Razvan Dinu

@Serbernari : currently we don't have support for a similarity threshold in `embeddings_only` mode. I'll mark this as a feature request. If you're interested in contributing this, let me know...

Hi @rblazsek! I think this is because you're using an input key called `"question"` rather than `"input"`. You can pass the input key value to `RunnableRails` constructor: ```python guardrails =...

@rblazsek : what's the content of `rails.co`? Typically you need to make sure you have enough examples for both on-topic and off-topic.

@rblazsek: to debug this further I suggest to run `nemoguardrails chat --config=PATH_TO_CONFIG --verbose` and then share the log. This will enable us to check if it's the input rail blocking...

Thanks @rblazsek. Based on the log, it seems that the self-check input rail is blocking the request. I guess the prompt used does not work well for this model. If...

Hi @thomasbtnfr ! We've seen this before related to the installation of `annoy`. Try updating your deployment to install `annoy` explicitly after installing `nemoguardrails`: `pip install --force --no-binary :all: annoy==1.17.1`...

@rblazsek : as I was suspecting, the LLM is blocking the request. It hallucinates. ``` Invocation Params {'model': 'luminous-supreme', 'maximum_tokens': 64, 'temperature': 0.0, 'top_k': 0, 'top_p': 0.0, 'presence_penalty': 0.0, 'frequency_penalty':...

Yes. I think with this prompt some will be answered, some not, but it doesn't seem to follow the instructions. Maybe having a few-shots prompt with some examples would help...

Hi @thomasbtnfr! Did you make any progress on this? I can guide you to use a mock `EmbeddingSearchProvider` (which won't use `annoy`) to check if that's the issue.

Hi @cmpeburak! If an action needs access to the entire history, adding an `events: List[dict]` parameter is the way to go. To transform the complete list of events into a...