TDgpt
This section describes how to install and use TDgpt, the AI agent for time-series analytics. It also explains how to add your own algorithms and models to the platform and use them in your queries.
📄️ Introduction
Numerous algorithms have been proposed to perform time-series forecasting, anomaly detection, imputation, and classification, with varying technical characteristics suited for different scenarios.
📄️ Installation
Before installing TDgpt, review the system requirements and ensure that your container or machine meets the minimum specifications.
📄️ Anode Management
Starting the TDgpt Service
📄️ Data Preprocessing
Analysis Workflow
🗃️ Time-Series Forecasting
3 items
🗃️ Anomaly Detection
3 items
📄️ Correlation Analysis
TDgpt provides the following correlation analysis capabilities for time-series data.
📄️ Data Imputation
TDgpt provides data imputation based on time-series foundation models. It automatically detects missing time-series data points based on timestamps.
🗃️ Algorithm Developer's Guide
3 items
📄️ Frequently Asked questions
1. During the installation process, uWSGI fails to compile
📄️ System Requirements
The system requirements on this page apply to the machine running the anode for TDgpt. Note that these are guidelines, and actual requirements scale with model size, request concurrency (QPS), context/window length, and any local caching/feature store footprint.