Skip to main content
Semantic Chunker
curl --request POST \
  --url https://api.example.com/v1/chunk/semantic
{
  "text": "<string>",
  "start_index": 123,
  "end_index": 123,
  "token_count": 123
}
The Semantic Chunker uses embeddings to identify natural break points in text based on semantic meaning, creating chunks where topic transitions occur.

​
Examples

​
Text Input

from chonkie.cloud import SemanticChunker

chunker = SemanticChunker(
    embedding_model="minishlab/potion-base-8M",
    chunk_size=512,
)

text = "Your text here..."
chunks = chunker.chunk(text)

​
File Input

from chonkie.cloud import SemanticChunker

chunker = SemanticChunker(
    embedding_model="minishlab/potion-base-8M",
    chunk_size=512,
)

# Chunk from file
with open("document.txt", "rb") as f:
    chunks = chunker.chunk(file=f)

​
Request

​
Parameters

​
text
string | string[]
The text to chunk. Can be a single string or an array of strings for batch processing. Either text or file is required.
​
file
file
File to chunk. Use multipart/form-data encoding. Either text or file is required.
​
embedding_model
string
default:"minishlab/potion-base-8M"
The embedding model to use to detect semantic similarity.
​
tokenizer
string
default:"gpt2"
Tokenizer to use for counting tokens.
​
chunk_size
integer
default:"512"
Target number of tokens per chunk (soft limit).
​
threshold
float
default:"0.8"
Threshold for semantic similarity (0-1). Lower values create more chunks.
​
min_sentences_per_chunk
integer
default:"1"
Minimum number of sentences per chunk.

​
Response

​
Returns

Array of Chunk objects with semantically coherent text segments.
​
text
string
The chunk text content.
​
start_index
integer
Starting character position in the original text.
​
end_index
integer
Ending character position in the original text.
​
token_count
integer
Number of tokens in the chunk.