core.IResolvable OR java.util.ListMetaExtractColumnsProperty>

Property metaExtractColumns: Metadata extraction configuration.

overlapSize^Optional

public java.lang.Object getOverlapSize();

• Type: java.lang.Number OR com.aliyun.ros.cdk.core.IResolvable

Property overlapSize: Overlap size, the number of overlapping characters between adjacent text slices.

Range [0-1024]. Defaults to 100. Must be less than ChunkSize.

pipelineCommercialCu^Optional

public java.lang.Object getPipelineCommercialCu();

• Type: java.lang.Number OR com.aliyun.ros.cdk.core.IResolvable

Property pipelineCommercialCu: RCU count for enterprise edition.

Only required when PipelineCommercialType is enterprise. Range [1-200].

pipelineCommercialType^Optional

public java.lang.Object getPipelineCommercialType();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property pipelineCommercialType: Knowledge base specification type.

standard: Standard edition. enterprise: Enterprise edition. Defaults to standard.

pipelineRetrieveRateLimitStrategy^Optional

public java.lang.Object getPipelineRetrieveRateLimitStrategy();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property pipelineRetrieveRateLimitStrategy: Retrieval rate limit strategy for enterprise edition.

Defaults to downgrade.

rerankInstruct^Optional

public java.lang.Object getRerankInstruct();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property rerankInstruct: Custom rerank instruction.

Required when RerankMode is custom.

rerankMinScore^Optional

public java.lang.Object getRerankMinScore();

• Type: java.lang.Number OR com.aliyun.ros.cdk.core.IResolvable

Property rerankMinScore: Similarity threshold.

Only text slices with similarity score exceeding this value will be recalled. Range [0.01-1.00]. Defaults to 0.01.

rerankMode^Optional

public java.lang.Object getRerankMode();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property rerankMode: Rerank mode.

qa: Q&A scenario (default). similar: similarity scenario. custom: custom rerank instruction, requires RerankInstruct.

rerankModelName^Optional

public java.lang.Object getRerankModelName();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property rerankModelName: Rerank model used by the knowledge base.

Defaults to qwen3-rerank when not specified.

separator^Optional

public java.lang.Object getSeparator();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property separator: Separator for chunking.

Only effective when ChunkMode is regex.

sinkInstanceId^Optional

public java.lang.Object getSinkInstanceId();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property sinkInstanceId: Vector storage instance ID.

Required when SinkType is ADB.

sinkRegion^Optional

public java.lang.Object getSinkRegion();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property sinkRegion: Region of the vector storage instance.

Required when SinkType is ADB.

sinkType^Optional

public java.lang.Object getSinkType();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property sinkType: Vector storage type.

BUILT_IN: managed by Bailian platform. ADB: AnalyticDB for PostgreSQL. Defaults to BUILT_IN. When set to ADB, SinkInstanceId and SinkRegion are required.

sparseSimilarityTopK^Optional

public java.lang.Object getSparseSimilarityTopK();

• Type: java.lang.Number OR com.aliyun.ros.cdk.core.IResolvable

Property sparseSimilarityTopK: Keyword retrieval Top K.

Retrieves text slices by exact keyword matching. Range [0-100]. Defaults to 100. DenseSimilarityTopK + SparseSimilarityTopK must be <= 200. Only supported in UpdateIndex, not in CreateIndex.

table^Optional

public java.lang.Object getTable();

• Type: java.lang.String OR com.aliyun.ros.cdk.core.IResolvable

Property table: Table name for structured knowledge base.

tableIds^Optional

public java.lang.Object getTableIds();

• Type: com.aliyun.ros.cdk.core.IResolvable OR java.util.List

Property tableIds: Table IDs to import when creating the knowledge base.