Build a Retrieval-Augmented Generation (RAG) Agent with NVIDIA Nemotron | NVIDIA Technical Blog
… Now that your NIM is running locally, we need to update the agent you created in rag agent.py to use it. llm = ChatNVIDIA base url="http://nemotron:8000/v1", model=LLM MODEL, temperature=0.6, top p=0.95, max tokens=8192 With your langgraph server still running, go back to our Simple Agents Client a… …