Generate questions endpoints working for all.
This commit is contained in:
Cristiano Ferreira
@@ -1,9 +1,17 @@
|
||||
import queue
|
||||
import nltk
|
||||
import random
|
||||
import re
|
||||
import uuid
|
||||
|
||||
from helper.api_messages import QuestionType
|
||||
from helper.openai_interface import make_openai_instruct_call
|
||||
from helper.token_counter import count_tokens
|
||||
from helper.constants import *
|
||||
from wonderwords import RandomWord
|
||||
|
||||
nltk.download('words')
|
||||
|
||||
|
||||
def divide_number_into_parts(number, parts):
|
||||
if number < parts:
|
||||
@@ -22,51 +30,598 @@ def divide_number_into_parts(number, parts):
|
||||
|
||||
return q
|
||||
|
||||
def fix_exercise_ids(exercises):
|
||||
|
||||
def fix_exercise_ids(exercise, start_id):
|
||||
# Initialize the starting ID for the first exercise
|
||||
current_id = 1
|
||||
current_id = start_id
|
||||
|
||||
# Iterate through exercises
|
||||
for exercise in exercises:
|
||||
questions = exercise["questions"]
|
||||
questions = exercise["questions"]
|
||||
|
||||
# Iterate through questions and update the "id" value
|
||||
for question in questions:
|
||||
question["id"] = str(current_id)
|
||||
current_id += 1
|
||||
# Iterate through questions and update the "id" value
|
||||
for question in questions:
|
||||
question["id"] = str(current_id)
|
||||
current_id += 1
|
||||
|
||||
return exercises
|
||||
return exercise
|
||||
|
||||
|
||||
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(re.escape(word), re.IGNORECASE)
|
||||
placeholder = '{{' + str(i) + '}}'
|
||||
text = pattern.sub(placeholder, text, 1)
|
||||
return text
|
||||
|
||||
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
|
||||
|
||||
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)
|
||||
|
||||
return combined_array
|
||||
|
||||
|
||||
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
|
||||
|
||||
|
||||
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
|
||||
|
||||
|
||||
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
|
||||
|
||||
def build_write_blanks_text_form(form: [], start_id):
|
||||
result = ""
|
||||
replaced_words = []
|
||||
for i, entry in enumerate(form, start=1):
|
||||
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
|
||||
|
||||
|
||||
def build_write_blanks_solutions(questions: [], start_id):
|
||||
solutions = []
|
||||
for i, q in enumerate(questions, start=start_id):
|
||||
solutions.append(
|
||||
{
|
||||
"id": str(i),
|
||||
"solution": q["possible_answers"]
|
||||
}
|
||||
)
|
||||
return solutions
|
||||
|
||||
def build_write_blanks_solutions_listening(words: [], start_id):
|
||||
solutions = []
|
||||
for i, word in enumerate(words, start=start_id):
|
||||
solutions.append(
|
||||
{
|
||||
"id": str(i),
|
||||
"solution": word
|
||||
}
|
||||
)
|
||||
return solutions
|
||||
|
||||
|
||||
def generate_reading_passage(type: QuestionType, topic: str):
|
||||
gen_reading_passage_1 = "Generate an extensive text for IELTS " + type.READING_PASSAGE_1.value + ", of at least 1500 words, on the topic " \
|
||||
"of " + topic + ". The passage should offer a substantial amount of " \
|
||||
"information, analysis, or narrative " \
|
||||
"relevant to the chosen subject matter. This text passage aims to serve as the primary reading " \
|
||||
"section of an IELTS test, providing an in-depth and comprehensive exploration of the topic." \
|
||||
"Provide your response in this json format: {'title': 'title of the text', 'text': 'generated text'}"
|
||||
gen_reading_passage_1 = "Generate an extensive text for IELTS " + type.value + ", of at least 1500 words, on the topic " \
|
||||
"of " + topic + ". The passage should offer a substantial amount of " \
