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

# Overview

> The dazense chat interface enables teams to interact with data through natural language queries.

## Getting Started

### Launch Options

**Command Line:**

```bash theme={null}
dazense chat
```

This starts a local server at `http://localhost:5005`.

**Docker with Example:**

```bash theme={null}
docker run -d \
  --name dazense \
  -p 5005:5005 \
  -e BETTER_AUTH_URL=http://localhost:5005 \
  metazense/dazense:latest
```

**Docker with Custom Project:**

```bash theme={null}
docker run -d \
  --name dazense \
  -p 5005:5005 \
  -e BETTER_AUTH_URL=http://localhost:5005 \
  -v /path/to/your/project:/app/project \
  -e DAZENSE_DEFAULT_PROJECT_PATH=/app/project \
  metazense/dazense:latest
```

Access the interface at `http://localhost:5005`.

<Note>
  The chat interface operates locally. Data transmission to external servers only occurs when you configure an external LLM provider.
</Note>

## Querying Data

**Entering Questions**

* Input queries in conversational language
* Reference earlier results in subsequent questions

**Response Components**

* **Answer**: Summary in plain language
* **SQL Query**: Generated query (expandable)
* **Data Table**: Tabular results
* **Visualizations**: Automatic charts when relevant
* **Sources**: Referenced context files

## User Feedback

Each response includes feedback options:

* Thumbs up for positive responses
* Thumbs down for problematic responses

User feedback is retained for audit purposes.

## Next Steps

* [Chat Capabilities](/dazense-agent/chat/capabilities): Explore available agent features
* [Slack Bot](/dazense-agent/chat/slack): Configure Slack team integration