prompt engineering activity 15
modified: app.py modified: research/activity15-choose-adventure.yaml
This commit is contained in:
parent
65404a4ecd
commit
8cca256c89
2 changed files with 11 additions and 12 deletions
1
app.py
1
app.py
|
|
@ -2318,7 +2318,6 @@ def categorize_response(question, response, buckets, tokens_for_ai):
|
|||
.message.content.strip()
|
||||
.lower()
|
||||
.replace(" ", "_")
|
||||
.strip("_")
|
||||
)
|
||||
return category
|
||||
except Exception as e:
|
||||
|
|
|
|||
|
|
@ -19,15 +19,15 @@ sections:
|
|||
- "You see a rug on the floor, a bookshelf with a book, and a safe on the wall."
|
||||
- "There is also an exit door, but it seems to be blocked by something."
|
||||
- "What do you do first? Look under the rug, examine the book, try to open the safe, or try to leave the room?"
|
||||
tokens_for_ai: "Guide the user to make a choice between looking under the rug, examining the book, trying to open the safe, or trying to leave the room. Provide feedback based on their choice. Be flexible to classify actions that lead to finding hidden items."
|
||||
tokens_for_ai: "Guide the user to make a choice between looking under the rug, examining the book, trying to open the safe, or trying to leave the room. Provide feedback based on their choice. Use off_topic sparringly if the response choice doesn't fit any other topic. Be flexible to classify actions that lead to finding hidden items."
|
||||
question: "What do you choose? Look under the rug, Examine the book, Try to open the safe, or Try to leave the room? 🤔"
|
||||
buckets:
|
||||
- look_under_rug
|
||||
- examine_book
|
||||
- try_open_safe
|
||||
- try_leave_room
|
||||
- off_topic
|
||||
- asking_clarifying_questions
|
||||
- off_topic
|
||||
transitions:
|
||||
look_under_rug:
|
||||
content_blocks:
|
||||
|
|
@ -55,7 +55,7 @@ sections:
|
|||
- "Congratulations! You have found the way out and successfully completed the escape room. 🎉"
|
||||
next_section_and_step: "section_6:step_1"
|
||||
ai_feedback:
|
||||
tokens_for_ai: "Provide positive reinforcement and guide the user to the final encounter. Be flexible to classify actions that lead to finding hidden items. Use emojis like 👍 and 🌟."
|
||||
tokens_for_ai: "The user has exited with the exit_key! The game is over, Use emojis like 👍 and 🌟."
|
||||
off_topic:
|
||||
content_blocks:
|
||||
- "It seems like your response is off-topic. Let's try to stay focused on the story. 🔄"
|
||||
|
|
@ -76,15 +76,15 @@ sections:
|
|||
- "You chose to look under the rug. 🧺"
|
||||
- "You find a key hidden under the rug."
|
||||
- "Do you take the key or continue exploring the room?"
|
||||
tokens_for_ai: "Guide the user to make a choice between taking the key or continuing to explore the room. Be flexible to classify actions that lead to finding hidden items. Provide feedback based on their choice."
|
||||
tokens_for_ai: "Guide the user to make a choice between taking the key or continuing to explore the room. Be flexible to classify actions that lead to finding hidden items. Use off_topic sparringly if the response choice doesn't fit any other topic. Provide feedback based on their choice."
|
||||
question: "What do you choose? Take the key or Continue exploring? 🤔"
|
||||
buckets:
|
||||
- take_key
|
||||
- continue_exploring
|
||||
- find_coin
|
||||
- go_back
|
||||
- off_topic
|
||||
- asking_clarifying_questions
|
||||
- off_topic
|
||||
transitions:
|
||||
take_key:
|
||||
content_blocks:
|
||||
|
|
@ -129,15 +129,15 @@ sections:
|
|||
- "You chose to examine the book. 📖"
|
||||
- "The book contains a note with a password: 'ESCAPE123'."
|
||||
- "Do you take note of the password or continue exploring the room?"
|
||||
tokens_for_ai: "Guide the user to make a choice between taking note of the password or continuing to explore the room. Be flexible to classify actions that lead to finding hidden items. Provide feedback based on their choice."
|
||||
tokens_for_ai: "Guide the user to make a choice between taking note of the password or continuing to explore the room. Be flexible to classify actions that lead to finding hidden items. Use off_topic sparringly if the response choice doesn't fit any other topic. Provide feedback based on their choice."
|
||||
question: "What do you choose? Take note of the password or Continue exploring? 🤔"
|
||||
buckets:
|
||||
- take_password
|
||||
- continue_exploring
|
||||
- find_paper
|
||||
- go_back
|
||||
- off_topic
|
||||
- asking_clarifying_questions
|
||||
- off_topic
|
||||
transitions:
|
||||
take_password:
|
||||
content_blocks:
|
||||
|
|
@ -182,15 +182,15 @@ sections:
|
|||
- "You chose to try to open the safe. 🔒"
|
||||
- "The safe is locked and requires both a key and a password to open."
|
||||
- "Do you use the key and enter the password to open the safe or continue exploring the room?"
|
||||
tokens_for_ai: "Guide the user to make a choice between using the key and entering the password to open the safe or continuing to explore the room. Be flexible to classify actions that lead to finding hidden items. Provide feedback based on their choice."
|
||||
tokens_for_ai: "Guide the user to make a choice between using the key and entering the password to open the safe or continuing to explore the room. Be flexible to classify actions that lead to finding hidden items. Use off_topic sparringly if the response choice doesn't fit any other topic. Provide feedback based on their choice."
|
||||
question: "What do you choose? Use the key and enter the password or Continue exploring? 🤔"
|
||||
buckets:
|
||||
- use_key_and_password
|
||||
- continue_exploring
|
||||
- go_back
|
||||
- off_topic
|
||||
- asking_clarifying_questions
|
||||
- use_coin
|
||||
- off_topic
|
||||
transitions:
|
||||
use_key_and_password:
|
||||
metadata_conditions:
|
||||
|
|
@ -240,14 +240,14 @@ sections:
|
|||
- "The compartment opens, revealing a second, smaller safe."
|
||||
- "This safe requires a combination to open."
|
||||
- "Do you try to solve the combination or leave it alone?"
|
||||
tokens_for_ai: "Guide the user to make a choice between solving the combination to open the second safe or leaving it alone. Be flexible to classify actions that lead to finding hidden items. Provide feedback based on their choice."
|
||||
tokens_for_ai: "Guide the user to make a choice between solving the combination to open the second safe or leaving it alone. Be flexible to classify actions that lead to finding hidden items. Use off_topic sparringly if the response choice doesn't fit any other topic. Provide feedback based on their choice."
|
||||
question: "What do you choose? Solve the combination or Leave it alone? 🤔"
|
||||
buckets:
|
||||
- solve_combination
|
||||
- leave_it_alone
|
||||
- go_back
|
||||
- off_topic
|
||||
- asking_clarifying_questions
|
||||
- off_topic
|
||||
transitions:
|
||||
solve_combination:
|
||||
metadata_conditions:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue