This project provides a medical chatbot leveraging Llama2 and Sentence Transformers, powered by Langchain and Chainlit. It aims to answer user queries with medical information, citing sources when available, and is suitable for developers and researchers in the medical AI domain.

How It Works

The chatbot utilizes a retrieval-augmented generation (RAG) approach. User queries are processed using Sentence Transformers to create embeddings, which are then used to retrieve relevant information from a FAISS vector store. This retrieved context, along with the original query, is fed into the Llama2 language model via Langchain to generate a comprehensive and sourced answer. This method enhances accuracy and provides explainability by referencing data sources.

Quick Start & Requirements

• Install dependencies: pip install -r requirements.txt
• Requires Python 3.6+.
• Needs a "decent CPU machine with a minimum of 16GB of RAM."
• Requires downloading language models and setting up a FAISS vector store (refer to Langchain documentation for specifics).
• Start the bot via a provided Python script or application integration.

Highlighted Details

• Leverages Llama2 for medical query responses.
• Integrates Sentence Transformers for semantic search.
• Built on Langchain and Chainlit for orchestration and UI.
• Aims to provide sourced answers to medical queries.

Maintenance & Community

No specific details on maintainers, community channels, or roadmap are provided in the README.

Licensing & Compatibility

• Licensed under the MIT License.
• Permissive for commercial use and integration with closed-source applications.

Limitations & Caveats

The README mentions the need to download language models and set up a vector store, with instructions pointing to external Langchain documentation, implying a non-trivial setup process. Specific model versions or performance benchmarks are not detailed.