public static interface ProcessOptions.LayoutConfig.ChunkingConfigOrBuilder extends MessageOrBuilderImplements
MessageOrBuilderMethods
getBreakpointPercentileThreshold()
public abstract int getBreakpointPercentileThreshold()Optional. The percentile of cosine dissimilarity that must be exceeded between a group of tokens and the next. The smaller this number is, the more chunks will be generated. THIS FIELD IS NOT YET USED.
int32 breakpoint_percentile_threshold = 4 [(.google.api.field_behavior) = OPTIONAL];
| Returns | |
|---|---|
| Type | Description |
int |
The breakpointPercentileThreshold. |
getChunkSize()
public abstract int getChunkSize()Optional. The chunk sizes to use when splitting documents, in order of level.
int32 chunk_size = 1 [(.google.api.field_behavior) = OPTIONAL];
| Returns | |
|---|---|
| Type | Description |
int |
The chunkSize. |
getIncludeAncestorHeadings()
public abstract boolean getIncludeAncestorHeadings()Optional. Whether or not to include ancestor headings when splitting.
bool include_ancestor_headings = 2 [(.google.api.field_behavior) = OPTIONAL];
| Returns | |
|---|---|
| Type | Description |
boolean |
The includeAncestorHeadings. |
getSemanticChunkingGroupSize()
public abstract boolean getSemanticChunkingGroupSize()Optional. The number of tokens to group together when evaluating semantic similarity. THIS FIELD IS NOT YET USED.
bool semantic_chunking_group_size = 3 [(.google.api.field_behavior) = OPTIONAL];
| Returns | |
|---|---|
| Type | Description |
boolean |
The semanticChunkingGroupSize. |