User Manual

Explore

Resources

Data Connector BQ

User Manual Documentation of Data Connector - BQ

version update 1.9.0

Initial Release

What is Data Connector ?

Data Connector is a powerful tool designed to enhance the capabilities of your AI agent in handling and retrieving structured data. This feature facilitates the seamless integration of external data sources, such as databases, cloud services, or other data repositories, into your AI agent's functionality.

acts as a pivotal bridge, enabling seamless conversations between your AI agent and connected datasets. This dynamic feature facilitates interactive queries, analysis, and insightful responses by integrating external data sources into the conversational flow. Let's explore how the Data Connector transforms your AI agent into a data-driven conversational partner using real-world

Data Connector BQ Guide

Create New Data Connector

Choose Tab Resource

In the Feedloop AI platform, navigate to the "Resource" tab to manage various resources, including data connectors.

Click Add Resource

Within the "Resource" tab, locate and click on the "Add Resource" button to initiate the creation of a new resource.

⁠

Click on the "Create Data Connector" button:

Once in the resource creation interface, find and click on the "Create Data Connector" button to begin the setup process for a new data connector.

Choose Connector Type

A selection menu will appear, prompting you to choose the type of data connector. Currently, the available options are:

BigQuery

Postgres (coming soon)

Qorebase (coming soon)

Choose the appropriate connector type based on your external data source.

Input Data Connector Information

Provide information about the data connector

⁠

Input Credentials:

If you choose BigQuery as the connector type, you'll need to input the following credentials:

Client Email

Example: your-service-account@your-project.iam.gserviceaccount.com

Private Key

Example:

vbnetCopy code

-----BEGIN PRIVATE KEY-----

Your_Private_Key_Content_Here

-----END PRIVATE KEY-----

Project ID

Example : projectname-283510

Connection ID

Example : projects/yourprojectname-283510/locations/us-central1/connections/dbtechsales

⁠

Click Next

After entering the necessary information and credentials, click on the "Next" button to proceed to the next stage of the data connector setup.

Choose Dataset

You will be presented with a list of datasets available in your BigQuery project. Choose the dataset that you want to connect to with the data connector.

⁠

Click Save Settings:

Once you have selected the dataset, click on the "Save Settings" button to save the configuration for the data connector.

⁠

Congratulations! You have successfully initiated the creation of a new data connector. The system will now proceed with the chosen settings and configurations to establish the connection with the selected dataset in BigQuery.

Configuring Dataset,Table and Column

Dataset Details

Once a data connector is successfully connected to a dataset in BigQuery, users can configure specific details. The interface provides information about the dataset, including its name and description retrieved from BigQuery.

Users have the option to add or enhance the description for the dataset. This description serves as crucial contextual information for the AI system. By providing a comprehensive description, users empower the AI to better understand the dataset's content, purpose, and context. system will retrieve the dataset, table and column descriptions from BQ automatically.If there is no description, we can add it manually

⁠

to edit description clik edit buton

Table Configuration

selecting tables and columns will determine the result data, select the tables and columns needed

Users can select multiple tables within the connected dataset. For each table, the following information is displayed:

⁠

Table Name: The name of the table.

Show Detail : to edit to view and edit description

⁠

Table Description: A description of the table obtained from BigQuery.

⁠

Checkbox to Enable: Users can select or enable multiple tables by using checkboxes, providing flexibility in data configuration.

⁠

Column Configuration

selecting tables and columns will determine the result data, select the tables and columns needed

click show detail fpr specific table to and clik columns to view column

⁠

Users can select multiple column within the connected dataset. For each column, the following information is displayed:

⁠

Colum Name: The name of the table.

Show Description : to edit to view and edit description

⁠

Checkbox to Enable: Users can select or enable multiple column by using checkboxes, providing flexibility in data configuration.

⁠

You have completed the configuration for your new data connector, providing the system with valuable information about the dataset, tables, and columns. The established connection with the selected dataset in BigQuery enables seamless data interaction

Editing and Updating Data Connectors

Easily edit and update existing data connectors by selecting existing data connector in resource page. Changes made to settings are saved and reflected in the system.

Deleting Data Connectors

If a data connector is no longer needed, use the "Delete" option. A confirmation prompt will prevent accidental deletion.

Enable Data Connector In Agent

Data Connector skill allows the agent to access external data connectors for advanced reporting and analysis capabilities.

Add Data Connector Skill

⁠

Navigate to "Agent Settings" in the Feedloop AI platform.

Choose the "Skills" tab.

⁠

Add a new skill by selecting the "Data Connector" skill.

Choose the type of skill:

Reporting: Configure reporting-type Data Connector skills.

Analysis: Configure analysis-type Data Connector skills.

Reporting-Type Data Connector Skill

The reporting-type Data Connector skill enables the agent to generate specific reports based on user queries, enhancing its reporting capabilities.

Skill Configuration

Title: Provide a user-defined title for the reporting-type Data Connector skill.

Input Condition: Specify conditions for activating the skill (e.g., user queries about GWI Score).

Input Reporting Rules: Define specific rules for reporting, such as SQL queries or data manipulation steps.

⁠

Adding Connectors

Choose Dataset: Select a dataset for the Data Connector.

Choose Table (Multiple): Choose multiple tables within the selected dataset.

Delete Connector: Remove a connector if needed.

⁠

Deleting Connectors

Users can remove connectors under this skill if not needed.

Analysis-Type Data Connector Skill

The analysis-type Data Connector skill allows the agent to perform in-depth analysis based on user queries, expanding its analytical capabilities.

Skill Configuration

Input Condition: User queries about the analysis of GWI Score.

Input Reporting Rules: Specific rules for reporting, similar to the reporting type.

Input Analysis Rules: Rules specific to analysis, such as additional SQL queries or data manipulation steps.

Add Connector (Multiple):

Choose Dataset: Select a dataset for the Data Connector.

Choose Table (Multiple): Choose multiple tables within the chosen dataset.

Delete Connector: Remove a connector if needed.

⁠

Adding Connectors

Choose Dataset: Select a dataset for the Data Connector.

Choose Table (Multiple): Choose multiple tables within the selected dataset.

Delete Connector: Remove a connector if needed.

⁠

Deleting Connectors

Users can remove connectors under this skill if not needed.

Example Skill Implementation

Type : Reporting

Title : GWI_iNDICATOR SCORE

condition : when user ask about GWI Score but not including gwi indicator where gwi score is the main subject of the question

The condition sets the trigger for the reporting skill. It activates when a user queries about GWI Score specifically, without mentioning the GWI indicator. The goal is to provide information related to GWI Score when it is the primary topic of the user's question.

reporting rules :