|
||||
"information, analysis, or narrative " \
|
||||
"relevant to the chosen subject matter. This text passage aims to serve as the primary reading " \
|
||||
"section of an IELTS test, providing an in-depth and comprehensive exploration of the topic." \
|
||||
"Provide your response in this json format: {\"title\": \"title of the text\", \"text\": \"generated text\"}"
|
||||
token_count = count_tokens(gen_reading_passage_1)["n_tokens"]
|
||||
return make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_reading_passage_1, token_count, GEN_TEXT_FIELDS,
|
||||
GEN_QUESTION_TEMPERATURE)
|
||||
GEN_QUESTION_TEMPERATURE)
|
||||
|
||||
def gen_multiple_choice_exercise(text: str, quantity: int):
|
||||
gen_multiple_choice_for_text = "Generate" + str(quantity) + "multiple choice questions for this text: " \
|
||||
"'" + text + "'\n" \
|
||||
"Use this format: 'questions': [{'id': '9', 'options': [{'id': 'A', 'text': " \
|
||||
"'Economic benefits'}, {'id': 'B', 'text': 'Government regulations'}, {'id': 'C', 'text': " \
|
||||
"'Concerns about climate change'}, {'id': 'D', 'text': 'Technological advancement'}], " \
|
||||
"'prompt': 'What is the main reason for the shift towards renewable energy sources?', " \
|
||||
"'solution': 'C', 'variant': 'text'}]"
|
||||
|
||||
def generate_listening_1_conversation(topic: str):
|
||||
gen_listening_1_conversation_2_people = "Compose an authentic conversation between two individuals in the everyday " \
|
||||
"social context of '" + topic + "'. Please include random names and genders " \
|
||||
"for the characters in your dialogue."
|
||||
token_count = count_tokens(gen_listening_1_conversation_2_people)["n_tokens"]
|
||||
response = make_openai_instruct_call(
|
||||
GPT_3_5_TURBO_INSTRUCT,
|
||||
gen_listening_1_conversation_2_people,
|
||||
token_count,
|
||||
None,
|
||||
GEN_QUESTION_TEMPERATURE
|
||||
)
|
||||
|
||||
conversation_json = '{"conversation": [{"name": "name", "gender": "gender", "text": "text"}]}'
|
||||
|
||||
parse_conversation = "Parse this conversation: '" + response + "' to the following json format: " + conversation_json
|
||||
|
||||
token_count = count_tokens(parse_conversation)["n_tokens"]
|
||||
processed = make_openai_instruct_call(
|
||||
GPT_3_5_TURBO_INSTRUCT,
|
||||
parse_conversation,
|
||||
token_count,
|
||||
['conversation'],
|
||||
GEN_QUESTION_TEMPERATURE
|
||||
)
|
||||
|
||||
name_to_voice = {}
|
||||
for segment in processed['conversation']:
|
||||
if 'voice' not in segment:
|
||||
name = segment['name']
|
||||
if name in name_to_voice:
|
||||
voice = name_to_voice[name]
|
||||
else:
|
||||
if segment['gender'].lower() == 'male':
|
||||
voice = random.choice(MALE_NEURAL_VOICES)['Id']
|
||||
else:
|
||||
voice = random.choice(FEMALE_NEURAL_VOICES)['Id']
|
||||
name_to_voice[name] = voice
|
||||
segment['voice'] = voice
|
||||
return response, processed
|
||||
|
||||
def generate_listening_2_monologue(topic: str):
|
||||
gen_listening_2_monologue_social = "Generate a comprehensive monologue set in the social context of: '" + topic + "'"
|
||||
token_count = count_tokens(gen_listening_2_monologue_social)["n_tokens"]
|
||||
response = make_openai_instruct_call(
|
||||
GPT_3_5_TURBO_INSTRUCT,
|
||||
gen_listening_2_monologue_social,
|
||||
token_count,
|
||||
None,
|
||||
GEN_QUESTION_TEMPERATURE
|
||||
)
|
||||
return response
|
||||
|
||||
def generate_listening_3_conversation(topic: str):
|
||||
gen_listening_3_conversation_4_people = "Compose an authentic and elaborate conversation between up to four individuals " \
|
||||
"in the everyday social context of '" + topic + \
|
||||
"'. Please include random names and genders for the characters in your dialogue."
