Skip to main content
POST
/
v1
/
projects
/
{project_id}
/
parse
/
{parse_result_id}
/
rechunk
Create Chunk Job
curl --request POST \
  --url https://api.example.com/v1/projects/{project_id}/parse/{parse_result_id}/rechunk \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --header 'x-selected-account-id: <api-key>' \
  --data '
{
  "chunking_options": {
    "strategy": "token_size",
    "chunk_size": 512,
    "chunk_overlap": 50,
    "encoding_name": "cl100k_base"
  }
}
'
{
  "id": "<string>",
  "project_id": "<string>",
  "operation": "parse",
  "status": "pending",
  "created_at": "2023-11-07T05:31:56Z",
  "object": "job",
  "source_id": "<string>",
  "correlation_id": "<string>",
  "started_at": "2023-11-07T05:31:56Z",
  "completed_at": "2023-11-07T05:31:56Z",
  "result": {},
  "error": "<string>",
  "history": [
    {
      "step": "<string>",
      "timestamp": "2023-11-07T05:31:56Z",
      "duration_ms": 123,
      "status": "<string>",
      "details": {}
    }
  ]
}

Authorizations

​
x-api-key
string
header
required

API key for authentication

​
x-selected-account-id
string
header
required

Selected Account ID

Path Parameters

​
project_id
string
required
​
parse_result_id
string
required

Body

application/json

Request model for rechunking a parse result.

​
chunking_options
TokenSizeChunkingOptions · object
required

Token-based chunking: Splits text into chunks by token count using a tokenizer (e.g., tiktoken). Best for LLM APIs with token limits, embedding models, and cost optimization. Use when you need precise control over token usage.

Response

Successful Response

Job response model representing an asynchronous operation.

​
id
string
required

ID of the entity

​
project_id
string
required

ID of the project

​
operation
enum<string>
required

Operation type (e.g., 'parse')

Available options:
parse,
extract,
vector_store,
chunk
​
status
enum<string>
required

Current job status

Available options:
pending,
running,
succeeded,
failed
​
created_at
string<date-time>
required

When the job was created

​
object
string
default:job
Allowed value: "job"
​
source_id
string | null

Source document/file ID

​
correlation_id
string | null

Request correlation ID for tracing

​
started_at
string<date-time> | null

When the job started processing

​
completed_at
string<date-time> | null

When the job completed

​
result
Result · object

Job result payload when completed

​
error
string | null

Error message if job failed

​
history
JobHistoryEvent · object[] | null

Timeline of job execution events