Knowledge check

RAG eliminates the need for large language models by relying entirely on document retrieval.

RAG enables agents to ground responses in current organizational information and provide source transparency.

RAG automatically retrains the language model whenever organizational documents change.

SharePoint Indexed, which pre-processes SharePoint content into Azure AI Search.

SharePoint Remote, which queries SharePoint sites and libraries in real-time.

Azure Blob Storage, which connects to SharePoint files stored as blobs.

To encrypt sensitive fields and protect confidential information during retrieval.

To boost specific fields or attributes so more important results surface first.

To configure how documents are chunked and embedded for semantic search.

Without proper instructions, agents might answer from training data instead of the knowledge base, provide unverifiable responses, or fail to cite sources.

Instructions determine the semantic ranking algorithm that Foundry IQ applies to search results.

Instructions enable the agent to automatically update knowledge base content when it detects outdated information.