Duplicate from pvanand/RASA_Omdena_demo_model_feature_followup_actions_server

.dockerignore

@@ -0,0 +1,35 @@
+# Include any files or directories that you don't want to be copied to your
+# container here (e.g., local build artifacts, temporary files, etc.).
+#
+# For more help, visit the .dockerignore file reference guide at
+# https://docs.docker.com/engine/reference/builder/#dockerignore-file
+
+**/.DS_Store
+**/__pycache__
+**/.venv
+**/.classpath
+**/.dockerignore
+**/.env
+**/.git
+**/.gitignore
+**/.project
+**/.settings
+**/.toolstarget
+**/.vs
+**/.vscode
+**/*.*proj.user
+**/*.dbmdl
+**/*.jfm
+**/bin
+**/charts
+**/docker-compose*
+**/compose*
+**/Dockerfile*
+**/node_modules
+**/npm-debug.log
+**/obj
+**/secrets.dev.yaml
+**/values.dev.yaml
+LICENSE
+README.md
+**/tests

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+.rasa

Dockerfile

@@ -0,0 +1,49 @@
+# syntax=docker/dockerfile:1
+
+# Comments are provided throughout this file to help you get started.
+# If you need more help, visit the Dockerfile reference guide at
+# https://docs.docker.com/engine/reference/builder/
+
+ARG PYTHON_VERSION=3.8
+FROM python:${PYTHON_VERSION}-slim as base
+
+# Copy the requirements file into the container.
+COPY requirements.txt .
+
+# Install the dependencies from the requirements file.
+RUN python -m pip install --no-cache-dir -r requirements.txt
+
+
+# Prevents Python from writing pyc files.
+ENV PYTHONDONTWRITEBYTECODE=1
+
+# Keeps Python from buffering stdout and stderr to avoid situations where
+# the application crashes without emitting any logs due to buffering.
+ENV PYTHONUNBUFFERED=1
+
+WORKDIR /app
+# Copy the source code into the container.
+COPY . .
+
+# Create a non-privileged user that the app will run under.
+# See https://docs.docker.com/develop/develop-images/dockerfile_best-practices/#user
+# Switch to the non-privileged user to run the application.
+
+# Run the Python script to generate the FAISS index and save the model.
+RUN python create_faiss_index.py
+
+USER 1001
+
+ENTRYPOINT [ "rasa" ]
+
+# Expose the port that the application listens on.
+EXPOSE 7860
+
+# Get secret openai and mount it
+RUN --mount=type=secret,id=openai,mode=0444,required=true 
+
+# To specify model path
+CMD ["run","actions","--port","7860"]
+
+#CMD ["python", "actions/actions_llm.py"]
+

README.md

@@ -0,0 +1,12 @@
+---
+title: pvanand/RASA_Omdena_demo_model_feature_followup
+emoji: 🏆
+colorFrom: yellow
+colorTo: green
+sdk: docker
+pinned: false
+license: mit
+duplicated_from: pvanand/RASA_Omdena_demo_model_feature_followup_actions_server
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

