# vijaykumar-devcode/documentanalyzer architecture

> Architecture diagram of the GitHub repository vijaykumar-devcode/documentanalyzer, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-30). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/vijaykumar-devcode/documentanalyzer
- Repository: https://github.com/vijaykumar-devcode/documentanalyzer

## Overview

Reading Level Analyzer is a Streamlit app that accepts pasted text or uploaded TXT/PDF documents, reports readability statistics, and uses retrieved knowledge-base examples to guide a Gemini reading-level assessment. Its main flow is input extraction, parallel statistics and RAG analysis, then presentation of the score, reasoning, and retrieved sources. The RAG module also builds the local index from curated samples and guidelines. Relationships are based on the excerpts and README; unsampled implementation details are not inferred.

Main entry points: [`rag_pipeline.py`](https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/rag_pipeline.py) (Context Retrieval), [`app.py`](https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/app.py) (Document Extraction), [`readability_stats.py`](https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/readability_stats.py) (Readability Statistics), [`knowledge_base`](https://github.com/vijaykumar-devcode/documentanalyzer/tree/main/knowledge_base) (Curated Samples)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interface["User Interface"]
  node_ui["Streamlit Interface<br/>[app.py]"]
  node_input["Text and File Input<br/>[app.py]"]
  node_extract["Document Extraction<br/>[app.py]"]
  node_results["Assessment Results<br/>[app.py]"]
  node_trace["Retrieved Source Trace<br/>[app.py]"]
end

subgraph group_readability["Readability Analysis"]
  node_stats["Readability Statistics"]
end

subgraph group_rag["RAG Assessment"]
  node_retrieval["Context Retrieval<br/>[rag_pipeline.py]"]
  node_prompt["Assessment Prompt<br/>[rag_pipeline.py]"]
  node_gemini{{"Gemini LLM"}}
  node_assessment["JSON Assessment<br/>[rag_pipeline.py]"]
end

subgraph group_knowledge["Knowledge Base"]
  node_kb["Curated Samples"]
  node_loader["Text Loader<br/>[rag_pipeline.py]"]
  node_chunker["Text Chunking<br/>[rag_pipeline.py]"]
  node_embeddings["Local Embeddings<br/>[rag_pipeline.py]"]
  node_faiss[("FAISS Index<br/>[rag_pipeline.py]")]
end

node_user(("User"))

node_user -->|"uses"| node_ui
node_ui -->|"offers input"| node_input
node_input -->|"extracts text"| node_extract
node_extract -->|"measures"| node_stats
node_extract -->|"analyzes text"| node_retrieval
node_kb -->|"loads files"| node_loader
node_loader -->|"splits documents"| node_chunker
node_chunker -->|"indexes chunks"| node_faiss
node_embeddings -->|"vectorizes documents"| node_faiss
node_faiss -->|"searches index"| node_retrieval
node_retrieval -->|"supplies context"| node_prompt
node_prompt -->|"invokes"| node_gemini
node_gemini -->|"returns response"| node_assessment
node_retrieval -->|"returns chunks"| node_assessment
node_assessment -->|"displays assessment"| node_results
node_assessment -->|"displays sources"| node_trace
node_stats -->|"displays metrics"| node_results

click node_ui "https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/app.py"
click node_input "https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/app.py"
click node_extract "https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/app.py"
click node_stats "https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/readability_stats.py"
click node_kb "https://github.com/vijaykumar-devcode/documentanalyzer/tree/main/knowledge_base"
click node_loader "https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/rag_pipeline.py"
click node_chunker "https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/rag_pipeline.py"
click node_embeddings "https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/rag_pipeline.py"
click node_faiss "https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/rag_pipeline.py"
click node_retrieval "https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/rag_pipeline.py"
click node_prompt "https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/rag_pipeline.py"
click node_assessment "https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/rag_pipeline.py"
click node_results "https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/app.py"
click node_trace "https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/app.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_ui,node_input,node_extract,node_results,node_trace,node_user toneBlue
class node_stats toneAmber
class node_retrieval,node_prompt,node_gemini,node_assessment toneMint
class node_kb,node_loader,node_chunker,node_embeddings,node_faiss toneRose
```

## Components

### User Interface

- [Streamlit Interface](https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/app.py): `app.py`
- [Text and File Input](https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/app.py): `app.py`
- [Document Extraction](https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/app.py): `app.py`
- [Assessment Results](https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/app.py): `app.py`
- [Retrieved Source Trace](https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/app.py): `app.py`

### Readability Analysis

- [Readability Statistics](https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/readability_stats.py): `readability_stats.py`

### RAG Assessment

- [Context Retrieval](https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/rag_pipeline.py): `rag_pipeline.py`
- [Assessment Prompt](https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/rag_pipeline.py): `rag_pipeline.py`
- **Gemini LLM**
- [JSON Assessment](https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/rag_pipeline.py): `rag_pipeline.py`

### Knowledge Base

- [Curated Samples](https://github.com/vijaykumar-devcode/documentanalyzer/tree/main/knowledge_base): `knowledge_base`
- [Text Loader](https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/rag_pipeline.py): `rag_pipeline.py`
- [Text Chunking](https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/rag_pipeline.py): `rag_pipeline.py`
- [Local Embeddings](https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/rag_pipeline.py): `rag_pipeline.py`
- [FAISS Index](https://github.com/vijaykumar-devcode/documentanalyzer/blob/main/rag_pipeline.py): `rag_pipeline.py`

### Other components

- **User**

## Connections

- User → Streamlit Interface: uses (evidence: `README.md`)
- Streamlit Interface → Text and File Input: offers input (evidence: `app.py`)
- Text and File Input → Document Extraction: extracts text (evidence: `app.py`)
- Document Extraction → Readability Statistics: measures (evidence: `app.py`)
- Document Extraction → Context Retrieval: analyzes text (evidence: `app.py`)
- Curated Samples → Text Loader: loads files (evidence: `rag_pipeline.py`)
- Text Loader → Text Chunking: splits documents (evidence: `rag_pipeline.py`)
- Text Chunking → FAISS Index: indexes chunks (evidence: `rag_pipeline.py`)
- Local Embeddings → FAISS Index: vectorizes documents (evidence: `rag_pipeline.py`)
- FAISS Index → Context Retrieval: searches index (evidence: `rag_pipeline.py`)
- Context Retrieval → Assessment Prompt: supplies context (evidence: `rag_pipeline.py`)
- Assessment Prompt → Gemini LLM: invokes (evidence: `rag_pipeline.py`)
- Gemini LLM → JSON Assessment: returns response (evidence: `rag_pipeline.py`)
- Context Retrieval → JSON Assessment: returns chunks (evidence: `rag_pipeline.py`)
- JSON Assessment → Assessment Results: displays assessment (evidence: `app.py`)
- JSON Assessment → Retrieved Source Trace: displays sources (evidence: `app.py`)
- Readability Statistics → Assessment Results: displays metrics (evidence: `app.py`)
