Configure Connections
On the Connections configuration page, provide details of your data source to enable querying data and AI provider to support query generation and metadata management.
Connections with at least a Project scope allow app admins to grant edit access.
Data Configuration
Configure your data source for smooth querying and analysis.
Data Source
Database type containing the data to be queried.
Supported data sources:
MySQL
PostgreSQL
Redshift
Snowflake
BigQuery (coming soon)
Oracle (coming soon)
Connection Name
Choose a connection name from the saved connections list or create a new one using the Add New Connection option.
To add a connection for MySQL data source, please refer to JDBC Connection documentation.
To add a connection for PostgreSQL data source, please refer to JDBC Connection documentation.
To add a connection for Redshift data source, please refer to Redshift Connection documentation.
To add a connection for Snowflake data source, please refer to Snowflake Connection documentation.
Warehouse Name
(For Snowflake only) Select a warehouse from the list associated with your chosen connection.
Schema and Tables
Schema details are retrieved from the database connection. Select the schema name where the target table resides. Once a schema is selected, the associated tables will appear in the adjacent drop-down for selection.
Query Credentials
The credentials provided in this section are used to query data from the data source during chat sessions.
For Data Sources other than Snowflake
Use same credentials as in the Data Configuration connection
Option to use the same credentials specified in the Data Configuration section for querying the data source during Q&A sessions or provide different credentials.
Important Note: Ensure that the connection credentials provided here have SELECT ONLY privileges.
Username
Enter the username required to connect to the database.
Password
Enter the password associated with the username to connect to the database.
For Snowflake Data Source
Role
Role to be used while querying data from data source during chat sessions.
Important Note: Ensure that the role should have READ ONLY privileges.
AI Provider
Select the AI provider and database type to support various features of your Data Intelligence application.
LLM Provider
To generate queries based on natural language inputs.
Choose an existing connection or configure a new one to link with the selected provider. Test the connection to ensure its availability.
To add a connection for OpenAI LLM provider, please refer to OpenAI Connection documentation.
To add a connection for Anthropic LLM provider, please refer to Anthropic Connection documentation.
Vector Database
To store and retrieve the vector representation of table(s) metadata.
Choose an existing connection or configure a new one to link with the selected provider. Test the connection to ensure its availability.
- To add a connection for Pinecone Vector DB, please refer to Pinecone Connection documentation.
Select or create an index to organize and store table(s) metadata.
Note: Refer to the Index configuration fields description for detailed explanations.
Embedding Provider
An embedding model to generate the vector representations of table(s) metadata.
Choose an existing connection or configure a new one to link with the selected provider. Test the connection to ensure its availability.
To add a connection for OpenAI Embedding provider, please refer to OpenAI Connection documentation.
Ensure that the dimensions of the vector database index match the dimensions of the embeddings generated by the model.To add a connection for Voyage AI Embedding provider, please refer to Voyage AI Connection documentation.
If you have any feedback on Gathr documentation, please email us!