actions/actions.py

@@ -0,0 +1,213 @@
+# This files contains your custom actions which can be used to run
+# custom Python code.
+#
+# See this guide on how to implement these action:
+# https://rasa.com/docs/rasa/custom-actions
+
+from typing import Any, Text, Dict, List
+from rasa_sdk import Action, Tracker
+from rasa_sdk.events import SlotSet, FollowupAction
+from rasa_sdk.executor import CollectingDispatcher
+import random
+import os
+import sys
+import openai
+
+# Add "/app/actions" to the sys.path
+actions_path = os.path.abspath("/app/actions")
+sys.path.insert(0, actions_path)
+
+print("-#-System-path-#-")
+for path in sys.path:
+    print(path)
+print("-#-END-OF-System-path-#-")
+# Import search_content.py from /actions folder
+from search_content import main_search
+
+
+# Import api key from secrets
+secret_value_0 = os.environ.get("openai")
+
+openai.api_key = secret_value_0
+# Provide your OpenAI API key
+
+def generate_openai_response(query, model_engine="text-davinci-002", max_tokens=124, temperature=0.8):
+    """Generate a response using the OpenAI API."""
+    
+    # Run the main function from search_content.py and store the results in a variable
+    results = main_search(query)
+
+    # Create context from the results
+    context = "".join([f"#{str(i)}" for i in results])[:2014] # Trim the context to 2014 characters - Modify as necessory
+    prompt_template = f"Relevant context: {context}\n\n Answer the question in detail: {query}"
+
+    # Generate a response using the OpenAI API
+    response = openai.Completion.create(
+        engine=model_engine,
+        prompt=prompt_template,
+        max_tokens=max_tokens,
+        temperature=temperature,
+        n=1,
+        stop=None,
+    )
+
+    return response.choices[0].text.strip()
+
+class GetOpenAIResponse(Action):
+
+    def name(self) -> Text:
+        return "action_get_response_openai"
+
+    def run(self,
+            dispatcher: CollectingDispatcher,
+            tracker: Tracker,
+            domain: Dict[Text, Any]) -> List[Dict[Text, Any]]:
+
+        # Use OpenAI API to generate a response
+        query = tracker.latest_message.get('text')
+        response = generate_openai_response(query)
+                
+        # Output the generated response to user
+        dispatcher.utter_message(text=response)
+                
+class GeneralHelp(Action):
+    def name(self) -> Text:
+        return "action_general_help"
+
+    def run(self, dispatcher: CollectingDispatcher,
+            tracker: Tracker,
+            domain: Dict[Text, Any]) -> List[Dict[Text, Any]]:
+        
+        user_role = tracker.slots.get("user_role", None)
+        
+        if user_role is None:
+            dispatcher.utter_message(text="Sure! Are you a developer or a client representing an organization?")
+        else:
+            return [FollowupAction("action_help_with_role")]
+
+# Modified from @Rohit Garg's code https://github.com/rohitkg83/Omdena/blob/master/actions/actions.py
+class ActionHelpWithRole(Action):
+
+    def name(self) -> Text:
+        return "action_help_with_role"
+
+    def run(self,
+            dispatcher: CollectingDispatcher,
+            tracker: Tracker,
+            domain: Dict[Text, Any]) -> List[Dict[Text, Any]]:
+
+        # Get the value of the first_occurrence_user_type slot
+        current_user_type = tracker.slots.get("user_role", None)
+   
+        if current_user_type == 'developer':
+            msg = "Thanks a lot for providing the details. You can join one of our local chapter and collaborate on " \
+                    "various projects and challenges to Develop Your Skills, Get Recognized, and Make an Impact. Please " \
+                    "visit https://omdena.com/community for more details. Do you have any other questions? "
+
+        elif current_user_type == 'client':
+            msg = "Thanks a lot for providing the details. With us you can Innovate, Deploy and Scale " \
+                    "AI Solutions in Record Time. For more details please visit https://omdena.com/offerings. Do you have any other questions? "
+        else:
+            msg = "Please enter either developer or client"
+
+        dispatcher.utter_message(text=msg)
+
+class ResetSlotsAction(Action):
+    def name(self) -> Text:
+        return "action_reset_slots"
+
+    def run(self, dispatcher: CollectingDispatcher,
+            tracker: Tracker,
+            domain: Dict[Text, Any]) -> List[Dict[Text, Any]]:
+        slots_to_reset = ["user_role"]  # Add the names of the slots you want to reset
+        events = [SlotSet(slot, None) for slot in slots_to_reset]
+        return events
+
+class ActionJoinClassify(Action):
+
+    def name(self) -> Text:
+        return "action_join_classify"
+
+    def run(self,
+            dispatcher: CollectingDispatcher,
+            tracker: Tracker,
+            domain: Dict[Text, Any]) -> List[Dict[Text, Any]]:
+
+        # Get the value of the latest intent 
+        last_intent = tracker.slots.get("local_chapter", None)
+
+        # Check if the last intent was 'local_chapter'
+        if last_intent == 'local chapter':
+            dispatcher.utter_message(template="utter_join_chapter")
+        else:
+            return [FollowupAction("action_get_response_openai")]
+            
+
+
+class ActionEligibilityClassify(Action):
+
+    def name(self) -> Text:
+        return "action_eligibility_classify"
+
+    def run(self,
+            dispatcher: CollectingDispatcher,
+            tracker: Tracker,
+            domain: Dict[Text, Any]) -> List[Dict[Text, Any]]:
+
+        # Get the value of the latest intent 
+        last_intent = tracker.slots.get("local_chapter", None)
+
+        # Check if the last intent was 'local_chapter'
+        if last_intent == 'local chapter':
+            dispatcher.utter_message(template="utter_local_chapter_participation_eligibility")
+        else:
+            return [FollowupAction("action_get_response_openai")]
+
+ 
+class ActionCostClassify(Action):
+
+    def name(self) -> Text:
+        return "action_cost_classify"
+
+    def run(self,
+            dispatcher: CollectingDispatcher,
+            tracker: Tracker,
+            domain: Dict[Text, Any]) -> List[Dict[Text, Any]]:
+
+        # Get the value of the latest intent 
+        last_intent = tracker.slots.get("local_chapter", None)
+
+        # Check if the last intent was 'local_chapter'
+        if last_intent == 'local chapter':
+            dispatcher.utter_message(template="utter_local_chapter_cost")
+        else:
+            return [FollowupAction("action_get_response_openai")]
+
+class SayHelloWorld(Action):
+
+    def name(self) -> Text:
+        return "action_hello_world"
+
+    def run(self,
+            dispatcher: CollectingDispatcher,
+            tracker: Tracker,
+            domain: Dict[Text, Any]) -> List[Dict[Text, Any]]:
+
+        # Use OpenAI API to generate a response
+        secret_value_0 = os.environ.get("openai")
+        openai.api_key = secret_value_0
+        model_engine = "text-davinci-002"
+        prompt_template = "Say hello world"
+
+        response = openai.Completion.create(
+            engine=model_engine,
+            prompt=prompt_template,
+            max_tokens=124,
+            temperature=0.8,
+            n=1,
+            stop=None,
+        )
+
+        # Output the generated response to user
+        generated_text = response.choices[0].text
+        dispatcher.utter_message(text=generated_text)

