II.
SkillArea overview
Reference · liveskill-area:document-indexing
Document Indexing overview
Document processing, chunking, and embedding for search and retrieval — parsing PDFs/HTML/markdown, semantic boundary detection, embedding model selection, index construction, and metadata extraction. The foundation layer that feeds all retrieval pipelines in the knowledge fabric.
Attributes
displayName
Document Indexing
description
Document processing, chunking, and embedding for search and
retrieval — parsing PDFs/HTML/markdown, semantic boundary
detection, embedding model selection, index construction,
and metadata extraction. The foundation layer that feeds
all retrieval pipelines in the knowledge fabric.
domains
expertiseLevels
- novice
- intermediate
- expert
Outgoing edges
applies_to2
- specialization:ai-agents-conversational·Specialization
- domain:software-engineering·DomainSoftware Engineering
prerequisite_for_learning2
- skill-area:embedding-optimization·SkillAreaEmbedding Optimization
- skill-area:knowledge-graph-management·SkillAreaKnowledge Graph Management
uses_library1
- library:llama-index·LibraryLlamaIndex
Incoming edges
contains1
- specialization:search-infrastructure·Specialization
library_used_by1
- library:llama-index·LibraryLlamaIndex