This release completely refactors the directory structure of the repository for a more seamless and intuitive developer journey. It also adds support to deploy the latest accelerated embedding and reranking models across the cloud, data center, and workstation using NVIDIA NeMo Retriever NIM microservices.

Added

• End-to-end RAG examples enhancements
  • Single-command deployment for all the examples using Docker Compose.
  • All end to end RAG examples are now more encapsulated with documentation, code and deployment assets residing in dedicated example specific directory.
  • Segregated examples into basic and advanced RAG with dedicated READMEs.
  • Added reranker model support to multi-turn RAG example.
  • Added dedicated prompt configuration file for every example.
  • Removed Python dev packages from containers to enhance security.
  • Updated to latest version of langchain-nvidia-ai-endpoints.
• Speech support using RAG Playground
  • Added support to access RIVA speech models from NVIDIA API Catalog.
  • Speech support in RAG Playground is opt-in.
• Documentation enhancements
  • Added more comprehensive how-to guides for end to end RAG examples.
  • Added example specific architecture diagrams in each example directory.
• Added a new industry specific top level directory
  • Added health care domain specific Medical Device Training Assistant RAG.
• Added notebooks showcasing new usecases
  • Basic langchain based RAG pipeline using latest NVIDIA API Catalog connectors.
  • Basic llamaindex based RAG pipeline using latest NVIDIA API Catalog connectors.
  • NeMo Guardrails with basic langchain RAG.
  • NVIDIA NIM microservices using NeMo Guardrails based RAG.
  • Using NeMo Evaluator using Llama 3.1 8B Instruct.
  • Agentic RAG pipeline with Nemo Retriever and NIM for LLMs.
• Added new community (before experimental) example
  • Create a simple web interface to interact with different selectable NIM endpoints. The provided interface of this project supports designing a system prompt to call the LLM.

Changed

• Major restructuring and reorganisation of the assets within the repository
  • Top level experimental directory has been renamed as community.
  • Top level RetrievalAugmentedGeneration directory has been renamed as just RAG.
  • The Docker Compose files inside top level deploy directory has been migrated to example-specific directories under RAG/examples. The vector database and on-prem NIM microservices deployment files are under RAG/examples/local_deploy.
  • Top level models has been renamed to finetuning.
  • Top level notebooks directory has been moved to under RAG/notebooks and has been organised framework wise.
  • Top level tools directory has been migrated to RAG/tools.
  • Top level integrations directory has been moved into RAG/src.
  • RetreivalAugmentedGeneration/common is now residing under RAG/src/chain_server.
  • RetreivalAugmentedGeneration/frontend is now residing under RAG/src/rag_playground/default.
  • 5 mins RAG No GPU example under top level examples directory, is now under community.

Deprecated

• Github pages based documentation is now replaced with markdown based documentation.
• Top level examples directory has been removed.
• Following notebooks were removed
  • 02_Option(1)_NVIDIA_AI_endpoint_simple.ipynb
  • notebooks/02_Option(2)_minimalistic_RAG_with_langchain_local_HF_LLM.ipynb
  • notebooks/03_Option(1)_llama_index_with_NVIDIA_AI_endpoint.ipynb
  • notebooks/03_Option(2)_llama_index_with_HF_local_LLM.ipynb