Chunking, Embeddings, and Indexing
Indexing prepares parsed content for retrieval. It divides content into chunks, creates embeddings, and writes searchable records. These stages occur after upload or source synchronization.
Before you begin
An accessible knowledge base and source files that can be parsed.
How indexing works
Chunk
A piece of source content stored or passed as a retrieval unit. Its boundaries affect how much surrounding evidence appears in a result.
Embedding
A numerical representation used for similarity-based search. It supports semantic matching; it is not the source document or a citation.
Index
Searchable records prepared from source content. A file must complete required processing before the index can return its content.
Parsing
Extraction of usable text or structure from source content. Review the extracted content when the workflow misses text, tables, or locations.
Configuration options
Chunk overlap
Content shared between adjacent chunks.
It can preserve continuity while also creating repeated passages in results.
Configure document indexing
Review the knowledge base’s chunking, OCR, and embedding settings.
Choose supported processing settings before ingestion. If the interface permits a later change, follow its reprocessing instructions.

Open Update Settings before ingestion and review the available processing controls.
Wait for those files to reach a usable indexed state, then inspect retrieval results.
Search returns relevant pieces of the indexed source material.
Behavior and limitations
Chunk size affects how much context appears in each result. Small chunks can lose surrounding context; large chunks can add irrelevant text. Some processing settings become read-only after ingestion. Review them before uploading. If reprocessing is available, confirm completion before expecting retrieval to reflect the new settings.
Related resources
Was this helpful?

