{"id":13491056,"url":"https://github.com/NVIDIA/GenerativeAIExamples","last_synced_at":"2025-03-28T07:31:43.793Z","repository":{"id":207656212,"uuid":"707237272","full_name":"NVIDIA/GenerativeAIExamples","owner":"NVIDIA","description":"Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.","archived":false,"fork":false,"pushed_at":"2025-03-18T19:16:15.000Z","size":72349,"stargazers_count":2919,"open_issues_count":43,"forks_count":689,"subscribers_count":67,"default_branch":"main","last_synced_at":"2025-03-21T18:01:51.295Z","etag":null,"topics":["gpu-acceleration","large-language-models","llm","llm-inference","microservice","nemo","rag","retrieval-augmented-generation","tensorrt","triton-inference-server"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/NVIDIA.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"docs/contributing.md","funding":null,"license":"LICENSE.DATA","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":"docs/support-matrix.md","governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-10-19T13:46:31.000Z","updated_at":"2025-03-21T08:58:01.000Z","dependencies_parsed_at":"2024-10-26T05:01:59.624Z","dependency_job_id":"e12331f8-5b4a-4456-b9ff-1d4801180979","html_url":"https://github.com/NVIDIA/GenerativeAIExamples","commit_stats":null,"previous_names":["nvidia/generativeaiexamples"],"tags_count":8,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2FGenerativeAIExamples","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2FGenerativeAIExamples/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2FGenerativeAIExamples/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2FGenerativeAIExamples/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NVIDIA","download_url":"https://codeload.github.com/NVIDIA/GenerativeAIExamples/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245868266,"owners_count":20685607,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["gpu-acceleration","large-language-models","llm","llm-inference","microservice","nemo","rag","retrieval-augmented-generation","tensorrt","triton-inference-server"],"created_at":"2024-07-31T19:00:53.171Z","updated_at":"2025-03-28T07:31:43.787Z","avatar_url":"https://github.com/NVIDIA.png","language":"Python","funding_links":[],"categories":["Python","A01_文本生成_文本对话","Building","Repos","Framework Examples"],"sub_categories":["大语言对话模型及数据","Workflows"],"readme":"\u003c!--\n  SPDX-FileCopyrightText: Copyright (c) 2023 NVIDIA CORPORATION \u0026 AFFILIATES. All rights reserved.\n  SPDX-License-Identifier: Apache-2.0\n--\u003e\n\n![](docs/images/apps-catalog-promo-web-banner-laptop-300@2x.jpg)\n\n# NVIDIA Generative AI Examples\n\nThis repository is a starting point for developers looking to integrate with the NVIDIA software ecosystem to speed up their generative AI systems. Whether you are building RAG pipelines, agentic workflows, or fine-tuning models, this repository will help you integrate NVIDIA, seamlessly and natively, with your development stack.\n\n## Table of Contents\n\u003c!-- TOC --\u003e\n\n* [What's New?](#whats-new)\n  * [Knowledge Graph RAG](#knowledge-graph-rag)\n  * [Agentic Workflows with Llama 3.1](#agentic-workflows-with-llama-31)\n  * [RAG with Local NIM Deployment and LangChain](#rag-with-local-nim-deployment-and-langchain)\n  * [Vision NIM Workflows](#vision-nim-workflows)\n* [Try it Now!](#try-it-now)\n* [RAG](#rag)\n  * [RAG Notebooks](#rag-notebooks)\n  * [RAG Examples](#rag-examples)\n  * [RAG Tools](#rag-tools)\n  * [RAG Projects](#rag-projects)\n* [Documentation](#documentation)\n  * [Getting Started](#getting-started)\n  * [How To's](#how-tos)\n  * [Reference](#reference)\n* [Community](#community)\n\n\u003c!-- /TOC --\u003e\n\n## What's New?