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.
This fixes some issues to enable the design with undefined user intent flows.
Hi, do you have in your plans to update the code to make it compatible with the newest langchain versions? Thanks a lot!
Hi I self hosted a NIM of Llama3 8B and would like to use this config to test out guardrails: ``` models: - type: main engine: nim model: meta/llama3-8b-instruct parameters:...
Below is my `config.yml` file and `rails.co` file contents : `config.yml` ``` models: - type: main engine: openai model: gpt-3.5-turbo instructions: - type: general content: | You are a helpful...
With the introduction of $self we no longer need this restriction for variable names.
Unify uuid generation function calls such that the uuid are consistent for multiple runs in debug mode
python call : from nemoguardrails import LLMRails rails = LLMRails(config) messages=[{ "role": "user", "content": "what is an mbr ?" }] options = {"output_vars": True} output = rails.generate(messages=messages, options=options) print(output) config.yml...
Cleanlab's latest release (v2.5 on 09/20) to `cleanlab-studio` pypi package updates the return type of `get_trustworthiness_score_async()` method from `float` to `typeddict`. Therefore, the `trustworthiness_score` is indexed out from the typed...
I am not able to implement guardrails on Azure GPT-4 Turbo Vision models. Can you please share of any options available to implement guardrails on images
