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

# Basic Usage

<CardGroup>
  <Card title="Interactive demo" icon="gamepad-modern" iconType="solid" href="https://colab.research.google.com/drive/1WKmRXZgsErej2xUriKzxrEAXdxMSgWbb?usp=sharing">
    Try Open Interpreter without installing anything on your computer
  </Card>

  <Card title="Example voice interface" icon="circle" iconType="solid" href="https://colab.research.google.com/drive/1NojYGHDgxH6Y1G1oxThEBBb2AtyODBIK">
    An example implementation of Open Interpreter's streaming capabilities
  </Card>
</CardGroup>

***

### Interactive Chat

To start an interactive chat in your terminal, either run `interpreter` from the command line or `interpreter.chat()` from a .py file.

<CodeGroup>
  ```shell Terminal theme={null}
  interpreter
  ```

  ```python Python theme={null}
  interpreter.chat()
  ```
</CodeGroup>

***

### Programmatic Chat

For more precise control, you can pass messages directly to `.chat(message)` in Python:

```python theme={null}
interpreter.chat("Add subtitles to all videos in /videos.")

# ... Displays output in your terminal, completes task ...

interpreter.chat("These look great but can you make the subtitles bigger?")

# ...
```

***

### Start a New Chat

In your terminal, Open Interpreter behaves like ChatGPT and will not remember previous conversations. Simply run `interpreter` to start a new chat.

In Python, Open Interpreter remembers conversation history. If you want to start fresh, you can reset it.

<CodeGroup>
  ```shell Terminal theme={null}
  interpreter
  ```

  ```python Python theme={null}
  interpreter.messages = []
  ```
</CodeGroup>

***

### Save and Restore Chats

In your terminal, Open Interpreter will save previous conversations to `<your application directory>/Open Interpreter/conversations/`.

You can resume any of them by running `--conversations`. Use your arrow keys to select one , then press `ENTER` to resume it.

In Python, `interpreter.chat()` returns a List of messages, which can be used to resume a conversation with `interpreter.messages = messages`.

<CodeGroup>
  ```shell Terminal theme={null}
  interpreter --conversations
  ```

  ```python Python theme={null}
  # Save messages to 'messages'
  messages = interpreter.chat("My name is Killian.")

  # Reset interpreter ("Killian" will be forgotten)
  interpreter.messages = []

  # Resume chat from 'messages' ("Killian" will be remembered)
  interpreter.messages = messages
  ```
</CodeGroup>

***

### Configure Default Settings

We save default settings to the `default.yaml` profile which can be opened and edited by running the following command:

```shell theme={null}
interpreter --profiles
```

You can use this to set your default language model, system message (custom instructions), max budget, etc.

<Info>
  **Note:** The Python library will also inherit settings from the default
  profile file. You can change it by running `interpreter --profiles` and
  editing `default.yaml`.
</Info>

***

### Customize System Message

In your terminal, modify the system message by [editing your configuration file as described here](#configure-default-settings).

In Python, you can inspect and configure Open Interpreter's system message to extend its functionality, modify permissions, or give it more context.

```python theme={null}
interpreter.system_message += """
Run shell commands with -y so the user doesn't have to confirm them.
"""
print(interpreter.system_message)
```

***

### Change your Language Model

Open Interpreter uses [LiteLLM](https://docs.litellm.ai/docs/providers/) to connect to language models.

You can change the model by setting the model parameter:

```shell theme={null}
interpreter --model gpt-3.5-turbo
interpreter --model claude-2
interpreter --model command-nightly
```

In Python, set the model on the object:

```python theme={null}
interpreter.llm.model = "gpt-3.5-turbo"
```

[Find the appropriate "model" string for your language model here.](https://docs.litellm.ai/docs/providers/)