Skip to main content
POST
/
v2
/
chunking
cURL
curl --request POST \
  --url https://api.orq.ai/v2/chunking \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "text": "The quick brown fox jumps over the lazy dog. This is a sample text that will be chunked into smaller pieces. Each chunk will maintain context while respecting the maximum chunk size.",
  "strategy": "semantic",
  "chunk_size": 256,
  "threshold": 0.8,
  "embedding_model": "openai/text-embedding-3-small",
  "mode": "window",
  "similarity_window": 1,
  "metadata": true
}'
{
  "chunks": [
    {
      "id": "01HQ3K4M5N6P7Q8R9SATBVCWDX",
      "text": "The quick brown fox jumps over the lazy dog.",
      "index": 0,
      "metadata": {
        "start_index": 0,
        "end_index": 44,
        "token_count": 10
      }
    },
    {
      "id": "01HQ3K4M5N6P7Q8R9SATBVCWDY",
      "text": "This is a sample text that will be chunked into smaller pieces.",
      "index": 1,
      "metadata": {
        "start_index": 45,
        "end_index": 108,
        "token_count": 12
      }
    }
  ]
}

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
  • Token Chunker Strategy
  • Sentence Chunker Strategy
  • Recursive Chunker Strategy
  • Semantic Chunker Strategy
  • Agentic Chunker Strategy

Request payload for text chunking with strategy-specific configuration Splits text based on token count. Best for ensuring chunks fit within LLM context windows and maintaining consistent chunk sizes for embedding models.

text
string
required

The text content to be chunked

strategy
enum<string>
required
Available options:
token
metadata
boolean
default:true

Whether to include metadata for each chunk

return_type
enum<string>
default:chunks

Return format: chunks (with metadata) or texts (plain strings)

Available options:
chunks,
texts
chunk_size
integer
default:512

Maximum tokens per chunk

Required range: x > 0
chunk_overlap
integer
default:0

Number of tokens to overlap between chunks

Required range: x >= 0

Response

200 - application/json

Text successfully chunked

chunks
object[]
required