|
||||
token_count = count_tokens(gen_listening_3_conversation_4_people)["n_tokens"]
|
||||
response = make_openai_instruct_call(
|
||||
GPT_3_5_TURBO_INSTRUCT,
|
||||
gen_listening_3_conversation_4_people,
|
||||
token_count,
|
||||
None,
|
||||
GEN_QUESTION_TEMPERATURE
|
||||
)
|
||||
conversation_json = '{"conversation": [{"name": "name", "gender": "gender", "text": "text"}]}'
|
||||
|
||||
parse_conversation = "Parse this conversation: '" + response + "' to the following json format: " + conversation_json
|
||||
|
||||
token_count = count_tokens(parse_conversation)["n_tokens"]
|
||||
processed = make_openai_instruct_call(
|
||||
GPT_3_5_TURBO_INSTRUCT,
|
||||
parse_conversation,
|
||||
token_count,
|
||||
['conversation'],
|
||||
GEN_QUESTION_TEMPERATURE
|
||||
)
|
||||
|
||||
name_to_voice = {}
|
||||
for segment in processed['conversation']:
|
||||
if 'voice' not in segment:
|
||||
name = segment['name']
|
||||
if name in name_to_voice:
|
||||
voice = name_to_voice[name]
|
||||
else:
|
||||
if segment['gender'].lower() == 'male':
|
||||
voice = random.choice(MALE_NEURAL_VOICES)['Id']
|
||||
else:
|
||||
voice = random.choice(FEMALE_NEURAL_VOICES)['Id']
|
||||
name_to_voice[name] = voice
|
||||
segment['voice'] = voice
|
||||
return response, processed
|
||||
|
||||
def generate_listening_4_monologue(topic: str):
|
||||
gen_listening_4_monologue_academic = "Generate a comprehensive monologue an academic subject of: '" + topic + "'"
|
||||
token_count = count_tokens(gen_listening_4_monologue_academic)["n_tokens"]
|
||||
response = make_openai_instruct_call(
|
||||
GPT_3_5_TURBO_INSTRUCT,
|
||||
gen_listening_4_monologue_academic,
|
||||
token_count,
|
||||
None,
|
||||
GEN_QUESTION_TEMPERATURE
|
||||
)
|
||||
return response
|
||||
|
||||
def generate_reading_exercises(passage: str, req_exercises: list, number_of_exercises_q, start_id):
|
||||
exercises = []
|
||||
for req_exercise in req_exercises:
|
||||
number_of_exercises = number_of_exercises_q.get()
|
||||
|
||||
if req_exercise == "multipleChoice":
|
||||
question = gen_multiple_choice_exercise(passage, number_of_exercises, start_id)
|
||||
exercises.append(question)
|
||||
print("Added multiple choice: " + str(question))
|
||||
elif req_exercise == "fillBlanks":
|
||||
question = gen_summary_fill_blanks_exercise(passage, number_of_exercises, start_id)
|
||||
exercises.append(question)
|
||||
print("Added fill blanks: " + str(question))
|
||||
elif req_exercise == "trueFalse":
|
||||
question = gen_true_false_not_given_exercise(passage, number_of_exercises, start_id)
|
||||
exercises.append(question)
|
||||
print("Added trueFalse: " + str(question))
|
||||
elif req_exercise == "writeBlanks":
|
||||
question = gen_write_blanks_exercise(passage, number_of_exercises, start_id)
|
||||
exercises.append(question)
|
||||
print("Added write blanks: " + str(question))
|
||||
|
||||
start_id = start_id + number_of_exercises
|
||||
|
||||
return exercises
|
||||
|
||||
def generate_listening_conversation_exercises(conversation: str, req_exercises: list, number_of_exercises_q, start_id):
|
||||
exercises = []
|
||||
for req_exercise in req_exercises:
|
||||
number_of_exercises = number_of_exercises_q.get()
|
||||
|
||||
if req_exercise == "multipleChoice":
|
||||
question = gen_multiple_choice_exercise_listening_conversation(conversation, number_of_exercises, start_id)
|
||||
exercises.append(question)
|
||||
print("Added multiple choice: " + str(question))
|
||||
elif req_exercise == "writeBlanksQuestions":
|
||||
question = gen_write_blanks_questions_exercise_listening_conversation(conversation, number_of_exercises, start_id)
|
||||
exercises.append(question)
|
||||
print("Added write blanks questions: " + str(question))
|
||||
