From 6fbf5a0ccc68920c648e617e67673dc5ba3e9279 Mon Sep 17 00:00:00 2001 From: Rouzbeh81 Date: Mon, 29 Sep 2025 14:57:57 +0200 Subject: [PATCH 1/2] Update README.md --- README.md | 275 +++++++++++++++++++++++++++++------------------------- 1 file changed, 146 insertions(+), 129 deletions(-) diff --git a/README.md b/README.md index d6e729e..608d698 100644 --- a/README.md +++ b/README.md @@ -93,7 +93,7 @@ The beauty of open source? You can have this running on your machine right now: ```bash # Clone the repository -git clone https://github.com/JayRHa/Document-Manager.git +git clone [https://github.com/JayRHa/Document-Manager.git](https://github.com/JayRHa/Document-Manager.git) cd Document-Manager # Run the setup script @@ -102,42 +102,62 @@ cd Document-Manager # Or manually with Docker docker build -t documentmanager . docker run -d \ - --name documentmanager \ - -p 8000:8000 \ - -v $(pwd)/data:/app/data \ - -v $(pwd)/storage:/app/storage \ - documentmanager -``` +  --name documentmanager \ +  -p 8000:8000 \ +  -v $(pwd)/data:/app/data \ +  -v $(pwd)/storage:/app/storage \ +  documentmanager -The application will be available at `http://localhost:8000` + The application will be available at http://localhost:8000 -### Windows Notes +⚠️ Windows Notes (Crucial Fixes) +Op Windows 10/11 moet u Git Bash gebruiken voor de meest betrouwbare installatie. De meegeleverde shell-scripts bevatten line endings die fouten veroorzaken in Linux-containers (exec... no such file or directory error). -- Use `./setup.ps1` instead of `./setup.sh` in PowerShell: +Aanbevolen Installatieprocedure op Windows (Na git clone): -```powershell -./setup.ps1 build -./setup.ps1 prod -``` +Corrigeer de Line Endings in Git Bash: +Repareer de docker-entrypoint.sh en docker-entrypoint-aio.sh scripts: -- Or run locally without Docker: +Bash -```powershell -python -m venv venv -venv\Scripts\Activate -pip install -r requirements.txt -python cli.py serve -``` +# Gebruik sed om de Windows-specifieke carriage return karakters te verwijderen +sed -i 's/\r$//' docker-entrypoint.sh +sed -i 's/\r$//' docker-entrypoint-aio.sh +Pas de SECRET_KEY aan: +De container crasht bij de start als de standaard SECRET_KEY niet is gewijzigd. Open het .env bestand en vervang de placeholder door een veilige, willekeurige waarde: -- OCR tools on Windows: - - Tesseract: `winget install tesseract-ocr` or `choco install tesseract` - - Poppler (for PDF OCR): `choco install poppler` or download binaries and set Settings.poppler_path to the poppler `bin` folder +Code snippet -### 🛠️ Using the Setup Script +# Wijzig dit in het .env bestand: +SECRET_KEY=een_unieke_en_lange_willekeurige_geheime_sleutel +Bouw de Image op een schone manier: +Dit zorgt ervoor dat de gecorrigeerde scripts worden meegenomen in de Docker image: -The `setup.sh` script provides an easy way to manage your DocumentManager installation: +Bash + +# Stop en verwijder eerdere mislukte containers +docker stop documentmanager 2>/dev/null +docker rm documentmanager 2>/dev/null + +# Herbouw de image +docker build -t documentmanager . +Start de Container: + +Bash + +docker run -d \ + --name documentmanager \ + -p 8000:8000 \ + -v $(pwd)/data:/app/data \ + -v $(pwd)/storage:/app/storage \ + documentmanager +Controleer de status met docker ps -f name=documentmanager. De status moet Up (healthy) zijn. + +🛠️ Using the Setup Script +The setup.sh script provides an easy way to manage your DocumentManager installation: + +Bash -```bash # Start development environment with hot reload ./setup.sh dev @@ -155,71 +175,65 @@ The `setup.sh` script provides an easy way to manage your DocumentManager instal # Stop all containers ./setup.sh stop -``` - -### 💻 Local Development +💻 Local Development +Bash -```bash # Create virtual environment python -m venv venv -source venv/bin/activate # On Windows: venv\Scripts\activate +source venv/bin/activate  # On Windows: venv\Scripts\activate # Install dependencies pip install -r requirements.txt # Run development server uvicorn app.main:app --reload --host 0.0.0.0 --port 8000 -``` - -## 📋 Initial Setup - -1. **Create Admin Account** - - Navigate to `http://localhost:8000` - - The first user registration automatically becomes admin - -2. **Configure AI Provider** - - Go to Settings → AI Configuration - - Choose between OpenAI or Azure OpenAI - - Enter your API credentials - - Test the connection - -3. **Start Using** - - Upload documents via drag-and-drop - - Watch AI automatically extract text, generate summaries, and categorize - - AI detects: Title, Summary, Correspondent, Document Type, Document Date, Tags, and Tax Relevance - - Use semantic search to find information instantly with natural language +📋 Initial Setup +Create Admin Account +   - Navigate to http://localhost:8000 +   - The first user registration automatically becomes admin + +Configure AI Provider +   - Go to Settings → AI Configuration +   - Choose between OpenAI or Azure OpenAI +   - Enter your API credentials +   - Test the connection + +Start Using +   - Upload documents via drag-and-drop +   - Watch AI automatically extract text, generate summaries, and categorize +   - AI detects: Title, Summary, Correspondent, Document Type, Document Date, Tags, and Tax Relevance +   - Use semantic search to find information instantly with natural language + +🏗️ Architecture +DocumentManager/ +├── app/                    # Backend FastAPI application +│   ├── api/               # REST API endpoints +│   ├── core/              # Core business logic +│   ├── models/            # SQLAlchemy models +│   └── services/          # AI, OCR, and storage services +├── frontend/              # Vanilla JS frontend +├── docker/                # Docker configuration +├── tests/                 # Test suite +└── docs/                  # Documentation +Technology Stack +Backend: FastAPI, SQLAlchemy, Pydantic -## 🏗️ Architecture +AI/ML: OpenAI GPT-4, Azure OpenAI, ChromaDB -``` -DocumentManager/ -├── app/ # Backend FastAPI application -│ ├── api/ # REST API endpoints -│ ├── core/ # Core business logic -│ ├── models/ # SQLAlchemy models -│ └── services/ # AI, OCR, and storage services -├── frontend/ # Vanilla JS frontend -├── docker/ # Docker configuration -├── tests/ # Test suite -└── docs/ # Documentation -``` +OCR: Tesseract (50+ languages) -### Technology Stack +Database: SQLite (default), PostgreSQL (production) -- **Backend**: FastAPI, SQLAlchemy, Pydantic -- **AI/ML**: OpenAI GPT-4, Azure OpenAI, ChromaDB -- **OCR**: Tesseract (50+ languages) -- **Database**: SQLite (default), PostgreSQL (production) -- **Frontend**: Vanilla JavaScript, modern CSS -- **Deployment**: Docker, Docker Compose +Frontend: Vanilla JavaScript, modern CSS -## 🔧 Configuration +Deployment: Docker, Docker Compose -### Environment Variables +🔧 Configuration +Environment Variables +Create a .env file in the root directory: -Create a `.env` file in the root directory: +Bash -```bash # Security - CHANGE IN PRODUCTION! SECRET_KEY=your-secret-key-here @@ -232,30 +246,29 @@ AI_PROVIDER=openai OPENAI_API_KEY=sk-... # Or for Azure: # AI_PROVIDER=azure -# AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com +# AZURE_OPENAI_ENDPOINT=[https://your-resource.openai.azure.com](https://your-resource.openai.azure.com) # AZURE_OPENAI_KEY=your-key # Application Settings ENVIRONMENT=production LOG_LEVEL=INFO -MAX_UPLOAD_SIZE=104857600 # 100MB +MAX_UPLOAD_SIZE=104857600  # 100MB ALLOWED_EXTENSIONS=pdf,jpg,jpeg,png,txt,doc,docx # Storage STORAGE_TYPE=local STORAGE_PATH=/app/data/storage -``` +📚 API Documentation +Interactive API Docs +Once running, access the interactive API documentation at: -## 📚 API Documentation +Swagger UI: http://localhost:8000/docs -### Interactive API Docs -Once running, access the interactive API documentation at: -- Swagger UI: `http://localhost:8000/docs` -- ReDoc: `http://localhost:8000/redoc` +ReDoc: http://localhost:8000/redoc -### Quick API Examples +Quick API Examples +Python -```python import requests # Base URL @@ -263,70 +276,78 @@ BASE_URL = "http://localhost:8000" # 1. Authentication response = requests.post(f"{BASE_URL}/api/auth/login", json={ - "username": "admin", - "password": "your-password" +    "username": "admin", +    "password": "your-password" }) session = requests.Session() session.cookies = response.cookies # 2. Upload Document with open("document.pdf", "rb") as f: - response = session.post( - f"{BASE_URL}/api/documents/upload", - files={"file": f}, - data={"title": "Q4 Report", "tags": "finance,quarterly"} - ) - document_id = response.json()["id"] +    response = session.post( +        f"{BASE_URL}/api/documents/upload", +        files={"file": f}, +        data={"title": "Q4 Report", "tags": "finance,quarterly"} +    ) +    document_id = response.json()["id"] # 3. Semantic Search response = session.get(f"{BASE_URL}/api/search/semantic", params={ - "query": "What were the Q4 revenue numbers?", - "limit": 5 +    "query": "What were the Q4 revenue numbers?", +    "limit": 5 }) results = response.json() # 4. Ask Questions response = session.post(f"{BASE_URL}/api/ai/ask", json={ - "question": "Summarize the key findings from Q4 reports", - "document_ids": [document_id] +    "question": "Summarize the key findings from Q4 reports", +    "document_ids": [document_id] }) answer = response.json()["answer"] -``` +🌟 Why Open Source? +Your document management system shouldn't be a black box. With DocumentManager you can: -## 🌟 Why Open Source? +Audit the code - Know exactly what happens to your documents -Your document management system shouldn't be a black box. With DocumentManager you can: -- **Audit the code** - Know exactly what