LLMs and Chat

Pegasus comes with an optional Chat UI for interacting with LLMs. This section covers how it works and the various supported options.

Choosing an LLM model

You can choose between two options for your LLM chat: OpenAI and LLM (generic). The OpenAI option limits you to OpenAI models, but supports streaming and asynchronous API access. The generic “LLM” option uses the litellm library and can be used with many different models---including local ones.

We recommend choosing “OpenAI” unless you know you want to use a different model.

Configuring OpenAI

If you’re using OpenAI, you need to set OPENAI_API_KEY in your environment or settings file (.env in development). You can also change the model used by setting OPENAI_MODEL, which defaults to "gpt-4o".

See this page for help finding your OpenAI API key.

Configuring LLM

If you built with generic LLM support, you can configure it by setting the LLM_MODELS and DEFAULT_LLM_MODEL values in your settings.py. For example:

LLM_MODELS = {
    "gpt-3.5-turbo": {"api_key": env("OPENAI_API_KEY", default="")},
    "gpt-4o": {"api_key": env("OPENAI_API_KEY", default="")},
    "claude-3-opus-20240229": {"api_key": env("ANTHROPIC_API_KEY", default="")},
    "ollama_chat/llama3": {"api_base": env("OLLAMA_API_BASE", default="http://localhost:11434")},  # requires a running ollama instance
}
DEFAULT_LLM_MODEL = env("DEFAULT_LLM_MODEL", default="gpt4")

The chat UI will use whatever is set in DEFAULT_LLM_MODEL out-of-the-box, but you can quickly change it to another model to try different options.

For further reading, see the documentation of the litellm Python API, and litellm providers.

Running open source LLMs

To run models like Mixtral or Llama3, you will need to run an Ollama server in a separate process.

Download and run Ollama or use the Docker image
Download the model you want to run:
Terminal window
```
ollama pull llama3
# or with docker
docker exec -it ollama ollama pull llama3
```
See the documentation for the list of supported models.

Update your django settings to point to the Ollama server. For example:

LLM_MODELS = {
    "ollama_chat/llama3": {"api_base": "http://localhost:11434"},
}
DEFAULT_LLM_MODEL = "ollama_chat/llama3"

Restart your Django server.

The Chat UI

The Chat UI has multiple different implementations, and the one that is used for your project will be determined by your build configuration.

If you build with asynchronous functionality enabled and htmx then it will use a websocket-based Chat UI. This Chat UI supports streaming responses for OpenAI models, and is the recommended option. It is also currently the only option that supports the chat widget that can be embedded on any page.

If you build without asynchronous functionality enabled, the chat UI will instead use Celery and polling. The React version of the chat UI also uses Celery and polling. This means that Celery must be running to get responses from the LLM.

The chat widget is currently only available if your project is using HTMX and Async.

The chat widget is a small component that can be embedded on any page of your app. By default, it is included in your chat_home.html file, so you can view a demo of the widget from the “AI Chat” tab in your app.

To add the chat widget to a page, you can follow the example in chat_home.html. There are two steps:

First, include the component at the end of the <body> tag. If you’re extending the app_base.html file this will be at the end of the {% block app %} block.

{% block app %}
...
{% include "chat/components/chat_overlay.html" %}
{% endblock app %}

Then, add the ws_initialize.js in your page JavaScript:

{% block page_js %}
<!-- If using vite -->
  {% vite_asset 'assets/javascript/chat/ws_initialize.ts' %}
<!-- If using webpack -->
  <script src="{% static 'js/chat-ws-initialize-bundle.js' %}" defer></script>
{% endblock page_js %}

If you want to add the chat widget to all pages in your app, you can add it to the base.html file. For all logged-in pages, you can add it to the app_base.html file.