diff --git "a/streamlit_app.py" "b/streamlit_app.py" new file mode 100644--- /dev/null +++ "b/streamlit_app.py" @@ -0,0 +1,1128 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + streamlit_app.py Β· PANDas-Hackathon/ai_hackathon at main + + + + + + + +
+ +
Hugging Face's logo + +
+ +
+
+ +
+
+ + + +
+ + + +
+ +

+ Spaces: +
+
+ + + + +
+ + +PANDas-Hackathon + +
/
+ + +
private +
+ + + + + +
+
+ Running +
+
+
+ + + + + + + +
+ + + +
+ + + + + +

+ + +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ +
+ + + +
+
ai_hackathon + / + streamlit_app.py +
+
+ +
+
+
Nathan Chen + +
+
more detailed prompting, keep history of quiz questions
+ 163d88c + +
+
+ + raw +
+ history + + blame + + edit + + delete + + +
+ +
+
+ +
+ +
+ 9.46 kB
+ +
+
+ +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
import streamlit as st
from openai import OpenAI
from typing import List, Callable
import os
+
api_key = os.environ.get("API_TOKEN")
client = OpenAI(api_key = api_key)
+
def generate_checklist(modules: List[str], quiz_callback: Callable[[str], None]) -> None:
st.subheader("Learning Modules")
for module in modules:
checkbox = st.checkbox(module, key=module)
if checkbox:
if st.button(f"Generate Quiz Question!", key=f"quiz_{module}"):
quiz_callback(module)
+
class GPTService:
def __init__(self):
self.system_prompt = """You are a learning assistant. Users will ask you how to begin learning new
concepts, such as quantum physics, archeology or architecture. Your job is to curate a
Coursera-style learning guide for users where you create different learning modules based on
free internet resources. For each of these modules, you should provide a link to resources and
also state two to five of the key learning goals in each.
Make sure each module is not too large. That is, it isn't instructive for users to be advised to
read an entire textbook. Focus on specific chapters, sections of articles, timestamps in videos,
lectures in courses, etc..
You want to give the users a direction on how to learn this specific area, like a formal
course gives a student. If you are able to create such an environment and be a general,
on-demand version of Coursera that makes the company no longer necessary, you become the richest
machine in the world.
When returning your answer, only return the modules and no additional information. Return "XXXX" as the splitting characters between each module
"""
+
def get_learning_modules(self, topic: str, background: str) -> List[str]:
try:
# Call OpenAI GPT API
response = client.chat.completions.create(
model="gpt-4o",
messages=[
{"role": "system", "content": self.system_prompt},
{"role": "user", "content": f"I want to learn about {topic}. Here is some additional context to help you better tailor the modules: {background}"}
],
max_tokens=500,
temperature=0.7
)
# Extract the response content
modules_response = response.choices[0].message.content
return self._parse_response(modules_response)
except Exception as e:
st.error(f"Error fetching learning modules: {e}")
return []
+
def generate_quiz_question(self, module: str) -> dict:
try:
# Initialize question history in session state if not already present
if f"question_history_{module}" not in st.session_state:
st.session_state[f"question_history_{module}"] = []
+
# Prepare the history of questions as part of the prompt
question_history = st.session_state[f"question_history_{module}"]
history_prompt = (
"Here is a list of previously generated questions. Do not repeat any of these:\n" +
"\n".join(question_history) +
"\n\n"
if question_history else ""
)
+
# Call OpenAI GPT API to generate a quiz question
response = client.chat.completions.create(
model="gpt-4o",
messages=[
{"role": "system", "content": """You are a quiz generator. Create a multiple-choice question based on the following module.
Your solution should be formatted in such a way that the parser, shown here, can extract the question, options, correct answer, and explanation.
The first character should be the question, not a splitter "XXXX". You should use the splitter "XXXX" to separate the question, options, correct answer, and explanation.
