Merge branch 'master' into git_ignore_fix

.deepsource.toml

@@ -0,0 +1,12 @@
+version = 1
+
+test_patterns = ["tests/**"]
+
+exclude_patterns = ["docs/**"]
+
+[[analyzers]]
+name = "python"
+enabled = true
+
+  [analyzers.meta]
+  runtime_version = "3.x.x"

.dockerignore

@@ -3,4 +3,4 @@ docs
 .git*
 **/*.pyc
 **/__pycache__
-
+!docker/configs

.github/ISSUE_TEMPLATE/bug_report.md

@@ -2,7 +2,7 @@
 name: Bug report
 about: Create a report to help us improve
 title: ''
-labels: bug
+labels: 'area:rasa-oss :ferris_wheel:,type:bug :bug:'
 assignees: ''
 
 ---
@@ -13,6 +13,8 @@ If you are asking a usage question (e.g. "How do I do xyz") please post your que
 
 **Rasa version**:
 
+**Rasa SDK version** (if used & relevant):
+
 **Rasa X version** (if used & relevant):
 
 **Python version**:

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,5 @@
+blank_issues_enabled: false
+contact_links:
+  - name: Ask a question
+    url: https://forum.rasa.com/
+    about: If you have a "How do I?" question please ask in the forum https://forum.rasa.com

.github/ISSUE_TEMPLATE/feature_request.md

@@ -2,7 +2,7 @@
 name: Feature request
 about: Suggest an idea on how to improve Rasa
 title: ''
-labels: enhancement
+labels: 'area:rasa-oss :ferris_wheel:,type:enhancement :sparkles:'
 assignees: ''
 
 ---

.github/PULL_REQUEST_TEMPLATE.md

@@ -2,8 +2,7 @@
 - ...
 
 **Status (please check what you already did)**:
-- [ ] made PR ready for code review
 - [ ] added some tests for the functionality
 - [ ] updated the documentation
-- [ ] updated the changelog
-- [ ] reformat files using `black` (please check [Readme](https://github.com/RasaHQ/rasa_nlu#code-style) for instructions)
+- [ ] updated the changelog (please check [changelog](https://github.com/RasaHQ/rasa/tree/master/changelog) for instructions)
+- [ ] reformat files using `black` (please check [Readme](https://github.com/RasaHQ/rasa#code-style) for instructions)

.github/configs/mr-test-example.yaml

@@ -0,0 +1,32 @@
+## Example configuration
+#################### syntax #################
+## include:
+##   - dataset: ["<dataset_name>"]
+##     config: ["<configuration_name>"]
+#
+## Example:
+## include:
+##  - dataset: ["Carbon Bot"]
+##    config: ["Sparse + DIET(bow) + ResponseSelector(bow)"]
+#
+## Shortcut:
+## You can use the "all" shortcut to include all available configurations or datasets
+#
+## Example: Use the "Sparse + EmbeddingIntent + ResponseSelector(bow)" configuration
+## for all available datasets
+## include:
+##  - dataset: ["all"]
+##    config: ["Sparse + DIET(bow) + ResponseSelector(bow)"]
+#
+## Example: Use all available configurations for the "Carbon Bot" and "Sara" datasets
+## and for the "Hermit" dataset use the "Sparse + DIET + ResponseSelector(T2T)" and
+## "Sparse + ConveRT + DIET + ResponseSelector(T2T)" configurations:
+## include:
+##  - dataset: ["Carbon Bot", "Sara"]
+##    config: ["all"]
+##  - dataset: ["Hermit"]
+##    config: ["Sparse + DIET(seq) + ResponseSelector(t2t)", "Sparse + ConveRT + DIET(seq) + ResponseSelector(t2t)"]
+
+include:
+  - dataset: ["Carbon Bot"]
+    config: ["Sparse + DIET(bow) + ResponseSelector(bow)"]