\n\n### Knowledge Graph RAG\n\nThis example implements a GPU-accelerated pipeline for creating and querying knowledge graphs using RAG by leveraging NIM microservices and the RAPIDS ecosystem to process large-scale datasets efficiently.\n\n- [Knowledge Graphs for RAG with NVIDIA AI Foundation Models and Endpoints](community/knowledge_graph_rag)\n\n### Agentic Workflows with Llama 3.1\n\n- Build an Agentic RAG Pipeline with Llama 3.1 and NVIDIA NeMo Retriever NIM microservices [[Blog](https://developer.nvidia.com/blog/build-an-agentic-rag-pipeline-with-llama-3-1-and-nvidia-nemo-retriever-nims/), [Notebook](RAG/notebooks/langchain/agentic_rag_with_nemo_retriever_nim.ipynb)]\n- [NVIDIA Morpheus, NIM microservices, and RAG pipelines integrated to create LLM-based agent pipelines](https://github.com/NVIDIA/GenerativeAIExamples/blob/v0.7.0/experimental/event-driven-rag-cve-analysis)\n\n\n### RAG with Local NIM Deployment and LangChain\n\n- Tips for Building a RAG Pipeline with NVIDIA AI LangChain AI Endpoints by Amit Bleiweiss. [[Blog](https://developer.nvidia.com/blog/tips-for-building-a-rag-pipeline-with-nvidia-ai-langchain-ai-endpoints/), [Notebook](https://github.com/NVIDIA/GenerativeAIExamples/blob/v0.7.0/notebooks/08_RAG_Langchain_with_Local_NIM.ipynb)]\n\nFor more information, refer to the [Generative AI Example releases](https://github.com/NVIDIA/GenerativeAIExamples/releases/).\n\n### Vision NIM Workflows\nA collection of Jupyter notebooks, sample code and reference applications built with Vision NIMs.\n\nTo pull the vision NIM workflows, clone this repository recursively:\n```\ngit clone https://github.com/nvidia/GenerativeAIExamples --recurse-submodules\n```\n\nThe workflows will then be located at [GenerativeAIExamples/vision_workflows](vision_workflows/README.md)\n\nFollow the links below to learn more:\n- [Learn how to use VLMs to automatically monitor a video stream for custom events.](nim_workflows/vlm_alerts/README.md)\n- [Learn how to search images with natural language using NV-CLIP.](nim_workflows/nvclip_multimodal_search/README.md)\n- [Learn how to combine VLMs, LLMs and CV models to build a robust text extraction pipeline.](nim_workflows/vision_text_extraction/README.md)\n- [Learn how to use embeddings with NVDINOv2 and a Milvus VectorDB to build a few shot classification model.](nim_workflows/nvdinov2_few_shot/README.md)\n\n\n## Try it Now!\n\nExperience NVIDIA RAG Pipelines with just a few steps!\n\n1. Get your NVIDIA API key.\n   1. Go to the [NVIDIA API Catalog](https://build.ngc.nvidia.com/explore/).\n   1. Select any model.\n   1. Click **Get API Key**.\n   1. Run:\n      ```console\n      export NVIDIA_API_KEY=nvapi-...\n      ``` \n\n1. Clone the repository.\n\n   ```console\n   git clone https://github.com/nvidia/GenerativeAIExamples.git\n   ```\n\n1. Build and run the basic RAG pipeline.\n\n   ```console\n   cd GenerativeAIExamples/RAG/examples/basic_rag/langchain/\n   docker compose up -d --build\n   ```\n\n1. Go to \u003chttps://localhost:8090/\u003e and submit queries to the sample RAG Playground.\n\n1. Stop containers when done. \n  \n   ```console\n   docker compose down\n   ``` \n      \n\n\n## RAG\n\n### RAG Notebooks\n\nNVIDIA has first-class support for popular generative AI developer frameworks like [LangChain](https://python.langchain.com/v0.2/docs/integrations/chat/nvidia_ai_endpoints/), [LlamaIndex](https://docs.llamaindex.ai/en/stable/examples/llm/nvidia/), and [Haystack](https://haystack.deepset.ai/integrations/nvidia). These end-to-end notebooks show how to integrate NIM microservices using your preferred generative AI development framework.\n\nUse these [notebooks](./RAG/notebooks/README.md) to learn about the LangChain and LlamaIndex connectors.