actions/actions_llm.py

@@ -0,0 +1,47 @@
+# run_search.py
+import os
+import sys
+import openai
+
+# Add "/actions" to the sys.path
+actions_path = os.path.abspath("/actions")
+sys.path.insert(0, actions_path)
+
+# Import search_content.py from /actions folder
+from search_content import main_search
+
+
+# Import api key from secrets
+secret_value_0 = os.environ.get("openai")
+
+openai.api_key = secret_value_0
+# Provide your OpenAI API key
+
+def generate_openai_response(query, model_engine="text-davinci-002", max_tokens=124, temperature=0.8):
+    """Generate a response using the OpenAI API."""
+    # Run the main function from search_content.py and store the results in a variable
+    results = main_search(query)
+
+    # Create context from the results
+    context = "".join([f"#{str(i)}" for i in results])[:2014] # Trim the context to 2014 characters - Modify as necessory
+    prompt_template = f"Relevant context: {context}\n\n Answer the question in detail: {query}"
+
+    # Generate a response using the OpenAI API
+    response = openai.Completion.create(
+        engine=model_engine,
+        prompt=prompt_template,
+        max_tokens=max_tokens,
+        temperature=temperature,
+        n=1,
+        stop=None,
+    )
+
+    return response.choices[0].text.strip()
+
+def main():
+    query = "What is omdena local chapters, how a developer can benifit from it"
+    response = generate_openai_response(query)
+    print(response)
+
+if __name__ == "__main__":
+    main()

