Merged in develop (pull request #51)

Develop

.dockerignore

@@ -5,3 +5,6 @@ README.md
 *.pyd
 __pycache__
 .pytest_cache
+postman
+/scripts
+/.venv

.env

@@ -1,3 +0,0 @@
-OPENAI_API_KEY=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
-JWT_SECRET_KEY=6e9c124ba92e8814719dcb0f21200c8aa4d0f119a994ac5e06eb90a366c83ab2
-JWT_TEST_TOKEN=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiJ0ZXN0In0.Emrs2D3BmMP4b3zMjw0fJTPeyMwWEBDbxx2vvaWguO0

.gitignore

@@ -1,2 +1,7 @@
 __pycache__
-.idea
+.idea
+.env
+.DS_Store
+.venv
+_scripts
+*.env

.idea/.gitignore

@@ -1,8 +0,0 @@
-# Default ignored files
-/shelf/
-/workspace.xml
-# Editor-based HTTP Client requests
-/httpRequests/
-# Datasource local storage ignored files
-/dataSources/
-/dataSources.local.xml

.idea/ielts-be.iml

@@ -1,21 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<module type="PYTHON_MODULE" version="4">
-  <component name="Flask">
-    <option name="enabled" value="true" />
-  </component>
-  <component name="NewModuleRootManager">
-    <content url="file://$MODULE_DIR$">
-      <excludeFolder url="file://$MODULE_DIR$/venv" />
-    </content>
-    <orderEntry type="jdk" jdkName="Python 3.9" jdkType="Python SDK" />
-    <orderEntry type="sourceFolder" forTests="false" />
-  </component>
-  <component name="TemplatesService">
-    <option name="TEMPLATE_CONFIGURATION" value="Jinja2" />
-    <option name="TEMPLATE_FOLDERS">
-      <list>
-        <option value="$MODULE_DIR$/../flaskProject\templates" />
-      </list>
-    </option>
-  </component>
-</module>

.idea/inspectionProfiles/profiles_settings.xml

@@ -1,6 +0,0 @@
-<component name="InspectionProjectProfileManager">
-  <settings>
-    <option name="USE_PROJECT_PROFILE" value="false" />
-    <version value="1.0" />
-  </settings>
-</component>

.idea/misc.xml

@@ -1,4 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9" project-jdk-type="Python SDK" />
-</project>

.idea/modules.xml

@@ -1,8 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="ProjectModuleManager">
-    <modules>
-      <module fileurl="file://$PROJECT_DIR$/.idea/ielts-be.iml" filepath="$PROJECT_DIR$/.idea/ielts-be.iml" />
-    </modules>
-  </component>
-</project>

.idea/vcs.xml

@@ -1,6 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="VcsDirectoryMappings">
-    <mapping directory="$PROJECT_DIR$" vcs="Git" />
-  </component>
-</project>

Dockerfile

@@ -1,6 +1,12 @@
+FROM python:3.11-slim as requirements-stage
+WORKDIR /tmp
+RUN pip install poetry
+COPY pyproject.toml ./poetry.lock* /tmp/
+# https://python-poetry.org/docs/cli#export
+RUN poetry self add poetry-plugin-export
+RUN poetry export -f requirements.txt --output requirements.txt --without-hashes
+
 
-# Use the official lightweight Python image.
-# https://hub.docker.com/_/python
 FROM python:3.11-slim
 
 # Allow statements and log messages to immediately appear in the logs
@@ -9,16 +15,35 @@ ENV PYTHONUNBUFFERED True
 # Copy local code to the container image.
 ENV APP_HOME /app
 WORKDIR $APP_HOME
+
 COPY . ./
 
-# Install production dependencies.
+COPY --from=requirements-stage /tmp/requirements.txt /app/requirements.txt
-RUN pip install --no-cache-dir -r requirements.txt
 
-EXPOSE 5000
+RUN apt update && apt install -y \
+    ffmpeg \
+    poppler-utils \
+    texlive-latex-base \
+    texlive-fonts-recommended \
+    texlive-latex-extra \
+    texlive-xetex \
+    pandoc \
+    librsvg2-bin \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN curl -sL https://deb.nodesource.com/setup_20.x | bash - \
+    && apt-get install -y nodejs
+
+RUN npm install -g firebase-tools
+
+RUN pip install --no-cache-dir -r /app/requirements.txt
+
+EXPOSE 8000
 
 # Run the web service on container startup. Here we use the gunicorn
 # webserver, with one worker process and 8 threads.
 # For environments with multiple CPU cores, increase the number of workers
 # to be equal to the cores available.
 # Timeout is set to 0 to disable the timeouts of the workers to allow Cloud Run to handle instance scaling.
-CMD exec gunicorn --bind 0.0.0.0:5000 --workers 1 --threads 8 --timeout 0 app:app
+ENTRYPOINT ["gunicorn", "--bind", "0.0.0.0:8000", "--workers", "1", "--threads", "8", "--timeout", "0", "-k", "uvicorn.workers.UvicornWorker", "ielts_be:app"]

README.md

@@ -0,0 +1,26 @@
+# Run the app
+
+1. pip install poetry
+2. poetry install
+3. python app.py
+
+# Modules
+
+- api -> endpoints
+- configs -> app configs and constants
+- controllers -> meant for handling exceptions, transforming data or orchestrate complex use cases with several services, for now mostly just calls services directly 
+- dtos -> pydantic models used for receiving data and for validation
+- exceptions -> if custom exceptions are needed to throw in services so they can be handled in the controllers to construct some specific http response
+- helpers -> a bunch of lightweight functions grouped by some kind of logic
+- mappers -> to map complex data
+- middlewares -> classes that are run before executing the endpoint code
+- repositories -> interfaces with data stores
+- services -> all the business logic goes here
+- utils -> loose functions used on one-off occasions
+
+# Dependency injection
+
+If you want to add new controllers/services/repositories you will have to change
+app/configs/dependency_injection.py
+
+Also make sure you have @inject on your endpoint when calling these.

app.py

@@ -1,105 +1,25 @@
-from flask import Flask, request
+import click
-from flask_jwt_extended import JWTManager, jwt_required
+import uvicorn
-from functools import reduce
-from helper.token_counter import count_tokens
-from helper.openai_interface import make_openai_call
-import os
-
 from dotenv import load_dotenv
 
 load_dotenv()
 
-app = Flask(__name__)
 
-app.config['JWT_SECRET_KEY'] = os.getenv("JWT_SECRET_KEY")
+@click.command()
-jwt = JWTManager(app)
+@click.option(
-
+    "--env",
-GRADING_TEMPERATURE = 0.1
+    type=click.Choice(["local", "staging", "production"], case_sensitive=False),
-GEN_QUESTION_TEMPERATURE = 0.7
+    default="staging",
-WRITING_TASK_2_POST_FIELDS = ['overall', 'comment', 'task_response']
+)
-WRITING_TASK_2_GET_FIELDS = ['question']
+def main(env: str):
-
+    uvicorn.run(
-@app.route('/writing_task2', methods=['POST'])
+        app="ielts_be:app",
-@jwt_required()
+        host="localhost",
-def grade_writing_task():
+        port=8000,
-    data = request.get_json()  # Assuming the request data is in JSON format
+        reload=True if env != "production" else False,
-    question = data.get('question')
+        workers=1,
-    answer = data.get('answer')
+    )
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a IELTS examiner.",
-        },
-        {
-            "role": "system",
-            "content": f"The question you have to grade is of type Writing Task 2 and is the following: {question}",
-        },
-        {
-            "role": "user",
-            "content": "It is mandatory for you to provide your response with the overall grade and breakdown grades, "
-                       "in the following json format: {'comment': 'comment about answer quality', 'overall': 7.0, 'task_response': {'Task Achievement': 8.0, "
-                       "'Coherence and Cohesion': 6.5, 'Lexical Resource': 7.5, 'Grammatical Range and Accuracy': "
-                       "6.0}}",
-        },
-        {
-            "role": "user",
-            "content": "Example output: { 'comment': 'Overall, the response is good but there are some areas that need "
-                       "improvement.\n\nIn terms of Task Achievement, the writer has addressed all parts of the question "
-                       "and has provided a clear opinion on the topic. However, some of the points made are not fully "
-                       "developed or supported with examples.\n\nIn terms of Coherence and Cohesion, there is a clear "
-                       "structure to the response with an introduction, body paragraphs and conclusion. However, there "
-                       "are some issues with cohesion as some sentences do not flow smoothly from one to another.\n\nIn "
-                       "terms of Lexical Resource, there is a good range of vocabulary used throughout the response and "
-                       "some less common words have been used effectively.\n\nIn terms of Grammatical Range and Accuracy, "
-                       "there are some errors in grammar and sentence structure which affect clarity in places.\n\nOverall, "
-                       "this response would score a band 6.5.', 'overall': 6.5, 'task_response': "
-                       "{ 'Coherence and Cohesion': 6.5, 'Grammatical Range and Accuracy': 6.0, 'Lexical Resource': 7.0, "
-                       "'Task Achievement': 7.0}}",
-        },
-        {
-            "role": "user",
-            "content": f"Evaluate this answer according to ielts grading system: {answer}",
-        },
-    ]
-    token_count = reduce(lambda count, item: count + count_tokens(item)['n_tokens'],
-                         map(lambda x: x["content"], filter(lambda x: "content" in x, messages)), 0)
-    response = make_openai_call(messages, token_count, WRITING_TASK_2_POST_FIELDS, GRADING_TEMPERATURE)
-    return response
-
-@app.route('/writing_task2', methods=['GET'])
-@jwt_required()
-def get_writing_task_question():
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a IELTS program that generates questions for the exams.",
-        },
-        {
-            "role": "system",
-            "content": "The question you have to generate is of type Writing Task 2 and is the following.",
-        },
-        {
-            "role": "user",
-            "content": "It is mandatory for you to provide your response with the question "
-                       "in the following json format: {'question': 'question'}",
-        },
-        {
-            "role": "user",
-            "content": "Example output: { 'question': 'We are becoming increasingly dependent on computers. "
-                       "They are used in businesses, hospitals, crime detection and even to fly planes. What things will "
-                       "they be used for in the future? Is this dependence on computers a good thing or should we he more "
-                       "auspicious of their benefits?'}",
-        },
-        {
-            "role": "user",
-            "content": "Generate a question for IELTS exam Writing Task 2.",
-        },
-    ]
-    token_count = reduce(lambda count, item: count + count_tokens(item)['n_tokens'],
-                         map(lambda x: x["content"], filter(lambda x: "content" in x, messages)), 0)
-    response = make_openai_call(messages, token_count, WRITING_TASK_2_GET_FIELDS, GEN_QUESTION_TEMPERATURE)
-    return response
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
-    app.run()
+    main()

docker-compose.yml

@@ -1,10 +1,10 @@
-version: "3"
+version: "3"
-
+
-services:
+services:
-  ielts-be:
+  ielts-be:
-    container_name: ielts-be
+    container_name: ielts-be
-    build: .
+    build: .
-    image: ecrop/ielts-be:latest
+    image: ecrop/ielts-be:latest
-    ports:
+    ports:
-      - 8080:5000
+      - 8080:8000
-    restart: unless-stopped
+    restart: unless-stopped

elai/AvatarEnum.py

@@ -0,0 +1,62 @@
+from enum import Enum
+
+
+class AvatarEnum(Enum):
+    # Works
+    GIA_BUSINESS = {
+        "avatar_code": "gia.business",
+        "avatar_gender": "female",
+        "avatar_url": "https://elai-avatars.s3.us-east-2.amazonaws.com/common/gia/business/gia_business.png",
+        "avatar_canvas": "https://elai-avatars.s3.us-east-2.amazonaws.com/common/gia/business/gia_business.png",
+        "voice_id": "EXAVITQu4vr4xnSDxMaL",
+        "voice_provider": "elevenlabs"
+    }
+    # Works
+    VADIM_BUSINESS = {
+        "avatar_code": "vadim.business",
+        "avatar_gender": "male",
+        "avatar_url": "https://elai-avatars.s3.us-east-2.amazonaws.com/common/vadim/business/vadim_business.png",
+        "avatar_canvas": "https://d3u63mhbhkevz8.cloudfront.net/common/vadim/business/vadim_business.png",
+        "voice_id": "flq6f7yk4E4fJM5XTYuZ",
+        "voice_provider": "elevenlabs"
+    }
+    ORHAN_BUSINESS = {
+        "avatar_code": "orhan.business",
+        "avatar_gender": "male",
+        "avatar_url": "https://elai-avatars.s3.us-east-2.amazonaws.com/common/orhan/business/orhan.png",
+        "avatar_canvas": "https://d3u63mhbhkevz8.cloudfront.net/common/orhan/business/orhan.png",
+        "voice_id": "en-US-AndrewMultilingualNeural",
+        "voice_provider": "azure"
+    }
+    FLORA_BUSINESS = {
+        "avatar_code": "flora.business",
+        "avatar_gender": "female",
+        "avatar_url": "https://elai-avatars.s3.us-east-2.amazonaws.com/common/flora/business/flora_business.png",
+        "avatar_canvas": "https://d3u63mhbhkevz8.cloudfront.net/common/flora/business/flora_business.png",
+        "voice_id": "en-US-JaneNeural",
+        "voice_provider": "azure"
+    }
+    SCARLETT_BUSINESS = {
+        "avatar_code": "scarlett.business",
+        "avatar_gender": "female",
+        "avatar_url": "https://elai-avatars.s3.us-east-2.amazonaws.com/common/scarlett/business/scarlett_business.png",
+        "avatar_canvas": "https://d3u63mhbhkevz8.cloudfront.net/common/scarlett/business/scarlett_business.png",
+        "voice_id": "en-US-NancyNeural",
+        "voice_provider": "azure"
+    }
+    PARKER_CASUAL = {
+        "avatar_code": "parker.casual",
+        "avatar_gender": "male",
+        "avatar_url": "https://elai-avatars.s3.us-east-2.amazonaws.com/common/parker/casual/parker_casual.png",
+        "avatar_canvas": "https://d3u63mhbhkevz8.cloudfront.net/common/parker/casual/parker_casual.png",
+        "voice_id": "en-US-TonyNeural",
+        "voice_provider": "azure"
+    }
+    ETHAN_BUSINESS = {
+        "avatar_code": "ethan.business",
+        "avatar_gender": "male",
+        "avatar_url": "https://elai-avatars.s3.us-east-2.amazonaws.com/common/ethan/business/ethan_business_low.png",
+        "avatar_canvas": "https://d3u63mhbhkevz8.cloudfront.net/common/ethan/business/ethan_business_low.png",
+        "voice_id": "en-US-JasonNeural",
+        "voice_provider": "azure"
+    }

elai/filter_json.py

@@ -0,0 +1,18 @@
+import json
+
+# Read JSON from a file
+input_filename = "english_voices.json"
+output_filename = "free_english_voices.json"
+
+with open(input_filename, "r") as json_file:
+    data = json.load(json_file)
+
+# Filter entries based on "language": "English"
+filtered_list = [entry for entry in data["data"]["list"] if not entry["is_paid"]]
+data["data"]["list"] = filtered_list
+
+# Write filtered JSON to a new file
+with open(output_filename, "w") as json_file:
+    json.dump(data, json_file, indent=2)
+
+print(f"Filtered JSON written to '{output_filename}'.")

