Chunk Text Node

C

AI/Preprocessing

Chunk Text

Splits long text into sized/overlapping chunks using the cached embedding model's splitter

chunk_textllmLong running

Inputs6

Outputs2

Security exposure1/10

Packagellm

Ratings

Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.

SecurityAttack surface and exposure impact.

1/10High

PrivacyPotential sensitivity of processed data.

1/10High

PerformanceRuntime or resource pressure.

2/10High

GovernancePolicy, audit, or compliance impact.

1/10High

ReliabilityOperational stability considerations.

2/10High

CostExternal or compute cost impact.

0/10High

Input Pins

6

Input

Execution

exec_in

Execution trigger

Text

String

text

Source string that needs chunking

Model

Struct

model

Cached embedding Bit providing the tokenizer/splitter

SchemaCachedEmbeddingModelCachedEmbeddingModelCachedEmbeddingModel2 fields

cache_keystringrequired

model_typeBitTypesrequired

enum "Llm", "Vlm", "Tts", "Stt"...

Schema enforced

Capacity

Integer

capacity

Max characters/tokens in each chunk

Default 512

Overlap

Integer

overlap

How many characters/tokens overlap between consecutive chunks

Default 20

Markdown

Boolean

markdown

Use a Markdown-aware splitter (true) or the plain splitter

Default true

Output Pins

2

Output

Execution

exec_out

Fires once chunking completes

Chunks

String Array

chunks

Array of chunked text segments

Node Info

Internal name

chunk_text

Category

AI/Preprocessing