engineering/opencompletion.com
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

make math progressively more difficult.

Browse source 
modified:   ../app.py
	modified:   activity23-math.yaml
This commit is contained in:
Russell Ballestrini 2024-08-11 11:27:32 -04:00
parent 7ac9c4583c
commit f09d24aefc
2 changed files with 241 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

4
app.py
View file

@ -2642,7 +2642,9 @@ def provide_feedback(
def translate_text(text, target_language):
# Guard clause for default language
if " english" in target_language.lower():
target_language = target_language.lower().split()
if "english" in target_language:
return text
openai_client, model_name = get_openai_client_and_model()

251
research/activity23-math.yaml
View file

@ -1,10 +1,10 @@
default_max_attempts_per_step: 3
sections:
- section_id: "section_1"
title: "Math Quiz"
title: "Math Quiz: From Basics to Algebra"
steps:
- step_id: "step_1"
title: "Addition Problem"
title: "Basic Addition"
content_blocks:
- "Solve the following problem: 5 + 3"
- "You can show your work and provide the final answer."
@ -15,7 +15,7 @@ sections:
If the answer is incorrect, categorize as 'incorrect'.
If the user wants to change the language, categorize as 'set_language'.
feedback_tokens_for_ai: |
Unless the user is correct, don't give them the answer when explaining the problem. Instead use a different contrived problem.
DO NOT answer or solve the question problem when explaining the problem. Instead use a different contrived problem.
buckets:
- correct
- incorrect
@ -24,7 +24,7 @@ sections:
transitions:
correct:
ai_feedback:
tokens_for_ai: "Great job! You got the correct answer."
tokens_for_ai: "Great job! You got the correct answer. if 'correct' give the answer and solve the question problem showing all work and explain the problem."
metadata_add:
score: "n+1"
next_section_and_step: "section_1:step_2"
@ -36,7 +36,7 @@ sections:
next_section_and_step: "section_1:step_1"
show_work:
ai_feedback:
tokens_for_ai: "Thanks for showing your work. Now, provide the final answer."
tokens_for_ai: "Thanks the user for showing work. Catch mistakes and suggest next steps. Remember give a separate example to show how to solve the answer, never reveal it."
metadata_add:
user_work: "the-users-response"
next_section_and_step: "section_1:step_1"
@ -49,7 +49,7 @@ sections:
next_section_and_step: "section_1:step_1"
- step_id: "step_2"
title: "Subtraction Problem"
title: "Basic Subtraction"
content_blocks:
- "Solve the following problem: 10 - 4"
- "You can show your work and provide the final answer."
@ -60,7 +60,7 @@ sections:
If the answer is incorrect, categorize as 'incorrect'.
If the user wants to change the language, categorize as 'set_language'.
feedback_tokens_for_ai: |
Unless the user is correct, don't give them the answer when explaining the problem. Instead use a different contrived problem.
DO NOT answer or solve the question problem when explaining the problem. Instead use a different contrived problem.
buckets:
- correct
- incorrect
@ -69,7 +69,7 @@ sections:
transitions:
correct:
ai_feedback:
tokens_for_ai: "Well done! You got the correct answer."
tokens_for_ai: "Great job! You got the correct answer. if 'correct' give the answer and solve the question problem showing all work and explain the problem."
metadata_add:
score: "n+1"
next_section_and_step: "section_1:step_3"
@ -81,7 +81,7 @@ sections:
next_section_and_step: "section_1:step_2"
show_work:
ai_feedback:
tokens_for_ai: "Thanks for showing your work. Now, provide the final answer."
tokens_for_ai: "Thanks the user for showing work. Catch mistakes and suggest next steps. Remember give a separate example to show how to solve the answer, never reveal it."
metadata_add:
user_work: "the-users-response"
next_section_and_step: "section_1:step_2"
@ -94,7 +94,7 @@ sections:
next_section_and_step: "section_1:step_2"
- step_id: "step_3"
title: "Multiplication Problem"
title: "Basic Multiplication"
content_blocks:
- "Solve the following problem: 4 * 2"
- "You can show your work and provide the final answer."
@ -114,10 +114,10 @@ sections:
transitions:
correct:
ai_feedback:
tokens_for_ai: "Excellent! You got the correct answer."
tokens_for_ai: "Great job! You got the correct answer. if 'correct' give the answer and solve the question problem showing all work and explain the problem."
metadata_add:
score: "n+1"
next_section_and_step: "section_2:step_1"
next_section_and_step: "section_1:step_4"
incorrect:
ai_feedback:
tokens_for_ai: "That's not quite right. Try again."
@ -126,7 +126,7 @@ sections:
