Home

Generative AI models have shown tremendous usefulness in increasing accessibility and automation of a wide range of tasks. Yet, their application to the biomedical domain is still limited, in part due to the lack of a common framework for deploying, testing, and evaluating the diverse models and auxiliary technologies that are needed. biochatter is a Python package implementing a generic backend library for the connection of biomedical applications to conversational AI. We describe the framework in this preprint; for a more hands-on experience, check out our two web app implementations:

•   BioChatter Light

  ---

  Agile framework in pure Python built with Streamlit, for fast prototyping and iteration.

  Go To BioChatter Light

•   BioChatter Next

  ---

  Advanced client-server architecture based on Flask and Next.js.

  Go To BioChatter Next

BioChatter is part of the BioCypher ecosystem, connecting natively to BioCypher knowledge graphs. The BioChatter paper is being written here and the current version can be read here.

Hot Topics

BioChatter natively extends BioCypher knowledge graphs. Check there for more information.

We have also recently published a perspective on connecting knowledge and machine learning to enable causal reasoning in biomedicine, with a particular focus on the currently emerging "foundation models." You can read it here.

Installation

To use the package, install it from PyPI, for instance using pip (pip install biochatter) or Poetry (poetry add biochatter).

Extras

The package has some optional dependencies that can be installed using the following extras (e.g. pip install biochatter[xinference]):

• xinference: support for querying open-source LLMs through Xorbits Inference

• podcast: support for podcast text-to-speech (for the free Google TTS; the paid OpenAI TTS can be used without this extra)

• streamlit: support for streamlit UI functions (used in ChatGSE)