K9 Companion

K9 Companion is an AI chat assistant that leverages the configured LLM to deliver intelligent, context-aware interactions. It is included as part of the Siren AI plugin.

K9 Companion

Capabilities

K9 Companion can automate user actions, such as search across your data and interact with graph.

K9 performing a global search

Because K9’s capabilities are expanding over time, to get a full list of the actions that K9 can perform for you, ask K9 directly!

Asking K9 about its capabilities

Using K9 Companion with a graph

One of the most powerful features of K9 Companion is its ability to understand and interact with graphs. When the K9 Companion is used while viewing a graph, the graph data is automatically attached to the conversation. You can use K9 to point out insights from very large graphs, ask questions, and even ask K9 to perform actions on the graph, like add, group and style nodes.

K9 styling a large graph

K9 can perform the actions described above when using OpenAI, Azure OpenAI, AWS Bedrock, or any provider that implements the OpenAI Chat Completions API specification.

Graph data sent to the LLM

The data sent to the LLM consists of the graph name, nodes, edges and groups. All types of nodes are supported, including local nodes and EIDs. This node data consists of the node label, the entity table ID, the entity table name, the index pattern, and the main fields as configured in the data model.

All edge types are supported, including local edges, aggregated edges, records-as-relation edges and grouped edges. The edge data consists of the edge label, the relation label, the relation inverse label, the source and target entity IDs, the source and target node IDs, as well as any record data associated with record-as-relation edges.