NVIDIA-NeMo / NVIDIA-NeMo/Guardrails

What are the options to use NeMo Guardrails with Agents until Agent support is added?

Open
#568 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
7.2k
Forks
843
Avg merge
3d 1h
Merged PRs (30d)
25

Description

I am currently looking for ways on how to integrate NeMo Guardrails in my Langchain Agents setup. As I understand the README, official Agent is coming soon, so I wanted to ask what options are already available now?

For example, would it be possible right now to "screen" the user input and the system output via NeMo Guardrails? How would I do that using Langchain? I envision it like this:

User Input -> User Input Screened by NeMo Guardrails -> Passed on to Agent -> System Output Screened by NeMo Guardrails -> System Output.

Thank you for your help.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No file, test, or entry point is named. Start by reading the README section describing agent support and reviewing the existing NeMo Guardrails and LangChain integration guidance. Done would mean documenting a currently supported way to screen user input and system output around a LangChain agent, if one exists.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.