https://github.com/developerslearnit/ai-document-processor-rag
The robust, enterprise-grade backend for the AI Document Processor, built with **.NET 10** using **Clean Architecture** principles. This service powers the RAG (Retrieval-Augmented Generation) pipeline, document ingestion, and secure user authentication.
https://github.com/developerslearnit/ai-document-processor-rag
ai-agent ai-backend aspnet-core csharp microsoft-agent-framework openai rag vector-database-embedding vector-search
Last synced: 2 days ago
JSON representation
The robust, enterprise-grade backend for the AI Document Processor, built with **.NET 10** using **Clean Architecture** principles. This service powers the RAG (Retrieval-Augmented Generation) pipeline, document ingestion, and secure user authentication.
- Host: GitHub
- URL: https://github.com/developerslearnit/ai-document-processor-rag
- Owner: developerslearnit
- Created: 2026-04-24T13:40:06.000Z (about 1 month ago)
- Default Branch: master
- Last Pushed: 2026-04-24T13:50:40.000Z (about 1 month ago)
- Last Synced: 2026-04-24T15:44:09.554Z (about 1 month ago)
- Topics: ai-agent, ai-backend, aspnet-core, csharp, microsoft-agent-framework, openai, rag, vector-database-embedding, vector-search
- Language: TypeScript
- Homepage:
- Size: 115 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🧠 DocMind AI: AI Document Intelligence System (RAG) – ASP.NET Core
**Author:** Adesina Mark Omoniyi
A production-grade AI system that allows users to upload documents and interact with them using natural language.
Built with ASP.NET Core and powered by LLM integrations, this system uses Retrieval-Augmented Generation (RAG) to deliver accurate, cost-efficient answers from large documents.
---
---
## 🚀 Core Capabilities
- **Intelligent Ingestion**: Asynchronous processing pipeline that extracts text, chunks content, and generates vector embeddings.
- **Semantic Search**: High-performance vector similarity search using **PostgreSQL (pgvector)**.
- **AI Chat & Grounding**: Natural language Q&A strictly grounded in your document's context using **Azure OpenAI (GPT-4o)**.
- **Premium UX**: A world-class dark mode interface with glassmorphism, fluid animations, and real-time status polling.
- **Secure Architecture**: Multi-tenant isolation with JWT-based authentication and secure cloud storage.
---
## 🏗️ Repository Structure
```bash
AIDocument/
├── backend/ # ASP.NET Core 10 Web API (Clean Architecture)
└── frontend/ # Next.js 15 + Tailwind CSS 4 + Framer Motion
```
### 🔙 [Backend](./backend)
Built with **.NET 10** following **Clean Architecture** principles:
- **Domain**: Pure business logic and entities.
- **Application**: Use cases, DTOs, and service orchestrators.
- **Infrastructure**: Azure OpenAI, Blob Storage, and DB implementations.
- **API**: RESTful controllers and Swagger documentation.
### 🔜 [Frontend](./frontend)
Built with **Next.js 15** for a premium user experience:
- **Design**: Custom CSS + Tailwind CSS 4 with a "World-Class" aesthetic.
- **Animations**: Framer Motion for high-fidelity transitions.
- **State**: Zustand for lightweight global auth and document state.
- **API**: Axios with centralized interceptors for secure communication.
---
## 🛠️ Technology Stack
| Layer | Technology |
| --- | --- |
| **Framework** | .NET 10 & Next.js 15 |
| **AI / LLM** | Azure OpenAI (GPT-4o & Text Embeddings) |
| **Database** | PostgreSQL + pgvector |
| **Storage** | Azure Blob Storage |
| **Styling** | Tailwind CSS 4 & Vanilla CSS |
| **Auth** | JWT (Custom implementation with BCrypt) |
| **Jobs** | Quartz.NET |
---
## 🏃 Getting Started
### 1. Prerequisites
- [.NET 10 SDK](https://dotnet.microsoft.com/download/dotnet/10.0)
- [Node.js 18+](https://nodejs.org/)
- [PostgreSQL](https://www.postgresql.org/) (with pgvector extension)
### 2. Backend Setup
1. Navigate to `backend/AIDocument.Api`.
2. Update `appsettings.json` with your Azure and Database credentials.
3. Apply migrations: `dotnet ef database update`.
4. Run: `dotnet run`.
### 3. Frontend Setup
1. Navigate to `frontend`.
2. Install dependencies: `npm install`.
3. Start the dev server: `npm run dev`.
4. Access at `http://localhost:3000`.
---
## 📄 Documentation
For detailed setup instructions, architecture diagrams, and API documentation, please refer to the individual READMEs:
- [Backend Documentation](./backend/README.md)
- [Frontend Documentation](./frontend/README.md)
---
## 👤 Author
**Adesina Mark Omoniyi**
*Software Engineer & AI Solutions Architect*
---
## 🛡️ License
This project is licensed under the MIT License - see the LICENSE file for details.