happens to your documents -- **Customize for your needs** - Modify anything to fit your workflow -- **Self-host everything** - Your documents, your rules -- **Contribute improvements** - Join the community making document management better +Customize for your needs - Modify anything to fit your workflow -No vendor lock-in. Complete transparency. Total control. +Self-host everything - Your documents, your rules + +Contribute improvements - Join the community making document management better -## 🚀 Roadmap +No vendor lock-in. Complete transparency. Total control. +🚀 Roadmap The foundation is solid, but we're just getting started: -- **Self-hosted AI models** - Run everything locally -- **Mobile apps** - For on-the-go access and document scanning -- **Workflow automation** - Documents that route themselves -- **Advanced analytics** - Insights from your document repository -- **Plugin system** - Custom integrations for your needs -## 🤝 Contributing +Self-hosted AI models - Run everything locally -We love contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details. +Mobile apps - For on-the-go access and document scanning -1. Fork the repository -2. Create your feature branch (`git checkout -b feature/AmazingFeature`) -3. Commit your changes (`git commit -m 'Add some AmazingFeature'`) -4. Push to the branch (`git push origin feature/AmazingFeature`) -5. Open a Pull Request +Workflow automation - Documents that route themselves -### Development Setup +Advanced analytics - Insights from your document repository + +Plugin system - Custom integrations for your needs + +🤝 Contributing +We love contributions! Please see our Contributing Guide for details. + +Fork the repository + +Create your feature branch (git checkout -b feature/AmazingFeature) + +Commit your changes (git commit -m 'Add some AmazingFeature') + +Push to the branch (git push origin feature/AmazingFeature) + +Open a Pull Request + +Development Setup +Bash -```bash # Clone your fork -git clone https://github.com/JayRHa/Document-Manager.git +git clone [https://github.com/JayRHa/Document-Manager.git](https://github.com/JayRHa/Document-Manager.git) cd Document-Manager # Create branch @@ -335,18 +356,14 @@ git checkout -b feature/your-feature # Install pre-commit hooks pip install pre-commit pre-commit install -``` - -## 📄 License - -This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details. - ---- +📄 License +This project is licensed under the MIT License - see the LICENSE file for details.
Built with ❤️ by Jannik Reinhard and Fabian Peschke ⭐ Star the repo if you find it useful — it really helps with motivation! -☕ If you want to support the project, you can [buy us a coffee](https://www.buymeacoffee.com/your-link) +☕ If you want to support the project, you can buy us a coffee +
From 8930b6c7d42b1f02978fccedba52ec120a573b48 Mon Sep 17 00:00:00 2001 From: Rouzbeh81 Date: Mon, 29 Sep 2025 15:01:03 +0200 Subject: [PATCH 2/2] Update README.md --- README.md | 467 ++++++++++++++++++++++++++---------------------------- 1 file changed, 225 insertions(+), 242 deletions(-) diff --git a/README.md b/README.md index 608d698..f45d89a 100644 --- a/README.md +++ b/README.md @@ -1,99 +1,91 @@ -# 📄 DocumentManager - +

