User query (via MCP client e.g. Cursor, Claude Desktop)
          │
          ▼
  ┌───────────────────┐
  │   MCP Server      │  server.py
  │  ask_ml_knowledge │
  └────────┬──────────┘
           │
           ▼
  ┌───────────────────┐
  │  Embed query      │  nomic-embed-text-v1.5
  └────────┬──────────┘
           │
           ▼
  ┌───────────────────┐
  │  Search Qdrant    │  cosine similarity
  └────────┬──────────┘
           │
     score >= 0.45?
      /           \
    YES            NO
     │              │
     ▼              ▼
  RAG context   Bright Data
  (local KB)    web search
     │              │
     └──────┬───────┘
            ▼
   ┌─────────────────┐
   │  LLM generates  │  OpenAI / local model
   │  grounded answer│
   └────────┬────────┘
            ▼
   Answer + numbered sources

mcp-agentic-rag/
├── data/                        # Knowledge base documents
│   ├── machine_learning.txt
│   ├── deep_learning.txt
│   ├── neural_networks.txt
│   ├── cnn.txt
│   ├── rnn.txt
│   ├── transformers.txt
│   ├── optimization.txt
│   └── regularization.txt
├── eval/
│   └── eval_retrieval.py        # Recall@3 evaluation (30 questions)
├── rag_code.py                  # EmbedData, QdrantVDB, Retriever, AnswerGenerator
├── ingest.py                    # One-time ingestion script
├── server.py                    # MCP server entry point
├── docker-compose.yml           # Qdrant vector database
├── requirements.txt
├── .env.example                 # Copy to .env and fill in credentials
└── notebook.ipynb               # Interactive exploration notebook

pip install -r requirements.txt

cp .env.example .env

docker compose up -d

python ingest.py

python ingest.py --reset

{
  "mcpServers": {
    "mcp-agentic-rag": {
      "command": "python",
      "args": ["/absolute/path/to/server.py"]
    }
  }
}

ollama pull llama3.2

OPENAI_BASE_URL=http://localhost:11434/v1
OPENAI_API_KEY=ollama
OPENAI_MODEL=llama3.2

python eval/eval_retrieval.py

python eval/eval_retrieval.py --output eval/results.json

============================================================
  Results Summary
============================================================
  Total questions : 30
  Correct (hit)   : 26
  Missed          : 4
  Recall@3        : 26/30 = 86.7%
============================================================

TITLE: Your Document Title
SOURCE: your_file.txt
URL: https://optional-reference-url.com

---

First chunk of text goes here.

---

Second chunk of text goes here.

python ingest.py --reset