Skip to main content

DeerTick: A Multi-Provider Language Model Interface for interacting with various AI models across different providers, supporting both interactive chat and file-based input/output.

Project description

DeerTick: Multi-Provider Language Model Interface

DeerTick is a versatile Python-based interface for interacting with various language models from different providers, including Replicate, OpenAI, Hugging Face, OpenRouter, and Mistral.

Features

  • Support for multiple AI providers and models
  • Interactive chat mode
  • File input/output support
  • Customizable system prompts
  • Image generation capabilities
  • Text-to-speech functionality

Installation

  1. Clone the repository:

    git clone https://github.com/deeterbleater/deertick
    cd deertick
    
  2. Install the required dependencies:

    pip install -r requirements.txt
    
  3. Set up your config.ini file with the necessary API keys:

    [keys]
    REPLICATE_API_TOKEN = your_replicate_token
    OPENAI_API_TOKEN = your_openai_token
    HUGGINGFACE_API_KEY = your_huggingface_key
    OPENROUTER_API_KEY = your_openrouter_key
    MISTRAL_API_KEY = your_mistral_key
    

Usage

Command Line Interface

python deertick.py [options]

Options:

  • -m, --model MODEL: Specify the model to use (e.g., "I-8b", "I-70b", "gpt-4")
  • -p, --provider PROVIDER: Specify the provider (e.g., "replicate", "openai")
  • -s, --system PROMPT: Set the system prompt for the conversation
  • -i, --interactive: Start an interactive chat session
  • -f, --file FILE: Read input from a file
  • -o, --output FILE: Write output to a file
  • -h, --help: Show the help message
  • -l, --list: List available models and providers

Interactive Mode

To start an interactive chat session:

python deertick.py -i -m I-8b -p replicate

File Input/Output

To process input from a file and save the output:

python deertick.py -f input.txt -o output.txt -m gpt-4 -p openai

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License - see the LICENSE file for details.

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

deertick-0.0.7.tar.gz (20.2 kB view details)

Uploaded Source

Built Distribution

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

deertick-0.0.7-py3-none-any.whl (21.5 kB view details)

Uploaded Python 3

File details

Details for the file deertick-0.0.7.tar.gz.

File metadata

  • Download URL: deertick-0.0.7.tar.gz
  • Upload date:
  • Size: 20.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.0

File hashes

Hashes for deertick-0.0.7.tar.gz
Algorithm Hash digest
SHA256 aa27043dad7007ebbcf93aad25e484dad9f49ecb4e95cb890ad9da09ae0a7f54
MD5 2ec1849ce171dc8e9d682bae5472b800
BLAKE2b-256 0e5ad43b8825d3841e5d7308eaaa7cc34fb01584b56ad0bc43fcd097e253b305

See more details on using hashes here.

File details

Details for the file deertick-0.0.7-py3-none-any.whl.

File metadata

  • Download URL: deertick-0.0.7-py3-none-any.whl
  • Upload date:
  • Size: 21.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.0

File hashes

Hashes for deertick-0.0.7-py3-none-any.whl
Algorithm Hash digest
SHA256 107e3fd05c9e8e62d13b2db2d7550b87b5e89d3f812f8113fe240d50ba95d961
MD5 ea47629f4d88120e19864053173b6ad3
BLAKE2b-256 3b73b6adc489e3ff94cced33f602105a00238ade9001462c5124dd99933df63e

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