RAG & Knowledge Bases
Connect your documents and data to agents through Retrieval-Augmented Generation (RAG). Give agents access to your organization's knowledge for accurate, contextual responses.
How RAG Works
RAG enhances AI responses by retrieving relevant context from your documents before generating an answer. This ensures agents have access to up-to-date, organization-specific information.
1. Ingest
Documents are chunked and embedded
2. Retrieve
Semantic search finds relevant chunks
3. Generate
Agent responds with context
Document Ingestion
Upload documents to create a searchable knowledge base. Aethyr supports multiple file formats and automatically handles chunking and embedding.
Supported Formats
Upload documents through the Console, or have your team configure automated ingestion from your existing document sources. Chunking, embedding, and indexing happen automatically—no preprocessing required on your side.
Semantic Search
Aethyr uses vector search for efficient semantic retrieval. Queries are embedded and compared against document chunks using cosine similarity.
Retrieval is tunable—result count and relevance thresholds are configured per knowledge base so agents get the right amount of context without noise. For richer reasoning, Aethyr also supports graph-enhanced retrieval that follows relationships between entities, not just text similarity.
Connecting to Agents
Link a knowledge base to an agent to enable automatic context retrieval during conversations.
Assign one or more knowledge bases to an agent and enable automatic retrieval. The agent then pulls relevant context into its reasoning on every turn, so answers stay grounded in your organization's own documents—no manual lookups, no copy-paste.