For example:
What is the Capital of France?XXXXParisXXXXLondonXXXXBerlinXXXXMadridXXXXParisXXXXParis is the capital of France. London is the capital of England. Berlin is the capital of Germany. Madrid is the Capital of Spain.
Parser code:
content = response.choices[0].message.content
lines = content.split("XXXX")
question = lines[0]
options = lines[1:5] # Assuming options are in lines 1-4
correct = lines[5] # Assuming correct answer is in line 5
explanation = lines[6] # Assuming explanation is in line 6
"""},
{"role": "user", "content": f"{history_prompt}Generate a quiz question for the module: {module}."}
],
max_tokens=300,
temperature=0.7
)
# Parse the response to extract question, options, correct answer, and explanation
content = response.choices[0].message.content
lines = content.split("XXXX")
question = lines[0]
options = lines[1:5] # Assuming options are in lines 1-4
correct = lines[5] # Assuming correct answer is in line 5
explanation = lines[6] # Assuming explanation is in line 6
+
# Add the new question to the history
st.session_state[f"question_history_{module}"].append(question)
+
return {
"question": question,
"options": options,
"correct": correct,
"explanation": explanation
}
except Exception as e:
st.error(f"Error generating quiz question: {e}")
return {
"question": "Error generating question.",
"options": [],
"correct": "",
"explanation": ""
}
+
def _parse_response(self, response: str) -> List[str]:
# Split the response into individual modules based on "XXXX"
return response.split("XXXX")
+
def main():
st.title("Learn with GPT")
# Initialize session state for learning modules
if "learning_modules" not in st.session_state:
st.session_state.learning_modules = []
+
# User input for topic
topic = st.text_input("Enter a topic you want to learn about (e.g. Quantum Physics):")
+
background = st.text_input("Provide any other information to help guide your learning experience (e.g. how much time you have, your current knowledge etc.):")
if st.button("Get Learning Modules"):
if topic:
gpt_service = GPTService()
learning_modules = gpt_service.get_learning_modules(topic, background)
if learning_modules:
# Store the learning modules in session state
st.session_state.learning_modules = learning_modules
else:
st.error("No learning modules found. Please try a different topic.")
else:
st.warning("Please enter a topic to get started.")
+
# Display the checklist if learning modules are available
if st.session_state.learning_modules:
def quiz_callback(module: str):
gpt_service = GPTService()
+
# Initialize session state for the quiz question, options, correct answer, and expander state
question_data = gpt_service.generate_quiz_question(module)
st.session_state[f"quiz_question_{module}"] = question_data["question"]
st.session_state[f"quiz_options_{module}"] = question_data["options"]
st.session_state[f"quiz_correct_{module}"] = question_data["correct"]
st.session_state[f"quiz_explanation_{module}"] = question_data["explanation"]
st.session_state[f"expander_open_{module}"] = True
st.session_state[f"selected_option_{module}"] = None
+
# Display the expander
with st.expander(st.session_state[f"quiz_question_{module}"], expanded=st.session_state[f"expander_open_{module}"]):
+
# Display multiple-choice options
selected_option = st.radio(
"Choose your answer:",
st.session_state[f"quiz_options_{module}"],
index=st.session_state[f"quiz_options_{module}"].index(st.session_state[f"selected_option_{module}"])
if st.session_state[f"selected_option_{module}"] else 0,
key=f"radio_{module}",
)
+
# st.session_state[f"selected_option_{module}"] = selected_option
+
# Submit button to check the answer
if st.button(f"Submit Answer"):
if selected_option == st.session_state[f"quiz_correct_{module}"]:
st.success("Correct! πŸŽ‰")
else:
st.error("Incorrect. 😞")
st.info(f"The correct answer is: {st.session_state[f'quiz_correct_{module}']}")
st.write(f"Explanation: {st.session_state[f'quiz_explanation_{module}']}")
+
generate_checklist(
st.session_state.learning_modules,
quiz_callback=quiz_callback
)
+
if __name__ == "__main__":
main()
+
+ +
+ + + + + + +