-
**Rasa version**: 2.7.1
**Rasa SDK version** (if used & relevant): 2.7.0
**Rasa X version** (if used & relevant):
**Python version**: 3.8.8
**Operating system** (windows, osx, ...): Wi…
liaeh updated
3 years ago
-
**Rasa version**: 2.5.0
**Rasa SDK version** (if used & relevant): 2.5.0
**Python version**: 3.7.4
**Operating system** (windows, osx, ...): Darwin-19.6.0-x86_64-i386-64bit
**Issue**…
-
**Rasa version**: 2.5.1
**Rasa SDK version** (if used & relevant): 2.5.0
**Rasa X version** (if used & relevant): None
**Python version**: 3.6.12
**Operating system** (windows, osx, ..…
-
**Description of Problem**:
If you want to train your assistant on a large dataset, it might happen that you run into memory issues as the complete dataset is loaded into memory and featurized.
r…
-
**Description of Problem**:
The new architecture will rely on the ability to fingerprint all data that passes through the training graph in-order to determine what needs to be re-run when re-training…
-
**Description of Problem**:
Large trackers can cause a slowdown / memory spike when making a prediction with RulePolicy.
**Definition of Done**:
- [x] Reproduce problem
- [ ] Scope possible fix…
-
I get following error in classification_report
"parameter".format(len(labels), len(target_names)):
ValueError:Number of classes, 5, does not match size of target_names, 10. Try specifying the la…
-
## Problem
The [migration docs](https://rasa.com/docs/rasa/migration-guide/#rasa-17-to-rasa-18) imply that the following configuration in Rasa 2.x:
```
- name: "DIETClassifier"
epochs: 300
…
-
**Rasa version**: 2.4.2
**Rasa SDK version** (if used & relevant):
**Rasa X version** (if used & relevant):
**Python version**: 3.7.6
**Operating system** (windows, osx, ...): macos, D…
-
*This PR is automatically created by the Scheduled Model Regression Test workflow. Checkout the Github Action Run [here](https://github.com/RasaHQ/rasa/actions/runs/717622576).* --- **Description of…