Training Data

Supercharge all of Pylon’s AI features by connecting training data for the AI to consume.

Pylon’s many AI features, like Ask AI, Copilot for Issues, AI Agents, Federated Search, and more all benefit from having access to more information.

By default, they have access to your past Pylon issues and your Pylon Knowledge base. Make them even more powerful by connecting any external sources of knowledge you have!

Setup

1. Go to the Training Data page in Settings and click “Import Data”.
2. Select a method of importing data and follow the instructions.

• Your Pylon knowledge base and past issues will be enabled by default and reindexed live
• Public URLs to individual webpages or a base url to crawl that will be reindexed every 7 or 30 days depending on your Pylon plan. Examples may include:
  • Public-facing documentation not hosted by Pylon
  • Public Google docs
  • Public GitHub repos
  • Your marketing website or pricing page
• Give Pylon a few moments to automatically scrape and index all your content

This data is now available to power all your AI features!

API Integration

For programmatic data ingestion, Pylon provides Training Data APIs that allow you to upload documents directly without publishing them to the public internet.

Upload Files

Endpoint: POST /training-data/upload

Upload files to a new or existing training data source via multipart form upload.

Parameter	Required	Description
training_data_id	No	ID of an existing data source to append to
training_data_name	Yes (for new sources)	Name for the new training data source
visibility	No	Access control: everyone, ai_agent_only, or user_only
files	Yes	One or more files to upload

Limits: Maximum 100MB per file, 500MB total per request.

Upload Text Content

Endpoint: POST /training-data/upload-content

Upload text content directly as a file to a new or existing training data source.

Parameter	Required	Description
training_data_id	No	ID of an existing data source to append to
training_data_name	Yes (for new sources)	Name for the new training data source
content	Yes	Text content to upload (max 100MB)
file_name	Yes	Name for the uploaded file
visibility	No	Access control setting
external_id	No	For idempotent updates—matches existing documents

Supports form-encoded, JSON, and Zapier POST requests.

Key Behaviors

• New sources: When no training_data_id is provided, a new training data source is created
• Appending: When an ID is supplied, content is appended to the existing source
• Idempotent updates: Use external_id to update existing documents without creating duplicates

Automation

Zapier integration is available for automated document routing as your content updates. This allows you to automatically sync documents to Pylon as they change in your source systems.

For full API details, see the Training Data APIs support article.