┌─────────────────────────────────────────────┐
   REST clients │  FastAPI app (single process, single worker)│
  ──────────────┤                                             │
   X-API-Key    │  RequestContext ─ ApiKey middleware         │
                │        │                                    │
   MCP clients  │   ┌────┴─────┐        ┌──────────────────┐  │
  ──────────────┤   │ /v1/*    │        │ /mcp (FastMCP)   │  │
   (agents)     │   └────┬─────┘        └───────┬──────────┘  │
                │        └───────┬──────────────┘             │
                │                ▼                            │
                │   EmbeddingService · SummarizationService   │
                │        (logging · tracing · limits)         │
                │                ▼                            │
                │        ModelRegistry (+ keep-warm loop)     │
                │      semaphores · lifecycle · lazy loads    │
                │        ▼                      ▼             │
                │  sentence-transformers      Ollama          │
                │  (CUDA / MPS / CPU)     (quantized LLMs)    │
                └─────────────────────────────────────────────┘

git clone <this-repo> && cd ds-ml-mcp-service
python -m venv .venv && source .venv/bin/activate   # Windows: .venv\Scripts\activate
pip install -e ".[embeddings]"

# Ollama powers summarization: https://ollama.com/download
ollama pull llama3.2:3b

cp .env.example .env      # set MLSERVE_API_KEYS to a long random value
mlserve                   # serves on http://127.0.0.1:8000

export KEY="<your api key>"

# Embeddings — single text or batch
curl -s http://127.0.0.1:8000/v1/embeddings \
  -H "X-API-Key: $KEY" -H "Content-Type: application/json" \
  -d '{"input": ["first text", "second text"]}'

# Summarization — instruction-guided
curl -s http://127.0.0.1:8000/v1/summarize \
  -H "X-API-Key: $KEY" -H "Content-Type: application/json" \
  -d '{"text": "<long text>", "instruction": "Three bullet points.", "max_words": 80}'

# Ops
curl -s http://127.0.0.1:8000/health                      # unauthenticated
curl -s -H "X-API-Key: $KEY" http://127.0.0.1:8000/v1/models
curl -s -X POST -H "X-API-Key: $KEY" http://127.0.0.1:8000/v1/models/embed-bge-small/load

{
  "mcpServers": {
    "mlserve": {
      "type": "http",
      "url": "http://127.0.0.1:8000/mcp",
      "headers": { "X-API-Key": "<your api key>" }
    }
  }
}

pip install -e ".[dev]"
pytest                    # fast suite, fake backends, no downloads
pytest -m integration     # real-model tests (downloads MiniLM, ~90 MB)