Skip to main content

No project description provided

Project description

ThinkHub

ThinkHub is a Python-based framework that provides a unified interface for interacting with multiple AI services. Designed for extensibility, users can integrate new services by creating and registering their own plugins or classes. The project simplifies configurations, supports multiple providers, and prioritizes user-friendly customization.

Key Features

  • Multi-Service Integration: Interact seamlessly with multiple AI services (e.g., chat, transcription).
  • Plugin System: Register and use custom classes to extend functionality.
  • Dynamic Configuration: Load and manage configurations with environment variable overrides.
  • Error Handling: Robust exception system for identifying and managing provider-related issues.
  • Poetry Support: Modern dependency and environment management with Poetry.
  • Python 3.11+: Leverages the latest features of Python for performance and simplicity.

Installation

  1. Clone the repository:

    git clone https://github.com/your-username/thinkhub.git
    cd thinkhub
    
  2. Install dependencies with Poetry: Ensure Poetry is installed on your system. Then run:

    poetry install
    
  3. Activate the virtual environment:

    poetry shell
    

Usage

Chat Services

To use a chat service like OpenAI:

from thinkhub.chat import get_chat_service

chat_service = get_chat_service("openai", model="gpt-4o")
async for response in chat_service.stream_chat_response("Hello, ThinkHub!"):
    print(response)

Transcription Services

To use a transcription service like Google:

from thinkhub.transcription import get_transcription_service

transcription_service = get_transcription_service("google")
result = await transcription_service.transcribe("path/to/audio.flac")
print(result)

Registering Custom Plugins

ThinkHub allows users to create and register their own services by extending the base classes and utilizing the factory functions (get_chat_service and get_transcription_service).

Example: Registering a Custom Chat Service

To register a custom chat service, extend the base class ChatServiceInterface and implement its methods:

from thinkhub.chat.base import ChatServiceInterface
from thinkhub.chat import register_chat_service

class CustomChatService(ChatServiceInterface):
    """A custom implementation of a chat service."""
    
    def __init__(self, **kwargs):
        self.custom_param = kwargs.get("custom_param", "default_value")
    
    async def stream_chat_response(self, input_data, system_prompt=""):
        yield f"Custom response to: {input_data}"

# Register the service
register_chat_service("custom", CustomChatService)

Usage

Once registered, the custom service can be retrieved via get_chat_service:

from thinkhub.chat import get_chat_service

chat_service = get_chat_service("custom", custom_param="example")
async for response in chat_service.stream_chat_response("Hello!"):
    print(response)

Example: Registering a Custom Transcription Service

Similarly, transcription services can be registered by extending the TranscriptionServiceInterface:

from thinkhub.transcription.base import TranscriptionServiceInterface
from thinkhub.transcription import register_transcription_service

class CustomTranscriptionService(TranscriptionServiceInterface):
    """A custom implementation of a transcription service."""
    
    async def transcribe(self, file_path):
        return f"Transcription for {file_path}"

# Register the service
register_transcription_service("custom", CustomTranscriptionService)

Usage

The custom transcription service can then be retrieved via get_transcription_service:

from thinkhub.transcription import get_transcription_service

transcription_service = get_transcription_service("custom")
result = await transcription_service.transcribe("path/to/file")
print(result)

Error Handling

Custom exceptions are provided to make debugging easier:

  • BaseServiceError: Base class for all service-related errors.
  • ProviderNotFoundError: Raised when a requested provider is not found.

Example:

from thinkhub.exceptions import ProviderNotFoundError

try:
    raise ProviderNotFoundError("Provider not found!")
except ProviderNotFoundError as e:
    print(e)

Development

  1. Run Tests: Add your tests in the appropriate directories and run:

    poetry run pytest
    
  2. Code Linting: Ensure code quality with:

    poetry run flake8
    
  3. Build the Project:

    poetry build
    

Contributing

Contributions are welcome! Please fork the repository and create a pull request for any changes.


License

This project is licensed under the MIT License.


Acknowledgments

Special thanks to the open-source community for providing the tools and libraries that made this project possible.

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

thinkhub-0.1.5.tar.gz (11.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

thinkhub-0.1.5-py3-none-any.whl (14.0 kB view details)

Uploaded Python 3

File details

Details for the file thinkhub-0.1.5.tar.gz.

File metadata

  • Download URL: thinkhub-0.1.5.tar.gz
  • Upload date:
  • Size: 11.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.4 CPython/3.11.2 Darwin/24.2.0

File hashes

Hashes for thinkhub-0.1.5.tar.gz
Algorithm Hash digest
SHA256 430461189481dc3e765643f380426e63861e6eb870fa4fe99bf5ccf855b96fa0
MD5 5499f5a6e943579dc92db90b02cac478
BLAKE2b-256 bcd8ed0bfade00693b6604073168839fd86e8fd828eba10e6b97b3a0468e2b19

See more details on using hashes here.

File details

Details for the file thinkhub-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: thinkhub-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 14.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.4 CPython/3.11.2 Darwin/24.2.0

File hashes

Hashes for thinkhub-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 cbf806f8aceb4d222e8a0170d54187d6b5e81e41856afc73b552e9c7b4e0149a
MD5 5781d1bc411885bde8d71ae932634539
BLAKE2b-256 0d23a0c4b8c5d2df1d891e91846636bac15f9f741a3e2b74351665b296f573d4

See more details on using hashes here.

Supported by

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