devops/encoach_backend
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Updated this to the latest version of develop, got rid of most of the duplication, might be missing some packages in toml, needs testing

Browse Source
This commit is contained in:
Carlos Mesquita
2024-08-30 02:35:11 +01:00
parent 3cf9fa5cba
commit f92a803d96
73 changed files with 3642 additions and 2703 deletions
Download Patch File Download Diff File Expand all files Collapse all files

174
app/services/impl/reading.py
View File

@@ -12,42 +12,25 @@ class ReadingService(IReadingService):
def __init__(self, llm: ILLMService):
self._llm = llm
self._passages = {
"passage_1": {
"question_type": QuestionType.READING_PASSAGE_1,
"start_id": 1
},
"passage_2": {
"question_type": QuestionType.READING_PASSAGE_2,
"start_id": 14
},
"passage_3": {
"question_type": QuestionType.READING_PASSAGE_3,
"start_id": 27
}
}
async def gen_reading_passage(
self,
passage_id: int,
part: int,
topic: str,
req_exercises: List[str],
number_of_exercises_q: Queue,
difficulty: str
difficulty: str,
start_id: int
):
_passage = self._passages[f'passage_{str(passage_id)}']
passage = await self.generate_reading_passage(_passage["question_type"], topic)
if passage == "":
return await self.gen_reading_passage(passage_id, topic, req_exercises, number_of_exercises_q, difficulty)
start_id = _passage["start_id"]
passage = await self.generate_reading_passage(part, topic)
exercises = await self._generate_reading_exercises(
passage["text"], req_exercises, number_of_exercises_q, start_id, difficulty
)
if ExercisesHelper.contains_empty_dict(exercises):
return await self.gen_reading_passage(passage_id, topic, req_exercises, number_of_exercises_q, difficulty)
return await self.gen_reading_passage(
part, topic, req_exercises, number_of_exercises_q, difficulty, start_id
)
return {
"exercises": exercises,
@@ -58,7 +41,17 @@ class ReadingService(IReadingService):
"difficulty": difficulty
}
async def generate_reading_passage(self, q_type: QuestionType, topic: str):
async def generate_reading_passage(self, part: int, topic: str, word_count: int = 800):
part_system_message = {
"1": 'The generated text should be fairly easy to understand and have multiple paragraphs.',
"2": 'The generated text should be fairly hard to understand and have multiple paragraphs.',
"3": (
'The generated text should be very hard to understand and include different points, theories, '
'subtle differences of opinions from people, correctly sourced to the person who said it, '
'over the specified topic and have multiple paragraphs.'
)
}
messages = [
{
"role": "system",
@@ -69,17 +62,26 @@ class ReadingService(IReadingService):
{
"role": "user",
"content": (
f'Generate an extensive text for IELTS {q_type.value}, of at least 1500 words, '
f'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. Make sure that the generated text '
'does not contain forbidden subjects in muslim countries.'
f'Generate an extensive text for IELTS Reading Passage {part}, of at least {word_count} words, '
f'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. Make sure that the generated text '
'does not contain forbidden subjects in muslim countries.'
)
},
{
"role": "system",
"content": part_system_message[str(part)]
}
]
if part == 3:
messages.append({
"role": "user",
"content": "Use real text excerpts on you generated passage and cite the sources."
})
return await self._llm.prediction(
GPTModels.GPT_4_O,
messages,
@@ -95,11 +97,15 @@ class ReadingService(IReadingService):
number_of_exercises = number_of_exercises_q.get()
if req_exercise == "fillBlanks":
question = await self._gen_summary_fill_blanks_exercise(passage, number_of_exercises, start_id, difficulty)
question = await self._gen_summary_fill_blanks_exercise(
passage, number_of_exercises, start_id, difficulty
)
exercises.append(question)
print("Added fill blanks: " + str(question))
elif req_exercise == "trueFalse":
question = await self._gen_true_false_not_given_exercise(passage, number_of_exercises, start_id, difficulty)
question = await self._gen_true_false_not_given_exercise(
passage, number_of_exercises, start_id, difficulty
)
exercises.append(question)
print("Added trueFalse: " + str(question))
elif req_exercise == "writeBlanks":
@@ -114,32 +120,28 @@ class ReadingService(IReadingService):
question = await self._gen_paragraph_match_exercise(passage, number_of_exercises, start_id)
exercises.append(question)
print("Added paragraph match: " + str(question))
elif req_exercise == "ideaMatch":
