diff --git a/README.md b/README.md index c5077451..4da91931 100644 --- a/README.md +++ b/README.md @@ -11,6 +11,8 @@ Chapkit provides domain-specific modules for building machine learning services on top of servicekit's core framework. Includes artifact storage, configuration management, and ML train/predict workflows. +**Want to run a forecasting model in Chap?** You do not need to write a chapkit service. Write train and predict scripts and an `MLproject` file, and evaluate them with `chap eval --run-config.as-chapkit`. See [Bring your existing model to Chap](https://chap.dhis2.org/chap-modeling-platform/external_models/existing_model/) and [Build a new model from a template](https://chap.dhis2.org/chap-modeling-platform/external_models/mlproject_tutorial/) in the Chap docs. + ## Features - **Artifact Module**: Hierarchical storage for models, data, and experiment tracking with parent-child relationships diff --git a/docs/guides/mlproject-runner.md b/docs/guides/mlproject-runner.md index 30ee28e5..128d465f 100644 --- a/docs/guides/mlproject-runner.md +++ b/docs/guides/mlproject-runner.md @@ -2,6 +2,8 @@ `chapkit mlproject run` turns any directory containing an MLflow-style `MLproject` file into a running chapkit service — no code generation, no changes to the MLproject repo. It is aimed at users coming to chapkit with an existing `train.r` / `predict.py` (or any shell-command-driven model) who want a chapkit HTTP API around their scripts in seconds. +To evaluate an MLproject model with Chap, you do not need to start the service yourself: `chap eval --model-name --run-config.as-chapkit` runs `chapkit mlproject run` for you. The Chap docs cover the whole flow, from your scripts to a published Docker image: [Bring your existing model to Chap](https://chap.dhis2.org/chap-modeling-platform/external_models/existing_model/) and [Build a new model from a template](https://chap.dhis2.org/chap-modeling-platform/external_models/mlproject_tutorial/). + ## Quick Start Point it at an MLproject file or the directory that holds one: diff --git a/docs/index.md b/docs/index.md index 58256100..4c975571 100644 --- a/docs/index.md +++ b/docs/index.md @@ -7,6 +7,9 @@ Build production-ready ML services with train/predict workflows, artifact storage, config management, and job scheduling - all in a few lines of code. +!!! tip "Want to run a forecasting model in Chap?" + You do not need to write a chapkit service or install chapkit yourself. Write a train and a predict script in R or Python and a short `MLproject` file, and evaluate the model with `chap eval --run-config.as-chapkit`, which starts the chapkit service for you. The Chap docs walk through it: [Bring your existing model to Chap](https://chap.dhis2.org/chap-modeling-platform/external_models/existing_model/) and [Build a new model from a template](https://chap.dhis2.org/chap-modeling-platform/external_models/mlproject_tutorial/). + ## Quick Start: ML Service ```python