Spaces:
Running
Running
File size: 11,906 Bytes
5798cfc |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 |
import os
import json
from dotenv import load_dotenv
import fitz # PyMuPDF
from langchain_openai import ChatOpenAI # Correct import from langchain-openai
from langchain.schema import HumanMessage, SystemMessage # For creating structured chat messages
QUESTIONS_PATH = "questions.json"
# Load environment variables
load_dotenv()
def split_text_into_chunks(text: str, chunk_size: int) -> list:
"""
Splits the text into chunks of a specified maximum size.
"""
# Trim the text to remove leading/trailing whitespace and reduce multiple spaces to a single space
cleaned_text = " ".join(text.split())
words = cleaned_text.split(" ")
chunks = []
current_chunk = []
current_length = 0
for word in words:
if current_length + len(word) + 1 > chunk_size:
chunks.append(" ".join(current_chunk))
current_chunk = [word]
current_length = len(word)
else:
current_chunk.append(word)
current_length += len(word) + 1
if current_chunk:
chunks.append(" ".join(current_chunk))
return chunks
def distribute_questions_across_chunks(n_chunks: int, n_questions: int) -> list:
"""
Distributes a specified number of questions across a specified number of chunks.
"""
questions_per_chunk = [1] * min(n_chunks, n_questions)
remaining_questions = n_questions - len(questions_per_chunk)
if remaining_questions > 0:
for i in range(len(questions_per_chunk)):
if remaining_questions == 0:
break
questions_per_chunk[i] += 1
remaining_questions -= 1
while len(questions_per_chunk) < n_chunks:
questions_per_chunk.append(0)
return questions_per_chunk
def extract_text_from_pdf(pdf_path):
text = ""
try:
print(f"[DEBUG] Opening PDF: {pdf_path}")
with fitz.open(pdf_path) as pdf:
print(f"[DEBUG] Extracting text from PDF: {pdf_path}")
for page in pdf:
text += page.get_text()
except Exception as e:
print(f"Error reading PDF: {e}")
raise RuntimeError("Unable to extract text from PDF.")
return text
def generate_questions_from_text(text, n_questions=5):
openai_api_key = os.getenv("OPENAI_API_KEY")
if not openai_api_key:
raise RuntimeError(
"OpenAI API key not found. Please add it to your .env file as OPENAI_API_KEY."
)
chat = ChatOpenAI(
openai_api_key=openai_api_key, model="gpt-4", temperature=0.7, max_tokens=750
)
messages = [
SystemMessage(
content="You are an expert interviewer who generates concise technical interview questions. Do not enumerate the questions. Answer only with questions."
),
HumanMessage(
content=f"Based on the following content, generate {n_questions} technical interview questions:\n{text}"
),
]
try:
print(f"[DEBUG] Sending request to OpenAI with {n_questions} questions.")
response = chat.invoke(messages)
questions = response.content.strip().split("\n\n")
questions = [q.strip() for q in questions if q.strip()]
except Exception as e:
print(f"[ERROR] Failed to generate questions: {e}")
questions = ["An error occurred while generating questions."]
return questions
def save_questions(questions):
with open(QUESTIONS_PATH, "w") as f:
json.dump(questions, f, indent=4)
def generate_and_save_questions_from_pdf(pdf_path, total_questions=5):
print(f"[INFO] Generating questions from PDF: {pdf_path}")
try:
pdf_text = extract_text_from_pdf(pdf_path)
if not pdf_text.strip():
raise RuntimeError("The PDF content is empty or could not be read.")
chunk_size = 2000
chunks = split_text_into_chunks(pdf_text, chunk_size)
n_chunks = len(chunks)
questions_distribution = distribute_questions_across_chunks(n_chunks, total_questions)
combined_questions = []
for i, (chunk, n_questions) in enumerate(zip(chunks, questions_distribution)):
print(f"[DEBUG] Processing chunk {i + 1} of {n_chunks}")
if n_questions > 0:
questions = generate_questions_from_text(chunk, n_questions=n_questions)
combined_questions.extend(questions)
if not combined_questions:
raise RuntimeError("No questions generated from the PDF content.")
print(f"[INFO] Total questions generated: {len(combined_questions)}")
save_questions(combined_questions)
print(f"[INFO] Questions saved to {QUESTIONS_PATH}")
# Return a status message and the JSON object
return "Questions generated successfully.", {"questions": combined_questions}
except Exception as e:
# Handle exceptions and return meaningful error messages
error_message = f"Error during question generation: {str(e)}"
print(f"[ERROR] {error_message}")
return error_message, {"questions": []}
import gradio as gr
import json
import os
import time
def generate_and_save_questions_from_pdf3_mock(pdf_path, total_questions=5):
print(f"[INFO] Generating questions from PDF: {pdf_path}")
if not os.path.exists(pdf_path):
yield "β Error: PDF file not found.", {}
return
yield "π PDF uploaded successfully. Processing started...", {}
try:
# Simulate PDF text extraction and processing
time.sleep(1)
pdf_text = "This is some mock PDF text for testing purposes."
