## Custom Action registered, but not being called

Hi John, is this in an NLU + LLM CALM bot, or LLM-only? Can you share your flow where you’re attempting to gather the feedback?

## Button SetSlot displaying when clicked

Your screenshot from the rasa-calm-demo is still following the original behavior. For this response the payload is no and that is what you are seeing in the inspector (as opposed to the payload of, e.g., /SetSlots...). If inspector were returning the same response as the widget, you would have inst...

## Button SetSlot displaying when clicked

Hi [@jlciii](https://forum.rasa.com/u/jlciii), The built-in inspector will show the button payload since the inspector is used during the development cycle and this can prove to be more useful during that process. When you are utilizing a chat widget (such as our’s – documentation available [here](/content/docs/rasa-pro/connectors/your-own-website/#chat-widget/index.html)), it will instead display the button...

## How to use Ollama models in Rasa CALM?

Hi Vivek, Are you able to access your locally running Ollama server with curl? e.g.  
`curl http://localhost:11434/api/generate -d '{ "model": "phi3", "prompt": "Why is the sky blue?", "stream": false }'`

## LLM command generator looking for openai license even with llama model

Hi Geeta, The flow_retrieval embeddings settings need to be under that key. For example:

```yaml
- name: LLMCommandGenerator
  llm:
    type: "cohere"
    model: "command-r-plus"
    temperature: 0.8
  flow_retrieval:
    embeddings:
      model: "embed-english-light-v3.0"
      type: "cohere"
```

Let us kno...

## How to use Ollama models in Rasa CALM?

Hi Vishni, The easiest way I’ve found to use Ollama (presuming you’re running the Ollama server locally) is to make use of its OpenAI-compatible entry point. Your config would look similar to:

```yaml
pipeline:
  - name: LLMCommandGenerator
    llm:
      model: "wizardlm2:7b"
      max_tokens: 20
      type: open...
```

## Rasa Pro Tutorial with Azure OpenAI Service not working

Thank you for the feedback and we will look to improve the documentation around this feature!

## Rasa Pro Tutorial with Azure OpenAI Service not working

Hi, this is due to the flow_retrieval being enabled by default. Note this line from your debug output:

```
2024-04-30 16:40:23 INFO rasa.dialogue_understanding.generator.llm_command_generator - [info ] llm_command_generator.flow_retrieval.enabled
```

If your assistant has a large number of flow...

## Error in dealing with rasa developer edition

Glad to hear it! The documentation has been updated as well.

## Error in dealing with rasa developer edition

Hi, As our documentation is currently written for this the environment variable will only be set in the powershell terminal where you typed it. For the environment variable to be persisted the command needs a third argument, which can be either USER or MACHINE. As a regular user you can set the s...