# karthick-005/multi-doc-qa-chatbot architecture

> Architecture diagram of the GitHub repository karthick-005/multi-doc-qa-chatbot, 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/karthick-005/multi-doc-qa-chatbot
- Repository: https://github.com/karthick-005/multi-doc-qa-chatbot

## Overview

This Flask application ingests documents and URLs, builds per-file vector indexes, and answers questions against a selected index. The browser provides upload, file-management, chat, and context-viewing interfaces; the backend also includes OCR and model-integration capabilities. The backend excerpt is partial, so the graph only connects stages where calls or data handling are visible, or where the README documents the capability. Some UI-to-route wiring is apparent from JavaScript requests, but not every route is shown in the excerpts.

Main entry points: [`app.py`](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py) (Flask application), [`static/upload.js`](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/static/upload.js) (Upload interface), [`static/chat.js`](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/static/chat.js) (Chat interface), [`static/index.js`](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/static/index.js) (File browser)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_ui["Web interface"]
  node_upload_ui["Upload interface<br/>[upload.js]"]
  node_chat_ui["Chat interface<br/>[chat.js]"]
  node_file_ui["File browser<br/>[index.js]"]
end

subgraph group_ingest["Ingestion and indexing"]
  node_document_loader["Document extraction<br/>[app.py]"]
  node_ocr["OCR processing<br/>[app.py]"]
  node_url_loader["URL extraction<br/>[app.py]"]
  node_chunking["Text chunking<br/>[app.py]"]
  node_embeddings["Vector embeddings<br/>[app.py]"]
  node_vector_index[("Vector index<br/>[app.py]")]
end

subgraph group_qa["Question answering"]
  node_retrieval["Context retrieval<br/>[app.py]"]
  node_qa_engine["Answer generation<br/>[app.py]"]
end

node_user(("User"))
node_flask["Flask application<br/>[app.py]"]
node_index_files[("Index files<br/>[app.py]")]
node_mistral{{"Mistral API"}}
node_gemini{{"Gemini API"}}
node_hf_models{{"Hugging Face models"}}

node_user -->|"uploads files"| node_upload_ui
node_user -->|"asks questions"| node_chat_ui
node_upload_ui -->|"submits files"| node_flask
node_upload_ui -->|"submits URLs"| node_flask
node_file_ui -->|"requests file list"| node_flask
node_chat_ui -->|"requests context"| node_flask
node_flask -->|"extracts documents"| node_document_loader
node_document_loader -->|"falls back to OCR"| node_ocr
node_flask -->|"processes URLs"| node_url_loader
node_document_loader -->|"chunks text"| node_chunking
node_flask -->|"chunks URL content"| node_chunking
node_chunking -->|"creates index"| node_embeddings
node_embeddings -->|"builds vectors"| node_vector_index
node_flask -->|"stores index"| node_index_files
node_flask -->|"loads index"| node_vector_index
node_flask -->|"retrieves contexts"| node_retrieval
node_retrieval -->|"provides context"| node_qa_engine
node_qa_engine -->|"generates answer"| node_mistral
node_flask -->|"configures model"| node_gemini
node_flask -->|"creates embeddings"| node_hf_models

click node_upload_ui "https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/static/upload.js"
click node_chat_ui "https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/static/chat.js"
click node_file_ui "https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/static/index.js"
click node_flask "https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py"
click node_document_loader "https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py"
click node_ocr "https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py"
click node_url_loader "https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py"
click node_chunking "https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py"
click node_embeddings "https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py"
click node_vector_index "https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py"
click node_index_files "https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py"
click node_retrieval "https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py"
click node_qa_engine "https://github.com/karthick-005/multi-doc-qa-chatbot/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_upload_ui,node_chat_ui,node_file_ui,node_user toneBlue
class node_document_loader,node_ocr,node_url_loader,node_chunking,node_embeddings,node_vector_index,node_index_files toneAmber
class node_retrieval,node_qa_engine,node_mistral,node_gemini toneMint
class node_flask toneTeal
class node_hf_models toneIndigo
```

## Components

### Web interface

- [Upload interface](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/static/upload.js): `static/upload.js`
- [Chat interface](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/static/chat.js): `static/chat.js`
- [File browser](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/static/index.js): `static/index.js`

### Ingestion and indexing

- [Document extraction](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py): `app.py`
- [OCR processing](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py): `app.py`
- [URL extraction](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py): `app.py`
- [Text chunking](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py): `app.py`
- [Vector embeddings](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py): `app.py`
- [Vector index](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py): `app.py`

### Question answering

- [Context retrieval](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py): `app.py`
- [Answer generation](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py): `app.py`

### Other components

- **User**
- [Flask application](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py): `app.py`
- [Index files](https://github.com/karthick-005/multi-doc-qa-chatbot/blob/main/app.py): `app.py`
- **Mistral API**
- **Gemini API**
- **Hugging Face models**

## Connections

- User → Upload interface: uploads files (evidence: `static/upload.js`)
- User → Chat interface: asks questions (evidence: `static/chat.js`)
- Upload interface → Flask application: submits files (evidence: `static/upload.js`)
- Upload interface → Flask application: submits URLs (evidence: `static/upload.js`)
- File browser → Flask application: requests file list (evidence: `static/index.js`)
- Chat interface → Flask application: requests context (evidence: `static/chat.js`)
- Flask application → Document extraction: extracts documents (evidence: `app.py`)
- Document extraction → OCR processing: falls back to OCR (evidence: `app.py`)
- Flask application → URL extraction: processes URLs (evidence: `app.py`)
- Document extraction → Text chunking: chunks text (evidence: `app.py`)
- Flask application → Text chunking: chunks URL content (evidence: `app.py`)
- Text chunking → Vector embeddings: creates index (evidence: `app.py`)
- Vector embeddings → Vector index: builds vectors (evidence: `app.py`)
- Flask application → Index files: stores index (evidence: `app.py`)
- Flask application → Vector index: loads index (evidence: `app.py`)
- Flask application → Context retrieval: retrieves contexts (evidence: `app.py`)
- Context retrieval → Answer generation: provides context (evidence: `app.py`)
- Answer generation → Mistral API: generates answer (evidence: `app.py`)
- Flask application → Gemini API: configures model (evidence: `app.py`)
- Flask application → Hugging Face models: creates embeddings (evidence: `app.py`)
