Skip to main content
Data Ingestion

Document Management and Parsing

Upload documents, view parsing results, and manage chunks

Documents serve as the content source for your knowledge base. After uploading, the system automatically performs parsing, chunking, vectorization, and index building.

Importing Data

1

Navigate to the Knowledge Base Details Page

Click the target knowledge base name on the Knowledge Management page.
2

Click Upload Data

Click Upload Data above the document list to begin the import process.
3

Select Data Source

Select a connector (default is “Default File Connector”), then choose your data source:
Data SourceDescription
Upload Files (default)Upload local files via the web interface; up to 50 files per batch. Supported formats and size limits are listed in Supported Formats.
Select CategoryChoose a file category from the connector; imports all files under that category and builds indexes. Supports automatic synchronization.
Select FilesManually select individual files from within a connector category; up to 50 files per batch.
Additional configuration options:
  • Category Configuration (required): Select the category to which the files belong, or click Add Category to create a new one.
  • Add Tags (optional): Assign tags to the imported files. Each tag may contain up to 32 characters.
4

Configure Index Settings

Click Next, then select a chunking method and segmentation parameters:
Chunking MethodDescription
Smart Chunking (default)A robust general-purpose method optimized for most document types, delivering strong retrieval performance across diverse content.
By LengthSuitable for scenarios with strict token count requirements.
By PageIdeal for documents where each page conveys an independent topic.
By HeadingBest for documents structured with clear headings demarcating distinct topics.
By Regular ExpressionSplits text using a custom regular expression.
By DelimiterSplits text based on specific delimiters present in the document.
ParameterDefault ValueRangeDescription
Maximum Chunk Length60010–6000Maximum number of tokens per chunk.
Metadata ExtractionOffOn/OffAutomatically extracts document metadata.
Excel Header ConcatenationOffOn/OffAppends Excel header information into chunk content.
5

Complete Import

Click Finish. The system automatically executes parsing, chunking, and index building. Once the document status changes to Parsing Completed, it becomes searchable.

Supported Formats

TypeExtensionsSize LimitsNotes
Documents.doc, .docx, .ppt, .pptx, .pdf≤ 150 MB or ≤ 1000 pagesElectronic PDFs are parsed directly; scanned PDFs undergo automatic OCR.
Spreadsheets.xls, .xlsxRecommended ≤ 10 MB and ≤ 100,000 rowsChunks are generated row-by-row; first row is treated as column headers.
Images.png, .jpg, .jpeg, .bmp, .gifSingle image ≤ 20 MB; shortest side > 15 px; longest side < 8192 px; aspect ratio < 50Used for mixed text-and-image scenarios.
Plain Text.md, .txt, .htmlRecommended ≤ 10 MBMarkdown files are chunked by heading; HTML content automatically strips <script> and <style> elements.

Document Status

StatusMeaningRecommended Action
UploadingFile transfer in progressWait
ParsingExtracting structure & text, chunking, generating vectorsWait
Parsing CompletedIndex built successfully; document is searchableNo action required
FailedParsing or indexing failedReview error details and re-upload after correction

Chunk Management

Navigate to the knowledge base details page and switch to the Chunk Details tab to view and manage all chunks. Each chunk displays:
  • ID and character count
  • Preview of chunk content
  • Associated document
  • Enable/Disable toggle
You can filter chunks by document using the All Files dropdown, or search by keyword using the search bar.

Creating a Chunk

Click Create Chunk, then fill in the following fields as needed:
FieldConstraintsDescription
Associated DocumentRequiredSelect from already-uploaded documents.
Chunk Title0–50 charactersDisplayed in the chunk list.
ImageSupports .png, .jpg, .bmp, .gif; ≤ 20 MB per imageOptional; used for mixed text-and-image chunks.
Chunk ContentRequired; 0–6000 charactersMain body of the chunk.
After submission, the chunk is automatically vectorized and immediately becomes searchable.

Chunk Operations

Each chunk supports the following actions:
ActionDescription
Chunk DetailsView full content and properties of the chunk.
View OriginalNavigate to the original document context containing this chunk.
DeleteImmediately removes the chunk from the index—irreversible.
Enable/DisableToggle whether this chunk participates in search results.

Document Operations

Each document in the document list supports the following operations:
ActionDescription
View ChunksNavigate to the chunk details page for this document.
MetadataView or edit the document’s metadata.
TagsAdd or manage tags for the document (accessible via the More menu).
DeleteDelete the document and all its associated chunks—irreversible (available in the More menu).
Batch OperationsSelect multiple files using checkboxes at the top, then perform bulk actions.
Deleting a document is irreversible. Previously returned search results remain unaffected, but subsequent queries will no longer retrieve chunks from the deleted document.

API Management

APIs related to document management:
After uploading documents, adjust your chunking and vectorization strategy to optimize retrieval quality.