.github/configs/mr-test-schedule.yaml

@@ -0,0 +1,63 @@
+##########
+## Available datasets
+##########
+# - "Carbon Bot"
+# - "Hermit"
+# - "Private 1"
+# - "Private 2"
+# - "Private 3"
+# - "Sara"
+
+##########
+## Available configurations
+##########
+# - "BERT + DIET(bow) + ResponseSelector(bow)"
+# - "BERT + DIET(seq) + ResponseSelector(t2t)"
+# - "ConveRT + DIET(bow) + ResponseSelector(bow)"
+# - "ConveRT + DIET(seq) + ResponseSelector(t2t)"
+# - "Spacy + DIET(bow) + ResponseSelector(bow)"
+# - "Spacy + DIET(seq) + ResponseSelector(t2t)"
+# - "Sparse + ConveRT + DIET(bow) + ResponseSelector(bow)"
+# - "Sparse + ConveRT + DIET(seq) + ResponseSelector(t2t)"
+# - "Sparse + DIET(bow) + ResponseSelector(bow)"
+# - "Sparse + DIET(seq) + ResponseSelector(t2t)"
+# - "Sparse + Spacy + DIET(bow) + ResponseSelector(bow)"
+# - "Sparse + Spacy + DIET(seq) + ResponseSelector(t2t)"
+
+## Example configuration
+#################### syntax #################
+## include:
+##   - dataset: <dataset_name>
+##     config: <configuration_name>
+#
+#include:
+#  - dataset: "Carbon Bot"
+#    config: "Sparse + EmbeddingIntent + ResponseSelector(bow)"
+###
+# matrix
+###
+# dataset: [<dataset>]
+# config: [<config>]
+
+
+dataset:
+  - "Carbon Bot"
+  - "Sara"
+  - "Hermit"
+  - "Private 1"
+  - "Private 2"
+  - "Private 3"
+
+config:
+  - "BERT + DIET(bow) + ResponseSelector(bow)"
+  - "BERT + DIET(seq) + ResponseSelector(t2t)"
+  - "ConveRT + DIET(bow) + ResponseSelector(bow)"
+  - "ConveRT + DIET(seq) + ResponseSelector(t2t)"
+  - "Spacy + DIET(bow) + ResponseSelector(bow)"
+  - "Spacy + DIET(seq) + ResponseSelector(t2t)"
+  - "Sparse + ConveRT + DIET(bow) + ResponseSelector(bow)"
+  - "Sparse + ConveRT + DIET(seq) + ResponseSelector(t2t)"
+  - "Sparse + DIET(bow) + ResponseSelector(bow)"
+  - "Sparse + DIET(seq) + ResponseSelector(t2t)"
+  - "Sparse + Spacy + DIET(bow) + ResponseSelector(bow)"
+  - "Sparse + Spacy + DIET(seq) + ResponseSelector(t2t)"

.github/dependabot.yml

@@ -0,0 +1,21 @@
+version: 2
+updates:
+- package-ecosystem: pip
+  directory: "/"
+  schedule:
+    interval: monthly
+    time: '13:00'
+  pull-request-branch-name:
+    separator: "-"
+  open-pull-requests-limit: 10
+  reviewers:
+  - alwx
+  labels:
+  - type:dependencies
+  ignore:
+  - dependency-name: prompt-toolkit
+    versions:
+    - "> 2.0.10"
+  - dependency-name: pytest-asyncio
+    versions:
+    - "> 0.10.0"

.github/no-response.yml

@@ -3,7 +3,7 @@
 # Number of days of inactivity before an Issue is closed for lack of response
 daysUntilClose: 14
 # Label requiring a response
-responseRequiredLabel: more-information-needed
+responseRequiredLabel: status:more-details-needed
 # Comment to post when closing an Issue for lack of response. Set to `false` to disable
 closeComment: >
   This issue has been automatically closed because there has been no response