if not pdf_text.strip():
yield "β Error: The PDF content is empty or could not be read.", {}
return
chunk_size = 2000
chunks = [pdf_text[i:i + chunk_size] for i in range(0, len(pdf_text), chunk_size)]
n_chunks = len(chunks)
yield f"π Splitting text into {n_chunks} chunks...", {}
questions_distribution = [total_questions // n_chunks] * n_chunks
combined_questions = []
for i, (chunk, n_questions) in enumerate(zip(chunks, questions_distribution)):
yield f"π Processing chunk {i + 1} of {n_chunks}...", {}
time.sleep(1) # Simulating processing time
combined_questions.append(f"Sample Question from Chunk {i + 1}")
if not combined_questions:
yield "β Error: No questions generated from the PDF content.", {}
return
yield f"β
Total {len(combined_questions)} questions generated. Saving questions...", {}
save_path = "generated_questions_from_pdf.json"
with open(save_path, "w") as f:
json.dump({"questions": combined_questions}, f)
yield "β
PDF processing complete. Questions saved successfully!", {"questions": combined_questions}
except Exception as e:
yield f"β Error during question generation: {str(e)}", {}
def generate_and_save_questions_from_pdf3_v1(pdf_path, total_questions=5):
print(f"[INFO] Generating questions from PDF: {pdf_path}")
if not os.path.exists(pdf_path):
yield "β Error: PDF file not found.", {}
return
yield "π PDF uploaded successfully. Processing started...", {}
try:
# Extract text from the PDF file
pdf_text = extract_text_from_pdf(pdf_path)
if not pdf_text.strip():
yield "β Error: The PDF content is empty or could not be read.", {}
return
# Split the PDF content into chunks
chunk_size = 2000 # Adjust this as necessary
chunks = split_text_into_chunks(pdf_text, chunk_size)
n_chunks = len(chunks)
yield f"π Splitting text into {n_chunks} chunks...", {}
# Distribute the total number of questions across chunks
questions_distribution = distribute_questions_across_chunks(n_chunks, total_questions)
combined_questions = []
# Process each chunk and generate questions
for i, (chunk, n_questions) in enumerate(zip(chunks, questions_distribution)):
yield f"π Processing chunk {i + 1} of {n_chunks}...", {}
if n_questions > 0:
questions = generate_questions_from_text(chunk, n_questions=n_questions)
combined_questions.extend(questions)
if not combined_questions:
yield "β Error: No questions generated from the PDF content.", {}
return
yield f"β
Total {len(combined_questions)} questions generated. Saving questions...", {}
# Save generated questions to a file
save_path = "generated_questions_from_pdf.json"
with open(save_path, "w") as f:
json.dump({"questions": combined_questions}, f)
yield "β
PDF processing complete. Questions saved successfully!", {"questions": combined_questions}
except Exception as e:
error_message = f"β Error during question generation: {str(e)}"
print(f"[ERROR] {error_message}")
yield error_message, {}
import json
import os
def generate_and_save_questions_from_pdf3(pdf_path, total_questions=5):
print(f"[INFO] Generating questions from PDF: {pdf_path}")
if not os.path.exists(pdf_path):
yield "β Error: PDF file not found.", {}
return
yield "π PDF uploaded successfully. Processing started...", {}
try:
# Extract text from the PDF file
pdf_text = extract_text_from_pdf(pdf_path)
if not pdf_text.strip():
yield "β Error: The PDF content is empty or could not be read.", {}
return
# Split the PDF content into chunks
chunk_size = 2000 # Adjust this as necessary
chunks = split_text_into_chunks(pdf_text, chunk_size)
n_chunks = len(chunks)
yield f"π Splitting text into {n_chunks} chunks...", {}
# Distribute the total number of questions across chunks
questions_distribution = distribute_questions_across_chunks(n_chunks, total_questions)
combined_questions = []
# Process each chunk and generate questions
for i, (chunk, n_questions) in enumerate(zip(chunks, questions_distribution)):
yield f"π Processing chunk {i + 1} of {n_chunks}...", {}
if n_questions > 0:
questions = generate_questions_from_text(chunk, n_questions=n_questions)
combined_questions.extend(questions)
if not combined_questions:
yield "β Error: No questions generated from the PDF content.", {}
return
yield f"β
Total {len(combined_questions)} questions generated. Saving questions...", {}
# Save the combined questions in `generated_questions_from_pdf.json` (detailed version)
detailed_save_path = "generated_questions_from_pdf.json"
with open(detailed_save_path, "w") as f:
json.dump({"questions": combined_questions}, f)
# Save only the questions (overwrite `questions.json` if it already exists)
simple_save_path = "questions.json"
with open(simple_save_path, "w") as f:
json.dump(combined_questions, f)
yield "β
PDF processing complete. Questions saved successfully!", {"questions": combined_questions}
except Exception as e:
error_message = f"β Error during question generation: {str(e)}"
print(f"[ERROR] {error_message}")
yield error_message, {}
if __name__ == "__main__":
pdf_path = "professional_machine_learning_engineer_exam_guide_english.pdf"
try:
generated_questions = generate_and_save_questions_from_pdf(
pdf_path, total_questions=5
)
print(f"Generated Questions:\n{json.dumps(generated_questions, indent=2)}")
except Exception as e:
print(f"Failed to generate questions: {e}")
|