Skip to main content

Use LLMs to call functions.

Project description

blablado

blablado is an extensible Assistant, that listens to your voice and can execute custom Python functions you provided. It can speak as well. It is based on LangChain and OpenAI's API. You need an openai API account to use it.

Usage: API

You can use it from Python (see example notebook) by

  • initializing an Assistant,
from blablado import Assistant
assistant = Assistant()
  • providing functions/tools and
from datetime import datetime

@assistant.register_tool
def book_room(room:str, author:str, start:datetime, end:datetime):
    """Book a room for a specific person from start to end time."""
    
    print(f"""
    Booking {room} for {author} from {start} to {end}.
    """)
  • prompting for tasks
assistant.do("Hi I'm Robert, please book room A03.21 for me from 3 to 4 pm tomorrow. Thanks")

Output:

I have successfully booked room A03.21 for Robert from 3 to 4 pm tomorrow.

Usage: Microphone

You can also use it via microphone (see example notebook). You need to install some more library before this works:

pip install SpeechRecognition pydub gTTS PyAudio

Therefore, it is recommended to print out the list of available microphones like this:

from blablado import list_microphones
list_microphones()

Example output:

['Microsoft Sound Mapper - Input',
 'Microphone (KLICK&SHOW Audio)',
 'AI Noise-cancelling Input (ASUS',
 'Headset (MAJOR IV Hands-Free AG',
 'Microphone Array (Realtek(R) Au']

Then, choose the right microphone after initializing the assistant:

from blablado import Assistant
assistant = Assistant()
assistant.microphone_index = 3

You can then call the assistant to listen to your voice and execute the function you want to call:

assistant.listen()

Usage: Voice output

To make the voice output work as well, just activate the voice when initializing the assistant:

from blablado import Assistant
assistant = Assistant(has_voice=True)

Installation

blablado is available on pypi and can be installed using pip. It is recommended to install it in a virtual environment, e.g. set up with mamba.

mamba create --name bla python=3.9
mamba activate bla
pip install blablado

To make the voice-output work (optional), consider installing ffmpeg using mamba.

mamba install ffmpeg

Issues

If you encounter any problems or want to provide feedback or suggestions, please create a thread on image.sc along with a detailed description and tag [@haesleinhuepf].

Acknowledgements

Parts of the code reused here were originally written by kevinyamauchi for the bia-bob project.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

blablado-0.2.0.tar.gz (9.9 kB view details)

Uploaded Source

Built Distribution

blablado-0.2.0-py3-none-any.whl (8.4 kB view details)

Uploaded Python 3

File details

Details for the file blablado-0.2.0.tar.gz.

File metadata

  • Download URL: blablado-0.2.0.tar.gz
  • Upload date:
  • Size: 9.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.9

File hashes

Hashes for blablado-0.2.0.tar.gz
Algorithm Hash digest
SHA256 b302d20ffc30605b5eedf7dd284431d9dc299f7368a1edb0573d0b10c56eb91d
MD5 6f224afee55732da2ae93186af548aa5
BLAKE2b-256 b1ecaa49f19f83e038ef0f56a1628d7c83778dc50c64389d07cf938a6ac7c70d

See more details on using hashes here.

File details

Details for the file blablado-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: blablado-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 8.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.9

File hashes

Hashes for blablado-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 fe4e0bdfc223cd848706bb90d56b4a10aa0d9f10795b7f52dd3767a1edb05fce
MD5 6840346c25647b4e9a05e6b292dc32c5
BLAKE2b-256 83935e2d3a59db175ca4c6fed390130f677d3f3c997a67f7b04a9708b51b9496

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page