Notebooks for NeMo Retriever Extraction
To get started using NeMo Retriever extraction, you can try one of the ready-made notebooks that are available.
Note
NeMo Retriever extraction is also known as NVIDIA Ingest and nv-ingest.
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 notebooks:
- NV-Ingest: CLI Client Quick Start Guide
- NV-Ingest: Python Client Quick Start Guide
- 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