Spaces:
Running
Running
File size: 9,316 Bytes
facdd69 10f46a6 6e83819 10f46a6 6e83819 10f46a6 8374697 21053fe 10f46a6 952fb99 8374697 10f46a6 8374697 10f46a6 8374697 10f46a6 8374697 952fb99 facdd69 952fb99 facdd69 952fb99 facdd69 10f46a6 952fb99 10f46a6 6e83819 10f46a6 6e83819 10f46a6 6e83819 10f46a6 952fb99 10f46a6 952fb99 10f46a6 6e83819 10f46a6 6e83819 10f46a6 6e83819 10f46a6 952fb99 facdd69 10f46a6 952fb99 10f46a6 952fb99 10f46a6 952fb99 10f46a6 facdd69 10f46a6 952fb99 10f46a6 6e83819 10f46a6 6e83819 10f46a6 6e83819 10f46a6 952fb99 facdd69 bc87def 952fb99 facdd69 10f46a6 facdd69 952fb99 facdd69 952fb99 facdd69 8374697 facdd69 952fb99 facdd69 952fb99 facdd69 952fb99 facdd69 952fb99 facdd69 10f46a6 952fb99 10f46a6 952fb99 facdd69 bc87def 8374697 952fb99 bc87def 952fb99 bc87def 952fb99 bc87def 10f46a6 952fb99 10f46a6 952fb99 facdd69 bc87def facdd69 a80fd49 8374697 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 |
import streamlit as st
from youtube_transcript_api import YouTubeTranscriptApi
import re
import tempfile
import os
import warnings
from groq import Groq
# Set up Groq client
client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
# Supported file types for Groq API
SUPPORTED_FILE_TYPES = ["mp3", "mp4", "mpeg", "mpga", "m4a", "wav", "webm"]
# Function to transcribe audio using Groq Whisper API
def transcribe_audio(file_path):
file_extension = os.path.splitext(file_path)[1][1:]
if file_extension not in SUPPORTED_FILE_TYPES:
return f"Error: Unsupported file type '{file_extension}'. Please upload a valid file."
try:
with open(file_path, "rb") as file:
transcription = client.audio.transcriptions.create(
file=(file_path, file.read()),
model="whisper-large-v3",
)
return transcription.text
except Exception as e:
return f"Error during transcription: {e}"
# Function to get transcript from YouTube
def get_transcript(url):
try:
video_id_match = re.search(r"(?:v=|\/)([0-9A-Za-z_-]{11}).*", url)
if not video_id_match:
return "Error: Invalid YouTube URL"
video_id = video_id_match.group(1)
transcript = YouTubeTranscriptApi.get_transcript(video_id)
transcript_text = ' '.join([entry['text'] for entry in transcript])
return transcript_text
except Exception as e:
return str(e)
# Function to summarize text using Groq API
def summarize_text(text):
try:
response = client.chat.completions.create(
messages=[
{
"role": "user",
"content": f"Summarize the following text:\n\n{text}"
}
],
model="llama3-8b-8192",
)
summary = response.choices[0].message.content.strip()
return summary
except Exception as e:
return f"Error summarizing text: {e}"
# Function to generate quiz questions using Groq API
def generate_quiz_questions(text):
try:
response = client.chat.completions.create(
messages=[
{
"role": "user",
"content": f"Generate quiz questions for the following text:\n\n{text}"
}
],
model="llama3-8b-8192",
)
quiz_questions = response.choices[0].message.content.strip()
return quiz_questions
except Exception as e:
return f"Error generating quiz questions: {e}"
# Function to parse quiz questions from generated text
def parse_quiz_questions(quiz_text):
questions = []
question_blocks = quiz_text.split("\n\n")
current_question = None
current_choices = []
correct_answer = None
for block in question_blocks:
lines = block.strip().split("\n")
if lines:
if re.match(r'^\d+\.', lines[0]): # This line is a question number
if current_question and current_choices and correct_answer:
questions.append({
"question": current_question,
"choices": current_choices,
"correct_answer": correct_answer
})
current_question = lines[0]
current_choices = lines[1:5]
correct_answer = lines[-1].split(": ")[-1].strip() if len(lines) > 5 else None
else: # This line is an answer
correct_answer = lines[-1].split(": ")[-1].strip()
# Add the last question if it exists
if current_question and current_choices and correct_answer:
questions.append({
"question": current_question,
"choices": current_choices,
"correct_answer": correct_answer
})
return questions
# Function to generate explanation for quiz answers using Groq API
def generate_explanation(question, correct_answer, user_answer):