firebase-configs/encoach-staging.json

@@ -0,0 +1,13 @@
+{
+  "type": "service_account",
+  "project_id": "encoach-staging",
+  "private_key_id": "5718a649419776df9637589f8696a258a6a70f6c",
+  "private_key": "-----BEGIN PRIVATE KEY-----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\n9kwpOmZpjNmC/ERD69imWhY=\n-----END PRIVATE KEY-----\n",
+  "client_email": "firebase-adminsdk-8rs9e@encoach-staging.iam.gserviceaccount.com",
+  "client_id": "108221424237414412378",
+  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+  "token_uri": "https://oauth2.googleapis.com/token",
+  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/firebase-adminsdk-8rs9e%40encoach-staging.iam.gserviceaccount.com",
+  "universe_domain": "googleapis.com"
+}

firebase-configs/mti-ielts-626a2dcf6091.json

@@ -0,0 +1,13 @@
+{
+  "type": "service_account",
+  "project_id": "mti-ielts",
+  "private_key_id": "626a2dcf60916a1b5011f388495b8f9c4fc065ef",
+  "private_key": "-----BEGIN PRIVATE KEY-----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\nTQqp88pfTbOnkdJBVi0AWs5B\n-----END PRIVATE KEY-----\n",
+  "client_email": "firebase-adminsdk-dyg6p@mti-ielts.iam.gserviceaccount.com",
+  "client_id": "104980563453519094431",
+  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+  "token_uri": "https://oauth2.googleapis.com/token",
+  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/firebase-adminsdk-dyg6p%40mti-ielts.iam.gserviceaccount.com",
+  "universe_domain": "googleapis.com"
+}

firebase-configs/storied-phalanx-349916.json

@@ -0,0 +1,13 @@
+{
+  "type": "service_account",
+  "project_id": "storied-phalanx-349916",
+  "private_key_id": "c9e05f6fe413b1031a71f981160075ff4b044444",
+  "private_key": "-----BEGIN PRIVATE KEY-----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\n8sDu//ohb7nCzceEI0DnWs13\n-----END PRIVATE KEY-----\n",
+  "client_email": "firebase-adminsdk-3ml0u@storied-phalanx-349916.iam.gserviceaccount.com",
+  "client_id": "114163760341944984396",
+  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+  "token_uri": "https://oauth2.googleapis.com/token",
+  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/firebase-adminsdk-3ml0u%40storied-phalanx-349916.iam.gserviceaccount.com",
+  "universe_domain": "googleapis.com"
+}

helper/generate_jwt.py

@@ -1,17 +0,0 @@
-import jwt
-import os
-
-from dotenv import load_dotenv
-
-load_dotenv()
-
-# Define the payload (data to be included in the token)
-payload = {'sub': 'test'}
-
-# Define the secret key
-secret_key = os.getenv("JWT_SECRET_KEY")
-
-# Generate the JWT
-jwt_token = jwt.encode(payload, secret_key, algorithm='HS256')
-
-print(jwt_token)

helper/generate_jwt_secret.py

@@ -1,5 +0,0 @@
-import secrets
-
-jwt_secret_key = secrets.token_hex(32)
-
-print(jwt_secret_key)

helper/openai_interface.py

@@ -1,53 +0,0 @@
-import json
-import openai
-import os
-
-from dotenv import load_dotenv
-
-load_dotenv()
-openai.api_key = os.getenv("OPENAI_API_KEY")
-
-
-MAX_TOKENS = 4097
-TOP_P = 0.9
-FREQUENCY_PENALTY = 0.5
-
-TRY_LIMIT = 1
-
-try_count = 0
-def process_response(input_string):
-    json_obj = {}
-    parsed_string = input_string.replace("'", "\"")
-    parsed_string = parsed_string.replace("\n\n", " ")
-    try:
-        json_obj = json.loads(parsed_string)
-    except json.JSONDecodeError:
-        print("Invalid JSON string!")
-
-    return json_obj
-
-def check_fields(obj, fields):
-    return all(field in obj for field in fields)
-
-def make_openai_call(messages, token_count, fields_to_check, temperature):
-    global try_count
-    result = openai.ChatCompletion.create(
-        model="gpt-3.5-turbo",
-        max_tokens=int(MAX_TOKENS - token_count - 300),
-        temperature=float(temperature),
-        top_p=float(TOP_P),
-        frequency_penalty=float(FREQUENCY_PENALTY),
-        messages=messages
-    )
-    processed_response = process_response(result["choices"][0]["message"]["content"])
-    if check_fields(processed_response, fields_to_check) is False and try_count < TRY_LIMIT:
-        try_count = try_count + 1
-        return make_openai_call(messages, token_count, fields_to_check)
-    elif try_count >= TRY_LIMIT:
-        try_count = 0
-        return result["choices"][0]["message"]["content"]
-    else:
-        try_count = 0
-        return processed_response
-
-

ielts_be/__init__.py

@@ -0,0 +1,156 @@
+import json
+import os
+import pathlib
+import logging.config
+import logging.handlers
+
+import aioboto3
+import contextlib
+from contextlib import asynccontextmanager
+from collections import defaultdict
+from typing import List
+from http import HTTPStatus
+
+import httpx
+from fastapi import FastAPI, Request
+from fastapi.encoders import jsonable_encoder
+from fastapi.exceptions import RequestValidationError
+from fastapi.middleware import Middleware
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import JSONResponse
+
+import nltk
+from starlette import status
+
+from ielts_be.api import router
+from ielts_be.configs import DependencyInjector
+from ielts_be.exceptions import CustomException
+from ielts_be.middlewares import AuthenticationMiddleware, AuthBackend
+from ielts_be.services.impl import OpenAIWhisper
+
+
+@asynccontextmanager
+async def lifespan(_app: FastAPI):
+    """
+        Startup and Shutdown logic is in this lifespan method
+
+        https://fastapi.tiangolo.com/advanced/events/
+    """
+
+    # NLTK required datasets download
+    nltk.download('words')
+    nltk.download("punkt")
+
+    # AWS Polly client instantiation
+    context_stack = contextlib.AsyncExitStack()
+    session = aioboto3.Session()
+    polly_client = await context_stack.enter_async_context(
+        session.client(
+            'polly',
+            region_name='eu-west-1',
+            aws_secret_access_key=os.getenv("AWS_SECRET_ACCESS_KEY"),
+            aws_access_key_id=os.getenv("AWS_ACCESS_KEY_ID")
+        )
+    )
+
+    http_client = httpx.AsyncClient()
+    stt = OpenAIWhisper()
+
+    DependencyInjector(
+        polly_client,
+        http_client,
+        stt
+    ).inject()
+
+    # Setup logging
+    config_file = pathlib.Path("./ielts_be/configs/logging/logging_config.json")
+    with open(config_file) as f_in:
+        config = json.load(f_in)
+
+    logging.config.dictConfig(config)
+
+    yield
+
+    stt.close()
+    await http_client.aclose()
+    await polly_client.close()
+    await context_stack.aclose()
+
+
+def setup_listeners(_app: FastAPI) -> None:
+    @_app.exception_handler(RequestValidationError)
+    async def custom_form_validation_error(request, exc):
+        """
+            Don't delete request param
+        """
+        reformatted_message = defaultdict(list)
+        for pydantic_error in exc.errors():
+            loc, msg = pydantic_error["loc"], pydantic_error["msg"]
+            filtered_loc = loc[1:] if loc[0] in ("body", "query", "path") else loc
+            field_string = ".".join(filtered_loc)
+            if field_string == "cookie.refresh_token":
+                return JSONResponse(
+                    status_code=401,
+                    content={"error_code": 401, "message": HTTPStatus.UNAUTHORIZED.description},
+                )
+            reformatted_message[field_string].append(msg)
+
+        return JSONResponse(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            content=jsonable_encoder(
+                {"details": "Invalid request!", "errors": reformatted_message}
+            ),
+        )
+
+    @_app.exception_handler(CustomException)
+    async def custom_exception_handler(request: Request, exc: CustomException):
+        """
+            Don't delete request param
+        """
+        return JSONResponse(
+            status_code=exc.code,
+            content={"error_code": exc.error_code, "message": exc.message},
+        )
+
+    @_app.exception_handler(Exception)
+    async def default_exception_handler(request: Request, exc: Exception):
+        """
+            Don't delete request param
+        """
+        return JSONResponse(
+            status_code=500,
+            content=str(exc),
+        )
+
+
+def setup_middleware() -> List[Middleware]:
+    middleware = [
+        Middleware(
+            CORSMiddleware,
+            allow_origins=["*"],
+            allow_credentials=True,
+            allow_methods=["*"],
+            allow_headers=["*"],
+        ),
+        Middleware(
+            AuthenticationMiddleware,
+            backend=AuthBackend()
+        )
+    ]
+    return middleware
+
+
+def create_app() -> FastAPI:
+    env = os.getenv("ENV")
+    _app = FastAPI(
+        docs_url="/docs" if env != "production" else None,
+        redoc_url="/redoc" if env != "production" else None,
+        middleware=setup_middleware(),
+        lifespan=lifespan
+    )
+    _app.include_router(router)
+    setup_listeners(_app)
+    return _app
+
+
+app = create_app()

ielts_be/api/__init__.py

@@ -0,0 +1,15 @@
+from fastapi import APIRouter
+
+from .training import training_router
+from .user import user_router
+from .exam import exam_router
+
+router = APIRouter(prefix="/api", tags=["Home"])
+
+@router.get('/healthcheck')
+async def healthcheck():
+    return {"healthy": True}
+
+router.include_router(training_router, prefix="/training", tags=["Training"])
+router.include_router(user_router, prefix="/user", tags=["Users"])
+router.include_router(exam_router)

ielts_be/api/exam/__init__.py

@@ -0,0 +1,16 @@
+from fastapi import APIRouter
+
+from .listening import listening_router
+from .reading import reading_router
+from .speaking import speaking_router
+from .writing import writing_router
+from .level import level_router
+from .grade import grade_router
+
+exam_router = APIRouter()
+exam_router.include_router(listening_router, prefix="/listening", tags=["Listening"])
+exam_router.include_router(reading_router, prefix="/reading", tags=["Reading"])
+exam_router.include_router(speaking_router, prefix="/speaking", tags=["Speaking"])
+exam_router.include_router(writing_router, prefix="/writing", tags=["Writing"])
+exam_router.include_router(level_router, prefix="/level", tags=["Level"])
+exam_router.include_router(grade_router, prefix="/grade", tags=["Grade"])

ielts_be/api/exam/grade.py

@@ -0,0 +1,64 @@
+from dependency_injector.wiring import inject, Provide
+from fastapi import APIRouter, Depends, Path, Request, BackgroundTasks
+
+from ielts_be.controllers import IGradeController
+from ielts_be.dtos.writing import WritingGradeTaskDTO
+from ielts_be.middlewares import Authorized, IsAuthenticatedViaBearerToken
+
+controller = "grade_controller"
+grade_router = APIRouter()
+
+
+@grade_router.post(
+    '/writing/{task}',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def grade_writing_task(
+    data: WritingGradeTaskDTO,
+    background_tasks: BackgroundTasks,
+    task: int = Path(..., ge=1, le=2),
+    grade_controller: IGradeController = Depends(Provide[controller])
+):
+    return await grade_controller.grade_writing_task(task, data, background_tasks)
+
+
+@grade_router.post(
+    '/speaking/{task}',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def grade_speaking_task(
+    request: Request,
+    background_tasks: BackgroundTasks,
+    task: int = Path(..., ge=1, le=3),
+    grade_controller: IGradeController = Depends(Provide[controller])
+):
+    form = await request.form()
+    return await grade_controller.grade_speaking_task(task, form, background_tasks)
+
+
+@grade_router.post(
+    '/summary',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def grading_summary(
+    request: Request,
+    grade_controller: IGradeController = Depends(Provide[controller])
+):
+    data = await request.json()
+    return await grade_controller.grading_summary(data)
+
+
+@grade_router.post(
+    '/short_answers',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def grade_short_answers(
+    request: Request,
+    grade_controller: IGradeController = Depends(Provide[controller])
+):
+    data = await request.json()
+    return await grade_controller.grade_short_answers(data)

ielts_be/api/exam/level.py

@@ -0,0 +1,67 @@
+from dependency_injector.wiring import Provide, inject
+from fastapi import APIRouter, Depends, UploadFile, Request
+
+from ielts_be.dtos.level import LevelExercisesDTO
+from ielts_be.middlewares import Authorized, IsAuthenticatedViaBearerToken
+from ielts_be.controllers import ILevelController
+
+controller = "level_controller"
+level_router = APIRouter()
+
+
+@level_router.post(
+    '/',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def generate_exercises(
+    dto: LevelExercisesDTO,
+    level_controller: ILevelController = Depends(Provide[controller])
+):
+    return await level_controller.generate_exercises(dto)
+
+@level_router.get(
+    '/',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def get_level_exam(
+    level_controller: ILevelController = Depends(Provide[controller])
+):
+    return await level_controller.get_level_exam()
+
+
+@level_router.get(
+    '/utas',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def get_level_utas(
+    level_controller: ILevelController = Depends(Provide[controller])
+):
+    return await level_controller.get_level_utas()
+
+
+@level_router.post(
+    '/import/',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def import_level(
+    exercises: UploadFile,
+    solutions: UploadFile = None,
+    level_controller: ILevelController = Depends(Provide[controller])
+):
+    return await level_controller.upload_level(exercises, solutions)
+
+@level_router.post(
+    '/custom/',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def custom_level(
+    request: Request,
+    level_controller: ILevelController = Depends(Provide[controller])
+):
+    data = await request.json()
+    return await level_controller.get_custom_level(data)

ielts_be/api/exam/listening.py

@@ -0,0 +1,89 @@
+import random
+
+from dependency_injector.wiring import Provide, inject
+from fastapi import APIRouter, Depends, Path, Query, UploadFile
+
+from ielts_be.middlewares import Authorized, IsAuthenticatedViaBearerToken
+from ielts_be.controllers import IListeningController
+from ielts_be.configs.constants import EducationalContent
+from ielts_be.dtos.listening import ListeningExercisesDTO, Dialog, InstructionsDTO
+
+controller = "listening_controller"
+listening_router = APIRouter()
+
+@listening_router.post(
+    '/import',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def upload(
+    exercises: UploadFile,
+    solutions: UploadFile = None,
+    listening_controller: IListeningController = Depends(Provide[controller])
+):
+    return await listening_controller.import_exam(exercises, solutions)
+
+
+@listening_router.get(
+    '/{section}',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def generate_listening_dialog(
+    section: int = Path(..., ge=1, le=4),
+    difficulty: str = Query(default=None),
+    topic: str = Query(default=None),
+    listening_controller: IListeningController = Depends(Provide[controller])
+):
+    difficulty = random.choice(EducationalContent.DIFFICULTIES) if not difficulty else difficulty
+    topic = random.choice(EducationalContent.TOPICS) if not topic else topic
+    return await listening_controller.generate_listening_dialog(section, topic, difficulty)
+
+@listening_router.post(
+    '/media',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def generate_mp3(
+    dto: Dialog,
+    listening_controller: IListeningController = Depends(Provide[controller])
+):
+    return await listening_controller.generate_mp3(dto)
+
+
+
+@listening_router.post(
+    '/transcribe',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def transcribe_dialog(
+    audio: UploadFile,
+    listening_controller: IListeningController = Depends(Provide[controller])
+):
+    return await listening_controller.transcribe_dialog(audio)
+
+
+@listening_router.post(
+    '/instructions',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def create_instructions(
+    dto: InstructionsDTO,
+    listening_controller: IListeningController = Depends(Provide[controller])
+):
+    return await listening_controller.create_instructions(dto.text)
+
+
+@listening_router.post(
+    '/',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def generate_listening_exercise(
+    dto: ListeningExercisesDTO,
+    listening_controller: IListeningController = Depends(Provide[controller])
+):
+    return await listening_controller.get_listening_question(dto)
+

ielts_be/api/exam/reading.py

@@ -0,0 +1,51 @@
+import random
+from typing import Optional
+
+from dependency_injector.wiring import Provide, inject
+from fastapi import APIRouter, Depends, Path, Query, UploadFile
+
+from ielts_be.configs.constants import EducationalContent
+from ielts_be.dtos.reading import ReadingDTO
+from ielts_be.middlewares import Authorized, IsAuthenticatedViaBearerToken
+from ielts_be.controllers import IReadingController
+
+controller = "reading_controller"
+reading_router = APIRouter()
+
+
+@reading_router.post(
+    '/import',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def upload(
+    exercises: UploadFile,
+    solutions: UploadFile = None,
+    reading_controller: IReadingController = Depends(Provide[controller])
+):
+    return await reading_controller.import_exam(exercises, solutions)
+
+@reading_router.get(
+    '/{passage}',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def generate_passage(
+    topic: Optional[str] = Query(None),
+    word_count: Optional[int] = Query(None),
+    passage: int = Path(..., ge=1, le=3),
+    reading_controller: IReadingController = Depends(Provide[controller])
+):
+    topic = random.choice(EducationalContent.TOPICS) if not topic else topic
+    return await reading_controller.generate_reading_passage(passage, topic, word_count)
+
+@reading_router.post(
+    '/',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def generate_reading(
+    dto: ReadingDTO,
+    reading_controller: IReadingController = Depends(Provide[controller])
+):
+    return await reading_controller.generate_reading_exercises(dto)

