Execute Pipeline

Execute a pipeline on text or file input

Execute Pipeline

cURL

curl --request POST \
  --url https://api.example.com/v1/pipeline/{slug}

200

{
  "chunks": [
    {
      "text": "<string>",
      "start_index": 123,
      "end_index": 123,
      "token_count": 123,
      "context": "<string>",
      "embedding": [
        {}
      ]
    }
  ]
}

Run a saved pipeline to process text or documents and return chunks.

Examples

Python

from chonkie.cloud import Pipeline

# Execute with text
pipeline = Pipeline.get("my-rag-pipeline")
chunks = pipeline.run(text="Your document text here...")

# Execute with multiple texts
chunks = pipeline.run(text=["First document", "Second document"])

# Execute with file (auto-uploaded)
chunks = pipeline.run(file="document.pdf")

# Access chunk data
for chunk in chunks:
    print(f"Text: {chunk.text[:100]}...")
    print(f"Tokens: {chunk.token_count}")

Path Parameters

slug · string · required

The pipeline slug to execute.

Request

text · string | array

Text content to process. Can be a single string or array of strings.

file · object

File reference for document processing. Use after uploading via the file upload endpoint.

Show child attributes

type · string

File type (e.g., “document”).

content · string

The uploaded filename or file reference.

Provide either text or file, not both.

Response

chunks · array

Array of chunk objects returned by the pipeline.

Show child attributes

text · string

The chunk text content.

start_index · integer

Starting character index in the original text.

end_index · integer

Ending character index in the original text.

token_count · integer

Number of tokens in the chunk.

context · string

Optional context added by refinement steps.

embedding · array

Optional embedding vector if embeddings step was included.

Errors

Status	Description
400	Invalid request (missing text/file or both provided)
404	Pipeline not found
422	Processing error