Chunk(mapping=None, *, ignore_unknown_fields=False, **kwargs)Chunk captures all raw metadata information of items to be recommended or searched in the chunk mode.
.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields
Attributes |
|
|---|---|
| Name | Description |
name |
str
The full resource name of the chunk. Format: projects/{project}/locations/{___location}/collections/{collection}/dataStores/{data_store}/branches/{branch}/documents/{document_id}/chunks/{chunk_id}.
This field must be a UTF-8 encoded string with a length
limit of 1024 characters.
|
id |
str
Unique chunk ID of the current chunk. |
content |
str
Content is a string from a document (parsed content). |
relevance_score |
float
Output only. Represents the relevance score based on similarity. Higher score indicates higher chunk relevance. The score is in range [-1.0, 1.0]. Only populated on SearchResponse. This field is a member of oneof_ _relevance_score.
|
document_metadata |
google.cloud.discoveryengine_v1.types.Chunk.DocumentMetadata
Metadata of the document from the current chunk. |
derived_struct_data |
google.protobuf.struct_pb2.Struct
Output only. This field is OUTPUT_ONLY. It contains derived data that are not in the original input document. |
page_span |
google.cloud.discoveryengine_v1.types.Chunk.PageSpan
Page span of the chunk. |
chunk_metadata |
google.cloud.discoveryengine_v1.types.Chunk.ChunkMetadata
Output only. Metadata of the current chunk. |
data_urls |
MutableSequence[str]
Output only. Image Data URLs if the current chunk contains images. Data URLs are composed of four parts: a prefix (data:), a MIME type indicating the type of data, an optional base64 token if non-textual, and the data itself: data:[][;base64], |
annotation_contents |
MutableSequence[str]
Output only. Annotation contents if the current chunk contains annotations. |
annotation_metadata |
MutableSequence[google.cloud.discoveryengine_v1.types.Chunk.AnnotationMetadata]
Output only. The annotation metadata includes structured content in the current chunk. |
Classes
AnnotationMetadata
AnnotationMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)The annotation metadata includes structured content in the current chunk.
ChunkMetadata
ChunkMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)Metadata of the current chunk. This field is only populated on SearchService.Search API.
DocumentMetadata
DocumentMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)Document metadata contains the information of the document of the current chunk.
PageSpan
PageSpan(mapping=None, *, ignore_unknown_fields=False, **kwargs)Page span of the chunk.
StructureType
StructureType(value)Defines the types of the structured content that can be extracted.
StructuredContent
StructuredContent(mapping=None, *, ignore_unknown_fields=False, **kwargs)The structured content information.