next_section_and_step: "section_1:step_3"
show_work:
ai_feedback:
tokens_for_ai: "Thanks for showing your work. Now, provide the final answer."
tokens_for_ai: "Thanks the user for showing work. Catch mistakes and suggest next steps. Remember give a separate example to show how to solve the answer, never reveal it."
metadata_add:
user_work: "the-users-response"
next_section_and_step: "section_1:step_3"
@ -138,6 +138,231 @@ sections:
counts_as_attempt: false
next_section_and_step: "section_1:step_3"
- step_id: "step_4"
title: "Basic Division"
content_blocks:
- "Solve the following problem: 16 / 4"
- "You can show your work and provide the final answer."
question: "What is 16 / 4? Show your work and provide the answer."
tokens_for_ai: |
Determine if the user's response is correct by checking if the final answer is 4.
If the user shows their work but doesn't provide a final answer, categorize as 'show_work'.
If the answer is incorrect, categorize as 'incorrect'.
If the user wants to change the language, categorize as 'set_language'.
feedback_tokens_for_ai: |
DO NOT answer or solve the question problem when explaining the problem. Instead use a different contrived problem.
buckets:
- correct
- incorrect
- show_work
- set_language
transitions:
correct:
ai_feedback:
tokens_for_ai: "Great job! You got the correct answer. if 'correct' give the answer and solve the question problem showing all work and explain the problem."
metadata_add:
score: "n+1"
next_section_and_step: "section_1:step_5"
incorrect:
ai_feedback:
tokens_for_ai: "That's not quite right. Try again."
metadata_add:
attempts: "n+1"
next_section_and_step: "section_1:step_4"
show_work:
ai_feedback:
tokens_for_ai: "Thanks the user for showing work. Catch mistakes and suggest next steps. Remember give a separate example to show how to solve the answer, never reveal it."
metadata_add:
user_work: "the-users-response"
next_section_and_step: "section_1:step_4"
set_language:
ai_feedback:
tokens_for_ai: "Language preference updated. Please continue in your preferred language."
metadata_add:
language: "the-users-response"
counts_as_attempt: false
next_section_and_step: "section_1:step_4"
- step_id: "step_5"
title: "Introduction to Variables"
content_blocks:
- "Solve for x: x + 5 = 10"
- "You can show your work and provide the final answer."
question: "What is the value of x in the equation x + 5 = 10? Show your work and provide the answer."
tokens_for_ai: |
Determine if the user's response is correct by checking if the final answer is x = 5.
If the user shows their work but doesn't provide a final answer, categorize as 'show_work'.
If the answer is incorrect, categorize as 'incorrect'.
If the user wants to change the language, categorize as 'set_language'.
feedback_tokens_for_ai: |
DO NOT answer or solve the question problem when explaining the problem. Instead use a different contrived problem.
buckets:
- correct
- incorrect
- show_work
- set_language
transitions:
correct:
ai_feedback:
tokens_for_ai: "Great job! You got the correct answer for x. if 'correct' give the answer and solve the question problem showing all work and explain the problem."
metadata_add:
score: "n+1"
next_section_and_step: "section_1:step_6"
incorrect:
ai_feedback:
tokens_for_ai: "That's not quite right. Try again."
metadata_add:
attempts: "n+1"
next_section_and_step: "section_1:step_5"
show_work:
ai_feedback:
tokens_for_ai: "Thanks the user for showing work. Catch mistakes and suggest next steps. Remember give a separate example to show how to solve the answer, never reveal it."
metadata_add:
user_work: "the-users-response"
next_section_and_step: "section_1:step_5"
set_language:
ai_feedback:
tokens_for_ai: "Language preference updated. Please continue in your preferred language."
metadata_add:
language: "the-users-response"
counts_as_attempt: false
next_section_and_step: "section_1:step_5"
- step_id: "step_6"
title: "Solving Linear Equations"
content_blocks:
- "Solve for x: 2x + 3 = 11"
- "You can show your work and provide the final answer."
question: "What is the value of x in the equation 2x + 3 = 11? Show your work and provide the answer."
tokens_for_ai: |
Determine if the user's response is correct by checking if the final answer is x = 4.
If the user shows their work but doesn't provide a final answer, categorize as 'show_work'.
If the answer is incorrect, categorize as 'incorrect'.
If the user wants to change the language, categorize as 'set_language'.
feedback_tokens_for_ai: |
DO NOT answer or solve the question problem when explaining the problem. Instead use a different contrived problem.
