MLflow
- Category
- AI and LLMs
- Docs outline
- 14 sections
Official docs outline
mlflow.org- MLflow Tracking
Experiments, runs, parameters, metrics, artifacts, and the tracking server.
- Tracking API
Logging with mlflow.log_param, log_metric, log_artifact, and managing runs.
- Autologging
Automatic capture of parameters, metrics, and models from ML libraries.
- MLflow Models
Model flavors, the MLmodel format, and saving and loading models.
- Model signatures and dependencies
Input and output schemas, environment dependencies, and python_function models.
- Model Registry
Registered models, versions, aliases, and lifecycle workflow.
- Model evaluation
Evaluating models and comparing metrics with mlflow.evaluate.
- Model deployment
Serving models locally, in Docker, SageMaker, and other targets.
- MLflow Projects
Packaging reproducible runs with MLproject files and environments.
- Searching runs and experiments
Filter syntax for querying runs, experiments, and models.
- GenAI overview
MLflow for LLM and agent applications.
- Tracing
Traces and spans for observing GenAI applications.
- GenAI evaluation
Scorers, datasets, and regression testing for LLM applications.
- Prompt Registry
Versioning and managing prompts with aliases.
Each section links to the official page. Titles and summaries by Extra Credit; the docs belong to their authors.