📄 DocumentManager

- -![Python](https://img.shields.io/badge/Python-3.12+-blue.svg?style=for-the-badge&logo=python) -![FastAPI](https://img.shields.io/badge/FastAPI-0.111+-00a393.svg?style=for-the-badge&logo=fastapi) -![Docker](https://img.shields.io/badge/Docker-Ready-2496ED.svg?style=for-the-badge&logo=docker) -![License](https://img.shields.io/badge/License-MIT-yellow.svg?style=for-the-badge) - -**Transform your document chaos into an AI-powered knowledge powerhouse** - -*Most document management systems feel like they're stuck in 2005. DocumentManager brings AI intelligence to understand your documents' actual content and meaning - not just their titles or tags.* - -[Features](#-features) • [Quick Start](#-quick-start) • [Demo](#-demo) • [Documentation](#-documentation) • [API](#-api) • [Contributing](#-contributing) - +

+ Python + FastAPI + Docker + License +

+

Transform your document chaos into an AI-powered knowledge powerhouse

+

Most document management systems feel like they're stuck in 2005. DocumentManager brings AI intelligence to understand your documents' actual content and meaning - not just their titles or tags.

+

+ Features • + Quick Start • + Demo • + Documentation • + API • + Contributing +

- ---- - -## 🌟 Features - -### 🤖 AI-Powered Intelligence -- **Semantic Search**: Find documents by meaning, not just keywords. Search for "payment terms" and find invoicing documents, contracts with payment clauses, and financial agreements - even if they never use those exact words -- **Smart OCR**: Extract text from scanned PDFs, photos of whiteboards, and documents in 50+ languages using Tesseract OCR -- **Auto-Tagging**: AI automatically categorizes documents based on content - financial reports get tagged as "finance", contracts as "legal", technical specs as "engineering" -- **Natural Language Queries**: Just ask questions like "Show me all contracts expiring this year" or "What were our Q4 marketing expenses?" -- **AI-Generated Summaries**: Understand large documents at a glance with automatic summary generation - -### 🔒 Enterprise-Ready Security -- **Role-Based Access Control**: Fine-grained permissions for users and groups -- **Complete Audit Trails**: Track all document activities -- **Privacy First**: Option to use Azure OpenAI to keep models in your own tenant -- **Self-Hosted**: All data stays on your infrastructure - no vendor lock-in -- **Session Management**: Secure session handling with automatic expiry - -### 🚀 Modern Architecture -- **RESTful API**: Complete OpenAPI 3.0 documented API built with FastAPI -- **Vector Database**: ChromaDB for lightning-fast semantic search using embeddings -- **Flexible AI**: Choose between OpenAI or Azure OpenAI (your choice) -- **Simple Frontend**: Vanilla JavaScript keeping it simple and fast -- **Docker-Ready**: Deploy in minutes with included setup script - -## 📸 Demo - +
+ +

🌟 Features

+

🤖 AI-Powered Intelligence

+ +

🔒 Enterprise-Ready Security

+ +

🚀 Modern Architecture

+ + +

📸 Demo

- -### Dashboard Overview -![Dashboard](images/dashboard-overview.png) -*Clean, intuitive dashboard showing document statistics and recent activities* - -### AI-Powered Search -![AI Search](images/ai-search.jpeg) -*Find documents by meaning, not just keywords - ask questions in natural language* - -### AI Chat -![AI Chat](images/ai-chat.png) -*Interactive AI chat for document analysis and knowledge extraction* - -### Document Upload & Processing -![Document Upload](images/document-upload.jpeg) -*Drag-and-drop interface with automatic text extraction and AI tagging* - -### Smart Tags & Organization -![Tags Management](images/tags.png) -*AI auto-generates correspondents, document types, and tags - fully customizable with color coding* - -### Document Viewer -![Document Viewer](images/document-viewer.png) -*Built-in document viewer with search highlighting and annotations* - -### User Management -![User Management](images/user-management.jpeg) -*Enterprise-grade user and permission management* - -### Settings & Configuration -![Settings](images/settings-page.jpeg) -*Easy configuration of AI providers and system settings* - +

Dashboard Overview

+ Dashboard +

Clean, intuitive dashboard showing document statistics and recent activities

+ + AI Search +

Find documents by meaning, not just keywords - ask questions in natural language

+

AI Chat

+ AI Chat +

Interactive AI chat for document analysis and knowledge extraction

+

Document Upload & Processing

+ Document Upload +

Drag-and-drop interface with automatic text extraction and AI tagging

+

Smart Tags & Organization

+ Tags Management +

AI auto-generates correspondents, document types, and tags - fully customizable with color coding

+

Document Viewer

+ Document Viewer +

Built-in document viewer with search highlighting and annotations

+

User Management

+ User Management +

Enterprise-grade user and permission management

+

Settings & Configuration

+ Settings +

Easy configuration of AI providers and system settings

-## 🚀 Quick Start - -### Getting Started in 3 Minutes - -The beauty of open source? You can have this running on your machine right now: - -### Prerequisites -- Docker installed and running -- 4GB+ RAM recommended -- 10GB+ free disk space - -### 🐳 Using Docker (Recommended) - -```bash -# Clone the repository -git clone [https://github.com/JayRHa/Document-Manager.git](https://github.com/JayRHa/Document-Manager.git) +

🚀 Quick Start

+

Getting Started in 3 Minutes

+

The beauty of open source? You can have this running on your machine right now:

+

Prerequisites

+ + +

🐳 Using Docker (Recommended)

+
# Clone the repository
+git clone https://github.com/JayRHa/Document-Manager.git
 cd Document-Manager
 
