latest--SentenceTransformersTokenTextSplitter
shared| Type | object |
|---|---|
| Schema URL | https://catalog.lintel.tools/schemas/schemastore/eidolon-resource/_shared/latest--SentenceTransformersTokenTextSplitter.json |
| Parent schema | eidolon-resource |
Type:
object
Properties
implementation
const: "SentenceTransformersTokenTextSplitter"
required
chunk_size
integer
Maximum size of chunks to return
chunk_overlap
integer
keep_separator
boolean
Whether to keep the separator in the chunks
strip_whitespace
boolean
If True, strips whitespace from the start and end of every document
model
string
Model name
tokens_per_chunk
integer | null
Number of tokens per chunk