Files
encoach_backend/helper/api_messages.py
2023-09-03 11:38:12 +01:00

381 lines
22 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
from enum import Enum
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"
def get_grading_messages(question_type: QuestionType, question: str, answer: str, context: str = None):
if QuestionType.WRITING_TASK_1 == question_type:
messages = [
{
"role": "user",
"content": "You are a IELTS examiner.",
},
{
"role": "user",
"content": f"The question you have to grade is of type Writing Task 1 and is the following: {question}",
}
]
if not (context is None or context == ""):
messages.append({
"role": "user",
"content": f"To grade the previous question, bear in mind the following context: {context}",
})
messages.extend([
{
"role": "user",
"content": "It is mandatory for you to provide your response with the overall grade and breakdown grades, "
"with just 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}",
},
])
return messages
elif QuestionType.WRITING_TASK_2 == question_type:
return [
{
"role": "user",
"content": "You are a IELTS examiner.",
},
{
"role": "user",
"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, "
"with just 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}",
},
]
elif QuestionType.SPEAKING_1 == question_type:
return [
{
"role": "user",
"content": "You are a IELTS examiner.",
},
{
"role": "user",
"content": f"The question you have to grade is of type Speaking Task Part 1 and is the following: {question}",
},
{
"role": "user",
"content": "It is mandatory for you to provide your response with the overall grade and breakdown grades, "
"with just the following json format: {'comment': 'comment about answer quality', 'overall': 7.0, "
"'task_response': {'Fluency and Coherence': 8.0, 'Lexical Resource': 6.5, "
"'Grammatical Range and Accuracy': 7.5, 'Pronunciation': 6.0}}",
},
{
"role": "user",
"content": "Example output: { 'comment': 'The candidate has provided a clear response to the question and has "
"given examples of how they spend their weekends. However, there are some issues with grammar and "
"pronunciation that affect the overall score. In terms of fluency and coherence, the candidate speaks "
"clearly and smoothly with only minor hesitations. They have also provided a well-organized response "
"that is easy to follow. Regarding lexical resource, the candidate has used a range of vocabulary "
"related to weekend activities but there are some errors in word choice that affect the meaning of "
"their sentences. In terms of grammatical range and accuracy, the candidate has used a mix of simple "
"and complex sentence structures but there are some errors in subject-verb agreement and preposition "
"use. Finally, regarding pronunciation, the candidate's speech is generally clear but there are some "
"issues with stress and intonation that make it difficult to understand at times.', 'overall': 6.5, "
"'task_response': {'Fluency and Coherence': 7.0, 'Lexical Resource': 6.5, 'Grammatical Range and Accuracy': 7.0,"
" 'Pronunciation': 6.0}}",
},
{
"role": "user",
"content": f"Evaluate this answer according to ielts grading system: {answer}",
},
]
elif QuestionType.SPEAKING_2 == question_type:
return [
{
"role": "user",
"content": "You are a IELTS examiner.",
},
{
"role": "user",
"content": f"The question you have to grade is of type Speaking Task Part 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, "
"with just the following json format: {'comment': 'comment about answer quality', 'overall': 7.0, "
"'task_response': {'Fluency and Coherence': 8.0, 'Lexical Resource': 6.5, "
"'Grammatical Range and Accuracy': 7.5, 'Pronunciation': 6.0}}",
},
{
"role": "user",
"content": "Example output: { 'comment': 'The candidate has provided a clear response to the question and has "
"given examples of how they spend their weekends. However, there are some issues with grammar and "
"pronunciation that affect the overall score. In terms of fluency and coherence, the candidate speaks "
"clearly and smoothly with only minor hesitations. They have also provided a well-organized response "
"that is easy to follow. Regarding lexical resource, the candidate has used a range of vocabulary "
