LLM Connector Overview

The LLM Connector tool, embedded in Paragon Automation, is an advanced AI-driven tool for leveraging large language models (LLMs) to streamline network monitoring operations.

Note:

The LLM Connector tool is a beta feature in this release.

LLM Connector facilitates the use of natural language to query network status and obtain troubleshooting information, without the need for traditional CLI commands. For example, if you encounter an issue with OSPF neighbors of a device, you query LLM Connector What is the status of OSPF neighbors of device A?. LLM Connector, by using the knowledge that the LLM (defined and configured by the user) has obtained from technical documentation and by its ability to execute functions, executes the show ospf neighbour command on the device to present you with the relevant information for troubleshooting.

When you initiate a query, LLM Connector connects with an LLM such as OpenAI GPT-3.5 Turbo, GPT-4 or GPT-4o, or Ilama 3.1 that you configure to provide contextual assistance. The LLM is trained on extensive documentation to interpret your query and prompts LLM Connector to execute the necessary network commands. The LLM also parses the result of the executed command and presents it in an easy-to-understand format.

The natural language interface supports a variety of query types, ranging from simple status checks to more complex troubleshooting commands. For example, you can ask, Show me the interface statistics or Is there any packet loss on the link between device A and device B?.

You are provided with an option to rate the answer that you got for your query and provide a feedback about the response.

LLM Connector can help you with:

• Retrieving device information.

• Executing Junos OS operational commands.

• Saving data (configuration and logs) to a file.

• Retrieving a list of all VPNs in your network and their details, metrics, and health information.

• Fetching information about customers and service instances associated with customers.

• Getting Insights based on the telemetry collected from the device.

To use the LLM Connector tool, you need to set up the LLM and provide parameters such as API keys and model details. For information about configuring LLM, see Configure LLM Connector.