Add A Datasource
Second stage of adding Datasource (check test datasource for the first step), this connects the datasource to a vectordb, creates a connection between the datasource and airbyte, starts a job to synchronise the rows and finally creates a tool for the datasource. A tool for the datasource is required as within agents a datasource is used as a ‘tool’ just the same as any other tool, this is required for the ‘RAG’ process.
Path Parameters
The resourceSlug is a url parameter of the teamId associated with the user. Anywhere the resourceSlug is used can be interpreted as a teamId
Body
Represents a data source configuration within the system, including connection details, status, chunking configurations, and record counts.
The name of the datasource.
The original name of the datasource.
The type of source for the datasource.
The identifier of the data source.
The identifier of the data destination.
The identifier of the workspace associated with the datasource.
The identifier of the connection associated with the datasource.
The date and time when the datasource was created.
Unique identifier for the datasource.
Identifier of the organization to which the datasource belongs.
Identifier of the team to which the datasource belongs.
Optional description of the datasource.
The name of the file associated with the datasource, if applicable.
The record count details for the datasource, including total, successful, and failed records.
Configuration settings for the datasource connection.
The date and time when the datasource was last synced. Null indicates it has never been synced.
The current status of the datasource.
draft
, processing
, embedding
, ready
Schema discovered during the data source connection. The structure depends on the source type.
Configuration settings for chunking unstructured data, including partitioning and chunking strategies, character limits, and similarity thresholds.
The field used for embedding within the datasource.
The field used to apply time weighting within the datasource.
Identifier of the embedding model used, if applicable.
Indicates whether the datasource is hidden from standard views.
Configuration settings for processing streams of data, breaking them into smaller chunks for more manageable processing.
A temporary field to limit CRON frequency based on the plan. This will be replaced with a more robust solution in the future.