"related to weekend activities but there are some errors in word choice that affect the meaning of "
"their sentences. In terms of grammatical range and accuracy, the candidate has used a mix of simple "
"and complex sentence structures but there are some errors in subject-verb agreement and preposition "
"use. Finally, regarding pronunciation, the candidate's speech is generally clear but there are some "
"issues with stress and intonation that make it difficult to understand at times.', 'overall': 6.5, "
"'task_response': {'Fluency and Coherence': 7.0, 'Lexical Resource': 6.5, 'Grammatical Range and Accuracy': 7.0,"
" 'Pronunciation': 6.0}}",
},
{
"role": "user",
"content": f"Evaluate this answer according to ielts grading system: {answer}",
},
]
else:
raise Exception("Question type not implemented: " + question_type.value)
def get_question_gen_messages(question_type: QuestionType):
if QuestionType.LISTENING_SECTION_1 == question_type:
return [
{
"role": "user",
"content": "You are a IELTS program that generates questions for the exams.",
},
{
"role": "user",
"content": "Provide me with a transcript similar to the ones in ielts exam Listening Section 1. "
"Create an engaging transcript simulating a conversation related to a unique type of service "
"that requires getting the customer's details. Make sure to include specific details "
"and descriptions to bring"
"the scenario to life. After the transcript, please "
"generate a 'form like' fill in the blanks exercise with 6 form fields (ex: name, date of birth)"
" to fill related to the customer's details. Finally, "
"provide the answers for the exercise. The response must be a json following this format: "
"{ 'type': '<type of registration (ex: hotel, gym, english course, etc)>', "
"'transcript': '<transcript of just the conversation about a registration of some sort, "
"identify the person talking in each speech line>', "
"'exercise': { 'form field': { '1': '<form field 1>', '2': '<form field 2>', "
"'3': '<form field 3>', '4': '<form field 4>', "
"'5': '<form field 5>', '6': '<form field 5>' }, "
"'answers': {'1': '<answer to fill blank space in form field 1>', '2': '<answer to fill blank "
"space in form field 2>', '3': '<answer to fill blank space in form field 3>', "
"'4': '<answer to fill blank space in form field 4>', '5': '<answer to fill blank space in form field 5>',"
" '6': '<answer to fill blank space in form field 6>'}}}",
}
]
elif QuestionType.LISTENING_SECTION_2 == question_type:
return [
{
"role": "user",
"content": "You are a IELTS program that generates questions for the exams.",
},
{
"role": "user",
"content": "Provide me with a transcript similar to the ones in ielts exam Listening section 2. After the transcript, please "
"generate a fill in the blanks exercise with 6 statements related to the text content. Finally, "
"provide the answers for the exercise. The response must be a json following this format: "
"{ 'transcript': 'transcript about some subject', 'exercise': { 'statements': { '1': 'statement 1 "
"with a blank space to fill', '2': 'statement 2 with a blank space to fill', '3': 'statement 3 with a "
"blank space to fill', '4': 'statement 4 with a blank space to fill', '5': 'statement 5 with a blank "
"space to fill', '6': 'statement 6 with a blank space to fill' }, "
"'answers': {'1': 'answer to fill blank space in statement 1', '2': 'answer to fill blank "
"space in statement 2', '3': 'answer to fill blank space in statement 3', "
"'4': 'answer to fill blank space in statement 4', '5': 'answer to fill blank space in statement 5',"
" '6': 'answer to fill blank space in statement 6'}}}",
}
]
elif QuestionType.LISTENING_SECTION_3 == question_type:
return [
{
"role": "user",
"content": "You are a IELTS program that generates questions for the exams.",
},
{
"role": "user",
"content": "Provide me with a transcript similar to the ones in ielts exam Listening section 3. After the transcript, please "
"generate 4 multiple choice questions related to the text content. Finally, "
"provide the answers for the exercise. The response must be a json following this format: "
"{ 'transcript': 'generated transcript similar to the ones in ielts exam Listening section 3', "
