Graph visualizer assistant

The graph visualizer assistant answers questions about the graph you have open in the dashboard. It searches the graph, reads entities, facts, and episodes, and shows each retrieval step as it runs.

Use the assistant to:

• Inspect what Zep extracted from your data
• See how two entities connect
• Find the source episodes behind a fact
• Find the earliest or most recent episodes, entities, or facts, or count entities of one type
• Check a graph before you write retrieval code against it

The assistant is also a working example of how an agent can use a Zep graph. It uses the same graph search and graph read operations that your own agent can call through the API and SDKs. Each step in the panel shows the operation, its arguments, and its result, so you can see how an agent turns a question into graph retrievals.

What the assistant can and cannot do

The assistant is read-only. It cannot add, update, or delete graph data.

Each conversation targets the one graph that is open in the visualizer. The assistant cannot read a different graph, project, or account. When you close the visualizer, the conversation is discarded.

The assistant grounds each answer in data it retrieved from the graph. It does not answer from general model knowledge. When a search returns no matches, the assistant tells you that it found no evidence.

Open the assistant

Ask a question

Type a question and press Enter, or click Send. Press Shift+Enter to insert a new line.

Ask about one topic at a time. The assistant runs a bounded number of retrievals for each question, so a narrow question gets a better answer than a broad one. You can ask follow-up questions that refer to earlier answers in the same conversation.

Click Stop to cancel a turn. The panel keeps the steps that already ran.

Read the answer

Each turn shows the retrieval steps as they run, followed by the answer. Up to three steps that do not depend on each other run at the same time. A step shows the operation, such as Search or Get node, a summary of its arguments, and a summary of its result and the time the operation took in milliseconds. Expand a step to read the full arguments and result. A long search result is collapsed to a preview; select Show more to read all of it. When a result is near the question but does not answer it, the assistant runs a bounded follow-up step on the graph nodes that result names. The panel shows a follow-up step in the same way as a step the assistant planned.

When the answer cites graph evidence, the panel lists the cited nodes and facts under the answer. It shows six items first. Select Show all to expand the list, or Show on graph to highlight the cited evidence. When a turn completes, the panel applies the cited evidence as the canvas highlight.

The steps and the canvas are linked:

• Select a step to highlight the entities and facts it retrieved on the canvas.
• Select an entity name under the answer to focus that entity on the canvas.

The canvas shows a bounded view of a large graph. When a step retrieves an entity that is not loaded on the canvas, the panel lists it under Not on canvas.

A large result is shortened before the assistant reads it. The expanded step reports that the assistant saw a shortened result and how many items were not shown. When this happens, ask a narrower follow-up question.

Limits

• A question can be up to 2,000 characters.
• A turn stops after 60 seconds.
• The conversation keeps the last 10 turns. The panel tells you when earlier turns left context.
• Each member can send 10 turns per minute, and each account 30 turns per minute.

When a turn cannot complete, the panel states the reason, such as a timeout, a rate limit, or a model that did not respond. Retry, or ask a narrower question.

The assistant is available only in the dashboard. It is not available through the public API or SDKs. For programmatic reads, use graph search and reading data from the graph.