ielts_be/api/exam/speaking.py

@@ -0,0 +1,74 @@
+import random
+from typing import Optional, List
+
+from dependency_injector.wiring import inject, Provide
+from fastapi import APIRouter, Path, Query, Depends
+
+from ielts_be.dtos.speaking import Video
+from ielts_be.middlewares import Authorized, IsAuthenticatedViaBearerToken
+from ielts_be.configs.constants import EducationalContent
+from ielts_be.controllers import ISpeakingController
+
+controller = "speaking_controller"
+speaking_router = APIRouter()
+
+@speaking_router.post(
+    '/media',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def generate_video(
+    video: Video,
+    speaking_controller: ISpeakingController = Depends(Provide[controller])
+):
+    return await speaking_controller.generate_video(video.text, video.avatar)
+
+
+@speaking_router.get(
+    '/media/{vid_id}',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def poll_video(
+    vid_id: str = Path(...),
+    speaking_controller: ISpeakingController = Depends(Provide[controller])
+):
+    return await speaking_controller.poll_video(vid_id)
+
+
+
+@speaking_router.get(
+    '/avatars',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def get_avatars(
+    speaking_controller: ISpeakingController = Depends(Provide[controller])
+):
+    return await speaking_controller.get_avatars()
+
+
+
+@speaking_router.get(
+    '/{task}',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def get_speaking_task(
+    task: int = Path(..., ge=1, le=3),
+    topic: Optional[str] = Query(None),
+    first_topic: Optional[str] = Query(None),
+    second_topic: Optional[str] = Query(None),
+    difficulty: Optional[str] = None,
+    speaking_controller: ISpeakingController = Depends(Provide[controller])
+):
+    if not second_topic:
+        topic_or_first_topic = topic if topic else random.choice(EducationalContent.MTI_TOPICS)
+    else:
+        topic_or_first_topic = first_topic if first_topic else random.choice(EducationalContent.MTI_TOPICS)
+
+    if not difficulty:
+        difficulty = random.choice(random.choice(EducationalContent.DIFFICULTIES))
+
+    second_topic = second_topic if second_topic else random.choice(EducationalContent.MTI_TOPICS)
+    return await speaking_controller.get_speaking_part(task, topic_or_first_topic, second_topic, difficulty)

ielts_be/api/exam/writing.py

@@ -0,0 +1,43 @@
+import random
+from typing import Optional, List
+
+from dependency_injector.wiring import inject, Provide
+from fastapi import APIRouter, Path, Query, Depends, UploadFile, File
+
+from ielts_be.middlewares import Authorized, IsAuthenticatedViaBearerToken
+from ielts_be.configs.constants import EducationalContent
+from ielts_be.controllers import IWritingController
+
+controller = "writing_controller"
+writing_router = APIRouter()
+
+
+@writing_router.post(
+    '/{task}/attachment',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def generate_writing_academic(
+        task: int = Path(..., ge=1, le=2),
+        file: UploadFile = File(...),
+        difficulty: Optional[List[str]] = None,
+        writing_controller: IWritingController = Depends(Provide[controller])
+):
+    difficulty = random.choice(EducationalContent.DIFFICULTIES) if not difficulty else difficulty
+    return await writing_controller.get_writing_task_academic_question(task, file, difficulty)
+
+
+@writing_router.get(
+    '/{task}',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def generate_writing(
+    task: int = Path(..., ge=1, le=2),
+    difficulty: Optional[str] = None,
+    topic: str = Query(default=None),
+    writing_controller: IWritingController = Depends(Provide[controller])
+):
+    difficulty = random.choice(EducationalContent.DIFFICULTIES) if not difficulty else difficulty
+    topic = random.choice(EducationalContent.MTI_TOPICS) if not topic else topic
+    return await writing_controller.get_writing_task_general_question(task, topic, difficulty)

ielts_be/api/home.py

@@ -0,0 +1,9 @@
+from fastapi import APIRouter
+home_router = APIRouter()
+
+
+@home_router.get(
+    '/healthcheck'
+)
+async def healthcheck():
+    return {"healthy": True}

ielts_be/api/training.py

@@ -0,0 +1,34 @@
+from dependency_injector.wiring import Provide, inject
+from fastapi import APIRouter, Depends, Request
+
+from ielts_be.dtos.training import FetchTipsDTO
+from ielts_be.middlewares import Authorized, IsAuthenticatedViaBearerToken
+from ielts_be.controllers import ITrainingController
+
+controller = "training_controller"
+training_router = APIRouter()
+
+
+@training_router.post(
+    '/tips',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def get_reading_passage(
+    data: FetchTipsDTO,
+    training_controller: ITrainingController = Depends(Provide[controller])
+):
+    return await training_controller.fetch_tips(data)
+
+
+@training_router.post(
+    '/',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def training_content(
+    request: Request,
+    training_controller: ITrainingController = Depends(Provide[controller])
+):
+    data = await request.json()
+    return await training_controller.get_training_content(data)

ielts_be/api/user.py

@@ -0,0 +1,21 @@
+from dependency_injector.wiring import Provide, inject
+from fastapi import APIRouter, Depends
+
+from ielts_be.dtos.user_batch import BatchUsersDTO
+from ielts_be.middlewares import Authorized, IsAuthenticatedViaBearerToken
+from ielts_be.controllers import IUserController
+
+controller = "user_controller"
+user_router = APIRouter()
+
+
+@user_router.post(
+    '/import',
+    dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]
+)
+@inject
+async def batch_import(
+    batch: BatchUsersDTO,
+    user_controller: IUserController = Depends(Provide[controller])
+):
+    return await user_controller.batch_import(batch)

ielts_be/configs/__init__.py

@@ -0,0 +1,5 @@
+from .dependency_injection import DependencyInjector
+
+__all__ = [
+    "DependencyInjector"
+]

