load_document
Load PDF, text, or markdown documents into the knowledge graph and automatically extract business rules for validation.
Instructions
Load a document (PDF, Text, Markdown) into the knowledge graph and automatically extract business rules.
Usage:
Load a file: load_document(file_path='/path/to/rules.pdf')
Upload content: load_document(content='Rule 1:...', title='My Rules')
What it does:
Parses the document
Stores metadata in the graph
Analyzes content with LLM to extract business rules
Saves extracted rules as 'PENDING' for validation
Options:
store_content: Set to True to save full text in graph
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | URL of the document (not yet implemented) | |
| title | No | Title of the document (optional, auto-detected if file) | |
| prefix | No | Prefix to add to extracted rule IDs (e.g., 'HR_', 'GDPR_') | |
| content | No | Direct text content to load | |
| file_path | No | Absolute path to the document file (PDF, TXT, MD) | |
| extract_rules | No | Whether to automatically extract rules using LLM | |
| store_content | No | Whether to store the full text content in the knowledge graph |