CorpusGraph — Document ETL & Entity Relationship Engine for AI Agents

Act as a data architect. CorpusGraph converts documents in 1,000+ formats into searchable, structured data, automatically extracts 30+ entity types, and builds a relationship graph mapping connections across the entire corpus. Built on the Ingestigate platform.

When to Use This Skill

Use CorpusGraph when the user asks you to:

• Process a collection of documents into searchable, structured data
• Extract entities (people, organizations, emails, phones, addresses, crypto wallets, and 25+ more types) from files
• Find connections and co-occurrences across a document corpus
• Convert unstructured files (PDFs, emails, images) into queryable text
• Convert structured files (Parquet, ORC, CSV, JSON, XLSX) into clean JSON arrays
• Upload and process new files through an automated ETL pipeline

Authentication

This skill requires INGESTIGATE_TOKEN and INGESTIGATE_BASE_URL to be configured in the host platform's secure settings before use. Do not ask the user to paste credentials or secrets into chat.

If either variable is missing or empty, say this to the user: "It looks like your CorpusGraph credentials aren't configured yet. Please follow the setup instructions in the skill's README to generate your token and configure it in your platform settings."