# ramamoorthy07/document_analysis_app architecture

> Architecture diagram of the GitHub repository ramamoorthy07/document_analysis_app, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-05). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/ramamoorthy07/document_analysis_app
- Repository: https://github.com/ramamoorthy07/document_analysis_app

## Overview

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`](https://github.com/ramamoorthy07/document_analysis_app/blob/main/app.py) (Streamlit app), [`ocr.py`](https://github.com/ramamoorthy07/document_analysis_app/blob/main/ocr.py) (Text extraction), [`report_generation.py`](https://github.com/ramamoorthy07/document_analysis_app/blob/main/report_generation.py) (PDF report), [`nlp_validation.py`](https://github.com/ramamoorthy07/document_analysis_app/blob/main/nlp_validation.py) (Content validation)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interface["User interface"]
  node_app["Streamlit app<br/>[app.py]"]
end

subgraph group_analysis["Document analysis"]
  node_ocr["Text extraction<br/>[ocr.py]"]
  node_validation["Content validation<br/>[nlp_validation.py]"]
  node_embeddings["Vector embeddings<br/>[embeddings.py]"]
  node_summarization["Text summarization<br/>[summarization.py]"]
end

subgraph group_outputs["Report output"]
  node_report["PDF report"]
end

node_user(("User"))
node_tesseract["Tesseract OCR"]

node_user -->|"uploads PDF"| node_app
node_app -->|"extracts text"| node_ocr
node_ocr -->|"recognizes images"| node_tesseract
node_app -->|"validates text"| node_validation
node_app -->|"generates vectors"| node_embeddings
node_app -->|"generates report"| node_report
node_report -->|"returns file path"| node_app
node_app -->|"offers PDF download"| node_user

click node_app "https://github.com/ramamoorthy07/document_analysis_app/blob/main/app.py"
click node_ocr "https://github.com/ramamoorthy07/document_analysis_app/blob/main/ocr.py"
click node_validation "https://github.com/ramamoorthy07/document_analysis_app/blob/main/nlp_validation.py"
click node_embeddings "https://github.com/ramamoorthy07/document_analysis_app/blob/main/embeddings.py"
click node_summarization "https://github.com/ramamoorthy07/document_analysis_app/blob/main/summarization.py"
click node_report "https://github.com/ramamoorthy07/document_analysis_app/blob/main/report_generation.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_app,node_user toneBlue
class node_ocr,node_validation,node_embeddings,node_summarization toneAmber
class node_report toneMint
class node_tesseract toneIndigo
```

## Components

### User interface

- [Streamlit app](https://github.com/ramamoorthy07/document_analysis_app/blob/main/app.py): `app.py`

### Document analysis

- [Text extraction](https://github.com/ramamoorthy07/document_analysis_app/blob/main/ocr.py): `ocr.py`
- [Content validation](https://github.com/ramamoorthy07/document_analysis_app/blob/main/nlp_validation.py): `nlp_validation.py`
- [Vector embeddings](https://github.com/ramamoorthy07/document_analysis_app/blob/main/embeddings.py): `embeddings.py`
- [Text summarization](https://github.com/ramamoorthy07/document_analysis_app/blob/main/summarization.py): `summarization.py`

### Report output

- [PDF report](https://github.com/ramamoorthy07/document_analysis_app/blob/main/report_generation.py): `report_generation.py`

### Other components

- **User**
- **Tesseract OCR**

## Connections

- User → Streamlit app: uploads PDF (evidence: `README.md`)
- Streamlit app → Text extraction: extracts text (evidence: `app.py`)
- Text extraction → Tesseract OCR: recognizes images (evidence: `ocr.py`)
- Streamlit app → Content validation: validates text (evidence: `app.py`)
- Streamlit app → Vector embeddings: generates vectors (evidence: `app.py`)
- Streamlit app → PDF report: generates report (evidence: `app.py`)
- PDF report → Streamlit app: returns file path (evidence: `app.py`)
- Streamlit app → User: offers PDF download (evidence: `app.py`)
