jina.types.sets.chunk

class jina.types.sets.chunk.ChunkSet(docs_proto, reference_doc)[source]

Bases: jina.types.sets.document.DocumentSet

ChunkSet inherits from DocumentSet. It’s a subset of Documents.

Parameters

  • docs_proto (Document) – Set of sub-documents (i.e chunks) of reference_doc

  • reference_doc (Document) – Reference Document for the sub-documents

Set constructor method.

Parameters

  • docs_proto – protobuf representation of the chunks

  • reference_doc (Document) – parent document

append(document, **kwargs)[source]

Add a sub-document (i.e chunk) to the current Document.

Parameters

  • document (Document) – Sub-document to be appended

  • kwargs – additional keyword arguments

Returns

the newly added sub-document in Document view

Return type

Document

Note

Comparing to DocumentSet.append(), this method adds more safeguard to make sure the added chunk is legit.

extend(iterable)[source]

Extend the DocumentSet by appending all the items from the iterable.

Parameters

iterable (Iterable[ForwardRef]) – the iterable of Documents to extend this set with

Return type

None

property reference_doc

Get the document that ChunkSet belongs to.

Return type

Document

Returns

reference doc

property granularity

Get granularity of all document in this set.

Return type

int

Returns

granularity

property adjacency

Get adjacency of all document in this set.

Return type

int

Returns

adjacency