# Synthefy Docs

- [Nori](https://docs.synthefy.com/index.md): Predict on any table in seconds, with no training.
- [Quickstart](https://docs.synthefy.com/nori/quickstart.md): Get predictions on tabular data, locally or through the hosted API.
- [Installation](https://docs.synthefy.com/setup/installation.md): Pick the right Synthefy package for what you want to do.
- [API Key](https://docs.synthefy.com/setup/api_key.md): Create the key that authenticates hosted Nori requests.
- [Examples](https://docs.synthefy.com/nori/examples.md): Worked examples using Synthefy Nori (Tabular).
- [Multi-Target Regression](https://docs.synthefy.com/nori/multi-target-regression.md): Predict related numeric targets together with joint uncertainty.
- [Embeddings](https://docs.synthefy.com/nori/embeddings.md): Turn any table row into a target-aware vector with Nori's encoder, then probe, cluster, search, or visualize it.
- [Forecasting](https://docs.synthefy.com/nori/forecasting.md): Forecast time series with custom targets and future-known data.
- [Text Features](https://docs.synthefy.com/nori/text-features.md): Hand Nori free-text columns. It embeds them, reduces them to a few numeric columns, and predicts on the widened table. Zero-shot, no training.
- [Explainability](https://docs.synthefy.com/nori/explainability.md): Explain Nori's predictions with SHAP / Shapley values, feature interactions, partial dependence, and feature selection.
- [Glass-box Models](https://docs.synthefy.com/nori/glassbox.md): Distill Nori into a readable, shippable glass-box model (EBM) in one call — feature importance, pruning, and an auditable additive model.
- [Categorical & Ordinal Targets](https://docs.synthefy.com/nori/categorical-targets.md): Predict labels on a discrete scale (ratings, counts, quality scores) instead of a continuous estimate.
- [Missing Values & Imputation](https://docs.synthefy.com/nori/missing-values.md): How Nori handles NaNs: what happens automatically, and how to impute yourself when you want control.
- [Large Tables](https://docs.synthefy.com/nori/large-data.md): Serve context tables larger than GPU memory or a bounded row budget, with memory_policy and large_context_policy.
- [Python Client](https://docs.synthefy.com/nori/client.md): Call Nori from the synthefy package — one client for the hosted API and for local inference, with DataFrames and retries handled for you.
- [Amazon SageMaker](https://docs.synthefy.com/nori/sagemaker.md): Subscribe to Nori in AWS Marketplace, deploy one GPU endpoint, and call all three models with the Synthefy client.
- [Snowflake](https://docs.synthefy.com/nori/snowflake.md): Run Nori on your Snowflake data directly from SQL, with no data export and no training.
- [InfluxDB](https://docs.synthefy.com/nori/influxdb.md): Run Nori regression inside InfluxDB 3 as a Processing Engine plugin, with predictions written back to your database.

## OpenAPI Specs

- [openapi](/api-reference/openapi.json)

## Optional

- [Website](https://synthefy.com)
- [GitHub](https://github.com/Synthefy)
- [Discord](https://discord.gg/jpsXMXGza)
- [Hugging Face](https://huggingface.co/Synthefy)
- [Colab Demo](https://colab.research.google.com/github/Synthefy/synthefy-nori/blob/main/examples/notebooks/Nori_Demo_Local.ipynb)