MCPcopy Index your code
hub / github.com/codingis4noobs2/QuickDigest / process_pdf

Function process_pdf

app.py:214–224  ·  view source on GitHub ↗
(pdf_path)

Source from the content-addressed store, hash-verified

212
213 # Process PDF files
214 def process_pdf(pdf_path):
215 reader = PdfReader(pdf_path)
216 all_text = ""
217 for page in reader.pages:
218 extracted_text = page.extract_text()
219 if extracted_text:
220 processed_text = ' '.join(extracted_text.split('\n'))
221 all_text += processed_text + "\n\n"
222 txt_filepath = save_extracted_text_to_txt(all_text, os.path.basename(pdf_path))
223 os.remove(pdf_path) # Delete the original PDF file
224 return txt_filepath
225
226 # Main logic for handling OpenAI API key and document processing
227 if "openai_api_key" not in st.session_state:

Callers 1

process_documentsFunction · 0.85

Calls 1

Tested by

no test coverage detected