ielts_be/configs/constants.py

@@ -0,0 +1,780 @@
+from enum import Enum
+
+########################################################################################################################
+# DISCLAIMER                                                                                                           #
+#                                                                                                                      #
+# All the array and dict "constants" are mutable variables, if somewhere in the app you modify them in any way, shape  #
+# or form all the other methods that will use these "constants" will also use the modified version. If you're unsure   #
+# whether a method will modify it use copy's deepcopy:                                                                 #
+#                                                                                                                      #
+# from copy import deepcopy                                                                                            #
+#                                                                                                                      #
+# new_ref = deepcopy(CONSTANT)                                                                                         #
+#                                                                                                                      #
+# Using a wrapper method that returns a "constant" won't handle nested mutables.                                       #
+########################################################################################################################
+
+BLACKLISTED_WORDS = ["jesus", "sex", "gay", "lesbian", "homosexual", "god", "angel", "pornography", "beer", "wine",
+                     "cocaine", "alcohol", "nudity", "lgbt", "casino", "gambling", "catholicism",
+                     "discrimination", "politic", "christianity", "islam", "christian", "christians",
+                     "jews", "jew", "discrimination", "discriminatory"]
+
+
+class UserDefaults:
+    DESIRED_LEVELS = {
+        "reading": 9,
+        "listening": 9,
+        "writing": 9,
+        "speaking": 9,
+    }
+
+    LEVELS = {
+        "reading": 0,
+        "listening": 0,
+        "writing": 0,
+        "speaking": 0,
+    }
+
+
+class ExamVariant(Enum):
+    FULL = "full"
+    PARTIAL = "partial"
+
+
+class ReadingExerciseType(str, Enum):
+    fillBlanks = "fillBlanks"
+    writeBlanks = "writeBlanks"
+    trueFalse = "trueFalse"
+    paragraphMatch = "paragraphMatch"
+    ideaMatch = "ideaMatch"
+    multipleChoice = "multipleChoice"
+
+
+class ListeningExerciseType(str, Enum):
+    multipleChoice = "multipleChoice"
+    multipleChoice3Options = "multipleChoice3Options"
+    writeBlanksQuestions = "writeBlanksQuestions"
+    writeBlanksFill = "writeBlanksFill"
+    writeBlanksForm = "writeBlanksForm"
+    trueFalse = "trueFalse"
+
+class LevelExerciseType(str, Enum):
+    multipleChoice = "multipleChoice"
+    mcBlank = "mcBlank"
+    mcUnderline = "mcUnderline"
+    blankSpace = "blankSpaceText"
+    passageUtas = "passageUtas"
+    fillBlanksMC = "fillBlanksMC"
+
+
+class CustomLevelExerciseTypes(Enum):
+    MULTIPLE_CHOICE_4 = "multiple_choice_4"
+    MULTIPLE_CHOICE_BLANK_SPACE = "multiple_choice_blank_space"
+    MULTIPLE_CHOICE_UNDERLINED = "multiple_choice_underlined"
+    BLANK_SPACE_TEXT = "blank_space_text"
+    READING_PASSAGE_UTAS = "reading_passage_utas"
+    WRITING_LETTER = "writing_letter"
+    WRITING_2 = "writing_2"
+    SPEAKING_1 = "speaking_1"
+    SPEAKING_2 = "speaking_2"
+    SPEAKING_3 = "speaking_3"
+    READING_1 = "reading_1"
+    READING_2 = "reading_2"
+    READING_3 = "reading_3"
+    LISTENING_1 = "listening_1"
+    LISTENING_2 = "listening_2"
+    LISTENING_3 = "listening_3"
+    LISTENING_4 = "listening_4"
+
+
+class QuestionType(Enum):
+    LISTENING_SECTION_1 = "Listening Section 1"
+    LISTENING_SECTION_2 = "Listening Section 2"
+    LISTENING_SECTION_3 = "Listening Section 3"
+    LISTENING_SECTION_4 = "Listening Section 4"
+    WRITING_TASK_1 = "Writing Task 1"
+    WRITING_TASK_2 = "Writing Task 2"
+    SPEAKING_1 = "Speaking Task Part 1"
+    SPEAKING_2 = "Speaking Task Part 2"
+    READING_PASSAGE_1 = "Reading Passage 1"
+    READING_PASSAGE_2 = "Reading Passage 2"
+    READING_PASSAGE_3 = "Reading Passage 3"
+
+
+class FilePaths:
+    AUDIO_FILES_PATH = 'download-audio/'
+    FIREBASE_LISTENING_AUDIO_FILES_PATH = 'listening_recordings/'
+    VIDEO_FILES_PATH = 'download-video/'
+    FIREBASE_SPEAKING_VIDEO_FILES_PATH = 'speaking_videos/'
+    FIREBASE_FAILED_TRANSCRIPTION_FILES_PATH = 'failed_transcriptions/'
+    WRITING_ATTACHMENTS = 'writing_attachments/'
+
+
+class TemperatureSettings:
+    GRADING_TEMPERATURE = 0.1
+    TIPS_TEMPERATURE = 0.2
+    GEN_QUESTION_TEMPERATURE = 0.7
+
+
+class GPTModels:
+    GPT_3_5_TURBO = "gpt-3.5-turbo"
+    GPT_4_TURBO = "gpt-4-turbo"
+    GPT_4_O = "gpt-4o"
+    GPT_3_5_TURBO_16K = "gpt-3.5-turbo-16k"
+    GPT_3_5_TURBO_INSTRUCT = "gpt-3.5-turbo-instruct"
+    GPT_4_PREVIEW = "gpt-4-turbo-preview"
+
+
+class FieldsAndExercises:
+    GRADING_FIELDS = ['comment', 'overall', 'task_response']
+    GEN_FIELDS = ['topic']
+    GEN_TEXT_FIELDS = ['title']
+    LISTENING_GEN_FIELDS = ['transcript', 'exercise']
+    READING_EXERCISE_TYPES = ['fillBlanks', 'writeBlanks', 'trueFalse', 'paragraphMatch']
+    READING_3_EXERCISE_TYPES = ['fillBlanks', 'writeBlanks', 'trueFalse', 'paragraphMatch', 'ideaMatch']
+
+    LISTENING_EXERCISE_TYPES = ['multipleChoice', 'writeBlanksQuestions', 'writeBlanksFill', 'writeBlanksForm']
+    LISTENING_1_EXERCISE_TYPES = ['multipleChoice', 'writeBlanksQuestions', 'writeBlanksFill', 'writeBlanksFill',
+                                  'writeBlanksForm', 'writeBlanksForm', 'writeBlanksForm', 'writeBlanksForm']
+    LISTENING_2_EXERCISE_TYPES = ['multipleChoice', 'writeBlanksQuestions']
+    LISTENING_3_EXERCISE_TYPES = ['multipleChoice3Options', 'writeBlanksQuestions']
+    LISTENING_4_EXERCISE_TYPES = ['multipleChoice', 'writeBlanksQuestions', 'writeBlanksFill', 'writeBlanksForm']
+
+    TOTAL_READING_PASSAGE_1_EXERCISES = 13
+    TOTAL_READING_PASSAGE_2_EXERCISES = 13
+    TOTAL_READING_PASSAGE_3_EXERCISES = 14
+
+    TOTAL_LISTENING_SECTION_1_EXERCISES = 10
+    TOTAL_LISTENING_SECTION_2_EXERCISES = 10
+    TOTAL_LISTENING_SECTION_3_EXERCISES = 10
+    TOTAL_LISTENING_SECTION_4_EXERCISES = 10
+
+
+class MinTimers:
+    LISTENING_MIN_TIMER_DEFAULT = 30
+    WRITING_MIN_TIMER_DEFAULT = 60
+    SPEAKING_MIN_TIMER_DEFAULT = 14
+
+
+class Voices:
+    EN_US_VOICES = [
+        {'Gender': 'Female', 'Id': 'Salli', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Name': 'Salli',
+         'SupportedEngines': ['neural', 'standard']},
+        {'Gender': 'Male', 'Id': 'Matthew', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Name': 'Matthew',
+         'SupportedEngines': ['neural', 'standard']},
+        {'Gender': 'Female', 'Id': 'Kimberly', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Name': 'Kimberly',
+         'SupportedEngines': ['neural', 'standard']},
+        {'Gender': 'Female', 'Id': 'Kendra', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Name': 'Kendra',
+         'SupportedEngines': ['neural', 'standard']},
+        {'Gender': 'Male', 'Id': 'Justin', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Name': 'Justin',
+         'SupportedEngines': ['neural', 'standard']},
+        {'Gender': 'Male', 'Id': 'Joey', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Name': 'Joey',
+         'SupportedEngines': ['neural', 'standard']},
+        {'Gender': 'Female', 'Id': 'Joanna', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Name': 'Joanna',
+         'SupportedEngines': ['neural', 'standard']},
+        {'Gender': 'Female', 'Id': 'Ivy', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Name': 'Ivy',
+         'SupportedEngines': ['neural', 'standard']}]
+    EN_GB_VOICES = [
+        {'Gender': 'Female', 'Id': 'Emma', 'LanguageCode': 'en-GB', 'LanguageName': 'British English', 'Name': 'Emma',
+         'SupportedEngines': ['neural', 'standard']},
+        {'Gender': 'Male', 'Id': 'Brian', 'LanguageCode': 'en-GB', 'LanguageName': 'British English', 'Name': 'Brian',
+         'SupportedEngines': ['neural', 'standard']},
+        {'Gender': 'Female', 'Id': 'Amy', 'LanguageCode': 'en-GB', 'LanguageName': 'British English', 'Name': 'Amy',
+         'SupportedEngines': ['neural', 'standard']}]
+    EN_GB_WLS_VOICES = [
+        {'Gender': 'Male', 'Id': 'Geraint', 'LanguageCode': 'en-GB-WLS', 'LanguageName': 'Welsh English', 'Name': 'Geraint',
+         'SupportedEngines': ['standard']}]
+    EN_AU_VOICES = [{'Gender': 'Male', 'Id': 'Russell', 'LanguageCode': 'en-AU', 'LanguageName': 'Australian English',
+                     'Name': 'Russell', 'SupportedEngines': ['standard']},
+                    {'Gender': 'Female', 'Id': 'Nicole', 'LanguageCode': 'en-AU', 'LanguageName': 'Australian English',
+                     'Name': 'Nicole', 'SupportedEngines': ['standard']}]
+
+    ALL_VOICES = EN_US_VOICES + EN_GB_VOICES + EN_GB_WLS_VOICES + EN_AU_VOICES
+
+    MALE_VOICES = [item for item in ALL_VOICES if item.get('Gender') == 'Male']
+    FEMALE_VOICES = [item for item in ALL_VOICES if item.get('Gender') == 'Female']
+
+
+class NeuralVoices:
+    NEURAL_EN_US_VOICES = [
+        {'Gender': 'Female', 'Id': 'Danielle', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Name': 'Danielle',
+         'SupportedEngines': ['neural']},
+        {'Gender': 'Male', 'Id': 'Gregory', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Name': 'Gregory',
+         'SupportedEngines': ['neural']},
+        {'Gender': 'Male', 'Id': 'Kevin', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Name': 'Kevin',
+         'SupportedEngines': ['neural']},
+        {'Gender': 'Female', 'Id': 'Ruth', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Name': 'Ruth',
+         'SupportedEngines': ['neural']},
+        {'Gender': 'Male', 'Id': 'Stephen', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Name': 'Stephen',
+         'SupportedEngines': ['neural']}]
+    NEURAL_EN_GB_VOICES = [
+        {'Gender': 'Male', 'Id': 'Arthur', 'LanguageCode': 'en-GB', 'LanguageName': 'British English', 'Name': 'Arthur',
+         'SupportedEngines': ['neural']}]
+    NEURAL_EN_AU_VOICES = [
+        {'Gender': 'Female', 'Id': 'Olivia', 'LanguageCode': 'en-AU', 'LanguageName': 'Australian English',
+         'Name': 'Olivia', 'SupportedEngines': ['neural']}]
+    NEURAL_EN_ZA_VOICES = [
+        {'Gender': 'Female', 'Id': 'Ayanda', 'LanguageCode': 'en-ZA', 'LanguageName': 'South African English',
+         'Name': 'Ayanda', 'SupportedEngines': ['neural']}]
+    NEURAL_EN_NZ_VOICES = [
+        {'Gender': 'Female', 'Id': 'Aria', 'LanguageCode': 'en-NZ', 'LanguageName': 'New Zealand English', 'Name': 'Aria',
+         'SupportedEngines': ['neural']}]
+    NEURAL_EN_IN_VOICES = [
+        {'Gender': 'Female', 'Id': 'Kajal', 'LanguageCode': 'en-IN', 'LanguageName': 'Indian English', 'Name': 'Kajal',
+         'SupportedEngines': ['neural']}]
+    NEURAL_EN_IE_VOICES = [
+        {'Gender': 'Female', 'Id': 'Niamh', 'LanguageCode': 'en-IE', 'LanguageName': 'Irish English', 'Name': 'Niamh',
+         'SupportedEngines': ['neural']}]
+
+    ALL_NEURAL_VOICES = NEURAL_EN_US_VOICES + NEURAL_EN_GB_VOICES + NEURAL_EN_AU_VOICES + NEURAL_EN_ZA_VOICES + NEURAL_EN_NZ_VOICES + NEURAL_EN_IE_VOICES
+
+    MALE_NEURAL_VOICES = [item for item in ALL_NEURAL_VOICES if item.get('Gender') == 'Male']
+    FEMALE_NEURAL_VOICES = [item for item in ALL_NEURAL_VOICES if item.get('Gender') == 'Female']
+
+
+class EducationalContent:
+    DIFFICULTIES = ["A1", "A2", "B1", "B2", "C1", "C2"]
+
+    MTI_TOPICS = [
+        "Education",
+        "Technology",
+        "Environment",
+        "Health and Fitness",
+        "Engineering",
+        "Work and Careers",
+        "Travel and Tourism",
+        "Culture and Traditions",
+        "Social Issues",
+        "Arts and Entertainment",
+        "Climate Change",
+        "Social Media",
+        "Sustainable Development",
+        "Health Care",
+        "Immigration",
+        "Artificial Intelligence",
+        "Consumerism",
+        "Online Shopping",
+        "Energy",
+        "Oil and Gas",
+        "Poverty and Inequality",
+        "Cultural Diversity",
+        "Democracy and Governance",
+        "Mental Health",
+        "Ethics and Morality",
+        "Population Growth",
+        "Science and Innovation",
+        "Poverty Alleviation",
+        "Cybersecurity and Privacy",
+        "Human Rights",
+        "Food and Agriculture",
+        "Cyberbullying and Online Safety",
+        "Linguistic Diversity",
+        "Urbanization",
+        "Artificial Intelligence in Education",
+        "Youth Empowerment",
+        "Disaster Management",
+        "Mental Health Stigma",
+        "Internet Censorship",
+        "Sustainable Fashion",
+        "Indigenous Rights",
+        "Water Scarcity",
+        "Social Entrepreneurship",
+        "Privacy in the Digital Age",
+        "Sustainable Transportation",
+        "Gender Equality",
+        "Automation and Job Displacement",
+        "Digital Divide",
+        "Education Inequality"
+    ]
+    TOPICS = [
+        "Art and Creativity",
+        "History of Ancient Civilizations",
+        "Environmental Conservation",
+        "Space Exploration",
+        "Artificial Intelligence",
+        "Climate Change",
+        "The Human Brain",
+        "Renewable Energy",
+        "Cultural Diversity",
+        "Modern Technology Trends",
+        "Sustainable Agriculture",
+        "Natural Disasters",
+        "Cybersecurity",
+        "Philosophy of Ethics",
+        "Robotics",
+        "Health and Wellness",
+        "Literature and Classics",
+        "World Geography",
+        "Social Media Impact",
+        "Food Sustainability",
+        "Economics and Markets",
+        "Human Evolution",
+        "Political Systems",
+        "Mental Health Awareness",
+        "Quantum Physics",
+        "Biodiversity",
+        "Education Reform",
+        "Animal Rights",
+        "The Industrial Revolution",
+        "Future of Work",
+        "Film and Cinema",
+        "Genetic Engineering",
+        "Climate Policy",
+        "Space Travel",
+        "Renewable Energy Sources",
+        "Cultural Heritage Preservation",
+        "Modern Art Movements",
+        "Sustainable Transportation",
+        "The History of Medicine",
+        "Artificial Neural Networks",
+        "Climate Adaptation",
+        "Philosophy of Existence",
+        "Augmented Reality",
+        "Yoga and Meditation",
+        "Literary Genres",
+        "World Oceans",
+        "Social Networking",
+        "Sustainable Fashion",
+        "Prehistoric Era",
+        "Democracy and Governance",
+        "Postcolonial Literature",
+        "Geopolitics",
+        "Psychology and Behavior",
+        "Nanotechnology",
+        "Endangered Species",
+        "Education Technology",
+        "Renaissance Art",
+        "Renewable Energy Policy",
+        "Modern Architecture",
+        "Climate Resilience",
+        "Artificial Life",
+        "Fitness and Nutrition",
+        "Classic Literature Adaptations",
+        "Ethical Dilemmas",
+        "Internet of Things (IoT)",
+        "Meditation Practices",
+        "Literary Symbolism",
+        "Marine Conservation",
+        "Sustainable Tourism",
+        "Ancient Philosophy",
+        "Cold War Era",
+        "Behavioral Economics",
+        "Space Colonization",
+        "Clean Energy Initiatives",
+        "Cultural Exchange",
+        "Modern Sculpture",
+        "Climate Mitigation",
+        "Mindfulness",
+        "Literary Criticism",
+        "Wildlife Conservation",
+        "Renewable Energy Innovations",
+        "History of Mathematics",
+        "Human-Computer Interaction",
+        "Global Health",
+        "Cultural Appropriation",
+        "Traditional cuisine and culinary arts",
+        "Local music and dance traditions",
+        "History of the region and historical landmarks",
+        "Traditional crafts and artisanal skills",
+        "Wildlife and conservation efforts",
+        "Local sports and athletic competitions",
+        "Fashion trends and clothing styles",
+        "Education systems and advancements",
+        "Healthcare services and medical innovations",
+        "Family values and social dynamics",
+        "Travel destinations and tourist attractions",
+        "Environmental sustainability projects",
+        "Technological developments and innovations",
+        "Entrepreneurship and business ventures",
+        "Youth empowerment initiatives",
+        "Art exhibitions and cultural events",
+        "Philanthropy and community development projects"
+    ]
+
+    TWO_PEOPLE_SCENARIOS = [
+        "Booking a table at a restaurant",
+        "Making a doctor's appointment",
+        "Asking for directions to a tourist attraction",
+        "Inquiring about public transportation options",
+        "Discussing weekend plans with a friend",
+        "Ordering food at a café",
+        "Renting a bicycle for a day",
+        "Arranging a meeting with a colleague",
+        "Talking to a real estate agent about renting an apartment",
+        "Discussing travel plans for an upcoming vacation",
+        "Checking the availability of a hotel room",
+        "Talking to a car rental service",
+        "Asking for recommendations at a library",
+        "Inquiring about opening hours at a museum",
+        "Discussing the weather forecast",
+        "Shopping for groceries",
+        "Renting a movie from a video store",
+        "Booking a flight ticket",
+        "Discussing a school assignment with a classmate",
+        "Making a reservation for a spa appointment",
+        "Talking to a customer service representative about a product issue",
+        "Discussing household chores with a family member",
+        "Planning a surprise party for a friend",
+        "Talking to a coworker about a project deadline",
+        "Inquiring about a gym membership",
+        "Discussing the menu options at a fast-food restaurant",
+        "Talking to a neighbor about a community event",
+        "Asking for help with computer problems",
+        "Discussing a recent sports game with a sports enthusiast",
+        "Talking to a pet store employee about buying a pet",
+        "Asking for information about a local farmer's market",
+        "Discussing the details of a home renovation project",
+        "Talking to a coworker about office supplies",
+        "Making plans for a family picnic",
+        "Inquiring about admission requirements at a university",
+        "Discussing the features of a new smartphone with a salesperson",
+        "Talking to a mechanic about car repairs",
+        "Making arrangements for a child's birthday party",
+        "Discussing a new diet plan with a nutritionist",
+        "Asking for information about a music concert",
+        "Talking to a hairdresser about getting a haircut",
+        "Inquiring about a language course at a language school",
+        "Discussing plans for a weekend camping trip",
+        "Talking to a bank teller about opening a new account",
+        "Ordering a drink at a coffee shop",
+        "Discussing a new book with a book club member",
+        "Talking to a librarian about library services",
+        "Asking for advice on finding a job",
+        "Discussing plans for a garden makeover with a landscaper",
+        "Talking to a travel agent about a cruise vacation",
+        "Inquiring about a fitness class at a gym",
+        "Ordering flowers for a special occasion",
+        "Discussing a new exercise routine with a personal trainer",
+        "Talking to a teacher about a child's progress in school",
+        "Asking for information about a local art exhibition",
+        "Discussing a home improvement project with a contractor",
+        "Talking to a babysitter about childcare arrangements",
+        "Making arrangements for a car service appointment",
+        "Inquiring about a photography workshop at a studio",
+        "Discussing plans for a family reunion with a relative",
+        "Talking to a tech support representative about computer issues",
+        "Asking for recommendations on pet grooming services",
+        "Discussing weekend plans with a significant other",
+        "Talking to a counselor about personal issues",
+        "Inquiring about a music lesson with a music teacher",
+        "Ordering a pizza for delivery",
+        "Making a reservation for a taxi",
+        "Discussing a new recipe with a chef",
+        "Talking to a fitness trainer about weight loss goals",
+        "Inquiring about a dance class at a dance studio",
+        "Ordering a meal at a food truck",
+        "Discussing plans for a weekend getaway with a partner",
+        "Talking to a florist about wedding flower arrangements",
+        "Asking for advice on home decorating",
+        "Discussing plans for a charity fundraiser event",
+        "Talking to a pet sitter about taking care of pets",
+        "Making arrangements for a spa day with a friend",
+        "Asking for recommendations on home improvement stores",
+        "Discussing weekend plans with a travel enthusiast",
+        "Talking to a car mechanic about car maintenance",
+        "Inquiring about a cooking class at a culinary school",
+        "Ordering a sandwich at a deli",
+        "Discussing plans for a family holiday party",
+        "Talking to a personal assistant about organizing tasks",
+        "Asking for information about a local theater production",
+        "Discussing a new DIY project with a home improvement expert",
+        "Talking to a wine expert about wine pairing",
+        "Making arrangements for a pet adoption",
+        "Asking for advice on planning a wedding"
+    ]
+
+    SOCIAL_MONOLOGUE_CONTEXTS = [
+        "A guided tour of a historical museum",
+        "An introduction to a new city for tourists",
+        "An orientation session for new university students",
+        "A safety briefing for airline passengers",
+        "An explanation of the process of recycling",
+        "A lecture on the benefits of a healthy diet",
+        "A talk on the importance of time management",
+        "A monologue about wildlife conservation",
+        "An overview of local public transportation options",
+        "A presentation on the history of cinema",
+        "An introduction to the art of photography",
+        "A discussion about the effects of climate change",
+        "An overview of different types of cuisine",
+        "A lecture on the principles of financial planning",
+        "A monologue about sustainable energy sources",
+        "An explanation of the process of online shopping",
+        "A guided tour of a botanical garden",
+        "An introduction to a local wildlife sanctuary",
+        "A safety briefing for hikers in a national park",
+        "A talk on the benefits of physical exercise",
+        "A lecture on the principles of effective communication",
+        "A monologue about the impact of social media",
+        "An overview of the history of a famous landmark",
+        "An introduction to the world of fashion design",
+        "A discussion about the challenges of global poverty",
+        "An explanation of the process of organic farming",
+        "A presentation on the history of space exploration",
+        "An overview of traditional music from different cultures",
+        "A lecture on the principles of effective leadership",
+        "A monologue about the influence of technology",
+        "A guided tour of a famous archaeological site",
+        "An introduction to a local wildlife rehabilitation center",
+        "A safety briefing for visitors to a science museum",
+        "A talk on the benefits of learning a new language",
+        "A lecture on the principles of architectural design",
+        "A monologue about the impact of renewable energy",
+        "An explanation of the process of online banking",
+        "A presentation on the history of a famous art movement",
+        "An overview of traditional clothing from various regions",
+        "A lecture on the principles of sustainable agriculture",
+        "A discussion about the challenges of urban development",
+        "A monologue about the influence of social norms",
+        "A guided tour of a historical battlefield",
+        "An introduction to a local animal shelter",
+        "A safety briefing for participants in a charity run",
+        "A talk on the benefits of community involvement",
+        "A lecture on the principles of sustainable tourism",
+        "A monologue about the impact of alternative medicine",
+        "An explanation of the process of wildlife tracking",
+        "A presentation on the history of a famous inventor",
+        "An overview of traditional dance forms from different cultures",
+        "A lecture on the principles of ethical business practices",
+        "A discussion about the challenges of healthcare access",
+        "A monologue about the influence of cultural traditions",
+        "A guided tour of a famous lighthouse",
+        "An introduction to a local astronomy observatory",
+        "A safety briefing for participants in a team-building event",
+        "A talk on the benefits of volunteering",
+        "A lecture on the principles of wildlife protection",
+        "A monologue about the impact of space exploration",
+        "An explanation of the process of wildlife photography",
+        "A presentation on the history of a famous musician",
+        "An overview of traditional art forms from different cultures",
+        "A lecture on the principles of effective education",
+        "A discussion about the challenges of sustainable development",
+        "A monologue about the influence of cultural diversity",
+        "A guided tour of a famous national park",
+        "An introduction to a local marine conservation project",
+        "A safety briefing for participants in a hot air balloon ride",
+        "A talk on the benefits of cultural exchange programs",
+        "A lecture on the principles of wildlife conservation",
+        "A monologue about the impact of technological advancements",
+        "An explanation of the process of wildlife rehabilitation",
+        "A presentation on the history of a famous explorer",
+        "A lecture on the principles of effective marketing",
+        "A discussion about the challenges of environmental sustainability",
+        "A monologue about the influence of social entrepreneurship",
+        "A guided tour of a famous historical estate",
+        "An introduction to a local marine life research center",
+        "A safety briefing for participants in a zip-lining adventure",
+        "A talk on the benefits of cultural preservation",
+        "A lecture on the principles of wildlife ecology",
+        "A monologue about the impact of space technology",
+        "An explanation of the process of wildlife conservation",
+        "A presentation on the history of a famous scientist",
+        "An overview of traditional crafts and artisans from different cultures",
+        "A lecture on the principles of effective intercultural communication"
+    ]
+
+    FOUR_PEOPLE_SCENARIOS = [
+        "A university lecture on history",
+        "A physics class discussing Newton's laws",
+        "A medical school seminar on anatomy",
+        "A training session on computer programming",
+        "A business school lecture on marketing strategies",
+        "A chemistry lab experiment and discussion",
+        "A language class practicing conversational skills",
+        "A workshop on creative writing techniques",
+        "A high school math lesson on calculus",
+        "A training program for customer service representatives",
+        "A lecture on environmental science and sustainability",
+        "A psychology class exploring human behavior",
+        "A music theory class analyzing compositions",
+        "A nursing school simulation for patient care",
+        "A computer science class on algorithms",
+        "A workshop on graphic design principles",
+        "A law school lecture on constitutional law",
+        "A geology class studying rock formations",
+        "A vocational training program for electricians",
+        "A history seminar focusing on ancient civilizations",
+        "A biology class dissecting specimens",
+        "A financial literacy course for adults",
+        "A literature class discussing classic novels",
+        "A training session for emergency response teams",
+        "A sociology lecture on social inequality",
+        "An art class exploring different painting techniques",
+        "A medical school seminar on diagnosis",
+        "A programming bootcamp teaching web development",
+        "An economics class analyzing market trends",
+        "A chemistry lab experiment on chemical reactions",
+        "A language class practicing pronunciation",
+        "A workshop on public speaking skills",
+        "A high school physics lesson on electromagnetism",
+        "A training program for IT professionals",
+        "A lecture on climate change and its effects",
+        "A psychology class studying cognitive psychology",
+        "A music class composing original songs",
+        "A nursing school simulation for patient assessment",
+        "A computer science class on data structures",
+        "A workshop on 3D modeling and animation",
+        "A law school lecture on contract law",
+        "A geography class examining world maps",
+        "A vocational training program for plumbers",
+        "A history seminar discussing revolutions",
+        "A biology class exploring genetics",
+        "A financial literacy course for teens",
+        "A literature class analyzing poetry",
+        "A training session for public speaking coaches",
+        "A sociology lecture on cultural diversity",
+        "An art class creating sculptures",
+        "A medical school seminar on surgical techniques",
+        "A programming bootcamp teaching app development",
+        "An economics class on global trade policies",
+        "A chemistry lab experiment on chemical bonding",
+        "A language class discussing idiomatic expressions",
+        "A workshop on conflict resolution",
+        "A high school biology lesson on evolution",
+        "A training program for project managers",
+        "A lecture on renewable energy sources",
+        "A psychology class on abnormal psychology",
+        "A music class rehearsing for a performance",
+        "A nursing school simulation for emergency response",
+        "A computer science class on cybersecurity",
+        "A workshop on digital marketing strategies",
+        "A law school lecture on intellectual property",
+        "A geology class analyzing seismic activity",
+        "A vocational training program for carpenters",
+        "A history seminar on the Renaissance",
+        "A chemistry class synthesizing compounds",
+        "A financial literacy course for seniors",
+        "A literature class interpreting Shakespearean plays",
+        "A training session for negotiation skills",
+        "A sociology lecture on urbanization",
+        "An art class creating digital art",
+        "A medical school seminar on patient communication",
+        "A programming bootcamp teaching mobile app development",
+        "An economics class on fiscal policy",
+        "A physics lab experiment on electromagnetism",
+        "A language class on cultural immersion",
+        "A workshop on time management",
+        "A high school chemistry lesson on stoichiometry",
+        "A training program for HR professionals",
+        "A lecture on space exploration and astronomy",
+        "A psychology class on human development",
+        "A music class practicing for a recital",
+        "A nursing school simulation for triage",
+        "A computer science class on web development frameworks",
+        "A workshop on team-building exercises",
+        "A law school lecture on criminal law",
+        "A geography class studying world cultures",
+        "A vocational training program for HVAC technicians",
+        "A history seminar on ancient civilizations",
+        "A biology class examining ecosystems",
+        "A financial literacy course for entrepreneurs",
+        "A literature class analyzing modern literature",
+        "A training session for leadership skills",
+        "A sociology lecture on gender studies",
+        "An art class exploring multimedia art",
+        "A medical school seminar on patient diagnosis",
+        "A programming bootcamp teaching software architecture"
+    ]
+
+    ACADEMIC_SUBJECTS = [
+        "Astrophysics",
+        "Microbiology",
+        "Political Science",
+        "Environmental Science",
+        "Literature",
+        "Biochemistry",
+        "Sociology",
+        "Art History",
+        "Geology",
+        "Economics",
+        "Psychology",
+        "History of Architecture",
+        "Linguistics",
+        "Neurobiology",
+        "Anthropology",
+        "Quantum Mechanics",
+        "Urban Planning",
+        "Philosophy",
+        "Marine Biology",
+        "International Relations",
+        "Medieval History",
+        "Geophysics",
+        "Finance",
+        "Educational Psychology",
+        "Graphic Design",
+        "Paleontology",
+        "Macroeconomics",
+        "Cognitive Psychology",
+        "Renaissance Art",
+        "Archaeology",
+        "Microeconomics",
+        "Social Psychology",
+        "Contemporary Art",
+        "Meteorology",
+        "Political Philosophy",
+        "Space Exploration",
+        "Cognitive Science",
+        "Classical Music",
+        "Oceanography",
+        "Public Health",
+        "Gender Studies",
+        "Baroque Art",
+        "Volcanology",
+        "Business Ethics",
+        "Music Composition",
+        "Environmental Policy",
+        "Media Studies",
+        "Ancient History",
+        "Seismology",
+        "Marketing",
+        "Human Development",
+        "Modern Art",
+        "Astronomy",
+        "International Law",
+        "Developmental Psychology",
+        "Film Studies",
+        "American History",
+        "Soil Science",
+        "Entrepreneurship",
+        "Clinical Psychology",
+        "Contemporary Dance",
+        "Space Physics",
+        "Political Economy",
+        "Cognitive Neuroscience",
+        "20th Century Literature",
+        "Public Administration",
+        "European History",
+        "Atmospheric Science",
+        "Supply Chain Management",
+        "Social Work",
+        "Japanese Literature",
+        "Planetary Science",
+        "Labor Economics",
+        "Industrial-Organizational Psychology",
+        "French Philosophy",
+        "Biogeochemistry",
+        "Strategic Management",
+        "Educational Sociology",
+        "Postmodern Literature",
+        "Public Relations",
+        "Middle Eastern History",
+        "Oceanography",
+        "International Development",
+        "Human Resources Management",
+        "Educational Leadership",
+        "Russian Literature",
+        "Quantum Chemistry",
+        "Environmental Economics",
+        "Environmental Psychology",
+        "Ancient Philosophy",
+        "Immunology",
+        "Comparative Politics",
+        "Child Development",
+        "Fashion Design",
+        "Geological Engineering",
+        "Macroeconomic Policy",
+        "Media Psychology",
+        "Byzantine Art",
+        "Ecology",
+        "International Business"
+    ]

