| Step Details | |
| Introduced in Version | 9.3.0 |
| Last Modified in Version | 9.3.0 |
| Location | AI > Postgres AI > Vector Preparation |
The Save Vector Embedding to Postgres step is used to allow the storage of vector embeddings in a PostgreSQL table. It takes the 'Vector Storage Info' and the list of vectors to store as input. This step is valuable for saving embeddings generated from various sources into the PostgreSQL database, providing a centralized location for vector data.
Prerequisites
This step requires the AI Common to be installed before it will be available in the toolbox.
Properties
Connection Settings
| Property | Description | Data Type |
|---|---|---|
| Override Vector Table Connection | Boolean enabling user to override default vector table connection | Boolean |
Query Settings
| Property | Description | Data Type |
|---|---|---|
| Vector Storage Info | Location of vector storage chosen from flow data | Flow Data |
Inputs
| Property | Description | Data Type |
|---|---|---|
| Embeddings to Store | List of embeddings to store | List of AITextEmbedding |
Outputs
| Property | Description | Data Type | |
|---|---|---|---|
| Error | |||
| Error Message | This output provides an error message that details any errors encountered during the process. If there are issues with the operation, this message will help identify and troubleshoot the problem. | String | |
Common Errors
Object Reference Not Set to an Instance of an Object
If the Vector Storage Info is not set, the step will cause an error.
To correct this, ensure there is valid and properly formatted vector storage info inputted.
Related Information