 # Run the setup script
@@ -107,58 +99,51 @@ docker run -d \
   -v $(pwd)/data:/app/data \
   -v $(pwd)/storage:/app/storage \
   documentmanager
-
-  The application will be available at http://localhost:8000
-
-⚠️ Windows Notes (Crucial Fixes)
-Op Windows 10/11 moet u Git Bash gebruiken voor de meest betrouwbare installatie. De meegeleverde shell-scripts bevatten line endings die fouten veroorzaken in Linux-containers (exec... no such file or directory error).
-
-Aanbevolen Installatieprocedure op Windows (Na git clone):
-
-Corrigeer de Line Endings in Git Bash:
-Repareer de docker-entrypoint.sh en docker-entrypoint-aio.sh scripts:
-
-Bash
-
-# Gebruik sed om de Windows-specifieke carriage return karakters te verwijderen
+
+

The application will be available at http://localhost:8000

+ +

⚠️ Windows Notes (Crucial Fixes)

+

Op Windows 10/11 moet u **Git Bash** gebruiken voor de meest betrouwbare installatie. De meegeleverde shell-scripts bevatten line endings die fouten veroorzaken in Linux-containers (exec... no such file or directory error).

+

Aanbevolen Installatieprocedure op Windows (Na git clone):

+
    +

  1. Corrigeer de Line Endings in Git Bash:
    + Repareer de docker-entrypoint.sh en docker-entrypoint-aio.sh scripts:

    + 
    # Gebruik sed om de Windows-specifieke carriage return karakters te verwijderen
 sed -i 's/\r$//' docker-entrypoint.sh
 sed -i 's/\r$//' docker-entrypoint-aio.sh
-Pas de SECRET_KEY aan:
-De container crasht bij de start als de standaard SECRET_KEY niet is gewijzigd. Open het .env bestand en vervang de placeholder door een veilige, willekeurige waarde:
-
-Code snippet
-
-# Wijzig dit in het .env bestand:
+
    +
    2. +

  2. Pas de SECRET_KEY aan:
    + De container crasht bij de start als de standaard SECRET_KEY niet is gewijzigd. Open het .env bestand en vervang de placeholder door een veilige, willekeurige waarde:

    + 
    # Wijzig dit in het .env bestand:
 SECRET_KEY=een_unieke_en_lange_willekeurige_geheime_sleutel
-Bouw de Image op een schone manier:
-Dit zorgt ervoor dat de gecorrigeerde scripts worden meegenomen in de Docker image:
-
-Bash
-
-# Stop en verwijder eerdere mislukte containers
+
    +
    3. +

  3. Bouw de Image op een schone manier:
    + Dit zorgt ervoor dat de gecorrigeerde scripts worden meegenomen in de Docker image:

    + 
    # Stop en verwijder eerdere mislukte containers
 docker stop documentmanager 2>/dev/null
 docker rm documentmanager 2>/dev/null
 
 # Herbouw de image
 docker build -t documentmanager .
-Start de Container:
-
-Bash
-
-docker run -d \
-  --name documentmanager \
-  -p 8000:8000 \
-  -v $(pwd)/data:/app/data \
-  -v $(pwd)/storage:/app/storage \
-  documentmanager
-Controleer de status met docker ps -f name=documentmanager. De status moet Up (healthy) zijn.
-
-🛠️ Using the Setup Script
-The setup.sh script provides an easy way to manage your DocumentManager installation:
-
-Bash
-
-# Start development environment with hot reload
+
    +
    4. +

  4. Start de Container:

    + 
    docker run -d \
+  --name documentmanager \
+  -p 8000:8000 \
+  -v $(pwd)/data:/app/data \
+  -v $(pwd)/storage:/app/storage \
+  documentmanager
+
    +

    Controleer de status met docker ps -f name=documentmanager. De status moet Up (healthy) zijn.