question = await self._gen_idea_match_exercise(passage, number_of_exercises, start_id)
exercises.append(question)
print("Added idea match: " + str(question))
start_id = start_id + number_of_exercises
return exercises
async def _gen_summary_fill_blanks_exercise(self, text: str, quantity: int, start_id, difficulty):
async def _gen_summary_fill_blanks_exercise(
self, text: str, quantity: int, start_id, difficulty, num_random_words: int = 1
):
messages = [
{
"role": "system",
"content": (
'You are a helpful assistant designed to output JSON on this format: '
'{ "summary": "summary", "words": ["word_1", "word_2"] }')
'You are a helpful assistant designed to output JSON on this format: { "summary": "summary" }'
)
},
{
"role": "user",
"content": (
f'Summarize this text: "{text}"'
)
},
{
"role": "user",
"content": (
f'Select {str(quantity)} {difficulty} difficulty words, it must be words and not '
'expressions, from the summary.'
)
"content": f'Summarize this text: "{text}"'
}
]
@@ -148,22 +150,45 @@ class ReadingService(IReadingService):
GPTModels.GPT_4_O, messages, ["summary"], TemperatureSettings.GEN_QUESTION_TEMPERATURE
)
replaced_summary = ExercisesHelper.replace_first_occurrences_with_placeholders(response["summary"], response["words"], start_id)
options_words = ExercisesHelper.add_random_words_and_shuffle(response["words"], 5)
messages = [
{
"role": "system",
"content": (
'You are a helpful assistant designed to output JSON on this format: '
'{"words": ["word_1", "word_2"] }'
)
},
{
"role": "user",
"content": (
f'Select {quantity} {difficulty} difficulty words, it must be words and not expressions, '
f'from this:\n{response["summary"]}'
)
}
]
words_response = await self._llm.prediction(
GPTModels.GPT_4_O, messages, ["words"], TemperatureSettings.GEN_QUESTION_TEMPERATURE
)
response["words"] = words_response["words"]
replaced_summary = ExercisesHelper.replace_first_occurrences_with_placeholders(
response["summary"], response["words"], start_id
)
options_words = ExercisesHelper.add_random_words_and_shuffle(response["words"], num_random_words)
solutions = ExercisesHelper.fillblanks_build_solutions_array(response["words"], 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 "
"Complete the summary below. Write the letter of 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
}
async def _gen_true_false_not_given_exercise(self, text: str, quantity: int, start_id, difficulty):
@@ -210,7 +235,8 @@ class ReadingService(IReadingService):
"role": "system",
"content": (
'You are a helpful assistant designed to output JSON on this format: '
'{"questions": [{"question": question, "possible_answers": ["answer_1", "answer_2"]}]}')
'{"questions": [{"question": question, "possible_answers": ["answer_1", "answer_2"]}]}'
)
},
{
"role": "user",
@@ -243,7 +269,8 @@ class ReadingService(IReadingService):
"role": "system",
"content": (
'You are a helpful assistant designed to output JSON on this format: '
'{"headings": [ {"heading": "first paragraph heading"}, {"heading": "second paragraph heading"}]}')
'{"headings": [ {"heading": "first paragraph heading"}, {"heading": "second paragraph heading"}]}'
)
},
{
"role": "user",
@@ -262,7 +289,7 @@ class ReadingService(IReadingService):
options = []
for i, paragraph in enumerate(paragraphs, start=0):
paragraph["heading"] = headings[i]
paragraph["heading"] = headings[i]["heading"]
options.append({
"id": paragraph["letter"],
"sentence": paragraph["paragraph"]
@@ -285,3 +312,38 @@ class ReadingService(IReadingService):
"sentences": sentences[:quantity],
"type": "matchSentences"
}
async def _gen_idea_match_exercise(self, text: str, quantity: int, start_id):
messages = [
{
"role": "system",
"content": (
'You are a helpful assistant designed to output JSON on this format: '
'{"ideas": [ '
'{"idea": "some idea or opinion", "from": "person, institution whose idea or opinion this is"}, '
'{"idea": "some other idea or opinion", "from": "person, institution whose idea or opinion this is"}'
']}'
)
},
{
"role": "user",
"content": (
f'From the text extract {quantity} ideas, theories, opinions and who they are from. '
f'The text: {text}'
)
}
]
response = await self._llm.prediction(
GPTModels.GPT_4_O, messages, ["ideas"], TemperatureSettings.GEN_QUESTION_TEMPERATURE
)
ideas = response["ideas"]
return {
"id": str(uuid.uuid4()),
"allowRepetition": False,
"options": ExercisesHelper.build_options(ideas),
"prompt": "Choose the correct author for the ideas/opinions from the list of authors below.",
"sentences": ExercisesHelper.build_sentences(ideas, start_id),
"type": "matchSentences"
}