Web Crawler & Document Ingestion

Automatically crawl documentation websites, scrape sitemaps, or ingest PDF files into Pinecone embeddings.

Extracts clean markdown from documentation portals, blogs, and help desks.

Headless Chrome

Connected

Connected

Available

Source URL / File	Type	Vectors	Status	Action
https://docs.cloudcorp.io/api/v2	Web Scraper	840 chunks	Complete
Security-Whitepaper-v3.pdf	Document	420 chunks	Complete

Tokenizer Model

Chunk Overlap

Distance Metric