RasaHQ/rasalit
Visualizations and helpers to improve and debug machine learning models for Rasa Open Source
This tool helps conversation designers and developers understand, debug, and improve their Rasa NLU models. You input your trained Rasa models and NLU training data, and it provides interactive visualizations of model performance, data clusters, and real-time prediction insights. Conversation designers, bot developers, and anyone responsible for the quality of a Rasa-powered chatbot would use this.
311 stars. No commits in the last 6 months.
Use this if you need to visually analyze your Rasa NLU model's behavior, identify misclassified intents, find patterns in unlabelled data, or understand how spelling errors affect predictions.
Not ideal if you are not using Rasa Open Source 2.x for building your conversational AI.
Stars
311
Forks
63
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Feb 10, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/RasaHQ/rasalit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
laresbernardo/lares
Analytics & Machine Learning R Sidekick
lucasmaystre/choix
Inference algorithms for models based on Luce's choice axiom
TheAlgorithms/R
Collection of various algorithms implemented in R.
easystats/performance
:muscle: Models' quality and performance metrics (R2, ICC, LOO, AIC, BF, ...)
mlr-org/mlr
Machine Learning in R