try:
response = client.chat.completions.create(
messages=[
{
"role": "user",
"content": f"Explain why the correct answer to the following question is '{correct_answer}' and not '{user_answer}':\n\n{question}"
}
],
model="llama3-8b-8192",
)
explanation = response.choices[0].message.content.strip()
return explanation
except Exception as e:
return f"Error generating explanation: {e}"
# Function to check answers and provide feedback
def check_answers(questions, user_answers):
feedback = []
correct_count = 0
for i, question in enumerate(questions):
correct_answer = question['correct_answer']
user_answer = user_answers.get(f"question_{i+1}", "")
if user_answer == correct_answer:
feedback.append({
"question": question['question'],
"user_answer": user_answer,
"correct_answer": correct_answer,
"status": "Correct"
})
correct_count += 1
else:
explanation = generate_explanation(question['question'], correct_answer, user_answer)
feedback.append({
"question": question['question'],
"user_answer": user_answer,
"correct_answer": correct_answer,
"status": "Incorrect",
"explanation": explanation
})
return feedback
# Function to handle uploaded files
def handle_uploaded_file(uploaded_file):
file_path = tempfile.mktemp(suffix=os.path.splitext(uploaded_file.name)[1])
with open(file_path, "wb") as f:
f.write(uploaded_file.read())
return file_path
# Streamlit app layout and functionality
st.title("YouTube Transcript Quiz Generator")
st.markdown("**Instructions:** Paste a YouTube link or upload a media file to generate a quiz.")
option = st.selectbox("Choose input type", ("YouTube URL", "Upload audio/video file"))
if "generated_quiz" not in st.session_state:
st.session_state.generated_quiz = False
if option == "YouTube URL":
url = st.text_input("YouTube URL", value="")
if url:
if st.button("Generate Quiz"):
transcript_text = get_transcript(url)
if "Error" not in transcript_text:
summary = summarize_text(transcript_text)
quiz_text = generate_quiz_questions(transcript_text)
questions = parse_quiz_questions(quiz_text)
if not questions:
st.error("No valid quiz questions could be generated.")
else:
st.session_state.summary = summary
st.session_state.questions = questions
st.session_state.user_answers = {}
st.session_state.generated_quiz = True
else:
st.error(transcript_text)
if option == "Upload audio/video file":
uploaded_file = st.file_uploader("Choose an audio or video file", type=SUPPORTED_FILE_TYPES)
if uploaded_file:
if st.button("Generate Quiz"):
tmp_file_path = handle_uploaded_file(uploaded_file)
transcript_text = transcribe_audio(tmp_file_path)
os.remove(tmp_file_path)
if "Error" not in transcript_text:
summary = summarize_text(transcript_text)
quiz_text = generate_quiz_questions(transcript_text)
questions = parse_quiz_questions(quiz_text)
if not questions:
st.error("No valid quiz questions could be generated.")
else:
st.session_state.summary = summary
st.session_state.questions = questions
st.session_state.user_answers = {}
st.session_state.generated_quiz = True
else:
st.error(transcript_text)
if st.session_state.generated_quiz:
st.write("## Summary")
st.write(st.session_state.summary)
st.write("## Quiz Questions")
for i, question in enumerate(st.session_state.questions):
st.write(f"### Question {i+1}")
st.write(question['question'])
st.session_state.user_answers[f"question_{i+1}"] = st.radio(
label="",
options=question['choices'],
key=f"question_{i+1}"
)
if st.button("Submit Answers"):
if "questions" in st.session_state and st.session_state.questions:
with st.spinner('Processing your answers...'):
feedback = check_answers(st.session_state.questions, st.session_state.user_answers)
st.write("## Feedback")
for i, item in enumerate(feedback):
with st.expander(f"Question {i+1} Feedback"):
st.write(f"### {item['question']}")
st.write(f"**Your answer:** {item['user_answer']}")
st.write(f"**Correct answer:** {item['correct_answer']}")
if item['status'] == "Incorrect":
st.write(f"**Explanation:** {item['explanation']}")
else:
st.write("Please generate the quiz first.")
|