ielts_be/configs/dependency_injection.py

@@ -0,0 +1,167 @@
+import json
+import os
+
+from dependency_injector import providers, containers
+from firebase_admin import credentials
+from motor.motor_asyncio import AsyncIOMotorClient
+from openai import AsyncOpenAI
+from httpx import AsyncClient as HTTPClient
+from dotenv import load_dotenv
+from sentence_transformers import SentenceTransformer
+
+from ielts_be.repositories.impl import *
+from ielts_be.services.impl import *
+from ielts_be.controllers.impl import *
+
+load_dotenv()
+
+
+class DependencyInjector:
+
+    def __init__(self, polly_client: any, http_client: HTTPClient, stt: OpenAIWhisper):
+        self._container = containers.DynamicContainer()
+        self._polly_client = polly_client
+        self._http_client = http_client
+        self._stt = stt
+
+    def inject(self):
+        self._setup_clients()
+        self._setup_third_parties()
+        self._setup_repositories()
+        self._setup_services()
+        self._setup_controllers()
+        self._container.wire(
+            packages=["ielts_be"]
+        )
+        return self
+
+    def _setup_clients(self):
+        self._container.openai_client = providers.Singleton(AsyncOpenAI)
+        self._container.polly_client = providers.Object(self._polly_client)
+        self._container.http_client = providers.Object(self._http_client)
+        self._container.stt = providers.Object(self._stt)
+
+    def _setup_third_parties(self):
+        self._container.llm = providers.Factory(OpenAI, client=self._container.openai_client)
+        self._container.tts = providers.Factory(AWSPolly, client=self._container.polly_client)
+
+        """
+        with open('ielts_be/services/impl/third_parties/elai/conf.json', 'r') as file:
+            elai_conf = json.load(file)
+
+        with open('ielts_be/services/impl/third_parties/elai/avatars.json', 'r') as file:
+            elai_avatars = json.load(file)
+        """
+
+        with open('ielts_be/services/impl/third_parties/heygen/avatars.json', 'r') as file:
+            heygen_avatars = json.load(file)
+
+        self._container.vid_gen = providers.Factory(
+            Heygen, client=self._container.http_client, token=os.getenv("HEY_GEN_TOKEN"), avatars=heygen_avatars
+        )
+        self._container.ai_detector = providers.Factory(
+            GPTZero, client=self._container.http_client, gpt_zero_key=os.getenv("GPT_ZERO_API_KEY")
+        )
+
+    def _setup_repositories(self):
+        cred = credentials.Certificate(os.getenv("GOOGLE_APPLICATION_CREDENTIALS"))
+        firebase_token = cred.get_access_token().access_token
+
+        self._container.document_store = providers.Factory(
+            MongoDB, mongo_db=AsyncIOMotorClient(os.getenv("MONGODB_URI"))[os.getenv("MONGODB_DB")]
+        )
+
+        self._container.firebase_instance = providers.Factory(
+            FirebaseStorage,
+            client=self._container.http_client, token=firebase_token, bucket=os.getenv("FIREBASE_BUCKET")
+        )
+
+    def _setup_services(self):
+        self._container.listening_service = providers.Factory(
+            ListeningService,
+            llm=self._container.llm,
+            stt=self._container.stt,
+            tts=self._container.tts,
+            file_storage=self._container.firebase_instance,
+            document_store=self._container.document_store
+        )
+        self._container.reading_service = providers.Factory(ReadingService, llm=self._container.llm)
+
+        self._container.speaking_service = providers.Factory(
+            SpeakingService, llm=self._container.llm,
+            file_storage=self._container.firebase_instance,
+            stt=self._container.stt
+        )
+
+        self._container.writing_service = providers.Factory(
+            WritingService, llm=self._container.llm, ai_detector=self._container.ai_detector, file_storage=self._container.firebase_instance
+        )
+
+        with open('ielts_be/services/impl/exam/level/mc_variants.json', 'r') as file:
+            mc_variants = json.load(file)
+
+        self._container.level_service = providers.Factory(
+            LevelService, llm=self._container.llm, document_store=self._container.document_store,
+            mc_variants=mc_variants, reading_service=self._container.reading_service,
+            writing_service=self._container.writing_service, speaking_service=self._container.speaking_service,
+            listening_service=self._container.listening_service
+        )
+
+        self._container.grade_service = providers.Factory(
+            GradeService, llm=self._container.llm
+        )
+
+        embeddings = SentenceTransformer('all-MiniLM-L6-v2')
+
+        self._container.training_kb = providers.Factory(
+            TrainingContentKnowledgeBase, embeddings=embeddings
+        )
+
+        self._container.training_service = providers.Factory(
+            TrainingService, llm=self._container.llm,
+            document_store=self._container.document_store, training_kb=self._container.training_kb
+        )
+
+        self._container.user_service = providers.Factory(
+            UserService, document_store=self._container.document_store
+        )
+
+        self._container.evaluation_service = providers.Factory(
+            EvaluationService, db=self._container.document_store,
+            writing_service=self._container.writing_service,
+            speaking_service=self._container.speaking_service
+        )
+
+    def _setup_controllers(self):
+
+        self._container.grade_controller = providers.Factory(
+            GradeController, grade_service=self._container.grade_service,
+            evaluation_service=self._container.evaluation_service
+        )
+
+        self._container.user_controller = providers.Factory(
+            UserController, user_service=self._container.user_service
+        )
+
+        self._container.training_controller = providers.Factory(
+            TrainingController, training_service=self._container.training_service
+        )
+
+        self._container.level_controller = providers.Factory(
+            LevelController, level_service=self._container.level_service
+        )
+        self._container.listening_controller = providers.Factory(
+            ListeningController, listening_service=self._container.listening_service
+        )
+
+        self._container.reading_controller = providers.Factory(
+            ReadingController, reading_service=self._container.reading_service
+        )
+
+        self._container.speaking_controller = providers.Factory(
+            SpeakingController, speaking_service=self._container.speaking_service, vid_gen=self._container.vid_gen
+        )
+
+        self._container.writing_controller = providers.Factory(
+            WritingController, writing_service=self._container.writing_service
+        )

ielts_be/configs/logging/__init__.py

@@ -0,0 +1,7 @@
+from .filters import ErrorAndAboveFilter
+from .queue_handler import QueueListenerHandler
+
+__all__ = [
+    "ErrorAndAboveFilter",
+    "QueueListenerHandler"
+]

ielts_be/configs/logging/filters.py

@@ -0,0 +1,6 @@
+import logging
+
+
+class ErrorAndAboveFilter(logging.Filter):
+    def filter(self, record: logging.LogRecord) -> bool | logging.LogRecord:
+        return record.levelno < logging.ERROR

ielts_be/configs/logging/formatters.py

@@ -0,0 +1,105 @@
+import datetime as dt
+import json
+import logging
+
+LOG_RECORD_BUILTIN_ATTRS = {
+    "args",
+    "asctime",
+    "created",
+    "exc_info",
+    "exc_text",
+    "filename",
+    "funcName",
+    "levelname",
+    "levelno",
+    "lineno",
+    "module",
+    "msecs",
+    "message",
+    "msg",
+    "name",
+    "pathname",
+    "process",
+    "processName",
+    "relativeCreated",
+    "stack_info",
+    "thread",
+    "threadName",
+    "taskName",
+}
+
+"""
+    This isn't being used since the app will be run on gcloud run but this can be used for future apps.
+    If you want to test it:
+     
+    formatters:
+    
+    "json": {
+      "()": "json_formatter.JSONFormatter",
+      "fmt_keys": {
+        "level": "levelname",
+        "message": "message",
+        "timestamp": "timestamp",
+        "logger": "name",
+        "module": "module",
+        "function": "funcName",
+        "line": "lineno",
+        "thread_name": "threadName"
+      }
+    } 
+    
+    handlers:
+    
+    "file_json": {
+      "class": "logging.handlers.RotatingFileHandler",
+      "level": "DEBUG",
+      "formatter": "json",
+      "filename": "logs/log",
+      "maxBytes": 1000000,
+      "backupCount": 3
+    }
+    
+    and add "cfg://handlers.file_json" to queue handler
+"""
+
+# From this video https://www.youtube.com/watch?v=9L77QExPmI0
+# Src here: https://github.com/mCodingLLC/VideosSampleCode/blob/master/videos/135_modern_logging/mylogger.py
+class JSONFormatter(logging.Formatter):
+    def __init__(
+        self,
+        *,
+        fmt_keys: dict[str, str] | None = None,
+    ):
+        super().__init__()
+        self.fmt_keys = fmt_keys if fmt_keys is not None else {}
+
+    def format(self, record: logging.LogRecord) -> str:
+        message = self._prepare_log_dict(record)
+        return json.dumps(message, default=str)
+
+    def _prepare_log_dict(self, record: logging.LogRecord):
+        always_fields = {
+            "message": record.getMessage(),
+            "timestamp": dt.datetime.fromtimestamp(
+                record.created, tz=dt.timezone.utc
+            ).isoformat(),
+        }
+        if record.exc_info is not None:
+            always_fields["exc_info"] = self.formatException(record.exc_info)
+
+        if record.stack_info is not None:
+            always_fields["stack_info"] = self.formatStack(record.stack_info)
+
+        message = {
+            key: msg_val
+            if (msg_val := always_fields.pop(val, None)) is not None
+            else getattr(record, val)
+            for key, val in self.fmt_keys.items()
+        }
+        message.update(always_fields)
+
+        for key, val in record.__dict__.items():
+            if key not in LOG_RECORD_BUILTIN_ATTRS:
+                message[key] = val
+
+        return message

ielts_be/configs/logging/logging_config.json

@@ -0,0 +1,53 @@
+{
+  "version": 1,
+  "objects": {
+    "queue": {
+      "class": "queue.Queue",
+      "maxsize": 1000
+    }
+  },
+  "disable_existing_loggers": false,
+  "formatters": {
+    "simple": {
+      "format": "[%(levelname)s] (%(module)s|L: %(lineno)d) %(asctime)s: %(message)s",
+      "datefmt": "%Y-%m-%dT%H:%M:%S%z"
+    }
+  },
+  "filters": {
+    "error_and_above": {
+      "()": "ielts_be.configs.logging.ErrorAndAboveFilter"
+    }
+  },
+  "handlers": {
+    "console": {
+      "class": "logging.StreamHandler",
+      "level": "INFO",
+      "formatter": "simple",
+      "stream": "ext://sys.stdout",
+      "filters": ["error_and_above"]
+    },
+    "error": {
+      "class": "logging.StreamHandler",
+      "level": "ERROR",
+      "formatter": "simple",
+      "stream": "ext://sys.stderr"
+    },
+    "queue_handler": {
+      "class": "ielts_be.configs.logging.QueueListenerHandler",
+      "handlers": [
+        "cfg://handlers.console",
+        "cfg://handlers.error"
+      ],
+      "queue": "cfg://objects.queue",
+      "respect_handler_level": true
+    }
+  },
+  "loggers": {
+    "root": {
+      "level": "DEBUG",
+      "handlers": [
+        "queue_handler"
+      ]
+    }
+  }
+}

ielts_be/configs/logging/queue_handler.py

@@ -0,0 +1,61 @@
+from logging.config import ConvertingList, ConvertingDict, valid_ident
+from logging.handlers import QueueHandler, QueueListener
+from queue import Queue
+import atexit
+
+
+class QueueHandlerHelper:
+
+    @staticmethod
+    def resolve_handlers(l):
+        if not isinstance(l, ConvertingList):
+            return l
+
+        # Indexing the list performs the evaluation.
+        return [l[i] for i in range(len(l))]
+
+    @staticmethod
+    def resolve_queue(q):
+        if not isinstance(q, ConvertingDict):
+            return q
+        if '__resolved_value__' in q:
+            return q['__resolved_value__']
+
+        cname = q.pop('class')
+        klass = q.configurator.resolve(cname)
+        props = q.pop('.', None)
+        kwargs = {k: q[k] for k in q if valid_ident(k)}
+        result = klass(**kwargs)
+        if props:
+            for name, value in props.items():
+                setattr(result, name, value)
+
+        q['__resolved_value__'] = result
+        return result
+
+
+# The guy from this video https://www.youtube.com/watch?v=9L77QExPmI0 is using logging features only available in 3.12
+# This article had the class required to build the queue handler in 3.11
+# https://rob-blackbourn.medium.com/how-to-use-python-logging-queuehandler-with-dictconfig-1e8b1284e27a
+class QueueListenerHandler(QueueHandler):
+
+    def __init__(self, handlers, respect_handler_level=False, auto_run=True, queue=Queue(-1)):
+        queue = QueueHandlerHelper.resolve_queue(queue)
+        super().__init__(queue)
+        handlers = QueueHandlerHelper.resolve_handlers(handlers)
+        self._listener = QueueListener(
+            self.queue,
+            *handlers,
+            respect_handler_level=respect_handler_level)
+        if auto_run:
+            self.start()
+            atexit.register(self.stop)
+
+    def start(self):
+        self._listener.start()
+
+    def stop(self):
+        self._listener.stop()
+
+    def emit(self, record):
+        return super().emit(record)

