BioChatter - Conversational AI for Biomedical Applications
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:
Basic Usage - Chat - BioChatter
BioChatter provides access to chat functionality via the Conversation class, which is implemented in several child classes (in the llm_connect.py module) to account for differences in APIs of the LLMs.
Open-source and Local LLMs - BioChatter
To support BioChatter applications in local and protected contexts, we provide API access via BioChatter classes in a unified way. Briefly, this module allows to connect to any open-source model supported by Xinference via the state-of-the-art and easy-to-use OpenAI API.
Developer Guide - BioChatter
We re-run the benchmark automatically if a test case has changed (reflected in a different md5 hash) or if there is a new biochatter version (potentially introducing changes in the behaviour of the framework). If a test case has changed, the old result is …
Home - BioChatter
Here we describe the features of the BioChatter framework and their standard usage scenarios. For individual components, please check the side bar navigation.
Knowledge Graph RAG - BioChatter
This vignette demonstrates the KG module of BioChatter as used by the BioChatter Next application. We connect to a BioCypher knowledge graph (KG) to retrieve relevant information for a given question. We then use the retrieved information to generate a response to the question.
The Living Benchmark - BioChatter
The BioChatter Living Benchmark. For trustworthy application of LLMs to real-world and biomedical problems, it is imperative to understand their performance and limitations.
Overview - BioChatter
Aug 6, 2024 · Here we collect the results of the living BioChatter benchmark. For an explanation, see the benchmarking documentation and the developer docs for further reading. Scores per model. Table sorted by median score in descending order. Click the column names to reorder.
Retrieval-Augmented Generation - BioChatter
BioChatter provides access to biological databases through chat via the API Agent. It is designed to interact with various external APIs and provides a structured approach to generating queries, fetching results, and interpreting the responses from different API services.
Podcast my Paper - BioChatter
from biochatter.podcast import Podcaster from biochatter.vectorstore import DocumentReader # Load document reader = DocumentReader document = reader. load_document ("test/dcn.pdf") # Initialise podcaster podcaster = Podcaster (document) # Generate podcast (LLM task) podcaster. generate_podcast (characters_per_paragraph = 5000) # Employ text-to ...