elif req_exercise == "writeBlanksFill":
|
||||
question = gen_write_blanks_notes_exercise_listening_conversation(conversation, number_of_exercises, start_id)
|
||||
exercises.append(question)
|
||||
print("Added write blanks notes: " + str(question))
|
||||
elif req_exercise == "writeBlanksForm":
|
||||
question = gen_write_blanks_form_exercise_listening_conversation(conversation, number_of_exercises, start_id)
|
||||
exercises.append(question)
|
||||
print("Added write blanks form: " + str(question))
|
||||
|
||||
start_id = start_id + number_of_exercises
|
||||
|
||||
return exercises
|
||||
|
||||
def generate_listening_monologue_exercises(monologue: str, req_exercises: list, number_of_exercises_q, start_id):
|
||||
exercises = []
|
||||
for req_exercise in req_exercises:
|
||||
number_of_exercises = number_of_exercises_q.get()
|
||||
|
||||
if req_exercise == "multipleChoice":
|
||||
question = gen_multiple_choice_exercise_listening_monologue(monologue, number_of_exercises, start_id)
|
||||
exercises.append(question)
|
||||
print("Added multiple choice: " + str(question))
|
||||
elif req_exercise == "writeBlanksQuestions":
|
||||
question = gen_write_blanks_questions_exercise_listening_monologue(monologue, number_of_exercises, start_id)
|
||||
exercises.append(question)
|
||||
print("Added write blanks questions: " + str(question))
|
||||
elif req_exercise == "writeBlanksFill":
|
||||
question = gen_write_blanks_notes_exercise_listening_monologue(monologue, number_of_exercises, start_id)
|
||||
exercises.append(question)
|
||||
print("Added write blanks notes: " + str(question))
|
||||
elif req_exercise == "writeBlanksForm":
|
||||
question = gen_write_blanks_form_exercise_listening_monologue(monologue, number_of_exercises, start_id)
|
||||
exercises.append(question)
|
||||
print("Added write blanks form: " + str(question))
|
||||
|
||||
start_id = start_id + number_of_exercises
|
||||
|
||||
return exercises
|
||||
|
||||
def gen_multiple_choice_exercise(text: str, quantity: int, start_id):
|
||||
gen_multiple_choice_for_text = "Generate " + str(quantity) + " multiple choice questions for this text: " \
|
||||
"'" + text + "'\n" \
|
||||
"Use this format: \"questions\": [{\"id\": \"9\", \"options\": [{\"id\": \"A\", \"text\": " \
|
||||
"\"Economic benefits\"}, {\"id\": \"B\", \"text\": \"Government regulations\"}, {\"id\": \"C\", \"text\": " \
|
||||
"\"Concerns about climate change\"}, {\"id\": \"D\", \"text\": \"Technological advancement\"}], " \
|
||||
"\"prompt\": \"What is the main reason for the shift towards renewable energy sources?\", " \
|
||||
"\"solution\": \"C\", \"variant\": \"text\"}]"
|
||||
token_count = count_tokens(gen_multiple_choice_for_text)["n_tokens"]
|
||||
mc_questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_multiple_choice_for_text, token_count,
|
||||
None,
|
||||
GEN_QUESTION_TEMPERATURE)
|
||||
parse_mc_questions = "Parse this '" + mc_questions + "' into this json format: 'questions': [{'id': '9', 'options': [{'id': 'A', 'text': " \
|
||||
"'Economic benefits'}, {'id': 'B', 'text': 'Government regulations'}, {'id': 'C', 'text': " \
|
||||
"'Concerns about climate change'}, {'id': 'D', 'text': 'Technological advancement'}], " \
|
||||
"'prompt': 'What is the main reason for the shift towards renewable energy sources?', " \
|
||||
"'solution': 'C', 'variant': 'text'}]"
|
||||
parse_mc_questions = "Parse the questions into this json format: {\"questions\": [{\"id\": \"9\", \"options\": [{\"id\": \"A\", \"text\": " \
|
||||
"\"Economic benefits\"}, {\"id\": \"B\", \"text\": \"Government regulations\"}, {\"id\": \"C\", \"text\": " \
|
||||
"\"Concerns about climate change\"}, {\"id\": \"D\", \"text\": \"Technological advancement\"}], " \
|
||||