ielts_be/controllers/__init__.py

@@ -0,0 +1,3 @@
+from .abc import *
+
+__all__ = abc.__all__

ielts_be/controllers/abc/__init__.py

@@ -0,0 +1,11 @@
+from .grade import IGradeController
+from .training import ITrainingController
+from .user import IUserController
+from .exam import *
+
+__all__ = [
+    "IGradeController",
+    "ITrainingController",
+    "IUserController",
+]
+__all__.extend(exam.__all__)

ielts_be/controllers/abc/exam/__init__.py

@@ -0,0 +1,13 @@
+from .level import ILevelController
+from .listening import IListeningController
+from .reading import IReadingController
+from .writing import IWritingController
+from .speaking import ISpeakingController
+
+__all__ = [
+    "IListeningController",
+    "IReadingController",
+    "IWritingController",
+    "ISpeakingController",
+    "ILevelController",
+]

ielts_be/controllers/abc/exam/level.py

@@ -0,0 +1,27 @@
+from abc import ABC, abstractmethod
+
+from fastapi import UploadFile
+from typing import Dict, Optional
+
+
+class ILevelController(ABC):
+
+    @abstractmethod
+    async def generate_exercises(self, dto):
+        pass
+
+    @abstractmethod
+    async def get_level_exam(self):
+        pass
+
+    @abstractmethod
+    async def get_level_utas(self):
+        pass
+
+    @abstractmethod
+    async def upload_level(self, file: UploadFile, solutions: Optional[UploadFile] = None):
+        pass
+
+    @abstractmethod
+    async def get_custom_level(self, data: Dict):
+        pass

ielts_be/controllers/abc/exam/listening.py

@@ -0,0 +1,30 @@
+from abc import ABC, abstractmethod
+
+from fastapi import UploadFile
+
+
+class IListeningController(ABC):
+
+    @abstractmethod
+    async def import_exam(self, exercises: UploadFile, solutions: UploadFile = None):
+        pass
+
+    @abstractmethod
+    async def generate_listening_dialog(self, section_id: int, topic: str, difficulty: str):
+        pass
+
+    @abstractmethod
+    async def get_listening_question(self, dto):
+        pass
+
+    @abstractmethod
+    async def generate_mp3(self, dto):
+        pass
+
+    @abstractmethod
+    async def transcribe_dialog(self, audio: UploadFile):
+        pass
+
+    @abstractmethod
+    async def create_instructions(self, text: str):
+        pass

ielts_be/controllers/abc/exam/reading.py

@@ -0,0 +1,20 @@
+from abc import ABC, abstractmethod
+from typing import Optional
+
+from fastapi import UploadFile
+
+
+class IReadingController(ABC):
+
+    @abstractmethod
+    async def import_exam(self, exercises: UploadFile, solutions: UploadFile = None):
+        pass
+
+    @abstractmethod
+    async def generate_reading_passage(self, passage: int, topic: Optional[str], word_count: Optional[int]):
+        pass
+
+    @abstractmethod
+    async def generate_reading_exercises(self, dto):
+        pass
+

ielts_be/controllers/abc/exam/speaking.py

@@ -0,0 +1,20 @@
+from abc import ABC, abstractmethod
+
+
+class ISpeakingController(ABC):
+
+    @abstractmethod
+    async def get_speaking_part(self, task: int, topic: str, second_topic: str, difficulty: str):
+        pass
+
+    @abstractmethod
+    async def get_avatars(self):
+        pass
+
+    @abstractmethod
+    async def generate_video(self, text: str, avatar: str):
+        pass
+
+    @abstractmethod
+    async def poll_video(self, vid_id: str):
+        pass

ielts_be/controllers/abc/exam/writing.py

@@ -0,0 +1,14 @@
+from abc import ABC, abstractmethod
+
+from fastapi.datastructures import UploadFile
+
+
+class IWritingController(ABC):
+
+    @abstractmethod
+    async def get_writing_task_general_question(self, task: int, topic: str, difficulty: str):
+        pass
+
+    @abstractmethod
+    async def get_writing_task_academic_question(self, task: int, attachment: UploadFile, difficulty: str):
+        pass

ielts_be/controllers/abc/grade.py

@@ -0,0 +1,30 @@
+from abc import ABC, abstractmethod
+from typing import Dict
+from fastapi import BackgroundTasks
+from fastapi.datastructures import FormData
+
+
+class IGradeController(ABC):
+
+    @abstractmethod
+    async def grade_writing_task(
+        self,
+        task: int, dto: any,
+        background_tasks: BackgroundTasks
+    ):
+        pass
+
+    @abstractmethod
+    async def grade_speaking_task(
+            self, task: int, form: FormData, background_tasks: BackgroundTasks
+    ):
+        pass
+
+    @abstractmethod
+    async def grade_short_answers(self, data: Dict):
+        pass
+
+    @abstractmethod
+    async def grading_summary(self, data: Dict):
+        pass
+

ielts_be/controllers/abc/training.py

@@ -0,0 +1,12 @@
+from abc import ABC, abstractmethod
+
+
+class ITrainingController(ABC):
+
+    @abstractmethod
+    async def fetch_tips(self, data):
+        pass
+
+    @abstractmethod
+    async def get_training_content(self, data):
+        pass

ielts_be/controllers/abc/user.py

@@ -0,0 +1,8 @@
+from abc import ABC, abstractmethod
+
+
+class IUserController(ABC):
+
+    @abstractmethod
+    async def batch_import(self, batch):
+        pass

ielts_be/controllers/impl/__init__.py

@@ -0,0 +1,12 @@
+from .training import TrainingController
+from .grade import GradeController
+from .user import UserController
+from .exam import *
+
+__all__ = [
+    "TrainingController",
+    "GradeController",
+    "UserController"
+]
+
+__all__.extend(exam.__all__)

ielts_be/controllers/impl/exam/__init__.py

@@ -0,0 +1,13 @@
+from .level import LevelController
+from .listening import ListeningController
+from .reading import ReadingController
+from .speaking import SpeakingController
+from .writing import WritingController
+
+__all__ = [
+    "LevelController",
+    "ListeningController",
+    "ReadingController",
+    "SpeakingController",
+    "WritingController",
+]

ielts_be/controllers/impl/exam/level.py

@@ -0,0 +1,26 @@
+from fastapi import UploadFile
+from typing import Dict, Optional
+
+from ielts_be.controllers import ILevelController
+from ielts_be.services import ILevelService
+
+
+class LevelController(ILevelController):
+
+    def __init__(self, level_service: ILevelService):
+        self._service = level_service
+
+    async def generate_exercises(self, dto):
+        return await self._service.generate_exercises(dto)
+
+    async def get_level_exam(self):
+        return await self._service.get_level_exam()
+
+    async def get_level_utas(self):
+        return await self._service.get_level_utas()
+
+    async def upload_level(self, exercises: UploadFile, solutions: Optional[UploadFile] = None):
+        return await self._service.upload_level(exercises, solutions)
+
+    async def get_custom_level(self, data: Dict):
+        return await self._service.get_custom_level(data)

ielts_be/controllers/impl/exam/listening.py

@@ -0,0 +1,53 @@
+import io
+
+from fastapi import UploadFile
+from fastapi.responses import StreamingResponse, Response
+
+from ielts_be.controllers import IListeningController
+from ielts_be.services import IListeningService
+from ielts_be.dtos.listening import ListeningExercisesDTO, Dialog
+
+
+class ListeningController(IListeningController):
+
+    def __init__(self, listening_service: IListeningService):
+        self._service = listening_service
+
+    async def import_exam(self, exercises: UploadFile, solutions: UploadFile = None):
+        res = await self._service.import_exam(exercises, solutions)
+        if not res:
+            return Response(status_code=500)
+        else:
+            return res
+
+    async def generate_listening_dialog(self, section_id: int, topic: str, difficulty: str):
+        return await self._service.generate_listening_dialog(section_id, topic, difficulty)
+
+    async def get_listening_question(self, dto: ListeningExercisesDTO):
+        return await self._service.get_listening_question(dto)
+
+    async def generate_mp3(self, dto: Dialog):
+        mp3 = await self._service.generate_mp3(dto)
+        return self._mp3_response(mp3)
+
+    async def create_instructions(self, text: str):
+        mp3 = await self._service.create_instructions(text)
+        return self._mp3_response(mp3)
+
+    async def transcribe_dialog(self, audio: UploadFile):
+        dialog = await self._service.transcribe_dialog(audio)
+        if dialog is None:
+            return Response(status_code=500)
+
+        return dialog
+
+    @staticmethod
+    def _mp3_response(mp3: bytes):
+        return StreamingResponse(
+            content=io.BytesIO(mp3),
+            media_type="audio/mpeg",
+            headers={
+                "Content-Type": "audio/mpeg",
+                "Content-Disposition": "attachment;filename=speech.mp3"
+            }
+        )

ielts_be/controllers/impl/exam/reading.py

@@ -0,0 +1,28 @@
+import logging
+from typing import Optional
+
+from fastapi import UploadFile, Response
+
+from ielts_be.controllers import IReadingController
+from ielts_be.services import IReadingService
+from ielts_be.dtos.reading import ReadingDTO
+
+
+class ReadingController(IReadingController):
+
+    def __init__(self, reading_service: IReadingService):
+        self._service = reading_service
+        self._logger = logging.getLogger(__name__)
+
+    async def import_exam(self, exercises: UploadFile, solutions: UploadFile = None):
+        res = await self._service.import_exam(exercises, solutions)
+        if not res:
+            return Response(status_code=500)
+        else:
+            return res
+
+    async def generate_reading_passage(self, passage: int, topic: Optional[str], word_count: Optional[int]):
+        return await self._service.generate_reading_passage(passage, topic, word_count)
+
+    async def generate_reading_exercises(self, dto: ReadingDTO):
+        return await self._service.generate_reading_exercises(dto)

ielts_be/controllers/impl/exam/speaking.py

@@ -0,0 +1,24 @@
+import logging
+
+from ielts_be.controllers import ISpeakingController
+from ielts_be.services import ISpeakingService, IVideoGeneratorService
+
+
+class SpeakingController(ISpeakingController):
+
+    def __init__(self, speaking_service: ISpeakingService, vid_gen: IVideoGeneratorService):
+        self._service = speaking_service
+        self._vid_gen = vid_gen
+        self._logger = logging.getLogger(__name__)
+
+    async def get_speaking_part(self, task: int, topic: str, second_topic: str, difficulty: str):
+        return await self._service.get_speaking_part(task, topic, second_topic, difficulty)
+
+    async def get_avatars(self):
+        return await self._vid_gen.get_avatars()
+
+    async def generate_video(self, text: str, avatar: str):
+        return await self._vid_gen.create_video(text, avatar)
+
+    async def poll_video(self, vid_id: str):
+        return await self._vid_gen.poll_status(vid_id)

ielts_be/controllers/impl/exam/writing.py

@@ -0,0 +1,18 @@
+from fastapi import UploadFile, HTTPException
+
+from ielts_be.controllers import IWritingController
+from ielts_be.services import IWritingService
+
+
+class WritingController(IWritingController):
+
+    def __init__(self, writing_service: IWritingService):
+        self._service = writing_service
+
+    async def get_writing_task_general_question(self, task: int, topic: str, difficulty: str):
+        return await self._service.get_writing_task_general_question(task, topic, difficulty)
+
+    async def get_writing_task_academic_question(self, task: int, attachment: UploadFile, difficulty: str):
+        if attachment.content_type not in ['image/jpeg', 'image/png']:
+            raise HTTPException(status_code=400, detail="Invalid file type. Only JPEG and PNG allowed.")
+        return await self._service.get_writing_task_academic_question(task, attachment, difficulty)

ielts_be/controllers/impl/grade.py

@@ -0,0 +1,105 @@
+import logging
+from typing import Dict
+
+from fastapi import BackgroundTasks, Response, HTTPException
+from fastapi.datastructures import FormData
+
+from ielts_be.controllers import IGradeController
+from ielts_be.services import IGradeService, IEvaluationService
+from ielts_be.dtos.evaluation import EvaluationType
+from ielts_be.dtos.speaking import GradeSpeakingItem
+from ielts_be.dtos.writing import WritingGradeTaskDTO
+
+class GradeController(IGradeController):
+
+    def __init__(
+            self,
+            grade_service: IGradeService,
+            evaluation_service: IEvaluationService,
+    ):
+        self._service = grade_service
+        self._evaluation_service = evaluation_service
+        self._logger = logging.getLogger(__name__)
+
+    async def grade_writing_task(
+        self,
+        task: int, dto: WritingGradeTaskDTO, background_tasks: BackgroundTasks
+    ):
+        await self._evaluation_service.begin_evaluation(
+            dto.userId, dto.sessionId, task, dto.exerciseId, EvaluationType.WRITING, dto, background_tasks
+        )
+
+        return Response(status_code=200)
+
+    async def grade_speaking_task(self, task: int, form: FormData, background_tasks: BackgroundTasks):
+        answers: Dict[int, Dict] = {}
+        user_id = form.get("userId")
+        session_id = form.get("sessionId")
+        exercise_id = form.get("exerciseId")
+
+        if not session_id or not exercise_id:
+            raise HTTPException(
+                status_code=400,
+                detail="Fields sessionId and exerciseId are required!"
+            )
+
+        for key, value in form.items():
+            if '_' not in key:
+                continue
+
+            field_name, index = key.rsplit('_', 1)
+            index = int(index)
+
+            if index not in answers:
+                answers[index] = {}
+
+            if field_name == 'question':
+                answers[index]['question'] = value
+            elif field_name == 'audio':
+                answers[index]['answer'] = value
+
+        for i, answer in answers.items():
+            if 'question' not in answer or 'answer' not in answer:
+                raise HTTPException(
+                    status_code=400,
+                    detail=f"Incomplete data for answer {i}. Both question and audio required."
+                )
+
+        items = [
+            GradeSpeakingItem(
+                question=answers[i]['question'],
+                answer=answers[i]['answer']
+            )
+            for i in sorted(answers.keys())
+        ]
+
+        ex_type = EvaluationType.SPEAKING if task == 2 else EvaluationType.SPEAKING_INTERACTIVE
+
+        await self._evaluation_service.begin_evaluation(
+            user_id, session_id, task, exercise_id, ex_type, items, background_tasks
+        )
+
+        return Response(status_code=200)
+
+    async def grade_short_answers(self, data: Dict):
+        return await self._service.grade_short_answers(data)
+
+    async def grading_summary(self, data: Dict):
+        section_keys = ['reading', 'listening', 'writing', 'speaking', 'level']
+        extracted_sections = self._extract_existing_sections_from_body(data, section_keys)
+        return await self._service.calculate_grading_summary(extracted_sections)
+
+    @staticmethod
+    def _extract_existing_sections_from_body(my_dict, keys_to_extract):
+        if 'sections' in my_dict and isinstance(my_dict['sections'], list) and len(my_dict['sections']) > 0:
+            return list(
+                filter(
+                    lambda item:
+                    'code' in item and
+                    item['code'] in keys_to_extract and
+                    'grade' in item and
+                    'name' in item,
+                    my_dict['sections']
+                )
+            )
+

ielts_be/controllers/impl/training.py

@@ -0,0 +1,17 @@
+from typing import Dict
+
+from ielts_be.controllers import ITrainingController
+from ielts_be.services import ITrainingService
+from ielts_be.dtos.training import FetchTipsDTO
+
+
+class TrainingController(ITrainingController):
+
+    def __init__(self, training_service: ITrainingService):
+        self._service = training_service
+
+    async def fetch_tips(self, data: FetchTipsDTO):
+        return await self._service.fetch_tips(data.context, data.question, data.answer, data.correct_answer)
+
+    async def get_training_content(self, data: Dict):
+        return await self._service.get_training_content(data)

ielts_be/controllers/impl/user.py

@@ -0,0 +1,12 @@
+from ielts_be.controllers import IUserController
+from ielts_be.services import IUserService
+from ielts_be.dtos.user_batch import BatchUsersDTO
+
+
+class UserController(IUserController):
+
+    def __init__(self, user_service: IUserService):
+        self._service = user_service
+
+    async def batch_import(self, batch: BatchUsersDTO):
+        return await self._service.batch_users(batch)