    +
    5. +
+ +

🛠️ Using the Setup Script

+

The setup.sh script provides an easy way to manage your DocumentManager installation:

+
# Start development environment with hot reload
 ./setup.sh dev
 
 # Start production environment
@@ -175,10 +160,10 @@ Bash
 
 # Stop all containers
 ./setup.sh stop
-💻 Local Development
-Bash
+
-# Create virtual environment +

💻 Local Development

+
# Create virtual environment
 python -m venv venv
 source venv/bin/activate  # On Windows: venv\Scripts\activate
 
@@ -187,25 +172,36 @@ pip install -r requirements.txt
 
 # Run development server
 uvicorn app.main:app --reload --host 0.0.0.0 --port 8000
-📋 Initial Setup
-Create Admin Account
-   - Navigate to http://localhost:8000
-   - The first user registration automatically becomes admin
-
-Configure AI Provider
-   - Go to Settings → AI Configuration
-   - Choose between OpenAI or Azure OpenAI
-   - Enter your API credentials
-   - Test the connection
-
-Start Using
-   - Upload documents via drag-and-drop
-   - Watch AI automatically extract text, generate summaries, and categorize
-   - AI detects: Title, Summary, Correspondent, Document Type, Document Date, Tags, and Tax Relevance
-   - Use semantic search to find information instantly with natural language
-
-🏗️ Architecture
-DocumentManager/
+
+ +

📋 Initial Setup

+
    +
  1. Create Admin Account +
      +
    • Navigate to http://localhost:8000
      • +
    • The first user registration automatically becomes admin
      • +
    +
    2. +
  2. Configure AI Provider +
      +
    • Go to Settings → AI Configuration
      • +
    • Choose between OpenAI or Azure OpenAI
      • +
    • Enter your API credentials
      • +
    • Test the connection
      • +
    +
    3. +
  3. Start Using +
      +
    • Upload documents via drag-and-drop
      • +
    • Watch AI automatically extract text, generate summaries, and categorize
      • +
    • AI detects: Title, Summary, Correspondent, Document Type, Document Date, Tags, and Tax Relevance
      • +
    • Use semantic search to find information instantly with natural language
      • +
    +
    4. +
+ +

🏗️ Architecture

+
DocumentManager/
 ├── app/                    # Backend FastAPI application
 │   ├── api/               # REST API endpoints
 │   ├── core/              # Core business logic
@@ -215,26 +211,22 @@ DocumentManager/
 ├── docker/                # Docker configuration
 ├── tests/                 # Test suite
 └── docs/                  # Documentation
-Technology Stack
-Backend: FastAPI, SQLAlchemy, Pydantic
-
-AI/ML: OpenAI GPT-4, Azure OpenAI, ChromaDB
-
-OCR: Tesseract (50+ languages)
-
-Database: SQLite (default), PostgreSQL (production)
-
-Frontend: Vanilla JavaScript, modern CSS
-
-Deployment: Docker, Docker Compose
-
-🔧 Configuration
-Environment Variables
-Create a .env file in the root directory:
-
-Bash
-
-# Security - CHANGE IN PRODUCTION!
+
+ +

Technology Stack

+ + +

🔧 Configuration

+

Environment Variables

+

Create a .env file in the root directory:

+
# Security - CHANGE IN PRODUCTION!
 SECRET_KEY=your-secret-key-here
 
 # Database
@@ -246,7 +238,7 @@ AI_PROVIDER=openai
 OPENAI_API_KEY=sk-...
 # Or for Azure:
 # AI_PROVIDER=azure
-# AZURE_OPENAI_ENDPOINT=[https://your-resource.openai.azure.com](https://your-resource.openai.azure.com)
+# AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com
 # AZURE_OPENAI_KEY=your-key
 
 # Application Settings
@@ -258,18 +250,18 @@ ALLOWED_EXTENSIONS=pdf,jpg,jpeg,png,txt,doc,docx
 # Storage
 STORAGE_TYPE=local
 STORAGE_PATH=/app/data/storage
-📚 API Documentation
-Interactive API Docs
-Once running, access the interactive API documentation at:
+
-Swagger UI: http://localhost:8000/docs +

