Skip to main content
{
  "id": "<string>",
  "slug": "<string>",
  "description": "<string>",
  "organization_slug": "<string>",
  "steps": [
    {}
  ],
  "created_at": "<string>",
  "updated_at": "<string>"
}
Create a reusable pipeline configuration that can be executed multiple times with different inputs.

​
Examples

from chonkie.cloud import Pipeline

pipeline = Pipeline(
    slug="my-rag-pipeline",
    description="Pipeline for RAG processing"
).chunk_with("recursive", chunk_size=512).refine_with("overlap", context_size=64)

# Pipeline is auto-saved on first run
chunks = pipeline.run(text="Your document text here")

​
Request

​
slug
string
required
Unique identifier for the pipeline. Must contain only lowercase letters, numbers, dashes, and underscores.
​
description
string
Optional description of the pipeline’s purpose.
​
steps
array
required
Array of pipeline step configurations. Must include at least one chunk step.Each step object contains:
  • type: Step type (process, chunk, or refine)
  • component: Component name (e.g., recursive, overlap, embeddings)
  • Additional parameters specific to the component

​
Response

​
id
string
Unique identifier for the pipeline.
​
slug
string
The pipeline slug.
​
description
string
Pipeline description.
​
organization_slug
string
Organization that owns the pipeline.
​
steps
array
Array of pipeline step configurations.
​
created_at
string
ISO 8601 timestamp of creation.
​
updated_at
string
ISO 8601 timestamp of last update.

​
Errors

StatusDescription
409Pipeline with this slug already exists
422Invalid slug format or missing required fields