ielts_be/dtos/evaluation.py

@@ -0,0 +1,18 @@
+from enum import Enum
+from typing import Dict, Optional
+from pydantic import BaseModel
+
+
+class EvaluationType(str, Enum):
+    WRITING = "writing"
+    SPEAKING_INTERACTIVE = "speaking_interactive"
+    SPEAKING = "speaking"
+
+class EvaluationRecord(BaseModel):
+    id: str
+    session_id: str
+    exercise_id: str
+    type: EvaluationType
+    task: int
+    status: str = "pending"
+    result: Optional[Dict] = None

ielts_be/dtos/exams/level.py

@@ -0,0 +1,60 @@
+from pydantic import BaseModel, Field
+from typing import List, Dict, Union, Optional
+from uuid import uuid4, UUID
+
+
+class Option(BaseModel):
+    id: str
+    text: str
+
+
+class MultipleChoiceQuestion(BaseModel):
+    id: str
+    prompt: str
+    variant: str = "text"
+    solution: str
+    options: List[Option]
+
+
+class MultipleChoiceExercise(BaseModel):
+    id: UUID = Field(default_factory=uuid4)
+    type: str = "multipleChoice"
+    prompt: str = "Select the appropriate option."
+    questions: List[MultipleChoiceQuestion]
+    userSolutions: List = Field(default_factory=list)
+
+
+class FillBlanksWord(BaseModel):
+    id: str
+    options: Dict[str, str]
+
+
+class FillBlanksSolution(BaseModel):
+    id: str
+    solution: str
+
+
+class FillBlanksExercise(BaseModel):
+    id: UUID = Field(default_factory=uuid4)
+    type: str = "fillBlanks"
+    variant: str = "mc"
+    prompt: str = "Click a blank to select the appropriate word for it."
+    text: str
+    solutions: List[FillBlanksSolution]
+    words: List[FillBlanksWord]
+    userSolutions: List = Field(default_factory=list)
+
+
+Exercise = Union[MultipleChoiceExercise, FillBlanksExercise]
+
+class Text(BaseModel):
+    content: str
+    title: str
+
+class Part(BaseModel):
+    exercises: List[Exercise]
+    text: Optional[Text] = Field(default=None)
+
+
+class Exam(BaseModel):
+    parts: List[Part]

ielts_be/dtos/exams/listening.py

@@ -0,0 +1,92 @@
+from enum import Enum
+from pydantic import BaseModel, Field
+from typing import List, Union, Optional, Literal, Any
+from uuid import uuid4, UUID
+
+from ielts_be.dtos.listening import Dialog
+
+
+class ExerciseBase(BaseModel):
+    id: UUID = Field(default_factory=uuid4)
+    type: str
+    prompt: str
+
+
+class TrueFalseSolution(str, Enum):
+    TRUE = "true"
+    FALSE = "false"
+    NOT_GIVEN = "not_given"
+
+class TrueFalseQuestions(BaseModel):
+    prompt: str
+    solution: TrueFalseSolution
+    id: str
+
+
+class TrueFalseExercise(ExerciseBase):
+    type: Literal["trueFalse"]
+    questions: List[TrueFalseQuestions]
+
+
+class MCOption(BaseModel):
+    id: str
+    text: str
+
+
+class MCQuestion(BaseModel):
+    id: str
+    prompt: str
+    options: List[MCOption]
+    solution: str
+    variant: str = "text"
+
+
+class MultipleChoiceExercise(ExerciseBase):
+    type: Literal["multipleChoice"]
+    questions: List[MCQuestion]
+
+
+class WriteBlankQuestion(BaseModel):
+    id: str
+    prompt: str
+    solution: List[str]
+
+class WriteBlanksVariant(str, Enum):
+    QUESTIONS = "questions"
+    FILL = "fill"
+    FORM = "form"
+
+class WriteBlanksQuestionExercise(ExerciseBase):
+    type: Literal["writeBlanks"]
+    maxWords: int
+    questions: List[WriteBlankQuestion]
+    variant: WriteBlanksVariant
+
+class WriteBlankSolution(BaseModel):
+    id: str
+    solution: List[str]
+
+class WriteBlanksExercise(ExerciseBase):
+    type: Literal["writeBlanks"]
+    maxWords: int
+    solutions: List[WriteBlankSolution]
+    text: str
+    variant: Optional[WriteBlanksVariant]
+
+
+ListeningExercise = Union[
+    TrueFalseExercise,
+    MultipleChoiceExercise,
+    WriteBlanksExercise
+]
+
+
+class ListeningSection(BaseModel):
+    exercises: List[ListeningExercise]
+    script: Optional[Union[List[Any] | str]] = None
+
+
+class ListeningExam(BaseModel):
+    module: str = "listening"
+    minTimer: Optional[int]
+    parts: List[ListeningSection]

ielts_be/dtos/exams/reading.py

@@ -0,0 +1,107 @@
+from enum import Enum
+
+from pydantic import BaseModel, Field
+from typing import List, Union, Optional
+from uuid import uuid4, UUID
+
+
+class WriteBlanksSolution(BaseModel):
+    id: str
+    solution: List[str]
+
+class WriteBlanksExercise(BaseModel):
+    id: UUID = Field(default_factory=uuid4)
+    type: str = "writeBlanks"
+    maxWords: int
+    solutions: List[WriteBlanksSolution]
+    text: str
+    prompt: str
+
+
+class MatchSentencesOption(BaseModel):
+    id: str
+    sentence: str
+
+class MatchSentencesSentence(MatchSentencesOption):
+    solution: str
+
+class MatchSentencesVariant(str, Enum):
+    HEADING = "heading"
+    IDEAMATCH = "ideaMatch"
+
+class MCOption(BaseModel):
+    id: str
+    text: str
+
+class MCQuestion(BaseModel):
+    id: str
+    prompt: str
+    options: List[MCOption]
+    solution: str
+    variant: Optional[str] = None
+
+class MultipleChoice(BaseModel):
+    questions: List[MCQuestion]
+    type: str
+    prompt: str
+
+
+class MatchSentencesExercise(BaseModel):
+    options: List[MatchSentencesOption]
+    sentences: List[MatchSentencesSentence]
+    type: str = "matchSentences"
+    variant: MatchSentencesVariant
+    prompt: str
+
+class TrueFalseSolution(str, Enum):
+    TRUE = "true"
+    FALSE = "false"
+    NOT_GIVEN = "not_given"
+
+class TrueFalseQuestions(BaseModel):
+    prompt: str
+    solution: TrueFalseSolution
+    id: str
+
+class TrueFalseExercise(BaseModel):
+    id: UUID = Field(default_factory=uuid4)
+    questions: List[TrueFalseQuestions]
+    type: str = "trueFalse"
+    prompt: str = "Do the following statements agree with the information given in the Reading Passage?"
+
+
+
+class FillBlanksSolution(BaseModel):
+    id: str
+    solution: str
+
+class FillBlanksWord(BaseModel):
+    letter: str
+    word: str
+
+class FillBlanksExercise(BaseModel):
+    id: UUID = Field(default_factory=uuid4)
+    solutions: List[FillBlanksSolution]
+    text: str
+    type: str = "fillBlanks"
+    words: List[FillBlanksWord]
+    allowRepetition: bool = False
+    prompt: str
+
+Exercise = Union[FillBlanksExercise, TrueFalseExercise, MatchSentencesExercise, WriteBlanksExercise, MultipleChoice]
+
+
+class Context(BaseModel):
+    title: str
+    content: str
+
+class Part(BaseModel):
+    exercises: List[Exercise]
+    text: Context
+
+class Exam(BaseModel):
+    id: UUID = Field(default_factory=uuid4)
+    module: str = "reading"
+    minTimer: int
+    isDiagnostic: bool = False
+    parts: List[Part]

ielts_be/dtos/level.py

@@ -0,0 +1,18 @@
+from typing import List, Optional
+
+from pydantic import BaseModel
+
+from ielts_be.configs.constants import LevelExerciseType
+
+
+class LevelExercises(BaseModel):
+    type: LevelExerciseType
+    quantity: int
+    text_size: Optional[int] = None
+    sa_qty: Optional[int] = None
+    mc_qty: Optional[int] = None
+    topic: Optional[str] = None
+
+class LevelExercisesDTO(BaseModel):
+    exercises: List[LevelExercises]
+    difficulty: Optional[str] = None

ielts_be/dtos/listening.py

@@ -0,0 +1,37 @@
+import random
+import uuid
+from typing import List, Dict, Optional
+
+from pydantic import BaseModel, Field
+
+from ielts_be.configs.constants import MinTimers, EducationalContent, ListeningExerciseType
+
+
+class SaveListeningDTO(BaseModel):
+    parts: List[Dict]
+    minTimer: int = MinTimers.LISTENING_MIN_TIMER_DEFAULT
+    difficulty: str = random.choice(EducationalContent.DIFFICULTIES)
+    id: str = str(uuid.uuid4())
+
+
+class ListeningExercises(BaseModel):
+    type: ListeningExerciseType
+    quantity: int
+
+class ListeningExercisesDTO(BaseModel):
+    text: str
+    exercises: List[ListeningExercises]
+    difficulty: Optional[str]
+
+class InstructionsDTO(BaseModel):
+    text: str
+
+class ConversationPayload(BaseModel):
+    name: str
+    gender: str
+    text: str
+    voice: Optional[str] = None
+
+class Dialog(BaseModel):
+    conversation: Optional[List[ConversationPayload]] = Field(default_factory=list)
+    monologue: Optional[str] = None

ielts_be/dtos/reading.py

@@ -0,0 +1,17 @@
+import random
+from typing import List, Optional
+
+from pydantic import BaseModel, Field
+
+from ielts_be.configs.constants import ReadingExerciseType, EducationalContent
+
+class ReadingExercise(BaseModel):
+    type: ReadingExerciseType
+    quantity: int
+    num_random_words: Optional[int] = Field(1)
+    max_words: Optional[int] = Field(3)
+
+class ReadingDTO(BaseModel):
+    text: str = Field(...)
+    exercises: List[ReadingExercise] = Field(...)
+    difficulty: Optional[str] = None

ielts_be/dtos/sheet.py

@@ -0,0 +1,29 @@
+from pydantic import BaseModel
+from typing import List, Dict, Union, Any, Optional
+
+
+class Option(BaseModel):
+    id: str
+    text: str
+
+
+class MultipleChoiceQuestion(BaseModel):
+    type: str = "multipleChoice"
+    id: str
+    prompt: str
+    variant: str = "text"
+    options: List[Option]
+
+
+class FillBlanksWord(BaseModel):
+    type: str = "fillBlanks"
+    id: str
+    options: Dict[str, str]
+
+
+Component = Union[MultipleChoiceQuestion, FillBlanksWord, Dict[str, Any]]
+
+
+class Sheet(BaseModel):
+    batch: Optional[int] = None
+    components: List[Component]

ielts_be/dtos/speaking.py

@@ -0,0 +1,11 @@
+from fastapi import UploadFile
+from pydantic import BaseModel
+
+
+class Video(BaseModel):
+    text: str
+    avatar: str
+
+class GradeSpeakingItem(BaseModel):
+    question: str
+    answer: UploadFile

ielts_be/dtos/training.py

@@ -0,0 +1,37 @@
+from pydantic import BaseModel
+from typing import List
+
+
+class FetchTipsDTO(BaseModel):
+    context: str
+    question: str
+    answer: str
+    correct_answer: str
+
+
+class QueryDTO(BaseModel):
+    category: str
+    text: str
+
+
+class DetailsDTO(BaseModel):
+    exam_id: str
+    date: int
+    performance_comment: str
+    detailed_summary: str
+
+
+class WeakAreaDTO(BaseModel):
+    area: str
+    comment: str
+
+
+class TrainingContentDTO(BaseModel):
+    details: List[DetailsDTO]
+    weak_areas: List[WeakAreaDTO]
+    queries: List[QueryDTO]
+
+
+class TipsDTO(BaseModel):
+    tip_ids: List[str]
+

ielts_be/dtos/user_batch.py

@@ -0,0 +1,35 @@
+import uuid
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+class DemographicInfo(BaseModel):
+  phone: str
+  passport_id: Optional[str] = None
+  country: Optional[str] = None
+
+class Entity(BaseModel):
+  id: str
+  role: str
+
+
+class UserDTO(BaseModel):
+  id: str
+  email: str
+  name: str
+  type: str
+  passport_id: str
+  passwordHash: str
+  passwordSalt: str
+  groupName: Optional[str] = None
+  corporate: Optional[str] = None
+  studentID: Optional[str] = None
+  expiryDate: Optional[str] = None
+  demographicInformation: Optional[DemographicInfo] = None
+  entities: list[dict] = Field(default_factory=list)
+
+
+class BatchUsersDTO(BaseModel):
+  makerID: str
+  users: list[UserDTO]

ielts_be/dtos/video.py

@@ -0,0 +1,14 @@
+from enum import Enum
+from typing import Optional
+
+from pydantic import BaseModel
+
+class TaskStatus(Enum):
+    STARTED = "STARTED"
+    IN_PROGRESS = "IN_PROGRESS"
+    COMPLETED = "COMPLETED"
+    ERROR = "ERROR"
+
+class Task(BaseModel):
+    status: TaskStatus
+    result: Optional[str] = None

ielts_be/dtos/writing.py

@@ -0,0 +1,12 @@
+from typing import Optional
+
+from pydantic import BaseModel
+
+
+class WritingGradeTaskDTO(BaseModel):
+    userId: str
+    sessionId: str
+    exerciseId: str
+    question: str
+    answer: str
+    attachment: Optional[str] = None

ielts_be/exceptions/__init__.py

@@ -0,0 +1,6 @@
+from .exceptions import CustomException, UnauthorizedException
+
+__all__ = [
+    "CustomException",
+    "UnauthorizedException"
+]

ielts_be/exceptions/exceptions.py

@@ -0,0 +1,21 @@
+from http import HTTPStatus
+
+
+class CustomException(Exception):
+    code = HTTPStatus.INTERNAL_SERVER_ERROR
+    error_code = HTTPStatus.INTERNAL_SERVER_ERROR
+    message = HTTPStatus.INTERNAL_SERVER_ERROR.description
+
+    def __init__(self, message=None):
+        if message:
+            self.message = message
+
+
+class UnauthorizedException(CustomException):
+    code = HTTPStatus.UNAUTHORIZED
+    error_code = HTTPStatus.UNAUTHORIZED
+    message = HTTPStatus.UNAUTHORIZED.description
+
+class TranscriptionException(CustomException):
+    code = HTTPStatus.INTERNAL_SERVER_ERROR
+    error_code = HTTPStatus.INTERNAL_SERVER_ERROR

ielts_be/helpers/__init__.py

@@ -0,0 +1,11 @@
+from .file import FileHelper
+from .text import TextHelper
+from .token_counter import count_tokens
+from .exercises import ExercisesHelper
+
+__all__ = [
+    "FileHelper",
+    "TextHelper",
+    "count_tokens",
+    "ExercisesHelper",
+]

