Skip to main content

Knowledge Assistant (RAG)

Knowledge Assistant is an AI product based on RAG (Retrieval-Augmented Generation) that combines search across an organization's knowledge base with answer generation based on an LLM.

The product exists in two variants: for internal users (employees) and for external users (customers).


Purpose

The Knowledge Assistant addresses fast access to an organization's knowledge. Instead of manually searching through documents, the user asks a question in natural language and receives a generated answer with links to sources.


RAG Architecture

A typical RAG system architecture includes the following components:

  1. Document ingestion — connecting to data sources
  2. Chunking — splitting documents into fragments
  3. Embedding — vectorizing the fragments
  4. Vector store — indexing and storing the embeddings
  5. Retrieval — finding relevant fragments for a query
  6. Generation — forming an answer based on the retrieved fragments via an LLM
  7. Answer to the user — an answer with citations and links to sources

Key Aspects

When developing and operating the Knowledge Assistant, you need to consider:

  • Data quality — answers are only as good as the source documents
  • Retrieval relevance — retrieval accuracy directly affects answer quality
  • Hallucination control — an LLM may generate inaccurate information
  • Access control — a user should see only the documents they have access to
  • Data freshness — documents require regular updating in the index

Two Product Variants

The Knowledge Assistant is implemented in two variants with different requirements:

AspectInternalExternal
UsersEmployeesCustomers
DataInternal documents, policiesPublic documentation, FAQs
Error toleranceMediumLow
Access controlBy roles and departmentsBy products and plans
EscalationTo an expertTo a support agent

Knowledge Assistant — Internal

Knowledge Assistant — External