n8n-nodes-nvidia-suite

Overview

Integrates NVIDIA's NIM (NVIDIA Inference Microservice) suite into n8n, providing nodes for Chat, Embeddings, and Reranking. This package is for n8n workflow builders using NVIDIA's AI models to build RAG pipelines or advanced AI agents.

Nodes & Operations

NVIDIA NIM Chat Model

Configures a NVIDIA NIM chat model as the core conversational component for n8n AI Agent or AI Chain nodes, allowing model selection and generation settings.

• Default · Default — Provides a NVIDIA NIM chat model for use as the Chat Model input to n8n AI Agent or AI Chain nodes. Select a model and optionally configure generation, retry, timeout, and response format settings.

Embeddings NVIDIA

Generates text and image embeddings via NVIDIA NIM's OpenAI-compatible endpoint and exposes them as n8n AI Embedding outputs for vector store integration.

• Default · Default — Generates text embeddings through NVIDIA’s OpenAI-compatible /embeddings endpoint and exposes them as an n8n AI Embedding output for downstream AI nodes.

Reranker NVIDIA

Reorders retrieved documents by relevance to a query using NVIDIA's API, serving as an AI Reranker that returns top-N documents with updated relevance scores.

• Default · Default — Rerank documents by relevance to a query using NVIDIA’s API. Connect this node as an AI Reranker; it returns up to Top N documents in ranked order, with each document’s metadata updated to include its relevance score.

Installation

Install as an n8n community node: in n8n, open Settings → Community nodes → Install and enter n8n-nodes-nvidia-suite.

Links

• n8n community nodes installation guide