ielts_be/helpers/exercises.py

@@ -0,0 +1,249 @@
+import queue
+import random
+import re
+import string
+from wonderwords import RandomWord
+
+from .text import TextHelper
+
+
+class ExercisesHelper:
+
+    @staticmethod
+    def divide_number_into_parts(number, parts):
+        if number < parts:
+            return None
+
+        part_size = number // parts
+        remaining = number % parts
+
+        q = queue.Queue()
+
+        for i in range(parts):
+            if i < remaining:
+                q.put(part_size + 1)
+            else:
+                q.put(part_size)
+
+        return q
+
+    @staticmethod
+    def fix_exercise_ids(exercise, start_id):
+        # Initialize the starting ID for the first exercise
+        current_id = start_id
+
+        questions = exercise["questions"]
+
+        # Iterate through questions and update the "id" value
+        for question in questions:
+            question["id"] = str(current_id)
+            current_id += 1
+
+        return exercise
+
+    @staticmethod
+    def replace_first_occurrences_with_placeholders(text: str, words_to_replace: list, start_id):
+        for i, word in enumerate(words_to_replace, start=start_id):
+            # Create a case-insensitive regular expression pattern
+            pattern = re.compile(r'\b' + re.escape(word) + r'\b', re.IGNORECASE)
+            placeholder = '{{' + str(i) + '}}'
+            text = pattern.sub(placeholder, text, 1)
+        return text
+
+    @staticmethod
+    def replace_first_occurrences_with_placeholders_notes(notes: list, words_to_replace: list, start_id):
+        replaced_notes = []
+        for i, note in enumerate(notes, start=0):
+            word = words_to_replace[i]
+            pattern = re.compile(r'\b' + re.escape(word) + r'\b', re.IGNORECASE)
+            placeholder = '{{' + str(start_id + i) + '}}'
+            note = pattern.sub(placeholder, note, 1)
+            replaced_notes.append(note)
+        return replaced_notes
+
+    @staticmethod
+    def add_random_words_and_shuffle(word_array, num_random_words):
+        r = RandomWord()
+        random_words_selected = r.random_words(num_random_words)
+
+        combined_array = word_array + random_words_selected
+
+        random.shuffle(combined_array)
+
+        result = []
+        for i, word in enumerate(combined_array):
+            letter = chr(65 + i)  # chr(65) is 'A'
+            result.append({"letter": letter, "word": word})
+
+        return result
+
+    @staticmethod
+    def fillblanks_build_solutions_array(words, start_id):
+        solutions = []
+        for i, word in enumerate(words, start=start_id):
+            solutions.append(
+                {
+                    "id": str(i),
+                    "solution": word
+                }
+            )
+        return solutions
+
+    @staticmethod
+    def remove_excess_questions(questions: [], quantity):
+        count_true = 0
+        result = []
+
+        for item in reversed(questions):
+            if item.get('solution') == 'true' and count_true < quantity:
+                count_true += 1
+            else:
+                result.append(item)
+
+        result.reverse()
+        return result
+
+    @staticmethod
+    def build_write_blanks_text(questions: [], start_id):
+        result = ""
+        for i, q in enumerate(questions, start=start_id):
+            placeholder = '{{' + str(i) + '}}'
+            result = result + q["question"] + placeholder + "\\n"
+        return result
+
+    @staticmethod
+    def build_write_blanks_text_form(form: [], start_id):
+        result = ""
+        replaced_words = []
+        for i, entry in enumerate(form, start=start_id):
+            placeholder = '{{' + str(i) + '}}'
+            # Use regular expression to find the string after ':'
+            match = re.search(r'(?<=:)\s*(.*)', entry)
+            # Extract the matched string
+            original_string = match.group(1)
+            # Split the string into words
+            words = re.findall(r'\b\w+\b', original_string)
+            # Remove words with only one letter
+            filtered_words = [word for word in words if len(word) > 1]
+            # Choose a random word from the list of words
+            selected_word = random.choice(filtered_words)
+            pattern = re.compile(r'\b' + re.escape(selected_word) + r'\b', re.IGNORECASE)
+
+            # Replace the chosen word with the placeholder
+            replaced_string = pattern.sub(placeholder, original_string, 1)
+            # Construct the final replaced string
+            replaced_string = entry.replace(original_string, replaced_string)
+
+            result = result + replaced_string + "\\n"
+            # Save the replaced word or use it as needed
+            # For example, you can save it to a file or a list
+            replaced_words.append(selected_word)
+        return result, replaced_words
+
+    @staticmethod
+    def build_write_blanks_solutions(questions: [], start_id):
+        solutions = []
+        for i, q in enumerate(questions, start=start_id):
+            solution = [q["possible_answers"]] if isinstance(q["possible_answers"], str) else q["possible_answers"]
+
+            solutions.append(
+                {
+                    "id": str(i),
+                    "solution": solution
+                }
+            )
+        return solutions
+
+    @staticmethod
+    def build_write_blanks_solutions_listening(words: [], start_id):
+        solutions = []
+        for i, word in enumerate(words, start=start_id):
+            solution = [word] if isinstance(word, str) else word
+
+            solutions.append(
+                {
+                    "id": str(i),
+                    "solution": solution
+                }
+            )
+        return solutions
+
+    @staticmethod
+    def answer_word_limit_ok(question):
+        # Check if any option in any solution has more than three words
+        return not any(
+                len(option.split()) > 3
+                for solution in question["solutions"]
+                for option in solution["solution"]
+            )
+
+    @staticmethod
+    def assign_letters_to_paragraphs(paragraphs):
+        result = []
+        letters = iter(string.ascii_uppercase)
+        for paragraph in paragraphs.split("\n\n"):
+            if TextHelper.has_x_words(paragraph, 10):
+                result.append({'paragraph': paragraph.strip(), 'letter': next(letters)})
+        return result
+
+    @staticmethod
+    def contains_empty_dict(arr):
+        return any(elem == {} for elem in arr)
+
+    @staticmethod
+    def fix_writing_overall(overall: float, task_response: dict):
+        grades = [category["grade"] for category in task_response.values()]
+
+        if overall > max(grades) or overall < min(grades):
+            total_sum = sum(grades)
+            average = total_sum / len(grades)
+            rounded_average = round(average, 0)
+            return rounded_average
+
+        return overall
+
+    @staticmethod
+    def build_options(ideas):
+        options = []
+        letters = iter(string.ascii_uppercase)
+        for idea in ideas:
+            options.append({
+                "id": next(letters),
+                "sentence": idea["from"]
+            })
+        return options
+
+    @staticmethod
+    def build_sentences(ideas, start_id):
+        sentences = []
+        letters = iter(string.ascii_uppercase)
+        for idea in ideas:
+            sentences.append({
+                "solution": next(letters),
+                "sentence": idea["idea"]
+            })
+
+        random.shuffle(sentences)
+        for i, sentence in enumerate(sentences, start=start_id):
+            sentence["id"] = i
+        return sentences
+
+    @staticmethod
+    def randomize_mc_options_order(questions):
+        option_ids = ['A', 'B', 'C', 'D']
+
+        for question in questions:
+            # Store the original solution text
+            original_solution_text = next(
+                option['text'] for option in question['options'] if option['id'] == question['solution'])
+
+            # Shuffle the options
+            random.shuffle(question['options'])
+
+            # Update the option ids and find the new solution id
+            for idx, option in enumerate(question['options']):
+                option['id'] = option_ids[idx]
+                if option['text'] == original_solution_text:
+                    question['solution'] = option['id']
+
+        return questions

ielts_be/helpers/file.py

@@ -0,0 +1,125 @@
+import base64
+import io
+import os
+import shutil
+import subprocess
+import uuid
+import datetime
+from pathlib import Path
+from typing import Optional, Tuple
+
+import aiofiles
+import numpy as np
+import pypandoc
+from PIL import Image
+from fastapi import UploadFile
+
+
+class FileHelper:
+
+    @staticmethod
+    def delete_files_older_than_one_day(directory: str):
+        current_time = datetime.datetime.now()
+
+        for entry in os.scandir(directory):
+            if entry.is_file():
+                file_path = Path(entry)
+                file_name = file_path.name
+                file_modified_time = datetime.datetime.fromtimestamp(file_path.stat().st_mtime)
+                time_difference = current_time - file_modified_time
+                if time_difference.days > 1 and "placeholder" not in file_name:
+                    file_path.unlink()
+                    print(f"Deleted file: {file_path}")
+
+    # Supposedly pandoc covers a wide range of file extensions only tested with docx
+    @staticmethod
+    def convert_file_to_pdf(input_path: str, output_path: str):
+        pypandoc.convert_file(input_path, 'pdf', outputfile=output_path, extra_args=[
+            '-V', 'geometry:paperwidth=5.5in',
+            '-V', 'geometry:paperheight=8.5in',
+            '-V', 'geometry:margin=0.5in',
+            '-V', 'pagestyle=empty'
+        ])
+
+    @staticmethod
+    def convert_file_to_html(input_path: str, output_path: str):
+        pypandoc.convert_file(input_path, 'html', outputfile=output_path)
+
+    @staticmethod
+    def pdf_to_png(path_id: str):
+        to_png = f"pdftoppm -png exercises.pdf page"
+        result = subprocess.run(to_png, shell=True, cwd=f'./tmp/{path_id}', capture_output=True, text=True)
+        if result.returncode != 0:
+            raise Exception(
+                f"Couldn't convert pdf to png. Failed to run command '{to_png}' -> ```cmd {result.stderr}```")
+
+    @staticmethod
+    def is_page_blank(image_bytes: bytes, image_threshold=10) -> bool:
+        with Image.open(io.BytesIO(image_bytes)) as img:
+            img_gray = img.convert('L')
+            img_array = np.array(img_gray)
+            non_white_pixels = np.sum(img_array < 255)
+
+        return non_white_pixels <= image_threshold
+
+    @classmethod
+    async def _encode_image(cls, image_path: str, image_threshold=10) -> Optional[str]:
+        async with aiofiles.open(image_path, "rb") as image_file:
+            image_bytes = await image_file.read()
+
+        if cls.is_page_blank(image_bytes, image_threshold):
+            return None
+
+        return base64.b64encode(image_bytes).decode('utf-8')
+
+    @classmethod
+    async def b64_pngs(cls, path_id: str, files: list[str]):
+        png_messages = []
+        for filename in files:
+            b64_string = await cls._encode_image(os.path.join(f'./tmp/{path_id}', filename))
+            if b64_string:
+                png_messages.append({
+                    "type": "image_url",
+                    "image_url": {
+                        "url": f"data:image/png;base64,{b64_string}"
+                    }
+                })
+        return png_messages
+
+    @staticmethod
+    def remove_directory(path):
+        try:
+            if os.path.exists(path):
+                if os.path.isdir(path):
+                    shutil.rmtree(path)
+        except Exception as e:
+            print(f"An error occurred while trying to remove {path}: {str(e)}")
+
+    @staticmethod
+    def remove_file(file_path):
+        try:
+            if os.path.exists(file_path):
+                if os.path.isfile(file_path):
+                    os.remove(file_path)
+        except Exception as e:
+            print(f"An error occurred while trying to remove the file {file_path}: {str(e)}")
+
+    @staticmethod
+    async def save_upload(file: UploadFile, name: str = "upload", path_id: str = None) -> Tuple[str, str]:
+        ext = file.filename.split('.')[-1]
+        path_id = str(uuid.uuid4()) if path_id is None else path_id
+        os.makedirs(f'./tmp/{path_id}', exist_ok=True)
+
+        tmp_filename = f'./tmp/{path_id}/{name}.{ext}'
+        file_bytes: bytes = await file.read()
+
+        async with aiofiles.open(tmp_filename, 'wb') as file:
+            await file.write(file_bytes)
+
+        return ext, path_id
+
+    @staticmethod
+    async def encode_image(image_path: str) -> str:
+        async with aiofiles.open(image_path, "rb") as image_file:
+            img = await image_file.read()
+        return base64.b64encode(img).decode('utf-8')

ielts_be/helpers/text.py

@@ -0,0 +1,28 @@
+from nltk.corpus import words
+
+
+class TextHelper:
+
+    @classmethod
+    def has_words(cls, text: str):
+        if not cls._has_common_words(text):
+            return False
+        english_words = set(words.words())
+        words_in_input = text.split()
+        return any(word.lower() in english_words for word in words_in_input)
+
+    @classmethod
+    def has_x_words(cls, text: str, quantity):
+        if not cls._has_common_words(text):
+            return False
+        english_words = set(words.words())
+        words_in_input = text.split()
+        english_word_count = sum(1 for word in words_in_input if word.lower() in english_words)
+        return english_word_count >= quantity
+
+    @staticmethod
+    def _has_common_words(text: str):
+        english_words = {"the", "be", "to", "of", "and", "a", "in", "that", "have", "i"}
+        words_in_input = text.split()
+        english_word_count = sum(1 for word in words_in_input if word.lower() in english_words)
+        return english_word_count >= 10

ielts_be/helpers/token_counter.py

@@ -1,89 +1,89 @@
-# This is a work in progress. There are still bugs. Once it is production-ready this will become a full repo.
+# This is a work in progress. There are still bugs. Once it is production-ready this will become a full repo.
-import os
+
-
+import tiktoken
-
+import nltk
-def count_tokens(text, model_name="gpt-3.5-turbo", debug=False):
+
-    """
+
-    Count the number of tokens in a given text string without using the OpenAI API.
+def count_tokens(text, model_name="gpt-3.5-turbo", debug=False):
-
+    """
-    This function tries three methods in the following order:
+    Count the number of tokens in a given text string without using the OpenAI API.
-    1. tiktoken (preferred): Accurate token counting similar to the OpenAI API.
+
-    2. nltk: Token counting using the Natural Language Toolkit library.
+    This function tries three methods in the following order:
-    3. split: Simple whitespace-based token counting as a fallback.
+    1. tiktoken (preferred): Accurate token counting similar to the OpenAI API.
-
+    2. nltk: Token counting using the Natural Language Toolkit library.
-    Usage:
+    3. split: Simple whitespace-based token counting as a fallback.
-    ------
+
-    text = "Your text here"
+    Usage:
-    result = count_tokens(text, model_name="gpt-3.5-turbo", debug=True)
+    ------
-    print(result)
+    text = "Your text here"
-
+    result = count_tokens(text, model_name="gpt-3.5-turbo", debug=True)
-    Required libraries:
+    print(result)
-    -------------------
+
-    - tiktoken: Install with 'pip install tiktoken'
+    Required libraries:
-    - nltk: Install with 'pip install nltk'
+    -------------------
-
+    - tiktoken: Install with 'pip install tiktoken'
-    Parameters:
+    - nltk: Install with 'pip install nltk'
-    -----------
+
-    text : str
+    Parameters:
-        The text string for which you want to count tokens.
+    -----------
-    model_name : str, optional
+    text : str
-        The OpenAI model for which you want to count tokens (default: "gpt-3.5-turbo").
+        The text string for which you want to count tokens.
-    debug : bool, optional
+    model_name : str, optional
-        Set to True to print error messages (default: False).
+        The OpenAI model for which you want to count tokens (default: "gpt-3.5-turbo").
-
+    debug : bool, optional
-    Returns:
+        Set to True to print error messages (default: False).
-    --------
+
-    result : dict
+    Returns:
-        A dictionary containing the number of tokens and the method used for counting.
+    --------
-    """
+    result : dict
-
+        A dictionary containing the number of tokens and the method used for counting.
-    # Try using tiktoken
+    """
-    try:
+
-        import tiktoken
+    # Try using tiktoken
-        encoding = tiktoken.encoding_for_model(model_name)
+    try:
-        num_tokens = len(encoding.encode(text))
+        encoding = tiktoken.encoding_for_model(model_name)
-        result = {"n_tokens": num_tokens, "method": "tiktoken"}
+        num_tokens = len(encoding.encode(text))
-        return result
+        result = {"n_tokens": num_tokens, "method": "tiktoken"}
-    except Exception as e:
+        return result
-        if debug:
+    except Exception as e:
-            print(f"Error using tiktoken: {e}")
+        if debug:
-        pass
+            print(f"Error using tiktoken: {e}")
-
+        pass
-    # Try using nltk
+
-    try:
+    # Try using nltk
-        import nltk
+    try:
-        nltk.download("punkt")
+        # Passed nltk.download("punkt") to server.py's @asynccontextmanager
-        tokens = nltk.word_tokenize(text)
+        tokens = nltk.word_tokenize(text)
-        result = {"n_tokens": len(tokens), "method": "nltk"}
+        result = {"n_tokens": len(tokens), "method": "nltk"}
-        return result
+        return result
-    except Exception as e:
+    except Exception as e:
-        if debug:
+        if debug:
-            print(f"Error using nltk: {e}")
+            print(f"Error using nltk: {e}")
-        pass
+        pass
-
+
-    # If nltk and tiktoken fail, use a simple split-based method
+    # If nltk and tiktoken fail, use a simple split-based method
-    tokens = text.split()
+    tokens = text.split()
-    result = {"n_tokens": len(tokens), "method": "split"}
+    result = {"n_tokens": len(tokens), "method": "split"}
-    return result
+    return result
-
+
-
+
-class TokenBuffer:
+class TokenBuffer:
-    def __init__(self, max_tokens=2048):
+    def __init__(self, max_tokens=2048):
-        self.max_tokens = max_tokens
+        self.max_tokens = max_tokens
-        self.buffer = ""
+        self.buffer = ""
-        self.token_lengths = []
+        self.token_lengths = []
-        self.token_count = 0
+        self.token_count = 0
-
+
-    def update(self, text, model_name="gpt-3.5-turbo", debug=False):
+    def update(self, text, model_name="gpt-3.5-turbo", debug=False):
-        new_tokens = count_tokens(text, model_name=model_name, debug=debug)["n_tokens"]
+        new_tokens = count_tokens(text, model_name=model_name, debug=debug)["n_tokens"]
-        self.token_count += new_tokens
+        self.token_count += new_tokens
-        self.buffer += text
+        self.buffer += text
-        self.token_lengths.append(new_tokens)
+        self.token_lengths.append(new_tokens)
-
+
-        while self.token_count > self.max_tokens:
+        while self.token_count > self.max_tokens:
-            removed_tokens = self.token_lengths.pop(0)
+            removed_tokens = self.token_lengths.pop(0)
-            self.token_count -= removed_tokens
+            self.token_count -= removed_tokens
-            self.buffer = self.buffer.split(" ", removed_tokens)[-1]
+            self.buffer = self.buffer.split(" ", removed_tokens)[-1]
-
+
-    def get_buffer(self):
+    def get_buffer(self):
-        return self.buffer
+        return self.buffer

ielts_be/mappers/__init__.py

@@ -0,0 +1,5 @@
+from .level import LevelMapper
+
+__all__ = [
+    "LevelMapper"
+]