"\"prompt\": \"What is the main reason for the shift towards renewable energy sources?\", " \
|
||||
"\"solution\": \"C\", \"variant\": \"text\"}]}. \nThe questions: '" + mc_questions + "'"
|
||||
token_count = count_tokens(parse_mc_questions)["n_tokens"]
|
||||
return make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, parse_mc_questions, token_count,
|
||||
["questions"],
|
||||
GEN_QUESTION_TEMPERATURE)
|
||||
question = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, parse_mc_questions, token_count,
|
||||
["questions"],
|
||||
GEN_QUESTION_TEMPERATURE)
|
||||
return fix_exercise_ids(question, start_id)
|
||||
|
||||
def gen_summary_fill_blanks_exercise(text: str, quantity: int, start_id):
|
||||
gen_summary_for_text = "Summarize this text: " + text
|
||||
token_count = count_tokens(gen_summary_for_text)["n_tokens"]
|
||||
text_summary = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_summary_for_text, token_count,
|
||||
None,
|
||||
GEN_QUESTION_TEMPERATURE)
|
||||
|
||||
gen_words_to_replace = "Select " + str(
|
||||
quantity) + " words, it must be words and not expressions, from the summary and respond in this " \
|
||||
"JSON format: { \"words\": [\"word_1\", \"word_2\"] }. The summary is: " + text_summary
|
||||
token_count = count_tokens(gen_words_to_replace)["n_tokens"]
|
||||
words_to_replace = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_words_to_replace, token_count,
|
||||
["words"],
|
||||
GEN_QUESTION_TEMPERATURE)["words"]
|
||||
|
||||
replaced_summary = replace_first_occurrences_with_placeholders(text_summary, words_to_replace, start_id)
|
||||
options_words = add_random_words_and_shuffle(words_to_replace, 5)
|
||||
solutions = fillblanks_build_solutions_array(words_to_replace, start_id)
|
||||
|
||||
return {
|
||||
"allowRepetition": True,
|
||||
"id": str(uuid.uuid4()),
|
||||
"prompt": "Complete the summary below. Click a blank to select the corresponding word(s) for it.\\nThere are "
|
||||
"more words than spaces so you will not use them all. You may use any of the words more than once.",
|
||||
"solutions": solutions,
|
||||
"text": replaced_summary,
|
||||
"type": "fillBlanks",
|
||||
"words": options_words
|
||||
|
||||
}
|
||||
|
||||
def gen_true_false_not_given_exercise(text: str, quantity: int, start_id):
|
||||
gen_true_false_not_given = "Generate " + str(
|
||||
quantity) + " statements in JSON format (True, False, or Not Given) " \
|
||||
"based on the provided text. Ensure that your statements " \
|
||||
"accurately represent information or inferences from the " \
|
||||
"text, and provide a variety of responses, including, at least one of each True, " \
|
||||
"False, and Not Given, as appropriate, in the JSON structure " \
|
||||
"{\"prompts\":[{\"prompt\": \"statement_1\", \"solution\": " \
|
||||
"\"true/false/not_given\"}, {\"prompt\": \"statement_2\", " \
|
||||
"\"solution\": \"true/false/not_given\"}]}. Reference text: " + text
|
||||
|
||||
token_count = count_tokens(gen_true_false_not_given)["n_tokens"]
|
||||
questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_true_false_not_given, token_count,
|
||||
["prompts"],
|
||||
GEN_QUESTION_TEMPERATURE)["prompts"]
|
||||
if len(questions) > quantity:
|
||||
questions = remove_excess_questions(questions, len(questions) - quantity)
|
||||
|
||||
for i, question in enumerate(questions, start=start_id):
|
||||
question["id"] = str(i)
|
||||
|
||||
return {
|
||||
"id": str(uuid.uuid4()),
|
||||
"prompt": "Do the following statements agree with the information given in the Reading Passage?",
|
||||
"questions": questions,
|
||||
"type": "trueFalse"
|
||||
}
|
||||
|
||||
def gen_write_blanks_exercise(text: str, quantity: int, start_id):
|
||||
