[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:nemo-guardrails":3},"\u003Ch1>NVIDIA NeMo Guardrails Library\u003C\u002Fh1>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fopensource.org\u002Flicenses\u002FApache-2.0\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-Apache_2.0-blue.svg\" alt=\"License\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Fnemoguardrails\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fnemoguardrails\" alt=\"PyPI\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Fnemoguardrails\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fpyversions\u002Fnemoguardrails\" alt=\"PyPI - Python Version\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FNVIDIA-NeMo\u002FGuardrails\u002Factions\u002Fworkflows\u002Fpr-tests.yml\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002FNVIDIA-NeMo\u002FGuardrails\u002Fpr-tests.yml?logo=github&label=Tests%2FLinux\" alt=\"Tests\u002FLinux\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FNVIDIA-NeMo\u002FGuardrails\u002Factions\u002Fworkflows\u002Ffull-tests.yml\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002FNVIDIA-NeMo\u002FGuardrails\u002Ffull-tests.yml?logo=github&label=Tests%2FWindows\" alt=\"Tests\u002FWindows\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FNVIDIA-NeMo\u002FGuardrails\u002Factions\u002Fworkflows\u002Ffull-tests.yml\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002FNVIDIA-NeMo\u002FGuardrails\u002Ffull-tests.yml?logo=github&label=Tests%2FmacOS\" alt=\"Tests\u002FmacOS\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FNVIDIA-NeMo\u002FGuardrails\u002Factions\u002Fworkflows\u002Flint.yml\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002FNVIDIA-NeMo\u002FGuardrails\u002Flint.yml?logo=github&label=Lint\" alt=\"Lint\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fpsf\u002Fblack\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcode%20style-black-000000.svg\" alt=\"Code style: black\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fdocs.nvidia.com\u002Fnemo\u002Fguardrails\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdocs-nvidia.com-blue.svg\" alt=\"Documentation\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.10501\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcs.CL-arXiv%3A2310.10501-b31b1b.svg\" alt=\"arXiv\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fpepy.tech\u002Fproject\u002Fnemoguardrails\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fstatic.pepy.tech\u002Fbadge\u002Fnemoguardrails\" alt=\"Downloads\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fpepy.tech\u002Fproject\u002Fnemoguardrails\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fstatic.pepy.tech\u002Fbadge\u002Fnemoguardrails\u002Fmonth\" alt=\"Downloads\" \u002F>\u003C\u002Fa>\u003C\u002Fp>\n\u003Cblockquote>\n\u003Cp>\u003Cstrong>LATEST RELEASE \u002F DEVELOPMENT VERSION\u003C\u002Fstrong>: The \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FNVIDIA-NeMo\u002FGuardrails\u002Ftree\u002Fdevelop\" rel=\"nofollow ugc noopener\">develop\u003C\u002Fa> branch tracks the latest top of tree development. The latest released version is \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FNVIDIA-NeMo\u002FGuardrails\u002Ftree\u002Fv0.23.0\" rel=\"nofollow ugc noopener\">0.23.0\u003C\u002Fa>.\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Cp>✨✨✨\u003C\u002Fp>\n\u003Cp>📌 \u003Cstrong>The official NeMo Guardrails library documentation is available at \u003Ca href=\"https:\u002F\u002Fdocs.nvidia.com\u002Fnemo\u002Fguardrails\" rel=\"nofollow ugc noopener\">docs.nvidia.com\u002Fnemo\u002Fguardrails\u003C\u002Fa>.\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cp>✨✨✨\u003C\u002Fp>\n\u003Cp>NVIDIA NeMo Guardrails library is an open-source toolkit for easily adding \u003Cem>programmable guardrails\u003C\u002Fem> to LLM-based conversational applications. Guardrails (or \"rails\" for short) are specific ways of controlling the output of a large language model, such as not talking about politics, responding in a particular way to specific user requests, following a predefined dialog path, using a particular language style, extracting structured data, and more.\u003C\u002Fp>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.10501\" rel=\"nofollow ugc noopener\">This paper\u003C\u002Fa> introduces the NeMo Guardrails library and contains a technical overview of the system and the current evaluation.\u003C\u002Fp>\n\u003Ch2>Requirements\u003C\u002Fh2>\n\u003Cp>Python 3.10, 3.11, 3.12 or 3.13.\u003C\u002Fp>\n\u003Ch2>Installation\u003C\u002Fh2>\n\u003Cp>To install using pip:\u003C\u002Fp>\n\u003Cpre>\u003Ccode class=\"language-bash\">> pip install nemoguardrails\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>For more detailed instructions, see the \u003Ca href=\"https:\u002F\u002Fdocs.nvidia.com\u002Fnemo\u002Fguardrails\u002Fget-started\u002Finstallation-guide\" rel=\"nofollow ugc noopener\">Installation Guide\u003C\u002Fa>.\u003C\u002Fp>\n\u003Ch2>Overview\u003C\u002Fh2>\n\u003Cp>The NeMo Guardrails library enables developers building LLM-based applications to add \u003Cstrong>programmable guardrails\u003C\u002Fstrong> between the application code and the LLM.\u003C\u002Fp>\n\u003Cdiv align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FNVIDIA-NeMo\u002FGuardrails\u002Fraw\u002Fdevelop\u002Fdocs\u002F_static\u002Fimages\u002Fprogrammable_guardrails.png\" width=\"75%\" alt=\"Programmable Guardrails\" \u002F>\n\u003C\u002Fdiv>\u003Cp>Key benefits of adding \u003Cem>programmable guardrails\u003C\u002Fem> include:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cp>\u003Cstrong>Building Trustworthy, Safe, and Secure LLM-based Applications:\u003C\u002Fstrong> you can define rails to guide and safeguard conversations; you can choose to define the behavior of your LLM-based application on specific topics and prevent it from engaging in discussions on unwanted topics.\u003C\u002Fp>\n\u003C\u002Fli>\n\u003Cli>\u003Cp>\u003Cstrong>Connecting models, chains, and other services securely:\u003C\u002Fstrong> you can connect an LLM to other services (a.k.a. tools) seamlessly and securely.\u003C\u002Fp>\n\u003C\u002Fli>\n\u003Cli>\u003Cp>\u003Cstrong>Controllable dialog\u003C\u002Fstrong>: you can steer the LLM t\u003C\u002Fp>\n\u003C\u002Fli>\n\u003C\u002Ful>\n",1784240407703]