actions/search_content.py

@@ -0,0 +1,61 @@
+# search_content.py
+
+import faiss
+import pandas as pd
+from sentence_transformers import SentenceTransformer
+
+# Define paths for model, Faiss index, and data file
+MODEL_SAVE_PATH = "all-distilroberta-v1-model.pkl"
+FAISS_INDEX_FILE_PATH = "index.faiss"
+DATA_FILE_PATH = "omdena_qna_dataset/omdena_faq_training_data.csv"
+
+def load_transformer_model(model_file):
+    """Load a sentence transformer model from a file."""
+    return SentenceTransformer.load(model_file)
+
+def load_faiss_index(filename):
+    """Load a Faiss index from a file."""
+    return faiss.read_index(filename)
+
+def load_data(file_path):
+    """Load data from a CSV file and preprocess it."""
+    data_frame = pd.read_csv(file_path)
+    data_frame["id"] = data_frame.index
+    
+    # Create a 'QNA' column that combines 'Questions' and 'Answers'
+    data_frame['QNA'] = data_frame.apply(lambda row: f"Question: {row['Questions']}, Answer: {row['Answers']}", axis=1)
+    return data_frame.set_index(["id"], drop=False)
+
+def search_content(query, data_frame_indexed, transformer_model, faiss_index, k=5):
+    """Search the content using a query and return the top k results."""
+    # Encode the query using the model
+    query_vector = transformer_model.encode([query])
+    
+    # Normalize the query vector
+    faiss.normalize_L2(query_vector)
+    
+    # Search the Faiss index using the query vector
+    top_k = faiss_index.search(query_vector, k)
+    
+    # Extract the IDs and similarities of the top k results
+    ids = top_k[1][0].tolist()
+    similarities = top_k[0][0].tolist()
+    
+    # Get the corresponding results from the data frame
+    results = data_frame_indexed.loc[ids]
+    
+    # Add a column for the similarities
+    results["similarities"] = similarities
+    return results
+
+def main_search(query):
+    """Main function to execute the search."""
+    transformer_model = load_transformer_model(MODEL_SAVE_PATH)
+    faiss_index = load_faiss_index(FAISS_INDEX_FILE_PATH)
+    data_frame_indexed = load_data(DATA_FILE_PATH)
+    results = search_content(query, data_frame_indexed, transformer_model, faiss_index)
+    return results['Answers']  # return the 'Answers' column
+
+if __name__ == "__main__":
+    query = "school courses"
+    print(main_search(query))  # print the results if this script is run directly

app.py

@@ -0,0 +1,20 @@
+import os
+import openai
+
+secret_value_0 = os.environ.get("openai")
+
+openai.api_key = secret_value_0
+
+model_engine = "text-davinci-002"
+prompt_template = "Say hello world" #prompt_template
+
+response = openai.Completion.create(
+    engine=model_engine,
+    prompt=prompt_template,
+    max_tokens=124,
+    temperature=0.8,
+    n=1,
+    stop=None,
+)
+
+print(response.choices[0].text)

compose.yaml

@@ -0,0 +1,49 @@
+# Comments are provided throughout this file to help you get started.
+# If you need more help, visit the Docker compose reference guide at
+# https://docs.docker.com/compose/compose-file/
+
+# Here the instructions define your application as a service called "server".
+# This service is built from the Dockerfile in the current directory.
+# You can add other services your application may depend on here, such as a
+# database or a cache. For examples, see the Awesome Compose repository:
+# https://github.com/docker/awesome-compose
+services:
+  server:
+    build:
+      context: .
+    ports:
+      - 7860:7860
+
+# The commented out section below is an example of how to define a PostgreSQL
+# database that your application can use. `depends_on` tells Docker Compose to
+# start the database before your application. The `db-data` volume persists the
+# database data between container restarts. The `db-password` secret is used
+# to set the database password. You must create `db/password.txt` and add
+# a password of your choosing to it before running `docker compose up`.
+#     depends_on:
+#       db:
+#         condition: service_healthy
+#   db:
+#     image: postgres
+#     restart: always
+#     user: postgres
+#     secrets:
+#       - db-password
+#     volumes:
+#       - db-data:/var/lib/postgresql/data
+#     environment:
+#       - POSTGRES_DB=example
+#       - POSTGRES_PASSWORD_FILE=/run/secrets/db-password
+#     expose:
+#       - 5432
+#     healthcheck:
+#       test: [ "CMD", "pg_isready" ]
+#       interval: 10s
+#       timeout: 5s
+#       retries: 5
+# volumes:
+#   db-data:
+# secrets:
+#   db-password:
+#     file: db/password.txt
+