gen_short_answer_questions = "Generate " + str(quantity) + " short answer questions, and the possible answers " \
|
||||
"(max 3 words per answer), about this text: '" + text + "'. " \
|
||||
"Provide your answer in this JSON format: {\"questions\": [{\"question\": question, " \
|
||||
"\"possible_answers\": [\"answer_1\", \"answer_2\"]}]}"
|
||||
|
||||
token_count = count_tokens(gen_short_answer_questions)["n_tokens"]
|
||||
questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_short_answer_questions, token_count,
|
||||
["questions"],
|
||||
GEN_QUESTION_TEMPERATURE)["questions"][:quantity]
|
||||
|
||||
return {
|
||||
"id": str(uuid.uuid4()),
|
||||
"maxWords": 3,
|
||||
"prompt": "Choose no more than three words and/or a number from the passage for each answer.",
|
||||
"solutions": build_write_blanks_solutions(questions, start_id),
|
||||
"text": build_write_blanks_text(questions, start_id),
|
||||
"type": "writeBlanks"
|
||||
}
|
||||
|
||||
def gen_multiple_choice_exercise_listening_conversation(text: str, quantity: int, start_id):
|
||||
gen_multiple_choice_for_text = "Generate " + str(quantity) + " multiple choice questions of 4 options for this conversation: " \
|
||||
"'" + text + "'"
|
||||
token_count = count_tokens(gen_multiple_choice_for_text)["n_tokens"]
|
||||
mc_questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_multiple_choice_for_text, token_count,
|
||||
None,
|
||||
GEN_QUESTION_TEMPERATURE)
|
||||
parse_mc_questions = "Parse the questions into this json format: {\"questions\": [{\"id\": \"9\", \"options\": [{\"id\": \"A\", \"text\": " \
|
||||
"\"Economic benefits\"}, {\"id\": \"B\", \"text\": \"Government regulations\"}, {\"id\": \"C\", \"text\": " \
|
||||
"\"Concerns about climate change\"}, {\"id\": \"D\", \"text\": \"Technological advancement\"}], " \
|
||||
"\"prompt\": \"What is the main reason for the shift towards renewable energy sources?\", " \
|
||||
"\"solution\": \"C\", \"variant\": \"text\"}]}. \nThe questions: '" + mc_questions + "'"
|
||||
token_count = count_tokens(parse_mc_questions)["n_tokens"]
|
||||
question = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, parse_mc_questions, token_count,
|
||||
["questions"],
|
||||
GEN_QUESTION_TEMPERATURE)
|
||||
return fix_exercise_ids(question, start_id)
|
||||
|
||||
def gen_multiple_choice_exercise_listening_monologue(text: str, quantity: int, start_id):
|
||||
gen_multiple_choice_for_text = "Generate " + str(quantity) + " multiple choice questions for this monologue: " \
|
||||
"'" + text + "'"
|
||||
token_count = count_tokens(gen_multiple_choice_for_text)["n_tokens"]
|
||||
mc_questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_multiple_choice_for_text, token_count,
|
||||
None,
|
||||
GEN_QUESTION_TEMPERATURE)
|
||||
parse_mc_questions = "Parse the questions into this json format: {\"questions\": [{\"id\": \"9\", \"options\": [{\"id\": \"A\", \"text\": " \
|
||||
"\"Economic benefits\"}, {\"id\": \"B\", \"text\": \"Government regulations\"}, {\"id\": \"C\", \"text\": " \
|
||||
"\"Concerns about climate change\"}, {\"id\": \"D\", \"text\": \"Technological advancement\"}], " \
|
||||
"\"prompt\": \"What is the main reason for the shift towards renewable energy sources?\", " \
|
||||
"\"solution\": \"C\", \"variant\": \"text\"}]}. \nThe questions: '" + mc_questions + "'"
|
||||
token_count = count_tokens(parse_mc_questions)["n_tokens"]
|
||||
question = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, parse_mc_questions, token_count,
|
||||
["questions"],
|
||||
GEN_QUESTION_TEMPERATURE)
|
||||
return fix_exercise_ids(question, start_id)
|
||||
|
||||
def gen_write_blanks_questions_exercise_listening_conversation(text: str, quantity: int, start_id):
|
||||
