> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cognee.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Search

> Ask questions about your knowledge graph and agent memory.

The Search page is a chat-style interface for querying your knowledge graphs. When a conversation is empty, the page greets you with **What are you looking for today?**

<Note>
  Search consumes token credits under Cognee Cloud's [usage-based billing](/cognee-cloud/functionality/account-and-billing). If your workspace runs out of prepaid credits, queries may fail — the workspace owner can top up on the **Billing** page.
</Note>

## Sending a query

1. Choose a dataset using the **Searching: …** picker above the input bar.
2. Choose a **scope** using the pills above the input bar (see [Search scope](#search-scope) below).
3. Type a natural language query in the search bar (placeholder **Ask a question about your data...**) and press **Enter** to send; use **Shift+Enter** for a newline.
4. Results appear in the conversation area below.

Suggestion chips are shown when a conversation is empty:

* "What are the main entities?"
* "Summarize the uploaded documents"
* "What relationships exist in the data?"

Click any chip to send it immediately.

Past searches are loaded from the backend and shown in the history sidebar. History persists across sessions and is fetched via the [`GET /api/v1/search`](/cognee-cloud/functionality/search-and-recall#search) endpoint.

## Dataset and scope

The active dataset (brain) is controlled by the current breadcrumb selection. The label above the input bar shows which brain is being searched.

Scope selector pills above the input bar control the retrieval target:

| Scope             | Description                                                                                 |
| ----------------- | ------------------------------------------------------------------------------------------- |
| **Company Brain** | Maps to graph search over the knowledge graph built from your uploaded documents (default). |
| **Agent Memory**  | Searches the most recent agent session and what connected agents stored in it.              |

**Agent Memory** uses the most recent session as context; if no recent session exists, the search has no session context to draw from.

## Conversation history

The sidebar on the left lists past conversations grouped by date. Click any conversation to reopen it, use **+** to start a new one, or use the sidebar toggle to collapse and expand the history panel.

Past searches are loaded from the backend via [`GET /api/v1/search`](/cognee-cloud/functionality/search-and-recall#search). New conversations created during the current page session appear alongside that history.

<Note>
  Conversations are backed by backend sessions whose ids are prefixed with `search-ui-`, so your history survives a page refresh. Legacy single-Q\&A entries are read-only; continuing one forks it into a new session.
</Note>

## How search works

The UI search calls the `POST /api/v1/recall` endpoint with the selected scope. **Company Brain** behaves like a standard graph retrieval, while **Agent Memory** adds the most recent agent session and trace context to the results. For details on available search types and parameters, see [Search Basics](/guides/search-basics).

<Note>
  The search bar on the [Dashboard](/cognee-cloud/ui/dashboard) provides the same functionality inline. The dedicated Search page offers more space for results and conversation history.
</Note>