# sanaya27/ai-research-paper-summarizer architecture

> Architecture diagram of the GitHub repository sanaya27/ai-research-paper-summarizer, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-11-24). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/sanaya27/ai-research-paper-summarizer
- Repository: https://github.com/sanaya27/ai-research-paper-summarizer

## Overview

##### Project type and purpose
- This is a modular, Python-based research paper summarization system. It comprises two primary backend components (PDF extractor and summarizer), a future frontend, an integration layer, a datasets store, and documentation. It is not yet a full end-to-end web app but is structured as discrete services that will eventually be orchestrated by a frontend or orchestration script (app.py).

##### File structure
- Top-level:
- app.py, pdf_utils.py, summarizer.py, test_pdf_extract.py – likely the orchestration & shared utilities
- pdf-text-extractor-backend/ – Khushboo’s extractor microservice
- summarizer/ – summarization microservice using LLM inference
- frontend/ (placeholder) – to be added by Riya
- integrations/ – code for tying services together and calling Gemini API
- datasets/ – storage of raw PDFs & metadata
- docs/ – architecture, methodology, flow docs
- Each microservice has its own main.py, llm_infer.py (or extraction logic), requirements.txt, sample inputs/outputs, and writes extracted_text.txt & summary.txt.
- .devcontainer, GitHub configs (.gitignore), license, README.md for overall orchestration.

##### README for insights
- Purpose: extract and preprocess PDF text, then summarize with Google Gemini 1.5 Pro.
- Team-driven, modular.
- Tech stack: Python 3.11+, PyMuPDF, dotenv, Google Gemini API, Streamlit (future UI), Streamlit Cloud.
- Deployment: currently local backends; frontend & integration to follow.

##### Final advice
- Be detailed: represent each folder/module as a component if it encapsulates a distinct responsibility
- Critical config files (.env handling, devcontainer) as annotations or notes
- Don’t over-segment—keep the pipeline flow clear and focused on extraction → summarization → output

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% Client/UI Layer
    UI["Client/UI (Streamlit App)"]:::orchestrator

    %% Orchestrator Layer
    subgraph "Orchestrator (Integration Layer)" 
        direction TB
        Apppy["app.py"] 
        PdfUtils["pdf_utils.py"]
        SummarizerPy["summarizer.py"]
        TestPDF["test_pdf_extract.py"]
    end

    %% PDF Extraction Service
    subgraph "PDF Extraction Service" 
        direction TB
        MainExt["main.py"]:::backend
        LLMExtract["llm_infer.py"]:::backend
    end

    %% Summarization Service
    subgraph "Summarization Service" 
        direction TB
        MainSum["main.py"]:::backend
        LLMSum["llm_infer.py"]:::backend
    end

    %% External LLM API
    Gemini["Google Gemini API"]:::external

    %% Data Store
    DataStore["Datasets Store\n(datasets/)"]:::datastore

    %% Documentation
    Docs["Documentation\n(docs/)"]:::note

    %% Data Flow
    UI -->|"upload PDF"| Apppy
    Apppy -->|"call extraction"| MainExt
    MainExt -->|"extract text"| LLMExtract
    LLMExtract -->|"returns extracted_text.txt"| Apppy
    PdfUtils -.-> MainExt
    Apppy -->|"call summarization"| SummarizerPy
    SummarizerPy -->|"invoke main.py"| MainSum
    MainSum -->|"call llm_infer"| LLMSum
    LLMSum -->|"invoke API"| Gemini
    Gemini -->|"returns summary"| LLMSum
    LLMSum -->|"returns summary.txt"| SummarizerPy
    SummarizerPy -->|"persist results"| DataStore
    Apppy -->|"persist raw PDFs"| DataStore

    %% Click Events - Orchestrator
    click Apppy "https://github.com/sanaya27/ai-research-paper-summarizer/blob/main/app.py"
    click PdfUtils "https://github.com/sanaya27/ai-research-paper-summarizer/blob/main/pdf_utils.py"
    click SummarizerPy "https://github.com/sanaya27/ai-research-paper-summarizer/blob/main/summarizer.py"
    click TestPDF "https://github.com/sanaya27/ai-research-paper-summarizer/blob/main/test_pdf_extract.py"

    %% Click Events - Extraction Service
    click MainExt "https://github.com/sanaya27/ai-research-paper-summarizer/blob/main/pdf-text-extractor-backend/main.py"
    click LLMExtract "https://github.com/sanaya27/ai-research-paper-summarizer/blob/main/pdf-text-extractor-backend/llm_infer.py"

    %% Click Events - Summarization Service
    click MainSum "https://github.com/sanaya27/ai-research-paper-summarizer/blob/main/summarizer/main.py"
    click LLMSum "https://github.com/sanaya27/ai-research-paper-summarizer/blob/main/summarizer/llm_infer.py"

    %% Click Events - Data Store & Docs
    click DataStore "https://github.com/sanaya27/ai-research-paper-summarizer/tree/main/datasets/"
    click Docs "https://github.com/sanaya27/ai-research-paper-summarizer/tree/main/docs/"

    %% Styles
    classDef backend fill:#ADD8E6,stroke:#000,stroke-width:1px
    classDef external fill:#98FB98,stroke:#000,stroke-width:1px
    classDef datastore fill:#FFDAB9,stroke:#000,stroke-width:1px
    classDef orchestrator fill:#DDA0DD,stroke:#000,stroke-width:1px
    classDef note fill:#F0E68C,stroke:#000,stroke-width:1px
```