gen_write_blanks_questions = "Generate " + str(quantity) + " short answer questions, and the possible answers " \
|
||||
"(max 3 words per answer), about a monologue and" \
|
||||
"respond in this JSON format: {\"questions\": [{\"question\": question, " \
|
||||
"\"possible_answers\": [\"answer_1\", \"answer_2\"]}]}." \
|
||||
"The monologue is this: '" + text + "'"
|
||||
|
||||
token_count = count_tokens(gen_write_blanks_questions)["n_tokens"]
|
||||
questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_write_blanks_questions, token_count,
|
||||
["questions"],
|
||||
GEN_QUESTION_TEMPERATURE)["questions"][:quantity]
|
||||
|
||||
return {
|
||||
"id": str(uuid.uuid4()),
|
||||
"maxWords": 3,
|
||||
"prompt": "You will hear a conversation. Answer the questions below using no more than three words or a number accordingly.",
|
||||
"solutions": build_write_blanks_solutions(questions, start_id),
|
||||
"text": build_write_blanks_text(questions, start_id),
|
||||
"type": "writeBlanks"
|
||||
}
|
||||
|
||||
def gen_write_blanks_questions_exercise_listening_monologue(text: str, quantity: int, start_id):
|
||||
gen_write_blanks_questions = "Generate " + str(quantity) + " short answer questions, and the possible answers " \
|
||||
"(max 3 words per answer), about a monologue and" \
|
||||
"respond in this JSON format: {\"questions\": [{\"question\": question, " \
|
||||
"\"possible_answers\": [\"answer_1\", \"answer_2\"]}]}." \
|
||||
"The monologue is this: '" + text + "'"
|
||||
|
||||
token_count = count_tokens(gen_write_blanks_questions)["n_tokens"]
|
||||
questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_write_blanks_questions, token_count,
|
||||
["questions"],
|
||||
GEN_QUESTION_TEMPERATURE)["questions"][:quantity]
|
||||
|
||||
return {
|
||||
"id": str(uuid.uuid4()),
|
||||
"maxWords": 3,
|
||||
"prompt": "You will hear a monologue. Answer the questions below using no more than three words or a number accordingly.",
|
||||
"solutions": build_write_blanks_solutions(questions, start_id),
|
||||
"text": build_write_blanks_text(questions, start_id),
|
||||
"type": "writeBlanks"
|
||||
}
|
||||
|
||||
def gen_write_blanks_notes_exercise_listening_conversation(text: str, quantity: int, start_id):
|
||||
gen_write_blanks_notes = "Generate " + str(quantity) + " notes taken from the conversation and and respond in this " \
|
||||
"JSON format: { \"notes\": [\"note_1\", \"note_2\"] }. The monologue is this: '" + text + "'"
|
||||
|
||||
token_count = count_tokens(gen_write_blanks_notes)["n_tokens"]
|
||||
questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_write_blanks_notes, token_count,
|
||||
["notes"],
|
||||
GEN_QUESTION_TEMPERATURE)["notes"][:quantity]
|
||||
formatted_phrases = "\n".join([f"{i + 1}. {phrase}" for i, phrase in enumerate(questions)])
|
||||
gen_words_to_replace = "Select 1 word from each phrase in the list and respond in this " \
|
||||
"JSON format: { \"words\": [\"word_1\", \"word_2\"] }. The phrases are: " + formatted_phrases
|
||||
words = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_words_to_replace, token_count,
|
||||
["words"],
|
||||
GEN_QUESTION_TEMPERATURE)["words"][:quantity]
|
||||
replaced_notes = replace_first_occurrences_with_placeholders_notes(questions, words, start_id)
|
||||
return {
|
||||
"id": str(uuid.uuid4()),
|
||||
"maxWords": 1,
|
||||
"prompt": "Fill the blank space with the word missing from the audio.",
|
||||
"solutions": build_write_blanks_solutions_listening(words, start_id),
|
||||
"text": "\\n".join(replaced_notes),
|
||||
"type": "writeBlanks"
|
||||
}
|
||||
|
||||
def gen_write_blanks_notes_exercise_listening_monologue(text: str, quantity: int, start_id):
|
||||
gen_write_blanks_notes = "Generate " + str(quantity) + " notes taken from the monologue and and respond in this " \
