Merge pull request RasaHQ#5595 from RasaHQ/train-retrieval-intents

Update POST /model/train endpoint to accept responses

Author: alwx

changelog/5595.improvement.rst

@@ -0,0 +1,2 @@
+Update ``POST /model/train`` endpoint to accept retrieval action responses
+at the ``responses`` key of the JSON payload.

data/test_domains/default_retrieval_intents.yml

@@ -0,0 +1,35 @@
+intents:
+  - greet
+  - goodbye
+  - affirm
+  - deny
+  - mood_great
+  - mood_unhappy
+  - bot_challenge
+  - chitchat
+  - chitchat/ask_name
+  - chitchat/ask_weather
+
+responses:
+  utter_greet:
+    - text: Hey! How are you?
+  utter_cheer_up:
+    - text: 'Here is something to cheer you up:'
+      image: https://i.imgur.com/nGF1K8f.jpg
+  utter_did_that_help:
+    - text: Did that help you?
+  utter_happy:
+    - text: Great, carry on!
+  utter_goodbye:
+    - text: Bye
+  utter_iamabot:
+    - text: I am a bot, powered by Rasa.
+
+actions:
+  - respond_chitchat
+  - utter_greet
+  - utter_cheer_up
+  - utter_did_that_help
+  - utter_happy
+  - utter_goodbye
+  - utter_iamabot

data/test_nlu/default_retrieval_intents.md

@@ -0,0 +1,65 @@
+## intent:greet
+- hey
+- hello
+- hi
+- good morning
+- good evening
+- hey there
+
+## intent:goodbye
+- bye
+- goodbye
+- see you around
+- see you later
+
+## intent:affirm
+- yes
+- indeed
+- of course
+- that sounds good
+- correct
+
+## intent:deny
+- no
+- never
+- I don't think so
+- don't like that
+- no way
+- not really
+
+## intent:mood_great
+- perfect
+- very good
+- great
+- amazing
+- wonderful
+- I am feeling very good
+- I am great
+- I'm good
+
+## intent:mood_unhappy
+- sad
+- very sad
+- unhappy
+- bad
+- very bad
+- awful
+- terrible
+- not very good
+- extremely sad
+- so sad
+
+## intent:bot_challenge
+- are you a bot?
+- are you a human?
+- am I talking to a bot?
+- am I talking to a human?
+
+## intent:chitchat/ask_name
+- what's your name
+- who are you?
+- what are you called?
+
+## intent:chitchat/ask_weather
+- how's weather?
+- is it sunny where you are?

data/test_responses/default.md

@@ -0,0 +1,7 @@
+## ask name
+* chitchat/ask_name
+    - my name is Sara, Rasa's documentation bot!
+
+## ask weather
+* chitchat/ask_weather
+    - it's always sunny where I live

data/test_stories/stories_retrieval_intents.md

@@ -0,0 +1,35 @@
+## happy path
+* greet
+  - utter_greet
+* mood_great
+  - utter_happy
+
+## sad path 1
+* greet
+  - utter_greet
+* mood_unhappy
+  - utter_cheer_up
+  - utter_did_that_help
+* affirm
+  - utter_happy
+
+## sad path 2
+* greet
+  - utter_greet
+* mood_unhappy
+  - utter_cheer_up
+  - utter_did_that_help
+* deny
+  - utter_goodbye
+
+## say goodbye
+* goodbye
+  - utter_goodbye
+
+## bot challenge
+* bot_challenge
+  - utter_iamabot
+
+## chitchat
+* chitchat
+   - respond_chitchat

docs/_static/spec/rasa.yml

@@ -1291,6 +1291,8 @@ components:
           $ref: '#/components/schemas/ConfigFile'
         nlu:
           $ref: '#/components/schemas/NLUTrainingData'
+        responses:
+          $ref: '#/components/schemas/RetrievalIntentsTrainingData'
         stories:
           $ref: '#/components/schemas/StoriesTrainingData'
         force:
@@ -1355,6 +1357,17 @@ components:
 
         - unhappy
 
+    RetrievalIntentsTrainingData:
+      type: string
+      description: Rasa response texts for retrieval intents in markdown format
+      example:  >-
+        ## ask name
+        * chitchat/ask_name
+            - my name is Sara, Rasa's documentation bot!
+
+        ## ask weather
+        * chitchat/ask_weather
+            - it's always sunny where I live
 
     StoriesTrainingData:
       type: string

rasa/server.py

@@ -771,6 +771,10 @@ async def train(request: Request) -> HTTPResponse:
             stories_path = os.path.join(temp_dir, "stories.md")
             rasa.utils.io.write_text_file(rjs["stories"], stories_path)
 
+        if "responses" in rjs:
+            responses_path = os.path.join(temp_dir, "responses.md")
+            rasa.utils.io.write_text_file(rjs["responses"], responses_path)
+
         domain_path = DEFAULT_DOMAIN_PATH
         if "domain" in rjs:
             domain_path = os.path.join(temp_dir, "domain.yml")

tests/test_server.py

@@ -432,6 +432,42 @@ def test_train_core_success(
     assert os.path.exists(os.path.join(model_path, "fingerprint.json"))
 
 
+def test_train_with_retrieval_events_success(rasa_app, default_stack_config):
+    with ExitStack() as stack:
+        domain_file = stack.enter_context(
+            open("data/test_domains/default_retrieval_intents.yml")
+        )
+        config_file = stack.enter_context(open(default_stack_config))
+        core_file = stack.enter_context(
+            open("data/test_stories/stories_retrieval_intents.md")
+        )
+        responses_file = stack.enter_context(open("data/test_responses/default.md"))
+        nlu_file = stack.enter_context(
+            open("data/test_nlu/default_retrieval_intents.md")
+        )
+
+        payload = dict(
+            domain=domain_file.read(),
+            config=config_file.read(),
+            stories=core_file.read(),
+            responses=responses_file.read(),
+            nlu=nlu_file.read(),
+        )
+
+    _, response = rasa_app.post("/model/train", json=payload)
+    assert response.status == 200
+
+    # save model to temporary file
+    tempdir = tempfile.mkdtemp()
+    model_path = os.path.join(tempdir, "model.tar.gz")
+    with open(model_path, "wb") as f:
+        f.write(response.body)
+
+    # unpack model and ensure fingerprint is present
+    model_path = unpack_model(model_path)
+    assert os.path.exists(os.path.join(model_path, "fingerprint.json"))
+
+
 def test_train_missing_config(rasa_app: SanicTestClient):
     payload = dict(domain="domain data", config=None)