ChatGPT Festivus

Categories : Holiday Projects

Abstract

Speaking gizmo gets festive quotes from OpenAI / ChatGPT

ChatGPT Talks

My Festivus gizmo connects to ChatGPT to ask it for "artificial intelligence generated" festivus quotes. It will then (try to ) turn the received reply into voice, and say the message.
Consistent with this "artificial content generation" theme: the logo is generated by Nightcafe. I asked it to create "chatgpt logo in christmas style".

Example quote:

Look and Feel

It's a plain looking device (yeah - I know - not very Holiday compliant). A box with a button, a speaker and a wall plug. When the bored partygoers want some distraction, they can push the button. They will get energised by a new intelligent festive thought.

Technology and Flow

Simplicity and off-the-shelf are the key words. I want to use existing assets.

OpenAI's Chat API
Python and shell scripts
OpenAI's Text To Speech API
Raspberry Pi
Little amplifier and speaker
Button

When the button is pushed, my scripts will run to call the API. The API returns a quote that's handed over to the speech module.

Artificial Intelligence content:

the gizmo quotes are generated by OpenAI
all speech is generated by OpenAI
all art in this article is generated by Nightcafe

Button Listener

todo

OpenAI API

This section describes how to get access to the API and use it as a query / response unit.

Key provisioning

Get yourself a ChaTGPT / OpenAI account. The standard free one will do. You can then request a secret API key.

Copy the key to a safe store. Don't share it. Note to self: also don't put it in source code that is uploaded to the forum.

Install OpenAI library

execute this command:

pip3 install -q openai

Code

I based the initial version on OpenAI's Assistant example.

Set the environment variable OPENAI_API_KEY

$Env:OPENAI_API_KEY = "<api key>"

Test with minimal changes to example:

# ---
assistant = client.beta.assistants.create(
    name="Festivus",
    instructions="You are a festivus narrator. Generate a random festivus quote when asked.",
    tools=[{"type": "code_interpreter"}],
    model="gpt-3.5-turbo",
)

# ---

message = client.beta.threads.messages.create(
    thread_id=thread.id,
    role="user",
    content="Please generate a new random festive quote",
)

run = client.beta.threads.runs.create(
    thread_id=thread.id,
    assistant_id=assistant.id,
    instructions="Be merry. Always generate a fresh quote.",
)

# ---

Result

PS > & python3.9.exe openai_festivus.py
checking assistant status.
in progress...
done!
messages:
{'role': 'assistant', 'message': 'Of course! Here\'s a merry quote just for you:\n\n"May your days be merry and bright, and may all your troubles be out of sight."'}
{'role': 'user', 'message': 'Please generate a new random quote'}
PS > & python3.9.exe openai_festivus.py
checking assistant status.
in progress...
in progress...
done!
messages:
{'role': 'assistant', 'message': 'Of course! Here\'s a new random quote just for you:\n\n"Believe you can and you\'re halfway there." - Theodore Roosevelt'}
{'role': 'user', 'message': 'Please generate a new random quote'}

Early success!

Train OpenAI to give only the quote. No confirmation or comments.

run = client.beta.threads.runs.create(
    thread_id=thread.id,
    assistant_id=assistant.id,
    instructions="Be merry. Always generate a fresh quote. Do not include any explanation.",
)

Result:

messages:
{'role': 'assistant', 'message': '"May your days be merry and bright."'}
{'role': 'user', 'message': 'Please generate a new random festive quote'}

Better!

Get the actual quote:

            if message.role == "assistant" :
                print(message.content[0].text.value)

'Tis the season to be jolly!

Best!

Speech

OpenAI has a speech module. You send it a text, and it can generate an mp3 file. I pass the part of the payload that represents the quote:

from pathlib import Path

# ---

speech_file_path = Path(__file__).parent / "speech.mp3"

# ---

            if message.role == "assistant" :
                response = openai.audio.speech.create(model="tts-1", voice="alloy", input=message.content[0].text.value)
                response.stream_to_file(speech_file_path)

# ---

Example result:

'Tis the season to be jolly!

Success!

Hardware Hookup

todo

Software Hookup

Almost everything is contained into a single python script. OpenAI does the majority of the work in the cloud: "get quote, turn to speech, say it".

