Release notes from GenerativeAIExamples

v0.8.0

2024-08-21T03:15:23Z

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

v0.7.0

2024-06-18T15:52:25Z

This release switches all examples to use cloud hosted GPU accelerated LLM and embedding models from Nvidia API Catalog as default. It also deprecates support to deploy on-prem models using NeMo Inference Framework Container and adds support to deploy accelerated generative AI models across the cloud, data center, and workstation using latest Nvidia NIM-LLM.

Added

Added model auto download and caching support for nemo-retriever-embedding-microservice and nemo-retriever-reranking-microservice. Updated steps to deploy the services can be found here.
Multimodal RAG Example enhancements
- Moved to the PDF Plumber library for parsing text and images.
- Added pgvector vector DB support.
- Added support to ingest files with .pptx extension
- Improved accuracy of image parsing by using tesseract-ocr
Added a new notebook showcasing RAG usecase using accelerated NIM based on-prem deployed models
Added a new experimental example showcasing how to create a developer-focused RAG chatbot using RAPIDS cuDF source code and API documentation.
Added a new experimental example demonstrating how NVIDIA Morpheus, NIMs, and RAG pipelines can be integrated to create LLM-based agent pipelines.

Changed

All examples now use llama3 models from Nvidia API Catalog as default. Summary of updated examples and the model it uses is available here.
Switched default embedding model of all examples to Snowflake arctic-embed-I model
Added more verbose logs and support to configure log level for chain server using LOG_LEVEL enviroment variable.
Bumped up version of langchain-nvidia-ai-endpoints, sentence-transformers package and milvus containers
Updated base containers to use ubuntu 22.04 image nvcr.io/nvidia/base/ubuntu:22.04_20240212
Added llama-index-readers-file as dependency to avoid runtime package installation within chain server.

Deprecated

Deprecated support of on-prem LLM model deployment using NeMo Inference Framework Container. Developers can use Nvidia NIM-LLM to deploy TensorRT optimized models on-prem and plug them in with existing examples.
Deprecated kubernetes operator support.
nvolveqa_40k embedding model was deprecated from Nvidia API Catalog. Updated all notebooks and experimental artifacts to use Nvidia embed-qa-4 model instead.
Removed notebooks numbered 00-04, which used on-prem LLM model deployment using deprecated NeMo Inference Framework Container.

v0.6.0

2024-05-10T17:19:40Z

This release adds ability to switch between API Catalog models and on-prem models using NIM-LLM and adds documentation on how to build an RAG application from scratch. It also releases a containerized end to end RAG evaluation application integrated with RAG chain-server APIs.

Added

Ability to switch between API Catalog models to on-prem models using NIM-LLM.
New API endpoint
- /health - Provides a health check for the chain server.
Containerized evaluation application for RAG pipeline accuracy measurement.
Observability support for langchain based examples.
New Notebooks
- Added Chat with NVIDIA financial data notebook.
- Added notebook showcasing langgraph agent handling.
A simple rag example template showcasing how to build an example from scratch.

Changed

Renamed example csv_rag to structured_data_rag
Model Engine name update
- nv-ai-foundation and nv-api-catalog llm engine are renamed to nvidia-ai-endpoints
- nv-ai-foundation embedding engine is renamed to nvidia-ai-endpoints
Embedding model update
- developer_rag example uses UAE-Large-V1 embedding model.
- Using ai-embed-qa-4 for api catalog examples instead of nvolveqa_40k as embedding model
Ingested data now persists across multiple sessions.
Updated langchain-nvidia-endpoints to version 0.0.11, enabling support for models like llama3.
File extension based validation to throw error for unsupported files.
The default output token length in the UI has been increased from 250 to 1024 for more comprehensive responses.
Stricter chain-server API validation support to enhance API security
Updated version of llama-index, pymilvus.
Updated pgvector container to pgvector/pgvector:pg16
LLM Model Updates
- Multiturn Chatbot now uses ai-mixtral-8x7b-instruct model for response generation.
- Structured data rag now uses ai-llama3-70b for response and code generation.

v0.5.0

2024-03-20T18:23:30Z

This release adds new dedicated RAG examples showcasing state of the art usecases, switches to the latest API catalog endpoints from NVIDIA and also refactors the API interface of chain-server. This release also improves the developer experience by adding github pages based documentation and streamlining the example deployment flow using dedicated compose files.

Added

Github pages based documentation.
New examples showcasing
Support for delete and list APIs in chain-server component
Streamlined RAG example deployment
- Dedicated new docker compose files for every examples.
- Dedicated docker compose files for launching vector DB solutions.
New configurations to control top k and confidence score of retrieval pipeline.
Added a notebook which covers how to train SLMs with various techniques using NeMo Framework.
Added more experimental examples showcasing new usecases.
New dedicated notebook showcasing a RAG pipeline using web pages.

