-
TLDR: Seems that LLM output can cause trouble if it evaluates into valid nested dictionaries.
An example where gpt-3.5-turbo produces garbage output that leads into unhandled exceptions (basically…
-
The user prompt must be detected by the guardrail for sensitive requests and return a appropriate response.
* [ ] Implement backend guardrail function which is called when frontend send a request t…
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
Hello Fello's!
I have tried multiple methods and I'm stuck with this one now:
```
…
-
I tried building the simple hello world demo, but I get errors as soon as I import `RailsConfig`:
`rails.py`
```python
from nemoguardrails import RailsConfig
config = RailsConfig.from_path("./…
-
**Describe the bug**
OpenAI output null values for keys are converted to True in the validated response
**To Reproduce**
Steps to reproduce the behavior:
```python
from typing import List, Di…
-
Hello
I was wondering if NeMo is compatible with TitanML, and if so, I want to ask if there are any tutorials with it.
[TitanML](https://docs.titanml.co/docs/intro)
Thanks in advance
-
**Describe the bug**
guard can return invalid object after a failed reask
**To Reproduce**
```
import guardrails as gd
from guardrails.validators import ValidChoices
from pydantic import BaseM…
-
**Description**
We should add Anthropic Claude as an option to `llm_providers.py`
**Why is this needed**
People are asking for it
https://discord.com/channels/1085077079697150023/115693208385644…
-
Not sure what I am doing wrong.
```py
!pip install git+https://github.com/bclavie/RAGatouille.git
from ragatouille import RAGPretrainedModel
RAG = RAGPretrainedModel.from_pretrained("colbert…
-
**Describe the bug**
When using a pydantic model in my rail output, I am getting the following error:
```
Traceback (most recent call last):
File "/Users/chasearmer/PycharmProjects/AnalysisAge…