#!/usr/bin/env python

from pathlib import Path
import time
import openai
from playsound import playsound


# gets API Key from environment variable OPENAI_API_KEY
client = openai.OpenAI()

speech_file_path = Path(__file__).parent

assistant = client.beta.assistants.create(
    name="Festivus",
    instructions="You are a festivus narrator. Generate a random festivus quote when asked.",
    tools=[{"type": "code_interpreter"}],
    model="gpt-3.5-turbo",
)

thread = client.beta.threads.create()

message = client.beta.threads.messages.create(
    thread_id=thread.id,
    role="user",
    content="Please generate a new random festive quote",
)

run = client.beta.threads.runs.create(
    thread_id=thread.id,
    assistant_id=assistant.id,
    instructions="Be merry. Always generate a fresh quote. Do not include any explanation.",
)

#print("checking assistant status. ")
while True:
    run = client.beta.threads.runs.retrieve(thread_id=thread.id, run_id=run.id)

    if run.status == "completed":
        #print("done!")
        messages = client.beta.threads.messages.list(thread_id=thread.id)

        #print("messages: ")
        for message in messages:
            assert message.content[0].type == "text"
            if message.role == "assistant" :
                print(message.content[0].text.value)
                response = openai.audio.speech.create(model="tts-1", voice="alloy", input="Ho! Ho! Ho!" + message.content[0].text.value)
                response.stream_to_file(speech_file_path / "speech.mp3")
                playsound('./speech.mp3')
        client.beta.assistants.delete(assistant.id)

        break
    else:
        #print("in progress...")
        time.sleep(5)

I need to create a button listener that executes the python script, when activity is detected.

todo

References

logo AI-generated: https://creator.nightcafe.studio/creation/ADSMAN2hDBg8iRYl1CWj

bored partygoer AI generated: https://creator.nightcafe.studio/creation/fHWqZDYB1ZRNunRenpTo

API I use to talk to OpenAI / ChatGPT: https://www.makeuseof.com/chatgpt-api-complete-guide/

examples I used as a starting point: https://github.com/openai/openai-python/tree/v1.3.4/examples

how to make result only return the quote: https://community.openai.com/t/how-to-let-gpt-do-not-return-any-accompanying-text/324513/8

text to speach: https://github.com/openai/openai-python/blob/v1.3.4/examples/audio.py

audio output for headless raspberry os: https://elinux.org/R-Pi_Troubleshooting#Sound

Jan Cumps 2 hours ago
I asked OpenAI to use Oscar Wilde's style
```
run = client.beta.threads.runs.create(
    thread_id=thread.id,
    assistant_id=assistant.id,
    instructions="Be merry. Always generate a fresh quote. Avoid religious references. Use the style of Oscar Wilde. Do not include any explanation.",
)
```
```
"May your holiday season be adorned with laughter, love, and a touch of fairy dust."
```
- Cancel
- Vote Up 0 Vote Down
- Sign in to reply
- More
- Cancel
Jan Cumps 9 hours ago

Progress: quote generated and played out loud

You don't have permission to edit metadata of this video.

Edit media

Dimensions x
Subject (required) Brief Description Tags (separated by comma) Video visibility in search results
Parent content

Poster
Upload Preview
- Cancel
- Vote Up 0 Vote Down
- Sign in to reply
- More
- Cancel
Jan Cumps 9 hours ago

Early success 2:
- Cancel
- Vote Up 0 Vote Down
- Sign in to reply
- More
- Cancel
Jan Cumps 12 hours ago in reply to Jan Cumps
If you saw the comment above, can you please tell how you got here?
- Did you get a notification? If yes: how?
- Did you see blog or comment on an activity list? If yes: from where?
- Did you (randomly) surf and land here? If yes: what were you looking for?
- Other
Related to this support request: The holidays member area landing page doesn't show participants blogs
- Cancel
- Vote Up 0 Vote Down
- Sign in to reply
- More
- Cancel

Jan Cumps 13 hours ago

Early success: I acquired an API key and have a festive conversation running

messages: 
{'role': 'assistant', 'message': 'Here is a festive quote for you: "Wishing you a season of joy, a season of blessings, and a season of love." Enjoy the holiday season!'}
{'role': 'user', 'message': 'Please generate a new random festive quote'}

Jan Cumps 11 days ago in reply to cstanton

I will. I published it now so I can share my ups and downs.
- Cancel
- Vote Up 0 Vote Down
- Sign in to reply
- More
- Cancel
cstanton 11 days ago

I'm looking forward to this one I hope you update the post with more detail as you progress! If you were posting about a project idea, it'd be best as a forum thread
- Cancel
- Vote Up 0 Vote Down
- Sign in to reply
- More
- Cancel

ChatGPT Festivus

Table of contents

Abstract

Project

ChatGPT Talks

Look and Feel

Technology and Flow

Button Listener

OpenAI API

Key provisioning

Install OpenAI library

Code

Train OpenAI to give only the quote. No confirmation or comments.

Speech

Hardware Hookup

Software Hookup

References