Changed

Switched from NVIDIA AI Foundation to NVIDIA API Catalog endpoints for accessing cloud hosted LLM models.
Refactored API schema of chain-server component to support runtime allocation of llm parameters like temperature, max tokens, chat history etc.
Renamed llm-playground service in compose files to rag-playground.
Switched base containers for all components to ubuntu instead of pytorch and optimized container build time as well as container size.
Deprecated yaml based configuration to avoid confusion, all configurations are now environment variable based.
Removed requirement of hardcoding NVIDIA_API_KEY in compose.env file.
Upgraded all python dependencies for chain-server and rag-playground services.

Fixed

Fixed a bug causing hallucinated answer when retriever fails to return any documents.
Fixed some accuracy issues for all the examples.

v0.4.0

2024-02-22T20:51:31Z

This release adds new dedicated notebooks showcasing usage of cloud based NVIDIA AI Foundation models, upgraded milvus container version to enable GPU accelerated vector search and added support for FAISS vector database. Detailed changes are listed below:

Added

New dedicated notebooks showcasing usage of cloud based Nvidia AI Foundation based models using Langchain connectors as well as local model deployment using Huggingface.
Upgraded milvus container version to enable GPU accelerated vector search.
Added support to interact with models behind NeMo Inference Microservices using new model engines nemo-embed and nemo-infer.
Added support to provide example specific collection name for vector databases using an environment variable named COLLECTION_NAME.
Added faiss as a generic vector database solution behind utils.py.

Changed

Upgraded and changed base containers for all components to pytorch 23.12-py3.
Added langchain specific vector database connector in utils.py.
Changed speech support to use single channel for Riva ASR and TTS.
Changed get_llm utility in utils.py to return Langchain wrapper instead of Llmaindex wrappers.

Fixed

Fixed a bug causing empty rating in evaluation notebook
Fixed document search implementation of query decomposition example.

v0.3.0

2024-01-22T16:48:50Z

This release adds support for PGvector Vector DB, speech-in speech-out support using RIVA and RAG observability tooling. This release also adds a dedicated example for RAG pipeline using only models from NVIDIA AI Foundation and one example demonstrating query decomposition. Detailed changes are listed below:

Added

New dedicated example showcasing Nvidia AI Playground based models using Langchain connectors.
New example demonstrating query decomposition.
Support for using PG Vector as a vector database in the developer rag canonical example.
Support for using Speech-in Speech-out interface in the sample frontend leveraging RIVA Skills.
New tool showcasing RAG observability support.
Support for on-prem deployment of TRTLLM based nemotron models.

Changed

Upgraded Langchain and llamaindex dependencies for all container.
Restructured README files for better intuitiveness.
Added provision to plug in multiple examples using a common base class.
Changed minio service's port to 9010from 9000 in docker based deployment.
Moved evaluation directory from top level to under tools and created a dedicated compose file.
Added an experimental directory for plugging in experimental features.
Modified notebooks to use TRTLLM and Nvidia AI foundation based connectors from langchain.
Changed ai-playground model engine name to nv-ai-foundation in configurations.

Fixed

Fixed issue #19

Release v0.2.0

2023-12-15T20:24:48Z

This release builds on the feedback received and brings many improvements, bugfixes and new features. This release is the first to include Nvidia AI Foundational models support and support for quantized LLM models. Detailed changes are listed below:

What's Added

Support for using Nvidia AI Foundational LLM models
Support for using Nvidia AI Foundational embedding models
Support for deploying and using quantized LLM models
Support for evaluating RAG pipeline

What's Changed

Repository restructing to allow better open source contributions
Upgraded dependencies for chain server container
Upgraded NeMo Inference Framework container version, no seperate sign up needed now for access.
Main README now provides more details.
Documentation improvements.
Better error handling and reporting mechanism for corner cases.
Renamed triton-inference-server container and service to llm-inference-server

What's Fixed

#13 of pipeline not able to answer questions unrelated to knowledge base
#12 typechecking while uploading PDF files

v0.1.0

2023-11-16T19:51:40Z

Bump postcss and next (#4)

Bumps [postcss](https://github.com/postcss/postcss) to 8.4.31 and updates ancestor dependency [next](https://github.com/vercel/next.js). These dependencies need to be updated together.

Updates `postcss` from 8.4.14 to 8.4.31
- [Release notes](https://github.com/postcss/postcss/releases)
- [Changelog](https://github.com/postcss/postcss/blob/main/CHANGELOG.md)
- [Commits](postcss/postcss@8.4.14...8.4.31)

Updates `next` from 13.4.12 to 13.5.6
- [Release notes](https://github.com/vercel/next.js/releases)
- [Changelog](https://github.com/vercel/next.js/blob/canary/release.js)
- [Commits](vercel/next.js@v13.4.12...v13.5.6)

---
updated-dependencies:
- dependency-name: postcss
dependency-type: indirect
- dependency-name: next
dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>