Enterprise Knowledge

Profile: general · Model: DEFAULT (gpt-5.6-terra) · Chunking: paragraph · Confidence: ≥ 0.65

Overview

The general profile is the catch-all for enterprise knowledge management — SharePoint libraries, Confluence spaces, mixed-domain document repositories. It extracts people, organisations, locations, products, events, and concepts to populate enterprise knowledge graphs.

Extracted entities

Entity type	Examples
Person	Employee names, contacts, stakeholders
Organisation	Companies, departments, business units
Location	Offices, regions, addresses
Product	Products, services, platforms
Event	Meetings, milestones, launches
Policy	Internal policies, compliance rules
Concept	Domain-specific terms and definitions
Date	Dates mentioned in documents
Value	Monetary amounts, percentages, quantities
Reference	Document IDs, codes, identifiers
Document	Referenced documents and attachments

Extracted relationships

HAS_DATE · HAS_VALUE · IDENTIFIED_BY · REFERENCES · RELATES_TO · PART_OF

Connector-driven workflows

Enterprise knowledge management typically uses connectors rather than individual file uploads:

SharePoint sync

curl -X POST http://localhost:8200/connectors/sync/sharepoint \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "site_url": "https://myorg.sharepoint.com/sites/mysite",
    "library": "Documents",
    "profile": "general",
    "recursive": true
  }'

Confluence sync

curl -X POST http://localhost:8200/connectors/sync/confluence \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "base_url": "https://myorg.atlassian.net/wiki",
    "space_key": "ENG",
    "profile": "general"
  }'

S3 sync

curl -X POST http://localhost:8200/connectors/sync/s3 \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "bucket": "company-docs",
    "prefix": "knowledge-base/",
    "glob": "*.pdf",
    "profile": "general"
  }'

Incremental processing

Enterprise libraries often contain thousands of documents. Incremental processing ensures that re-syncs only process new or modified documents — zero cost for unchanged files.

Typical workflow

SharePoint / Confluence / S3
    ↓
Connector sync → DocIntel (general profile)
    ↓
Entities + relationships → JSON API / Graph
    ↓
KMS → browse, search, curate
Cortex → AI-powered Q&A over enterprise knowledge

When to use a specialised profile

If your documents are consistently from one domain, consider using a specialised profile instead:

Document type	Better profile
Contracts, NDAs, agreements	contract
Invoices, POs, financial statements	financial
Academic papers, technical reports	scientific
IFC models, CAD drawings	aec
Mixed / unknown	general (auto-classifies)

You can also omit the profile parameter entirely — DocIntel's auto-classification will select the best profile per document.