.github/runner/github-runner-deployment.yaml.tmpl

@@ -0,0 +1,74 @@
+# GitHub Runner deployment - uses to deploy a github runner
+# which is used by the CI for model regression tests
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: github-runner-{{getenv "GITHUB_RUN_ID"}}
+  namespace: github-runner
+  labels:
+    app: github-runner
+    pod: github-runner-{{getenv "GITHUB_RUN_ID"}}
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: github-runner
+      pod: github-runner-{{getenv "GITHUB_RUN_ID"}}
+  template:
+    metadata:
+      labels:
+        app: github-runner
+        pod: github-runner-{{getenv "GITHUB_RUN_ID"}}
+    spec:
+      priorityClassName: high-priority
+      automountServiceAccountToken: false
+      terminationGracePeriodSeconds: 180
+      containers:
+      - name: github-runner
+        image: us.gcr.io/rasa-platform/github-runner:latest
+        imagePullPolicy: Always
+        livenessProbe:
+          initialDelaySeconds: 30
+          periodSeconds: 15
+          failureThreshold: 3
+          exec:
+            command:
+            - /bin/bash
+            - -c
+            - "if [[ `curl -sX GET -H \"Authorization: token ${GITHUB_PAT}\" \
+              https://api.github.com/repos/${GITHUB_OWNER}/${GITHUB_REPOSITORY}/actions/runners | \
+              jq -r '.runners[] | select(.name == \"'${POD_NAME}'\") | .status'` == \"offline\" ]]; then \
+              echo \"The GitHub API returns offline status for the ${POD_NAME} runner\" && exit 1; fi"
+        resources:
+          limits:
+            nvidia.com/gpu: 1
+          requests:
+            nvidia.com/gpu: 1
+            memory: 10Gi
+        env:
+        - name: POD_NAME
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.name
+        # RUNNER_LABELS - defines labels
+        # with which a github-runner will be registered
+        - name: RUNNER_LABELS
+          value: "self-hosted,gpu,kubernetes"
+        # GITHUB_OWNER - a name of the repository owner
+        - name: GITHUB_OWNER
+          valueFrom:
+            secretKeyRef:
+              name: github-rasa
+              key: owner
+        # GITHUB_REPOSITORY - a name of the repository
+        - name: GITHUB_REPOSITORY
+          valueFrom:
+            secretKeyRef:
+              name: github-rasa
+              key: repository
+        # GITHUB_PAT - Personal Access Token
+        - name: GITHUB_PAT
+          valueFrom:
+            secretKeyRef:
+              name: github-rasa
+              key: pat

.github/scripts/mr_generate_summary.py

@@ -0,0 +1,60 @@
+# Collect the results of the various model test runs which are done as part of
+# The model regression CI pipeline and dump them as a single file artifact.This artifact will the then be published at the end of the tests.
+import json
+import os
+
+SUMMARY_FILE = os.environ["SUMMARY_FILE"]
+CONFIG = os.environ["CONFIG"]
+DATASET = os.environ["DATASET_NAME"]
+task_mapping = {
+    "intent_report.json": "intent_classification",
+    "CRFEntityExtractor_report.json": "entity_prediction",
+    "DIETClassifier_report.json": "entity_prediction",
+    "response_selection_report.json": "response_selection",
+}
+
+
+def generate_json(file, task, data):
+    if not DATASET in data:
+        data = {DATASET: {CONFIG: {}}, **data}
+    elif not CONFIG in data[DATASET]:
+        data[DATASET] = {CONFIG: {}, **data[DATASET]}
+
+    data[DATASET][CONFIG] = {
+        "accelerator_type": os.environ["ACCELERATOR_TYPE"],
+        "test_run_time": os.environ["TEST_RUN_TIME"],
+        "train_run_time": os.environ["TRAIN_RUN_TIME"],
+        "total_run_time": os.environ["TOTAL_RUN_TIME"],
+        **data[DATASET][CONFIG],
+    }
+
+    data[DATASET][CONFIG][task] = {**read_results(file)}
+
+    return data
+
+
+def read_results(file):
+    with open(file) as json_file:
+        data = json.load(json_file)
+
+        keys = ["accuracy", "weighted avg", "macro avg", "micro avg"]
+        result = {key: data[key] for key in keys if key in data}
+
+    return result
+
+
+if __name__ == "__main__":
+    data = {}
+    if os.path.exists(SUMMARY_FILE):
+        with open(SUMMARY_FILE) as json_file:
+            data = json.load(json_file)
+
+    for dirpath, dirnames, files in os.walk(os.environ["RESULT_DIR"]):
+        for f in files:
+            if f not in task_mapping.keys():
+                continue
+
+            data = generate_json(os.path.join(dirpath, f), task_mapping[f], data)
+
+    with open(SUMMARY_FILE, "w") as f:
+        json.dump(data, f, sort_keys=True, indent=2)