Class DocumentChunk
Contents
[
Hide
]DocumentChunk class
Represents a single chunk of content extracted from a document.
public sealed class DocumentChunk
Constructors
| Name | Description |
|---|---|
| DocumentChunk(string, string, int, string) | Initializes a new instance of the DocumentChunk class. |
Properties
| Name | Description |
|---|---|
| Content { get; } | Gets the text content of the chunk. |
| Context { get; } | Gets the structural context of this chunk, typically the header path indicating where this chunk appears in the document hierarchy. |
| Embedding { get; set; } | Gets or sets the embedding vector for this chunk. |
| Id { get; } | Gets the unique identifier of the chunk. |
| Index { get; } | Gets the zero-based index of the chunk within the document. |
| Metadata { get; } | Gets the metadata associated with this chunk. |
Methods
| Name | Description |
|---|---|
| static GetVectorDefinition(int) | Returns a VectorStoreCollectionDefinition describing the schema of DocumentChunk for use with a vector store collection. |
Remarks
Document chunks are the fundamental units used for AI processing, embedding generation, and vector indexing operations.
See Also
- namespace Aspose.Pdf.AI
- assembly Aspose.PDF