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

ENCOA-255 gpt was grouping parts by sections and the reading passages were not updated with text.content instead of the old context field

Browse Source
This commit is contained in:
Carlos-Mesquita
2024-12-03 11:57:42 +00:00
parent 1603fa4ee6
commit 4e05c4d913
4 changed files with 37 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
app/api/level.py
View File

@@ -54,7 +54,6 @@ async def import_level(
):
return await level_controller.upload_level(exercises, solutions)
@level_router.post(
'/custom/',
dependencies=[Depends(Authorized([IsAuthenticatedViaBearerToken]))]

5
app/dtos/exams/level.py
View File

@@ -47,10 +47,13 @@ class FillBlanksExercise(BaseModel):
Exercise = Union[MultipleChoiceExercise, FillBlanksExercise]
class Text(BaseModel):
content: str
title: str
class Part(BaseModel):
exercises: List[Exercise]
context: Optional[str] = Field(default=None)
text: Optional[Text] = Field(default=None)
class Exam(BaseModel):

13
app/mappers/level.py
View File

@@ -5,7 +5,7 @@ from pydantic import ValidationError
from app.dtos.exams.level import (
MultipleChoiceExercise,
FillBlanksExercise,
Part, Exam
Part, Exam, Text
)
from app.dtos.sheet import Sheet, Option, MultipleChoiceQuestion, FillBlanksWord
@@ -17,7 +17,7 @@ class LevelMapper:
parts = []
for part in response['parts']:
part_exercises = part['exercises']
context = part.get('context', None)
text = part.get('text', None)
exercises = []
for exercise in part_exercises:
@@ -32,8 +32,13 @@ class LevelMapper:
exercises.append(exercise_model)
part_kwargs = {"exercises": exercises}
if context is not None:
part_kwargs["context"] = context
if text is not None and text.get('content', None):
title = text.get('title', 'Untitled')
if title == '':
title = 'Untitled'
part_kwargs["text"] = Text(title=title, content=text['content'])
else:
part_kwargs["text"] = None
part_model = Part(**part_kwargs)
parts.append(part_model)

55
app/services/impl/exam/level/upload.py
View File

@@ -57,7 +57,10 @@ class UploadLevelModule:
return {
"parts": [
{
"context": "<this attribute is optional you may exclude it if not required>",
"text": {
"content": "<this attribute is mandatory if there is a text passage else this 'text' field is omitted>",
"title": "<this attribute is optional you may exclude it if not required>",
},
"exercises": [
self._multiple_choice_html(),
self._passage_blank_space_html()
@@ -86,7 +89,7 @@ class UploadLevelModule:
"role": "system",
"content": (
'You are GPT Scraper and your job is to clean dirty html into clean usable JSON formatted data.'
'Your current task is to scrape html english questions sheets.\n\n'
'Your current task is to scrape html english questions sheets and structure them into parts NOT sections.\n\n'
'In the question sheet you will only see 4 types of question:\n'
'- blank space multiple choice\n'
@@ -111,23 +114,24 @@ class UploadLevelModule:
'out the best paragraph separation possible.'
'You will place all the information in a single JSON: '
'{"parts": [{"exercises": [{...}], "context": ""}]}\n '
'{"parts": [{"exercises": [{...}], "text": {"title": "", "content": ""} ]}\n '
'Where {...} are the exercises templates for each part of a question sheet and the optional field '
'context.'
'IMPORTANT: The question sheet may be divided by sections but you need to only consider the parts, '
'so that you can group the exercises by the parts that are in the html, this is crucial since only '
'reading passage multiple choice require context and if the context is included in parts where it '
'is not required the UI will be messed up. Some make sure to correctly group the exercises by parts.\n'
'text, which contains the reading passages that are required in order to solve the part questions, '
'(if there are passages) place them in text.content and if there is a title place it in text.title '
'else omit the title field.\n'
'IMPORTANT: As stated earlier your job is to structure the questions into PARTS not SECTION, this means '
'that if there is for example: Section 1, Part 1 and Part 2, Section 2, Part 1 and Part 2, you MUST '
'place in the parts array 4 parts NOT 2 parts with the exercises of both parts! You must strictly '
'adhere to this instruction, do not mistake sections for parts!\n'
'The templates for the exercises are the following:\n'
'- blank space multiple choice, underline multiple choice and reading passage multiple choice: '
f'{self._multiple_choice_html()}\n'
f'- reading passage blank space multiple choice: {self._passage_blank_space_html()}\n'
'IMPORTANT: For the reading passage multiple choice the context field must be set with the reading '
'passages without paragraphs or line numbers, with 2 newlines between paragraphs, for the other '
'exercises exclude the context field.'
'IMPORTANT: The text.content field must be set with the reading passages of a part (if there is one)'
'without paragraphs or line numbers, with 2 newlines between paragraphs.'
)
}
@@ -135,30 +139,19 @@ class UploadLevelModule:
def _multiple_choice_html():
return {
"type": "multipleChoice",
"prompt": "Select the appropriate option.",
"prompt": "<general instructions for this section>",
"questions": [
{
"id": "<the question id>",
"prompt": "<the question>",
"solution": "<the option id solution>",
"id": "<question number as string>",
"prompt": "<question text>",
"options": [
{
"id": "A",
"text": "<the a option>"
},
{
"id": "B",
"text": "<the b option>"
},
{
"id": "C",
"text": "<the c option>"
},
{
"id": "D",
"text": "<the d option>"
"id": "<A/B/C/D>",
"text": "<option text>"
}
]
],
"solution": "<correct option letter>",
"variant": "text"
}
]
}