Relevance AI Action

General
1

Morning

Would you be able to create a Relevance AI Action or if someone has created one, would love to. see how it was done

2

Hi @ihmunro can you please explain what you are trying to achieve?

You can chat with the relevance agents as you do with Pickaxes.

To use a Pickaxe assistant to handle the conversation with a Relevance assistant is not that easy as you would need to connect to the agent, run a relevance job and poll the conversations. I struggle to see the benefits of doing this through a Pickaxe.

1 Like
3

Morning

I was just wondering if we could have ran an Agent or Tool from within the action.

Nothing in particular.

If I could just get the Make action to work, then I could run the scenarios that have Relevance AI modules built in.

Really struggling to figure out the Make action

Iain

4

Morning

Just came across a perfect example of why would should have a Relevance AI Action.

I have a Relevance Tool that will take an Audio file, transcribe it and provide a number of outputs such as a summary, keywords etc.

I started off trying in Make with a Relevance AI Module.

Plus, I am restricted to 10Mb with Tally, where as Relevance it is a lot larger.

I need to create Tally form and upload the video or create a google drive and watch for a new file, then we need to download it, then run the Relevance AI module to run the tool.

Having a Relevance AI actio, we can just upload the file and the Relevance AI tool will run and gives you the output.

Efficiency is what I am going for.

5

Hi @ihmunro,

You cannot upload an audio file directly in a Pickaxe but you can upload a link

See Uploading audio for transcription, get an analysis and then download it

I’m not sure what your process is so I can’t comment on the best user experience for your clients.

What I can say is that any tool has some limitations. I guess you need to decide which ones to use based on your specific use case.

What I meant in my previous post is that if you are using Relevance AI then you don’t really need Pickaxe as you can embed the Relevance AI agent.

Obviously, you lose the ability to have a studio and monetise from it.

6

I took a look at your Relevance AI action request. It’s a good idea! We have a lot of fish to fry with upcoming features first.

1 Like
7

Thanks Mike

Looking forward to seeing it in the future.

8

Hi Mike

Any idea on timing for this ?

9

Sorry, no update at this moment.

1 Like
10

Hi Mike

Any update on the Relevance AI Action ?

Iain

11

We have not done any work on a Relevance AI Action. We are working on getting out our redesign this month.

I will ping @nathaniel about building this action!

1 Like
12

Many thanks Mike

Appreciate it.

Regards

13

Hi @admin_mike

Just thought I would check in to see if there had been any progress on getting the Relevance AI Action in place?

1 Like
14

Hi @ihmunro,

Relevance AI is a bit too case-dependent. It would be better if you create your agent—we’ll guide you through connecting it with your Pickaxe.

1 Like
15

Hi Stephen

Thanks

I have lots of agents, so ready when you are.

Iain

16

I did set one up, but having some issues with it

17

Mind sharing your code?

18

def trigger_relevance(homestars_url: str):
“”"
triggers relevance

Args:
    homestars_url (string): url
"""

# Insert your PYTHON code below. You can access environment variables using os.environ[].
# Currently, only the requests library is supported, but more libraries will be available soon.
# Use print statements or return values to display results to the user.
# If you save a png, pdf, csv, jpg, webp, gif, or html file in the root directory, it will be automatically displayed to the user.
# You do not have to call this function as the bot will automatically call and fill in the parameters.

url = "URL"

headers = {
    "Content-Type": "application/json",
    "Authorization": "API Key"  # Replace this with your actual Relevance API key
}

payload = {
    "homestars_url": homestars_url
}

print("Sending payload:", payload)

try:
    response = requests.post(url, headers=headers, data=json.dumps(payload), timeout=10)

    print(f"Status code: {response.status_code}")
    print(f"Response content: {response.text}")

    if response.status_code == 200:
        return {
            "status": "success",
            "response": response.json()
        }
    else:
        return {
            "status": "failed",
            "error": response.text
        }

except requests.exceptions.Timeout:
    return {"status": "error", "message": "Request timed out"}
except requests.exceptions.RequestException as e:
    return {"status": "error", "message": str(e)}
1 Like
19

I took out the URL and API key

20

Try to adding import json under import requests

1 Like