How ramamoorthy07/document_analysis_app works
The product is a Streamlit document-analysis app: a user uploads a PDF, the app extracts text, validates it and generates embeddings, then creates a downloadable PDF report. The report includes a validation outcome and embedding excerpt. The README also describes summarization and gap analysis, but the sampled app does not invoke the standalone summarizer, and the semantic_search.py file is empty. The shown PDF extractor uses pdfplumber; image extraction uses Tesseract. The map follows demonstrated calls and documented capabilities, not assumed integrations.
Main entry points: app.py Streamlit app · ocr.py Text extraction · report_generation.py PDF report · nlp_validation.py Content validation
Components 8
User interface
- Streamlit app
app.py
Document analysis
- Text extraction
ocr.py - Content validation
nlp_validation.py - Vector embeddings
embeddings.py - Text summarization
summarization.py
Report output
- PDF report
report_generation.py
Other components
- User
- Tesseract OCR
Connections 8
- User → Streamlit app: uploads PDF
README.md - Streamlit app → Text extraction: extracts text
app.py - Text extraction → Tesseract OCR: recognizes images
ocr.py - Streamlit app → Content validation: validates text
app.py - Streamlit app → Vector embeddings: generates vectors
app.py - Streamlit app → PDF report: generates report
app.py - PDF report → Streamlit app: returns file path
app.py - Streamlit app → User: offers PDF download
app.py