Pipelines

🛑Alpha

OpenTelemetry support is currently in alpha and may undergo significant changes.

Pipelines

The pipelines SDK provides programmatic access to Gentrace pipelines. Pipelines are the top-level organizational unit that contains datasets, experiments, and traces.

Overview

The SDK is built by Stainless and provides type-safe access to Gentrace entities. The pipelines object exposes methods to create, retrieve, update, and list pipelines.

Basic usage

TypeScript

typescript
import { init, pipelines } from 'gentrace';
init({
  apiKey: process.env.GENTRACE_API_KEY,
});
// List pipelines
const pipelineList = await pipelines.list();
// Access the pipelines
for (const pipeline of pipelineList.data) {
  console.log(pipeline.slug);
  console.log(pipeline.displayName);
}

Python

python
import os
from gentrace import init, pipelines
init(api_key=os.environ["GENTRACE_API_KEY"])
# List pipelines
pipeline_list = await pipelines.list()
# Access the pipelines
for pipeline in pipeline_list.data:
    print(pipeline.slug)
    print(pipeline.display_name)

Pipeline structure

Each pipeline contains:

• id: Unique identifier (UUID)
• slug: URL-friendly unique identifier
• displayName: Optional human-readable name
• folderId: Optional folder UUID for organization
• goldenDatasetId: UUID of the golden dataset (if set)
• archivedAt: Timestamp when archived (null if active)
• createdAt: Creation timestamp
• updatedAt: Last update timestamp

Resource methods

Create a pipeline

TypeScript

typescript
const pipeline = await pipelines.create({
  slug: 'customer-support-ai',
  displayName: 'Customer Support AI Pipeline',
  folderId: 'folder-uuid', // optional
});

Python

python
pipeline = await pipelines.create(
    slug="customer-support-ai",
    display_name="Customer Support AI Pipeline",
    folder_id="folder-uuid",  # optional
)

Retrieve a pipeline

TypeScript

typescript
const pipeline = await pipelines.retrieve('pipeline-id');
console.log(pipeline.slug);

Python

python
pipeline = await pipelines.retrieve("pipeline-id")
print(pipeline.slug)

Update a pipeline

TypeScript

typescript
const pipeline = await pipelines.update('pipeline-id', {
  displayName: 'Updated Pipeline Name',
  isArchived: false,
});

Python

python
pipeline = await pipelines.update(
    "pipeline-id",
    display_name="Updated Pipeline Name",
    is_archived=False,
)

List with filters

TypeScript

typescript
// Filter by folder or slug
const pipelineList = await pipelines.list({
  folderId: 'folder-id',
  slug: 'customer-support', // exact match or use advanced filters
});

Python

python
# Filter by folder or slug
pipeline_list = await pipelines.list(
    folder_id="folder-id",
    slug="customer-support",  # exact match
)

Usage in AI workflows

Pipelines are used throughout Gentrace to organize your AI workflows:

TypeScript

typescript
// Use pipeline ID with interaction()
const tracedFunction = interaction('My AI Function', myAIFunction, {
  pipelineId: pipeline.id,
});
// Use pipeline ID with experiment()
experiment(pipeline.id, async () => {
  // Your experiment code
});

Python

python
# Use pipeline ID with interaction()
@interaction(pipeline_id=pipeline.id, name="My AI Function")
async def traced_function():
    # Your AI function code
    pass
# Use pipeline ID with experiment()
@experiment(pipeline_id=pipeline.id)
async def my_experiment():
    # Your experiment code
    pass

See also

• Pipelines API Reference - Full API documentation
• Datasets - Managing datasets within pipelines
• Experiments - Running experiments on pipelines
• interaction() - Tracing functions within pipelines
• experiment() - Creating experiments for pipelines