Comments (4)
Thanks for the follow up @Serbernari! Yes, it is now possible. It appears this feature is not documented. There's a brief mention in the docstring for the generate_async
function: https://github.com/NVIDIA/NeMo-Guardrails/blob/develop/nemoguardrails/rails/llm/llmrails.py#L491.
[
{"role": "context", "content": {"user_name": "John"}},
{"role": "user", "content": "Hello! How are you?"},
{"role": "assistant", "content": "I am fine, thank you!"},
{"role": "event", "event": {"type": "UserSilent"}},
...
]
So, you have to use "role": "event"
. The type is important as this will be used for matching. For example, in the above example, a flow would match the UserSilent
event with:
define flow
event UserSilent
bot ask question again
Let me know if you need more information at this point. We'll update the docs in the coming weeks.
from nemo-guardrails.
Not yet, but it's a feature that is already on our short list as it's been requested multiple times. Right now you can do a hack and make a convention to define special canonical forms that represent events e.g.
define user event X
"event X"
So, essentially when you want to trigger the event, you just send the text "event X".
from nemo-guardrails.
okay, thanks @drazvan
from nemo-guardrails.
any update on that?
from nemo-guardrails.
Related Issues (20)
- Issue with azure openAI Api key HOT 3
- AzureOpenAI is not supported HOT 6
- NeMo-Guardrails breaks Langfuse integration / Runnable config is ignored in LLM call
- Problems integrating Guardrails in Langchain / Answer quality and streaming HOT 1
- How to save and load conversation history ? HOT 1
- How to initialize the Context variable in the UI HOT 2
- Sagemaker endpoint not integrated
- UI not working - ASGI exception HOT 8
- Support for Text Embeddings Inference HOT 2
- Value Error for GPT 3.5 HOT 1
- Input guardrails error HOT 1
- Running several Rails until completion regardless of the outcome? HOT 1
- groq not supported - would help having fast inference HOT 7
- RunnableRails performance weirdness HOT 3
- Add support to register custom embedding models
- Support for custom embedding model
- Instance of embedding search provider in action HOT 3
- Change "Failed to register" action message from DEBUG to ERROR
- `generate_events` fails with colang 2.0 HOT 7
- [BUG] llm_params from GenerationOptions are not considered during generate_user_intent in generation.py when single_call is False HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from nemo-guardrails.