"'exercise': { 'questions': [ { 'question': "
"'question 1', 'options': ['option 1', 'option 2', 'option 3', 'option 4'], 'answer': 1}, "
"{'question': 'question 2', 'options': ['option 1', 'option 2', 'option 3', 'option 4'], "
"'answer': 3}, {'question': 'question 3', 'options': ['option 1', 'option 2', 'option 3', "
"'option 4'], 'answer': 0}, {'question': 'question 4', 'options': ['option 1', 'option 2', "
"'option 3', 'option 4'], 'answer': 2}]}}",
}
]
elif QuestionType.LISTENING_SECTION_4 == question_type:
return [
{
"role": "user",
"content": "You are a IELTS program that generates questions for the exams.",
},
{
"role": "user",
"content": "Provide me with a transcript similar to the ones in ielts exam Listening section 4. After the transcript, please "
"generate 4 completion-type questions related to the text content to complete with 1 word. Finally, "
"provide the answers for the exercise. The response must be a json following this format: "
"{ 'transcript': 'generated transcript similar to the ones in ielts exam Listening section 4', "
"'exercise': [ { 'question': 'question 1', 'answer': 'answer 1'}, "
"{'question': 'question 2', 'answer': 'answer 2'}, {'question': 'question 3', 'answer': 'answer 3'}, "
"{'question': 'question 4', 'answer': 'answer 4'}]}",
}
]
elif QuestionType.WRITING_TASK_2 == question_type:
return [
{
"role": "user",
"content": "You are a IELTS program that generates questions for the exams.",
},
{
"role": "user",
"content": "The question you have to generate is of type Writing Task 2.",
},
{
"role": "user",
"content": "It is mandatory for you to provide your response with the question "
"just with 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.",
},
]
elif QuestionType.SPEAKING_1 == question_type:
return [
{
"role": "user",
"content": "You are a IELTS program that generates questions for the exams.",
},
{
"role": "user",
"content": "The question you have to generate is of type Speaking Task Part 1.",
},
{
"role": "user",
"content": "It is mandatory for you to provide your response with the question "
"just with the following json format: {'question': 'question'}",
},
{
"role": "user",
"content": "Example output: { 'question': 'Lets talk about your home town or village. "
"What kind of place is it? Whats the most interesting part of your town/village? "
"What kind of jobs do the people in your town/village do? "
"Would you say its a good place to live? (Why?)'}",
},
{
"role": "user",
"content": "Generate a question for IELTS exam Speaking Task.",
},
]
elif QuestionType.SPEAKING_2 == question_type:
return [
{
"role": "user",
"content": "You are a IELTS program that generates questions for the exams.",
},
{
"role": "user",
"content": "The question you have to generate is of type Speaking Task Part 2.",
},
{
"role": "user",
"content": "It is mandatory for you to provide your response with the question "
"just with the following json format: {'question': 'question'}",
},
{
"role": "user",
"content": "Example output: { 'question': 'Describe something you own which is very important to you. "
"You should say: where you got it from how long you have had it what you use it for and "
"explain why it is important to you.'}",
},
{
"role": "user",
"content": "Generate a question for IELTS exam Speaking Task.",
},
]
else:
raise Exception("Question type not implemented: " + question_type.value)
def get_question_tips(question: str, answer: str, correct_answer: str, context: str = None):
messages = [
{
"role": "system",
"content": "You are a IELTS exam program that analyzes incorrect answers to questions and gives tips to "
"help students understand why it was a wrong answer and explains how their thought process "
"should have been. The tip should refer to the context and question.",
}
]
if not (context is None or context == ""):
messages.append({
"role": "system",
"content": f"This is the context for the question: {context}",
})
messages.extend([
{
"role": "system",
"content": f"This is the question: {question}",
},
{
"role": "system",
"content": f"This is the answer: {answer}",
},
{
"role": "system",
"content": f"This is the correct answer: {correct_answer}",
}
])
return messages