Time Series Forecast API Documentation

[jinan-zhou]

Fixes

This PR adds the documentation for the Time Series LLM Forecast API. This API specification defines a consistent, extensible format for time series forecasting requests and responses and set the best practices for interoperability and clarity in the field. It describes request and response schemas, enumerations, usage examples, and best practices, supporting both univariate and multivariate time series forecasting with quantile support.

Proposed Changes

• Introduces the first version of API documentation for /v1/timeseries/forecast, detailing request/response fields, enumerations, and usage examples.
• Documents usage patterns for both minimal and advanced time series forecasting scenarios.
• Clarifies extensibility through support for arbitrary metadata and additional fields.
• Provides FAQ and best practices for robust client and server implementations.
• Adds a changelog and table of contents for discoverability and maintainability.

Why

This documentation aims to:

• Standardize the time series API to make integration easier for vendors, open source projects, and researchers.
• Help users and contributors understand every request/response field and common patterns for the new forecasting API.
• Promote best practices for extensibility, error handling, and forward compatibility.
• Enable rapid onboarding and clear guidance for all users of time series LLMs and related services.

Implementation

This standard is implemented inside the KServe HuggingFace Server at this PR.

[netlify]

✅ Deploy Preview for elastic-nobel-0aef7a ready!

Name	Link
🔨 Latest commit	092f7bb
🔍 Latest deploy log	https://app.netlify.com/projects/elastic-nobel-0aef7a/deploys/6901510cf6b6470008ffa104
😎 Deploy Preview	https://deploy-preview-507--elastic-nobel-0aef7a.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.