plano/demos/getting_started/llm_gateway/README.md

LLM Routing

This demo shows how you can use Plano gateway to manage keys and route to upstream LLM.

Starting the demo

1. Please make sure the pre-requisites are installed correctly
2. Start Plano

   sh run_demo.sh
   

3. Test with curl (see example below)

To also start the AnythingLLM chat UI and Jaeger tracing, pass --with-ui:

sh run_demo.sh --with-ui

Then navigate to http://localhost:3001/ for AnythingLLM.

Following screen shows an example of interaction with Plano gateway showing dynamic routing. You can select between different LLMs using "override model" option in the chat UI.

You can also pass in a header to override model when sending prompt. Following example shows how you can use x-arch-llm-provider-hint header to override model selection,

$ curl --header 'Content-Type: application/json' \
  --header 'x-arch-llm-provider-hint: mistral/ministral-3b' \
  --data '{"messages": [{"role": "user","content": "hello"}], "model": "gpt-4o"}' \
  http://localhost:12000/v1/chat/completions 2> /dev/null | jq .
{
  "id": "xxx",
  "object": "chat.completion",
  "created": 1737760394,
  "model": "ministral-3b-latest",
  "choices": [
    {
      "index": 0,
      "messages": {
        "role": "assistant",
        "tool_calls": null,
        "content": "Hello! How can I assist you today? Let's chat about anything you'd like."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 4,
    "total_tokens": 25,
    "completion_tokens": 21
  }
}

Observability

For tracing, start with --with-ui and head over to http://localhost:16686/ to view recent traces.

Following is a screenshot of tracing UI showing call received by Plano gateway and making upstream call to LLM,