experimental

Experimental Examples

What is an Experimental Example?

Experimental examples are sample code and deployments for RAG pipelines that are not tested by NVIDIA personnel.

Inventory

• NVIDIA RAG Streaming Document Ingestion Pipeline

  This example demonstrate the construction of a performance-oriented pipeline that accepts a stream of heterogenous documents, divides the documents into smaller segments or chunks, computes the embedding vector for each of these chunks, and uploads the text chunks along with their associated embeddings to a Vector Database. This pipeline builds on the Morpheus SDK to take advantage of end-to-end asynchronous processing. This pipeline showcases pipeline parallelism (including CPU and GPU-accelerated nodes), as well as, a mechanism to horizontally scale out data ingestion workers.

• NVIDIA Live FM Radio ASR RAG

  This example is a demonstration of a RAG workflow that ingests streaming text derived from live FM radio signals. An SDR signal processing pipeline built with NVIDIA Holoscan is used to process I/Q samples sent over UDP. ASR is performed on the processed audio data using NVIDIA Riva and stored in a time-informed FAISS database. Uses LangChain connectors to NVIDIA AI Foundation Models Endpoint or models running on-prem with NVIDIA NIM.

• NVIDIA ORAN chatbot multimodal Assistant

  This example is designed to make it extremely easy to set up your own retrieval-augmented generation chatbot for ORAN techncial specifications and processes. The backend here calls the NVIDIA NeMo Service, which makes it very easy to deploy on a thin client or Virtual Machine (ie, without a GPU setup).

• NVIDIA Retrieval Customization

  This example is a sample demonstration on how Large Language Models (LLMs) could be used to synthetically generate training data, which can then be used to adapt retriever models.

• NVIDIA Multimodal RAG Assistant

  This example is able to ingest PDFs, PowerPoint slides, Word and other documents with complex data formats including text, images, slides and tables. It allows users to ask questions through a text interface and optionally with an image query, and it can respond with text and reference images, slides and tables in its response, along with source links and downloads.

• Run RAG-LLM in Azure Machine Learning

  This example shows the configuration changes to using Docker containers and local GPUs that are required to run the RAG-LLM pipelines in Azure Machine Learning.

• NVIDIA Developer RAG Chatbot

  This example shows how to create a developer-focused RAG chatbot using RAPIDS cuDF source code and API documentation as a representative example of a typical codebase.

• NVIDIA Event Driven RAG for CVE Analysis with NVIDIA Morpheus

  This example demonstrates how NVIDIA Morpheus, NIMs, and RAG pipelines can be integrated to create LLM-based agent pipelines. These pipelines will be used to automatically and scalably traige and detect Common Vulnerabilities and Exposures (CVEs) in Docker containers using references to source code, dependencies, and information about the CVEs.