buckets:
- correct
- incorrect
- show_work
- set_language
transitions:
correct:
ai_feedback:
tokens_for_ai: "Great job! You got the correct answer for x. if 'correct' give the answer and solve the question problem showing all work and explain the problem."
metadata_add:
score: "n+1"
next_section_and_step: "section_1:step_7"
incorrect:
ai_feedback:
tokens_for_ai: "That's not quite right. Try again."
metadata_add:
attempts: "n+1"
next_section_and_step: "section_1:step_6"
show_work:
ai_feedback:
tokens_for_ai: "Thanks the user for showing work. Catch mistakes and suggest next steps. Remember give a separate example to show how to solve the answer, never reveal it."
metadata_add:
user_work: "the-users-response"
next_section_and_step: "section_1:step_6"
set_language:
ai_feedback:
tokens_for_ai: "Language preference updated. Please continue in your preferred language."
metadata_add:
language: "the-users-response"
counts_as_attempt: false
next_section_and_step: "section_1:step_6"
- step_id: "step_7"
title: "Quadratic Equations"
content_blocks:
- "Solve the quadratic equation: x^2 - 5x + 6 = 0"
- "You can show your work and provide the final answer."
question: "What are the values of x in the equation x^2 - 5x + 6 = 0? Show your work and provide the answers."
tokens_for_ai: |
Determine if the user's response is correct by checking if the final answers are x = 2 and x = 3.
If the user shows their work but doesn't provide final answers, categorize as 'show_work'.
If the answers are incorrect, categorize as 'incorrect'.
If the user wants to change the language, categorize as 'set_language'.
feedback_tokens_for_ai: |
DO NOT answer or solve the question problem when explaining the problem. Instead use a different contrived problem.
buckets:
- correct
- incorrect
- show_work
- set_language
transitions:
correct:
ai_feedback:
tokens_for_ai: "Well done! You found the correct roots of the equation. if 'correct' give the answer and solve the question problem showing all work and explain the problem."
metadata_add:
score: "n+1"
next_section_and_step: "section_1:step_8"
incorrect:
ai_feedback:
tokens_for_ai: "That's not quite right. Try again."
metadata_add:
attempts: "n+1"
next_section_and_step: "section_1:step_7"
show_work:
ai_feedback:
tokens_for_ai: "Thanks the user for showing work. Catch mistakes and suggest next steps. Remember give a separate example to show how to solve the answer, never reveal it."
metadata_add:
user_work: "the-users-response"
next_section_and_step: "section_1:step_7"
set_language:
ai_feedback:
tokens_for_ai: "Language preference updated. Please continue in your preferred language."
metadata_add:
language: "the-users-response"
counts_as_attempt: false
next_section_and_step: "section_1:step_7"
- step_id: "step_8"
title: "Simplifying Expressions"
content_blocks:
- "Simplify the expression: 3(x + 2) - 4x"
- "You can show your work and provide the final answer."
question: "What is the simplified form of the expression 3(x + 2) - 4x? Show your work and provide the answer."
tokens_for_ai: |
Determine if the user's response is correct by checking if the final answer is 2 - x.
If the user shows their work but doesn't provide a final answer, categorize as 'show_work'.
If the answer is incorrect, categorize as 'incorrect'.
If the user wants to change the language, categorize as 'set_language'.
feedback_tokens_for_ai: |
DO NOT answer or solve the question problem when explaining the problem. Instead use a different contrived problem.
buckets:
- correct
- incorrect
- show_work
- set_language
transitions:
correct:
ai_feedback:
tokens_for_ai: "Excellent! You simplified the expression correctly. if 'correct' give the answer and solve the question problem showing all work and explain the problem."
metadata_add:
score: "n+1"
next_section_and_step: "section_2:step_1"
incorrect:
ai_feedback:
tokens_for_ai: "That's not quite right. Try again."
metadata_add:
attempts: "n+1"
next_section_and_step: "section_1:step_8"
show_work:
ai_feedback:
tokens_for_ai: "Thanks the user for showing work. Catch mistakes and suggest next steps. Remember give a separate example to show how to solve the answer, never reveal it."
metadata_add:
user_work: "the-users-response"
next_section_and_step: "section_1:step_8"
set_language:
ai_feedback:
tokens_for_ai: "Language preference updated. Please continue in your preferred language."
metadata_add:
language: "the-users-response"
counts_as_attempt: false
next_section_and_step: "section_1:step_8"
- section_id: "section_2"
title: "Quiz Complete"
steps: