Official documentationNot tested by AQI AI
Nemotron 3.5: separate parsing, retrieval and reranking
NVIDIA introduces multimodal Embed, Rerank and Parse models for finding, ordering and extracting evidence. These serve distinct retrieval tasks, not three chat backends.
A quick glossary
Models generate and reason. Agents use tools to work on tasks. A harness manages an agent’s environment. MCP connects tools and data. Skills are reusable task guidance.
Original sources
- Nemotron 3.5: separate parsing, retrieval and reranking ↗
huggingface.co · · Official documentation