config.yml

@@ -0,0 +1,50 @@
+# The config recipe.
+# https://rasa.com/docs/rasa/model-configuration/
+recipe: default.v1
+
+# The assistant project unique identifier
+# This default value must be replaced with a unique assistant name within your deployment
+assistant_id: placeholder_default
+
+# Configuration for Rasa NLU.
+# https://rasa.com/docs/rasa/nlu/components/
+language: en
+
+pipeline:
+# # No configuration for the NLU pipeline was provided. The following default pipeline was used to train your model.
+# # If you'd like to customize it, uncomment and adjust the pipeline.
+# # See https://rasa.com/docs/rasa/tuning-your-model for more information.
+#   - name: WhitespaceTokenizer
+#   - name: RegexFeaturizer
+#   - name: LexicalSyntacticFeaturizer
+#   - name: CountVectorsFeaturizer
+#   - name: CountVectorsFeaturizer
+#     analyzer: char_wb
+#     min_ngram: 1
+#     max_ngram: 4
+#   - name: DIETClassifier
+#     epochs: 100
+#     constrain_similarities: true
+#   - name: EntitySynonymMapper
+#   - name: ResponseSelector
+#     epochs: 100
+#     constrain_similarities: true
+#   - name: FallbackClassifier
+#     threshold: 0.3
+#     ambiguity_threshold: 0.1
+
+# Configuration for Rasa Core.
+# https://rasa.com/docs/rasa/core/policies/
+policies:
+# # No configuration for policies was provided. The following default policies were used to train your model.
+# # If you'd like to customize them, uncomment and adjust the policies.
+# # See https://rasa.com/docs/rasa/policies for more information.
+#   - name: MemoizationPolicy
+#   - name: RulePolicy
+#   - name: UnexpecTEDIntentPolicy
+#     max_history: 5
+#     epochs: 100
+#   - name: TEDPolicy
+#     max_history: 5
+#     epochs: 100
+#     constrain_similarities: true

