A .NET 9 real-time, file-driven RAG (Retrieval-Augmented Generation) engine that watches a folder, ingests documents, and serves fast answers over an HTTP API (with Qdrant vector search).

Click to watch the demo video

• Real-time ingestion: watches a folder and keeps your index up to date
• Formats: .pdf, .docx, .txt, .md, .html, .png, .jpg, .jpeg, .webp
• Providers: OpenAI / Azure OpenAI / Anthropic / Ollama (local)
• Vector store: Qdrant
• API: /api/query, /api/documents, /api/health
• Example UI: mock company landing page + popup help chat (examples/HelpChat)

• Tutorial 1: Local dev (recommended): Ollama + Qdrant + dotnet run (fastest to try)
• Tutorial 2: HelpChat demo UI: run a static page that calls your local API
• Tutorial 3: Docker deploy: docker-compose up -d (self-contained stack)
• Tutorial 4: Testing: fast vs integration tests
• Tutorial 5: Production tips: hardening checklist

This uses the defaults in src/DNFileRAG/appsettings.Development.json:

• API on http://localhost:8181
• ApiSecurity:RequireApiKey = false (no key needed)
• Embeddings + LLM via Ollama
• Qdrant vector size 1024 (matches mxbai-embed-large)

docker run -p 6333:6333 -p 6334:6334 qdrant/qdrant

ollama pull mxbai-embed-large
ollama pull llama3.2:3b
ollama pull llava

Images: Vision extraction is enabled by default in Development via Vision:Enabled=true and uses the Ollama model llava (configurable).

dotnet run --project ./src/DNFileRAG

Put files into:

• src/DNFileRAG/data/documents/

If you want to watch a different folder, change FileWatcher:WatchPath in:

• src/DNFileRAG/appsettings.Development.json

curl http://localhost:8181/api/documents

• cURL

curl -X POST http://localhost:8181/api/query \
  -H "Content-Type: application/json" \
  -d "{\"query\":\"What are our support hours?\"}"

• PowerShell

Invoke-RestMethod http://localhost:8181/api/query -Method Post -ContentType "application/json" -Body (@{ query = "What are our support hours?" } | ConvertTo-Json)

HelpChat is a static mock company page under examples/HelpChat/ that opens a popup chat and calls your local DNFileRAG API.

Follow Tutorial 1 so the API is running at http://localhost:8181.

cd examples/HelpChat
python -m http.server 3000

Open http://localhost:3000 and click Help.

You can open examples/HelpChat/index.html directly, but some browsers restrict file:// pages from calling http://localhost.

This uses docker-compose.yml to run:

• Qdrant
• Ollama
• DNFileRAG API on http://localhost:8080

docker-compose up -d

Files in ./documents are mounted into the container at /app/data/documents:

mkdir -p documents
cp /path/to/your/files/* documents/

curl -X POST http://localhost:8080/api/query \
  -H "Content-Type: application/json" \
  -d '{"query":"What are our support hours?"}'

docker-compose down
docker-compose down -v   # also removes Qdrant + Ollama volumes

• Windows (PowerShell)

dotnet test .\DNFileRAG.sln -c Release --filter "Category!=Integration"

• macOS/Linux (bash/zsh)

dotnet test ./DNFileRAG.sln -c Release --filter "Category!=Integration"

Integration tests may start Docker containers (Testcontainers) and will run slower.

• Windows (PowerShell)

dotnet test .\DNFileRAG.sln -c Release

• macOS/Linux (bash/zsh)

dotnet test ./DNFileRAG.sln -c Release

Tests use FluentAssertions. If you plan commercial use, you may need a commercial license (see the warning emitted during test runs).

• Enable API keys: set ApiSecurity:RequireApiKey = true and configure ApiSecurity:ApiKeys.
• Run behind HTTPS: terminate TLS at a reverse proxy (or configure Kestrel HTTPS). Ensure forwarded headers are configured if applicable.
• CORS: lock down origins (avoid AllowAnyOrigin() for production).

• Persist Qdrant: store Qdrant data on durable storage (volumes/backups).
• Health checks: use /api/health and /api/health/detailed for monitoring.
• Resource sizing: embeddings + parsing can be CPU/RAM heavy; size accordingly.

• Vector size must match your embedding model (e.g., mxbai-embed-large → 1024).
• Tune chunking: Chunking:ChunkSize and Chunking:ChunkOverlap.
• Tune retrieval: Rag:DefaultTopK and Rag:MinRelevanceScore.

• Logging: keep Production log levels at Info/Warn (Debug is noisy).
• Documents path: ensure your FileWatcher:WatchPath points to the mounted directory in your environment.

dotnet add package DNFileRAG.Infrastructure

Then register services:

using DNFileRAG;

var builder = WebApplication.CreateBuilder(args);
builder.Services.AddDNFileRAGServices(builder.Configuration);

DNFileRAG/
├── src/
│   ├── DNFileRAG/                 # Web API host
│   ├── DNFileRAG.Core/            # Domain models & interfaces
│   └── DNFileRAG.Infrastructure/  # External service implementations
├── tests/
│   └── DNFileRAG.Tests/           # Test suite
└── examples/
    └── HelpChat/                  # Mock landing page + popup support chat

Contributions are welcome! Please see CONTRIBUTING.md for guidelines.

MIT License — see LICENSE.

• Qdrant - Vector database
• Serilog - Structured logging
• PdfPig - PDF parsing
• DocumentFormat.OpenXml - DOCX parsing