📚 API Documentation

+

Interactive API Docs

+

Once running, access the interactive API documentation at:

+ -ReDoc: http://localhost:8000/redoc - -Quick API Examples -Python - -import requests +

Quick API Examples

+
import requests
 
 # Base URL
 BASE_URL = "http://localhost:8000"
@@ -292,62 +284,53 @@ with open("document.pdf", "rb") as f:
     document_id = response.json()["id"]
 
 # 3. Semantic Search
-response = session.get(f"{BASE_URL}/api/search/semantic", params={
+response = requests.get(f"{BASE_URL}/api/search/semantic", params={
     "query": "What were the Q4 revenue numbers?",
     "limit": 5
 })
 results = response.json()
 
 # 4. Ask Questions
-response = session.post(f"{BASE_URL}/api/ai/ask", json={
+response = requests.post(f"{BASE_URL}/api/ai/ask", json={
     "question": "Summarize the key findings from Q4 reports",
     "document_ids": [document_id]
 })
 answer = response.json()["answer"]
-🌟 Why Open Source?
-Your document management system shouldn't be a black box. With DocumentManager you can:
-
-Audit the code - Know exactly what happens to your documents
-
-Customize for your needs - Modify anything to fit your workflow
-
-Self-host everything - Your documents, your rules
-
-Contribute improvements - Join the community making document management better
-
-No vendor lock-in. Complete transparency. Total control.
-
-🚀 Roadmap
-The foundation is solid, but we're just getting started:
-
-Self-hosted AI models - Run everything locally
-
-Mobile apps - For on-the-go access and document scanning
-
-Workflow automation - Documents that route themselves
-
-Advanced analytics - Insights from your document repository
-
-Plugin system - Custom integrations for your needs
-
-🤝 Contributing
-We love contributions! Please see our Contributing Guide for details.
-
-Fork the repository
-
-Create your feature branch (git checkout -b feature/AmazingFeature)
-
-Commit your changes (git commit -m 'Add some AmazingFeature')
-
-Push to the branch (git push origin feature/AmazingFeature)
-
-Open a Pull Request
-
-Development Setup
-Bash
-
-# Clone your fork
-git clone [https://github.com/JayRHa/Document-Manager.git](https://github.com/JayRHa/Document-Manager.git)
+
+ +

🌟 Why Open Source?

+

Your document management system shouldn't be a black box. With DocumentManager you can:

+ +

No vendor lock-in. Complete transparency. Total control.

+ +

🚀 Roadmap

+

The foundation is solid, but we're just getting started:

+ + +

🤝 Contributing

+

We love contributions! Please see our Contributing Guide for details.

+
    +
  1. Fork the repository
    2. +
  2. Create your feature branch (git checkout -b feature/AmazingFeature)
    3. +
  3. Commit your changes (git commit -m 'Add some AmazingFeature')
    4. +
  4. Push to the branch (git push origin feature/AmazingFeature)
    5. +
  5. Open a Pull Request
    6. +
+ +

Development Setup

+
# Clone your fork
+git clone https://github.com/JayRHa/Document-Manager.git
 cd Document-Manager
 
 # Create branch
@@ -356,14 +339,14 @@ git checkout -b feature/your-feature
 # Install pre-commit hooks
 pip install pre-commit
 pre-commit install
-📄 License
-This project is licensed under the MIT License - see the LICENSE file for details.
-
-

-Built with ❤️ by Jannik Reinhard and Fabian Peschke
+
-⭐ Star the repo if you find it useful — it really helps with motivation! - -☕ If you want to support the project, you can buy us a coffee +

📄 License

+

This project is licensed under the MIT License - see the LICENSE file for details.

+
+
+

Built with ❤️ by Jannik Reinhard and Fabian Peschke

+

⭐ Star the repo if you find it useful — it really helps with motivation!

+

☕ If you want to support the project, you can buy us a coffee