Notebooks for NeMo Retriever Library
To get started using NeMo Retriever Library, you can try one of the guides or ready-made notebooks that are available.
Note
NVIDIA Ingest (nv-ingest) has been renamed NeMo Retriever Library.
Dataset Downloads for Benchmarking
If you plan to run benchmarking or evaluation tests, you must download the Benchmark Datasets (Bo20, Bo767, Bo10k) from Digital Corpora. This is a prerequisite for all benchmarking operations.
Getting Started
To get started with the basics, try one of the following guides or notebooks:
- CLI Client Quick Start Guide — walkthrough for
nv-ingest-cli/retrieverwith the self-hosted stack - Python Client Quick Start Guide — walkthrough for the Python client with the self-hosted stack
- How to add metadata to your documents and filter searches
- How to reindex a collection
For more advanced scenarios, try one of the following notebooks:
- Build a Custom Vector Database Operator
- Try Enterprise RAG Blueprint
- Evaluate bo767 retrieval recall accuracy with NV-Ingest and Milvus
- Multimodal RAG with LangChain
- Multimodal RAG with LlamaIndex