Cloudera Docs

Agent Studio inbuilt tools

Learn about the various inbuilt tools in Agent Studios.

Calculator Tool

The Calculator Tool allows you to execute basic arithmetic functions. Its primary purpose is to illustrate the process of tool creation.

Jira Integration Tool

The Jira Integration Tool enables you to create, update, delete and search issues from Jira. The following information is required to configure this tool:

  • Jira URL
  • Authentication token
  • Registered Jira email address

Web Search Tool

The Web Search Tool, comparable to a Google search, enables you to search information on the internet.

Configuration Requirement: A Serper API key is necessary for this tool, for more information, see Serper.

Webpage Scraper Tool

The Webpage Scraper Tool allows you to extract content from a specific URL.

Email Tool

The Email Tool facilitates sending emails by connecting to an SMTP server. The following parameters are necessary to configure this tool:
  • SMTP Server - The address of the SMTP server.
  • SMTP Port – The port number for the SMTP connection.
  • SMTP Password – The password required for authenticating with the SMTP server.

Slack Tool

The Slack Tool enables sending messages to specific users to their email addresses or to any channel using a configured Slack bot.

This tool requires the Slack API Token to be configured.

Calendar Tool

The Calendar Tool enables the management of events, specifically creation, modification, and deletion of calendar events, within an .ics calendar file.

PDF Tool

The PDF Tool allows you to convert Markdown content into a PDF file or read an existing PDF file.

File Read Tool

The File Read Tool allows you to read the content of a given file.

Directory Read Tool

The Directory Read Tool allows you to read all the files in the given directory.

The tool requires the directory path for file listing to be configured.

Cloudera Data Flow HuggingFace Readyflow Deploy Tool

The Cloudera Data Flow HuggingFace Readyflow Deploy Tool allows you to import a huggingface dataset into a path in the Cloudera Data Lake.

The following parameters are required to configure this tool:

  • Cloudera workload username - The username for accessing Cloudera workloads.
  • Cloudera API Access Key - Used for authentication with the Cloudera API.
  • Cloudera API Private Key - It works along with the Access Key for secure API access.
  • CRN of a running Cloudera Data Flow service - The unique identifier of an active Cloudera Data Flow service instance.

Cloudera Data Visualization Dataset Creation Tool

The Cloudera Data Visualization Dataset Creation Tool facilitates generating a Cloudera Data Visualization dataset directly from an existing SQL table.

The tool requires the following configurations:

  • Dataset connection ID - The identifier for the data connection in Cloudera Data Visualization.
  • Cloudera Data Visualization Base URL - The URL of your Cloudera Data Visualization instance.
  • Cloudera AI APIv2 application key - Required for authentication with Cloudera AI APIs.

Cloudera Data Visualization Smart Visual Tool

The Cloudera Data Visualization Smart Visual Tool enables the generation of a visualization within Cloudera Data Visualization Smart Visual Tool, utilizing a specified dataset. The Cloudera Data Visualization Smart Visual Tool needs the following configuration settings:
  • Cloudera Data Visualization Base URL - The URL of your Cloudera Data Visualization instance.
  • Cloudera AI APIv2 Application Key - Necessary for authenticating with Cloudera AI APIs.

Cloudera Data Warehouse Hive Table from S3 Parquet Tool

The Cloudera Data Warehouse Hive Table from S3 Parquet Tool enables the creation of a table in Cloudera Data Warehouse by loading an existing parquet file from S3. This tool validates the successful creation of the table by returning sample data from the newly accessible table.

This tool requires the following configurations:

  • Workload User – The username required for Cloudera Data Warehouse workload access.
  • Workload Password – The corresponding password needed for authentication.
  • Hive Cloudera AI Data connection name – The name of the data connection linking Hive to the Parquet file located in S3.