NeMo-Guardrails icon indicating copy to clipboard operation
NeMo-Guardrails copied to clipboard

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Results 351 NeMo-Guardrails issues
Sort by recently updated
recently updated
newest added

Hi I have created some basic rails and those work well with the chat. However, when i try to launch it with the UI, i have this error when i...

documentation
enhancement
question

I want to use custom embedding and custom llm (which are bascally API endpoints )to integrate with nemo guardrails. I already have it implemented in langchain. how do i use...

question

Hello. I understand that the way to pass context to chat in API format is "role":"context". What if I want to put a specific value in the Context variable on...

question

response = rails.generate(messages=[{ "role": "user", "content": "What is the capital of France?" }]) print(response["content"]) WARNING: nemoguardrails.actions.action_dispatcher:Error while execution generate_user_intent: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}...

bug
status: waiting confirmation

While using nemo guardrail it supports sagemaker endpoint in provider list but when try to do inference then it generating complete garbage responce. This is the code snippet I am...

Added support for calling embedding models from `langchain-nvidia-ai-endpoints` and included user guide for this. Added embedding model and engine information to internal events logged to verify model used for creating...

`action` decorator does not preserve the decorator argument options if applied to staticmethods or classmethods. For example: ```python import os from nemoguardrails import LLMRails from nemoguardrails import RailsConfig from nemoguardrails.actions.actions...

Hello. I have a question about managing conversation history. I want to save the history and state of an ongoing conversation, recall an existing conversation based on a key value,...

question

Hi @drazvan I dont see Azurechatopenai supports parameters like top_p, presence_penalty,frequency_penalty. But its supported by AzureOpenAI, but this is supported in Nemo LLM providers. Please clarify, if we can use,...

status: needs info

When [Langfuse](https://github.com/langfuse/langfuse/) is used for tracing (instead of Langsmith), the usage of NeMo-Guardrails in a Langchain chain completely breaks the tracing functionality. The reason seems to be, that the langchain...

enhancement
good first issue
status: help wanted