NeMo-Guardrails
NeMo-Guardrails copied to clipboard
NVIDIA
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
Hi team, Is it possible to configure Nemo-Guardrails to avoid sending the actual user input to the LLM? I understand that the actual user input won't be sent if the...
The pattern used in various places is: ```python with llm_params(llm, **params): result = await llm_call(llm, prompt) ``` However, if multiple parallel requests are made, and for example, one of them...
Hello, I am running a function to run only the self_check_output function ``` prompt = "This is a difficult project" messages = [ {"role": "user", "content": "Explain the project in...
I'd like to propose adding support for the Azure OpenAI embedding model. My primary reason for this is to enable the use of the text-embedding-ada-002 model as the embedding model....
Currently I am using the nemo guardrail topical rail like this i have a **config.yml** file ``` instructions: - type: general content: | You are an AI assistant that supports...
Hi i am trying to setup the output guard rail only as per the instructions mentioned in this link https://docs.nvidia.com/nemo/guardrails/user_guides/advanced/generation-options.html#output-rails-only My function is: ``` # sample user input async def...
## Description Add release notes so that recent additions to this large set of HTML pages are more findable. ## Related Issue(s) ## Checklist - [ ] I've read the...
## Description This PR introduces improvements to reasoning trace handling. ## Key Changes - **Reasoning Trace Extraction** - Added `ReasoningExtractionResult` and `ParsedTaskOutput` dataclasses for better encapsulation - Replaced `remove_reasoning_traces` with...
The `return_context` argument has been removed from the LLMRails class methods as it was deprecated. Users are encouraged to use `GenerationOptions.output_vars = True` instead. This change simplifies the interface and...
## Description Revise the GS example: - Replace errant model_name field with model in config.yml. - Remove printing the LLM timing calls. ## Related Issue(s) ## Checklist - [ ]...