model-deployment
/model-deployment
Wdraża wytrenowany model w produkcji: bezpieczne ładowanie potoku, usługę predykcji w FastAPI, obraz Docker, monitoring dryfu i eksport ONNX.
- Autor
- Harrypatria ↗
- Repozytorium
- data-mining-ml ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 31.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 2
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 31.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Wdraża wytrenowany model w produkcji: bezpieczne ładowanie potoku, usługę predykcji w FastAPI, obraz Docker, monitoring dryfu i eksport ONNX.
Oryginalny opis (EN)
Model Deployment. Serve a trained model in production - load a pickled pipeline safely, FastAPI prediction service (predict, batch, what-if, SHAP explanations, LLM narrative), Pydantic validation from schema.json, Docker multi-stage image, docker-compose with nginx, health checks, API keys, CORS, rate limits, JSON logging, Prometheus metrics, drift monitoring (PSI, KS), batch scoring, ONNX or PMML export and air-gapped installs. Use for deploy, serve, productionize, REST API, MLOps, model serving, monitoring or containerizing a model.
Jak działa
- Steps
- Endpoints
- Engineering rules
Podgląd SKILL.md
--- name: model-deployment description: Model Deployment. Serve a trained model in production - load a pickled pipeline safely, FastAPI prediction service (predict, batch, what-if, SHAP explanations, LLM narrative), Pydantic validation from schema.json, Docker multi-stage image, docker-compose with nginx, health checks, API keys, CORS, rate limits, JSON logging, Prometheus metrics, drift monitoring (PSI, KS), batch scoring, ONNX or PMML export and air-gapped installs. Use for deploy, serve, productionize, REST API, MLOps, model serving, monitoring or containerizing a model. --- # Model Deployment Scaffold: `templates/ml-service/` (becomes `api/` via `bin/data-mining-ml init`). The pickled pipeline from model-training is the model of record. ## Steps 1. Verify the bundle: `bin/data-mining-ml verify-model models/<version>`. 2. Copy the scaffold, install `src/<package>` into the image, pin `api/requirements.txt` to `metadata.json` `libraries`. 3. Run tests: `cd api && pytest` (schema validation, predict, what-if additivity, explanations, narrative with the provider mocked, grounding, security limits, tamper detection). 4. Run locally: `uvicorn app.main:create_app --factory --port 8000` with `MODEL_DIR=../models APP_ENV=development`. 5. Build and run: `docker compose up --build` (API plus nginx serving the React app; nginx injects the API key). 6. Wire monitoring: scrape `/metrics`; alert on `feature_drift_psi` above 0.2, rising `input_range_violations_total`, and explainer fallbacks. ## Endpoints | Route | Purpose | |---|---| | `GET /health/live`, `GET /health/ready` | Liveness; readiness means loaded and verified | | `GET /v1/model`, `GET /v1/schema` | Version, metrics with intervals, threshold, limits; predictor definitions for the UI | | `POST /v1/predict`, `POST /v1/predict/batch` | Probability or value, label at the stored threshold, version, request id, extrapolation flags | | `POST /v1/whatif` | Baseline versus scenario, delta, contributions for both | | `POST /v1/explain/local`, `POST /v1/explain/counterfactuals` | Shapley contributions; smallest threshold-crossing changes | | `POST /v1/explain/narrative` | Server-built RTCC context, LLM answer, grounding check, SSE stream | ## Engineering rules - Load once in the `lifespan` handler; keep it on `app.state`; never load inside a route. - Inference is blocking: plain `def` routes (FastAPI threadpool) or `run_in_threadpool`. - Pydantic models generated from `schema.json`; unknown fields rejected; categories enumerated; out-of-range numerics need `allow_extrapolation` and come back flagged. - Column order and dtypes come from the schema, enforced before `predict`. - The server recomputes everything it sends to the LLM; clients never send explanation values. - API key dependency, explicit CORS allowlist without credentials, body size limit, rate limit, no upload endpoint. - JSON logs with request id and no raw personal data; `/metrics` with request counts, latency, prediction distribution, range violations and PSI drift. - Docker: multi-stage, slim base, pinned requirements, non-root user, no `--reload`, `HEALTHCHECK`, model directory mounted read-only. Each worker holds its own model copy; size workers to memory. - Air-gapped: vendored wheels (`pip download` then `--no-index --find-links`), `LLM_PROVIDER=none` makes no external calls and uses template explanations. Details, batch scoring, ONNX and PMML, Java and .NET: `references/fastapi-serving.md`.
Pliki w paczce (2)
- SKILL.md 3 KB
- references/fastapi-serving.md 4 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · Harrypatria/data-mining-ml | 90 | MIT |
| secondsky/claude-skills | 100 | MIT |
| seb1n/awesome-ai-agent-skills | 100 | MIT |
| awslabs/agent-plugins | 90 | Apache-2.0 |
| Amey-Thakur/AI-SKILLS | 90 | MIT |
| 420company/artemis | 85 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki 919aa70c6038 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100model-serving
Prowadzi przez wdrożenie wytrenowanego modelu za API: usługi inferencji we FastAPI, bezpieczne ładowanie artefaktów, walidacja żądań, batching, ONNX, kwantyzacja i monitoring. - 100domino-model-monitoring
Monitoruje modele produkcyjne Domino pod kątem dryfu danych i jakości, z przechwytywaniem predykcji, testami dryfu i powiadomieniami. - 81python-backend-fastapi-docker-agents
Pomaga założyć projekt w Pythonie, zbudować usługę FastAPI, utwardzić obraz Docker i stworzyć agenta AI w Pydantic AI. - 100senior-ml-engineer
Wdraża modele ML do produkcji, buduje pipeline'y MLOps i integruje LLM: deployment, feature stores, monitoring dryfu, systemy RAG i optymalizacja kosztów (MLflow, Kubeflow, Kubernetes, Docker). - 100senior-ml-engineer
Przygotowuje modele ML i funkcje LLM do produkcji: specyfikacje wdrożenia, monitoring dryfu, RAG i kontrolę kosztów. - 90devops-mlops
Wdraża MLOps: pipeline CI/CD modeli, rejestr modeli, wdrożenia canary, monitoring dryfu i wycofywanie modeli.