|
||||
"JSON format: { \"notes\": [\"note_1\", \"note_2\"] }. The monologue is this: '" + text + "'"
|
||||
|
||||
token_count = count_tokens(gen_write_blanks_notes)["n_tokens"]
|
||||
questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_write_blanks_notes, token_count,
|
||||
["notes"],
|
||||
GEN_QUESTION_TEMPERATURE)["notes"][:quantity]
|
||||
formatted_phrases = "\n".join([f"{i + 1}. {phrase}" for i, phrase in enumerate(questions)])
|
||||
gen_words_to_replace = "Select 1 word from each phrase in the list and respond in this " \
|
||||
"JSON format: { \"words\": [\"word_1\", \"word_2\"] }. The phrases are: " + formatted_phrases
|
||||
words = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_words_to_replace, token_count,
|
||||
["words"],
|
||||
GEN_QUESTION_TEMPERATURE)["words"][:quantity]
|
||||
replaced_notes = replace_first_occurrences_with_placeholders_notes(questions, words, start_id)
|
||||
return {
|
||||
"id": str(uuid.uuid4()),
|
||||
"maxWords": 1,
|
||||
"prompt": "Fill the blank space with the word missing from the audio.",
|
||||
"solutions": build_write_blanks_solutions_listening(words, start_id),
|
||||
"text": "\\n".join(replaced_notes),
|
||||
"type": "writeBlanks"
|
||||
}
|
||||
|
||||
def gen_write_blanks_form_exercise_listening_conversation(text: str, quantity: int, start_id):
|
||||
gen_write_blanks_form = "Generate a form with " + str(quantity) + " key-value pairs about the conversation. " \
|
||||
"The conversation is this: '" + text + "'"
|
||||
token_count = count_tokens(gen_write_blanks_form)["n_tokens"]
|
||||
form = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_write_blanks_form, token_count,
|
||||
None,
|
||||
GEN_QUESTION_TEMPERATURE)
|
||||
parse_form = "Parse the form to this JSON format: { \"form\": [\"string\", \"string\"] }. The form is this: '" + form + "'"
|
||||
token_count = count_tokens(parse_form)["n_tokens"]
|
||||
parsed_form = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, parse_form, token_count,
|
||||
["form"],
|
||||
GEN_QUESTION_TEMPERATURE)["form"][:quantity]
|
||||
replaced_form, words = build_write_blanks_text_form(parsed_form, start_id)
|
||||
return {
|
||||
"id": str(uuid.uuid4()),
|
||||
"maxWords": 1,
|
||||
"prompt": "You will hear a conversation. Fill the form with words/numbers missing.",
|
||||
"solutions": build_write_blanks_solutions_listening(words, start_id),
|
||||
"text": replaced_form,
|
||||
"type": "writeBlanks"
|
||||
}
|
||||
|
||||
def gen_write_blanks_form_exercise_listening_monologue(text: str, quantity: int, start_id):
|
||||
gen_write_blanks_form = "Generate a form with " + str(quantity) + " key-value pairs about the monologue. " \
|
||||
"The monologue is this: '" + text + "'"
|
||||
token_count = count_tokens(gen_write_blanks_form)["n_tokens"]
|
||||
form = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_write_blanks_form, token_count,
|
||||
None,
|
||||
GEN_QUESTION_TEMPERATURE)
|
||||
parse_form = "Parse the form to this JSON format: { \"form\": [\"string\", \"string\"] }. The form is this: '" + form + "'"
|
||||
token_count = count_tokens(parse_form)["n_tokens"]
|
||||
parsed_form = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, parse_form, token_count,
|
||||
["form"],
|
||||
GEN_QUESTION_TEMPERATURE)["form"][:quantity]
|
||||
replaced_form, words = build_write_blanks_text_form(parsed_form, start_id)
|
||||
return {
|
||||
"id": str(uuid.uuid4()),
|
||||
"maxWords": 1,
|
||||
"prompt": "You will hear a monologue. Fill the form with words/numbers missing.",
|
||||
"solutions": build_write_blanks_solutions_listening(words, start_id),
|
||||
"text": replaced_form,
|
||||
"type": "writeBlanks"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user