Settings

Configure your newsroom application

API Configuration

Google AI Studio API Key

Required for embeddings and article generation (get from aistudio.google.com)

Google Model

e.g., gemini-1.5-flash, gemini-1.5-pro

Automatic Crawler Scheduler

Configure periodic crawling to automatically fetch new articles

Enable Periodic Crawling

When enabled, the crawler runs automatically at the specified interval

Crawl Interval (minutes)

How often to automatically crawl for new articles (scheduler checks this interval)

Max Articles per Run

Maximum number of articles to fetch during each scheduled crawl

Note: Cookies and source-specific configurations are now managed in the News Sources page.

Automatic Clustering Scheduler

Configure periodic clustering to automatically group articles into topics

Enable Periodic Clustering

When enabled, clustering runs automatically at the specified interval

Clustering Interval (minutes)

How often to automatically run clustering analysis

Clustering Parameters

Fine-tune clustering behavior and similarity thresholds

Minimum Articles per Cluster

Similarity Threshold

Higher values create tighter clusters

Article Generation Configuration

Temperature

Higher values = more creative output

Max Words

Maximum word count for generated articles

Database Configuration

Database Host

Configure via environment variable

Database Port

Configure via environment variable

Pipeline Scheduler Info

The pipeline scheduler runs as a background service and manages multiple automated jobs.

How it works:

Reads settings from Redis periodically
Enqueues crawler and clustering jobs when enabled
Respects individual interval settings for each pipeline
Changes take effect on next cycle

Save your settings to apply them immediately.

System Information

Version

1.0.0

API Status

Online

Database Status

Connected

Redis Status

Connected

Documentation

Learn more about configuring and using the newsroom application.

View Documentation