POST
/
v1
/
chunk
/
recursive
curl --request POST \
  --url https://api.chonkie.ai/v1/chunk/recursive \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form tokenizer_or_token_counter=gpt2 \
  --form chunk_size=512 \
  --form recipe=default \
  --form lang=en \
  --form min_characters_per_chunk=12 \
  --form return_type=chunks
[
  {
    "text": "<string>",
    "start_index": 123,
    "end_index": 123,
    "token_count": 123,
    "level": 123
  }
]

Authorizations

​
Authorization
string
header
required

Your API Key from the Chonkie Cloud dashboard

Body

multipart/form-data
​
file
file

The file to chunk.

​
tokenizer_or_token_counter
string
default:gpt2

Tokenizer or token counting function to use. Can be a string identifier or an instance.

​
chunk_size
integer
default:512

Maximum number of tokens per chunk.

​
recipe
string
default:default

Pre-defined rules for chunking. Find all recipes on our Hugging Face Hub.

​
lang
string
default:en

Language of the text, used with recipes. Must match the language of the recipe.

​
min_characters_per_chunk
integer
default:12

Minimum number of characters per chunk.

​
return_type
enum<string>
default:chunks

Whether to return chunks as text strings or as RecursiveChunk objects.

Available options:
texts,
chunks

Response

200 - application/json
Successful Response: A list of `RecursiveChunk` objects.
​
text
string

The actual text content of the chunk.

​
start_index
integer

The starting character index of the chunk within the original input text.

​
end_index
integer

The ending character index (exclusive) of the chunk within the original input text.

​
token_count
integer

The number of tokens in this specific chunk, according to the tokenizer used.

​
level
integer

The level of this chunk in the recursive splitting process (starts from 0).