create_faiss_index.py

@@ -0,0 +1,58 @@
+# -*- coding: utf-8 -*-
+"""create_faiss_index.py
+"""
+
+import pandas as pd
+import numpy as np
+import faiss
+from sentence_transformers import InputExample, SentenceTransformer
+
+DATA_FILE_PATH = "omdena_qna_dataset/omdena_faq_training_data.csv"
+TRANSFORMER_MODEL_NAME = "all-distilroberta-v1"
+CACHE_DIR_PATH = "../working/cache/"
+MODEL_SAVE_PATH = "all-distilroberta-v1-model.pkl"
+FAISS_INDEX_FILE_PATH = "index.faiss"
+
+def load_data(file_path):
+    qna_dataset = pd.read_csv(file_path)
+    qna_dataset["id"] = qna_dataset.index
+    return qna_dataset.dropna(subset=['Answers']).copy()
+
+def create_input_examples(qna_dataset):
+    qna_dataset['QNA'] = qna_dataset.apply(lambda row: f"Question: {row['Questions']}, Answer: {row['Answers']}", axis=1)
+    return qna_dataset.apply(lambda x: InputExample(texts=[x["QNA"]]), axis=1).tolist()
+
+def load_transformer_model(model_name, cache_folder):
+    transformer_model = SentenceTransformer(model_name, cache_folder=cache_folder)
+    return transformer_model
+
+def save_transformer_model(transformer_model, model_file):
+    transformer_model.save(model_file)
+    
+def create_faiss_index(transformer_model, qna_dataset):
+    faiss_embeddings = transformer_model.encode(qna_dataset.Answers.values.tolist())
+    qna_dataset_indexed = qna_dataset.set_index(["id"], drop=False)
+    id_index_array = np.array(qna_dataset_indexed.id.values).flatten().astype("int")
+    normalized_embeddings = faiss_embeddings.copy()
+    faiss.normalize_L2(normalized_embeddings)
+    faiss_index = faiss.IndexIDMap(faiss.IndexFlatIP(len(faiss_embeddings[0])))
+    faiss_index.add_with_ids(normalized_embeddings, id_index_array)
+    return faiss_index
+
+def save_faiss_index(faiss_index, filename):
+    faiss.write_index(faiss_index, filename)
+
+def load_faiss_index(filename):
+    return faiss.read_index(filename)
+
+def main():
+    qna_dataset = load_data(DATA_FILE_PATH)
+    input_examples = create_input_examples(qna_dataset)
+    transformer_model = load_transformer_model(TRANSFORMER_MODEL_NAME, CACHE_DIR_PATH)
+    save_transformer_model(transformer_model, MODEL_SAVE_PATH)
+    faiss_index = create_faiss_index(transformer_model, qna_dataset)
+    save_faiss_index(faiss_index, FAISS_INDEX_FILE_PATH)
+    faiss_index = load_faiss_index(FAISS_INDEX_FILE_PATH)
+
+if __name__ == "__main__":
+    main()

credentials.yml

@@ -0,0 +1,33 @@
+# This file contains the credentials for the voice & chat platforms
+# which your bot is using.
+# https://rasa.com/docs/rasa/messaging-and-voice-channels
+
+rest:
+#  # you don't need to provide anything here - this channel doesn't
+#  # require any credentials
+
+
+#facebook:
+#  verify: "<verify>"
+#  secret: "<your secret>"
+#  page-access-token: "<your page access token>"
+
+#slack:
+#  slack_token: "<your slack token>"
+#  slack_channel: "<the slack channel>"
+#  slack_signing_secret: "<your slack signing secret>"
+
+socketio:
+  user_message_evt: user_uttered
+  bot_message_evt: bot_uttered
+  session_persistence: true
+
+#mattermost:
+#  url: "https://<mattermost instance>/api/v4"
+#  token: "<bot token>"
+#  webhook_url: "<callback URL>"
+
+# This entry is needed if you are using Rasa Enterprise. The entry represents credentials
+# for the Rasa Enterprise "channel", i.e. Talk to your bot and Share with guest testers.
+rasa:
+  url: "http://localhost:5002/api"

data/nlu.yml

@@ -0,0 +1,91 @@
+version: "3.1"
+
+nlu:
+- intent: greet
+  examples: |
+    - hey
+    - hello
+    - hi
+    - hello there
+    - good morning
+    - good evening
+    - moin
+    - hey there
+    - let's go
+    - hey dude
+    - goodmorning
+    - goodevening
+    - good afternoon
+
+- intent: goodbye
+  examples: |
+    - cu
+    - good by
+    - cee you later
+    - good night
+    - bye
+    - goodbye
+    - have a nice day
+    - see you around
+    - bye bye
+    - see you later
+
+- intent: affirm
+  examples: |
+    - yes
+    - y
+    - indeed
+    - of course
+    - that sounds good
+    - correct
+
+- intent: deny
+  examples: |
+    - no
+    - n
+    - never
+    - I don't think so
+    - don't like that
+    - no way
+    - not really
+
+- intent: mood_great
+  examples: |
+    - perfect
+    - great
+    - amazing
+    - feeling like a king
+    - wonderful
+    - I am feeling very good
+    - I am great
+    - I am amazing
+    - I am going to save the world
+    - super stoked
+    - extremely good
+    - so so perfect
+    - so good
+    - so perfect
+
+- intent: mood_unhappy
+  examples: |
+    - my day was horrible
+    - I am sad
+    - I don't feel very well
+    - I am disappointed
+    - super sad
+    - I'm so sad
+    - sad
+    - very sad
+    - unhappy
+    - not good
+    - not very good
+    - extremly sad
+    - so saad
+    - so sad
+
+- intent: bot_challenge
+  examples: |
+    - are you a bot?
+    - are you a human?
+    - am I talking to a bot?
+    - am I talking to a human?

