ReferenceSchemas
Chunk
Reference for the arke/chunk@v1 profile -- text fragments for RAG and semantic search.
Profile
arke/chunk@v1
Required Properties
| Property | Type | Description |
|---|---|---|
label | string | Chunk identifier (e.g. "Chunk 0") |
content | string | Text content of the chunk |
sequence | number | Order within the parent file |
Optional Properties
| Property | Type | Description |
|---|---|---|
embedding_status | string | pending / complete |
token_count | number | Number of tokens in the chunk |
Relationships
| Predicate | Peer Type | Required | Description |
|---|---|---|---|
parent | file | Yes | Source file this chunk was extracted from |
Usage
Chunks are created automatically by the chunking pipeline when files are processed. They enable:
- Semantic search -- Each chunk is independently embedded and indexed in Pinecone
- RAG -- Relevant chunks are retrieved and passed to LLMs as context
- Granular discovery -- Find specific passages within large documents