Knowledge & Data · Software component
Knowledge Retrieval Agent
Software componentKnowledge & DataKnowledge & Dataarc:KnowledgeRetrievalAgent
A specialised agent that searches the knowledge base by vector similarity and returns documents filtered to the requester's access level.
Responsibility. Retrieves relevant knowledge-base documents for a request.
Also known as: Retrieval Agent, Agent-as-tool retrieval agent, Knowledge retrieval service
Variant of Worker Agent abstract
Relationships
deployed on structural
invokes dependency
is cached by dependency
is invoked by dependency
- Answer Synthesizer abstract Ch4.2
- Worker Agent abstract Ch2.4
reads dependency
- Vector Index Store abstract Ch1.3
receives data from dynamic
sends data to dynamic
- Answer Synthesizer abstract Ch1.3
- Intent Router Ch1.3
is guarded by control
is orchestrated by control
Design guidance
- SHOULD filter retrieved documents by the requester's entitlement (e.g., product tier).
- SHOULD own all document search and expose a simple query(text, limit) API so other services do not duplicate embedding models and vector search.
- SHOULD run on CPU-optimised, high-memory instances rather than GPUs.
Classification
- Patterns
- Vector similarity searchMetadata filtering
- Technologies
- LangChain
- Quality attributes
- Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)
- Risks mitigated
- Duplicate capabilities and doubled vector database cost across overlapping services
Sources
- Ch1.3: T. Nguyen, "Multi-Agent Systems," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.3. ISBN: 9798244538229.
- Ch2.4: T. Nguyen, "Multi-Agent Frameworks," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 2.4. ISBN: 9798244538229.
- Ch4.2: T. Nguyen, "Deployment and Scaling," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 4.2. ISBN: 9798244538229.