data/rules.yml

@@ -0,0 +1,13 @@
+version: "3.1"
+
+rules:
+
+- rule: Say goodbye anytime the user says goodbye
+  steps:
+  - intent: goodbye
+  - action: utter_goodbye
+
+- rule: Say 'I am a bot' anytime the user challenges
+  steps:
+  - intent: bot_challenge
+  - action: utter_iamabot

data/stories.yml

@@ -0,0 +1,30 @@
+version: "3.1"
+
+stories:
+
+- story: happy path
+  steps:
+  - intent: greet
+  - action: utter_greet
+  - intent: mood_great
+  - action: utter_happy
+
+- story: sad path 1
+  steps:
+  - intent: greet
+  - action: utter_greet
+  - intent: mood_unhappy
+  - action: utter_cheer_up
+  - action: utter_did_that_help
+  - intent: affirm
+  - action: utter_happy
+
+- story: sad path 2
+  steps:
+  - intent: greet
+  - action: utter_greet
+  - intent: mood_unhappy
+  - action: utter_cheer_up
+  - action: utter_did_that_help
+  - intent: deny
+  - action: utter_goodbye

domain.yml

@@ -0,0 +1,34 @@
+version: "3.1"
+
+intents:
+  - greet
+  - goodbye
+  - affirm
+  - deny
+  - mood_great
+  - mood_unhappy
+  - bot_challenge
+
+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."
+
+session_config:
+  session_expiration_time: 60
+  carry_over_slots_to_new_session: true

endpoints.yml

@@ -0,0 +1,42 @@
+# This file contains the different endpoints your bot can use.
+
+# Server where the models are pulled from.
+# https://rasa.com/docs/rasa/model-storage#fetching-models-from-a-server
+
+#models:
+#  url: http://my-server.com/models/default_core@latest
+#  wait_time_between_pulls:  10   # [optional](default: 100)
+
+# Server which runs your custom actions.
+# https://rasa.com/docs/rasa/custom-actions
+
+action_endpoint:
+ url: "http://localhost:7860/webhook"
+
+# Tracker store which is used to store the conversations.
+# By default the conversations are stored in memory.
+# https://rasa.com/docs/rasa/tracker-stores
+
+#tracker_store:
+#    type: redis
+#    url: <host of the redis instance, e.g. localhost>
+#    port: <port of your redis instance, usually 6379>
+#    db: <number of your database within redis, e.g. 0>
+#    password: <password used for authentication>
+#    use_ssl: <whether or not the communication is encrypted, default false>
+
+#tracker_store:
+#    type: mongod
+#    url: <url to your mongo instance, e.g. mongodb://localhost:27017>
+#    db: <name of the db within your mongo instance, e.g. rasa>
+#    username: <username used for authentication>
+#    password: <password used for authentication>
+
+# Event broker which all conversation events should be streamed to.
+# https://rasa.com/docs/rasa/event-brokers
+
+#event_broker:
+#  url: localhost
+#  username: username
+#  password: password
+#  queue: queue

readme.txt

@@ -0,0 +1,2 @@
+API DEBUG COLAB
+https://colab.research.google.com/drive/1iDJmwVHloe65ajywejV4PDwGY3D6rIFX?usp=sharing

requirements.txt

@@ -0,0 +1,9 @@
+rasa
+transformers==4.11.0
+datasets
+torch
+numpy
+pandas
+openai
+faiss-cpu==1.7.4 
+sentence_transformers