The knowledge base is the single source of truth for your AI assistant. Every response is grounded in content that your team has curated, reviewed, and approved — the assistant never invents answers or pulls from external sources. This design ensures traceability, accuracy, and compliance.
Two Content Types
AskRAI supports two types of knowledge content, each suited to different use cases:
| Type | What it is | Best for |
|---|---|---|
| Q&A pairs | A question and its answer, written by a curator | Direct answers to common questions (Resolve, Inform) |
| Document chunks | Segments extracted from uploaded files (PDF, DOCX, XLSX, etc.) | Reference material, policies, and detailed procedures (Inform, Support) |
Both types live in the same knowledge base and are searchable together. The difference is in how they enter the system.
Content Ingestion Pipeline
When you upload a document to a knowledge pack, AskRAI processes it through an automated pipeline.
- Upload — drag and drop files into a document-type knowledge pack. Supported formats include PDF, DOCX, PPTX, XLSX, and image files.
- Parse — the system extracts text content, preserving page numbers and section headings.
- Chunk — long documents are split into semantic segments that each capture a coherent unit of information.
- Index — chunks are added to both the text search index and the vector index for semantic search.
For Q&A pairs, you write the question and answer directly — no parsing pipeline needed.
A new Q&A is not live when you save it. It is created as a Draft, and drafts are excluded from the search index — the assistant cannot retrieve it. To publish a Q&A you must approve it, and the index is refreshed on the next indexer run (approving in bulk, or clicking Sync Index on the Knowledge Packs page, triggers one). If a curator adds an answer and users still get "I don't know", an unapproved draft is the first thing to check.
Knowledge Packs
Knowledge packs are containers that group related content together. Each pack has a content type (Q&A or Document) chosen at creation, and content within a pack shares the same lifecycle and access controls.
Packs serve two purposes:
- Organization — group content by topic, department, or use case (e.g., "HR Policies", "Building Permits", "IT Self-Service")
- Access control — groups reference knowledge packs to control which users can access which content
A user's AI assistant only searches knowledge packs that their group memberships grant access to. Content in packs outside their groups is invisible to their queries.
Content Lifecycle
Every knowledge item follows a status workflow that controls whether it appears in search results:
| Status | Visible to users? | Description |
|---|---|---|
| Draft | No | The starting status for a hand-written Q&A — awaiting review |
| Approved | Yes | Reviewed and live — appears in search results |
| Needs Attention | No | Flagged for review — temporarily hidden |
| Discarded | No | Soft-deleted — excluded from all searches |
Only Approved content appears in user-facing AI responses. This ensures that every answer the assistant gives comes from vetted, curator-approved material.
The two content types do not start in the same place. A Q&A you write by hand starts as Draft, so it is not searchable until you approve it. Chunks produced by the document-processing pipeline are created Approved and are live as soon as the index run finishes — uploading a document publishes its content without a review step. If you want documents reviewed before they can be used, review them after upload rather than assuming an approval gate exists.
Two Search Modes
AskRAI offers two ways to search the knowledge base:
- Text Search — keyword-based search that matches exact terms in questions, answers, and document content. Fast and predictable.
- AI Search (semantic) — meaning-based search that finds relevant content even when the wording differs from the query. Uses vector embeddings to match by concept rather than keywords.
These two modes are a curator tool on the Knowledge Base page — they are how you look content up. They are not a runtime setting. At query time the assistant always issues one hybrid keyword-plus-vector search; there is no per-tenant switch that selects a retrieval mode, and nothing to configure.
Next Steps
- Knowledge Base — create and manage Q&A pairs and document chunks
- Knowledge Packs — organize content into collections and upload files
- Guardrails — understand how safety rules protect knowledge-based responses
- Access Control — learn how groups control access to knowledge packs