\n\n#### LangChain Notebooks\n\n- RAG\n  - [Basic RAG with CHATNVIDIA LangChain Integration](./RAG/notebooks/langchain/langchain_basic_RAG.ipynb)\n  - [RAG using local NIM microservices for LLMs and Retrieval](./RAG/notebooks/langchain/RAG_Langchain_with_Local_NIM.ipynb)\n  - [RAG for HTML Documents](./RAG/notebooks/langchain/RAG_for_HTML_docs_with_Langchain_NVIDIA_AI_Endpoints.ipynb)\n  - [Chat with NVIDIA Financial Reports](./RAG/notebooks/langchain/Chat_with_nvidia_financial_reports.ipynb)\n- Agents\n  - [NIM Tool Calling 101](https://github.com/langchain-ai/langchain-nvidia/blob/main/cookbook/nvidia_nim_agents_llama3.1.ipynb)\n  - [Agentic RAG with NeMo Retriever](./RAG/notebooks/langchain/agentic_rag_with_nemo_retriever_nim.ipynb)\n  - [Agents with Human in the Loop](./RAG/notebooks/langchain/LangGraph_HandlingAgent_IntermediateSteps.ipynb)\n\n\n#### LlamaIndex Notebooks\n\n- [Basic RAG with LlamaIndex Integration](./RAG/notebooks/llamaindex/llamaindex_basic_RAG.ipynb)\n\n### RAG Examples\n\nBy default, these end-to-end [examples](RAG/examples/README.md) use preview NIM endpoints on [NVIDIA API Catalog](https://catalog.ngc.nvidia.com). Alternatively, you can run any of the examples [on premises](./RAG/examples/local_deploy/).\n\n#### Basic RAG Examples\n\n  - [LangChain example](./RAG/examples/basic_rag/langchain/README.md)\n  - [LlamaIndex example](./RAG/examples/basic_rag/llamaindex/README.md)\n\n#### Advanced RAG Examples\n\n  - [Multi-Turn](./RAG/examples/advanced_rag/multi_turn_rag/README.md)\n  - [Multimodal Data](./RAG/examples/advanced_rag/multimodal_rag/README.md)\n  - [Structured Data](./RAG/examples/advanced_rag/structured_data_rag/README.md) (CSV)\n  - [Query Decomposition](./RAG/examples/advanced_rag/query_decomposition_rag/README.md)\n\n### RAG Tools\n\nExample tools and tutorials to enhance LLM development and productivity when using NVIDIA RAG pipelines.\n\n- [Evaluation](./RAG/tools/evaluation/README.md)\n- [Observability](./RAG/tools/observability/README.md)\n\n### RAG Projects\n\n- [NVIDIA Tokkio LLM-RAG](https://docs.nvidia.com/ace/latest/workflows/tokkio/text/Tokkio_LLM_RAG_Bot.html): Use Tokkio to add avatar animation for RAG responses.\n- [Hybrid RAG Project on AI Workbench](https://github.com/NVIDIA/workbench-example-hybrid-rag): Run an NVIDIA AI Workbench example project for RAG.\n\n## Documentation\n\n### Getting Started\n\n- [Prerequisites](./docs/common-prerequisites.md)\n\n### How To's\n\n- [Changing the Inference or Embedded Model](./docs/change-model.md)\n- [Customizing the Vector Database](./docs/vector-database.md)\n- [Customizing the Chain Server](./docs/chain-server.md):\n  - [Chunking Strategy](./docs/text-splitter.md)\n  - [Prompting Template Engineering](./docs/prompt-customization.md)\n- [Configuring LLM Parameters at Runtime](./docs/llm-params.md)\n- [Supporting Multi-Turn Conversations](./docs/multiturn.md)\n- [Speaking Queries and Listening to Responses with NVIDIA Riva](./docs/riva-asr-tts.md)\n\n### Reference\n\n- [Support Matrix](./docs/support-matrix.md)\n- [Architecture](./docs/architecture.md)\n- [Using the Sample Chat Web Application](./docs/using-sample-web-application.md)\n- [RAG Playground Web Application](./docs/frontend.md)\n- [Software Component Configuration](./docs/configuration.md)\n\n\n## Community\nWe're posting these examples on GitHub to support the NVIDIA LLM community and facilitate feedback.\nWe invite contributions! Open a GitHub issue or pull request! See [contributing](docs/contributing.md) Check out the [community](./community/README.md) examples and notebooks.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FNVIDIA%2FGenerativeAIExamples","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FNVIDIA%2FGenerativeAIExamples","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FNVIDIA%2FGenerativeAIExamples/lists"}