Datyo Docs

English

中文

English

中文

Appearance

Datasets & connectors ​

A dataset is a source for analysis. On creation, the system reads its schema and sample data so the Agent can understand it. Connection secrets are stored encrypted and never shown in plaintext.

Create a dataset ​

Go to Datasets → New → pick a type → enter connection info → test the connection → save. After saving, the status moves through "syncing → connected"; on failure it shows the error with an explanation.

One dataset can be reused across multiple Spaces.

Supported data sources ​

Datyo supports relational databases, cloud warehouses, lakehouse and object-storage formats, logs, NoSQL, and direct file uploads. Each connector — its fields, how to obtain credentials, its capabilities, and troubleshooting — is documented individually in the Connectors section:

The Connectors overview also explains the shared concepts — federated vs. native execution, read-only access, object-storage credentials, and the managed vs. self-hosted distinction for local file paths — and lists recommended approaches for source types shown as "planned" (for example ClickHouse via the PostgreSQL connector, or TiDB via the MySQL connector). The exact selectable types are shown in the console.

Improve answer accuracy ​

  • Fill in column descriptions: adding business meaning to fields makes the Agent's SQL more accurate.
  • Maintain business notes: write table relations and metric definitions in the Space.
  • Re-sync: after connection or schema changes, re-sync so the Agent reads the latest structure.

Troubleshooting ​

  • Connection test fails: check credentials, network reachability, and that the database / table names are correct.
  • Abnormal status: open the dataset details for the specific error — often expired credentials or a network issue.

Datyo · The Agent-native intelligent data analytics platform

© 2026 Datyo