Skip to content

Latest commit

 

History

History
27 lines (15 loc) · 868 Bytes

README.md

File metadata and controls

27 lines (15 loc) · 868 Bytes

A simple chatbot based on LLM and RAG architecture

Authors

Ippocratis Saltas

Code

  • The code provides a simple chatbot which can assist with information assistance, using Retrieval Augmented Generation (RAG) technology combined with a pre-trained Large Language Model (LLM). The code is also capable of summarising papers from the scientific repository arXiv.

  • This version of the code is a very pre-liminary version and has received extremely basic testing only. The current form of the code runs on a Jupyter notebook for illustrative convenience.

Versions

python 3
langchain  0.1.16
torch  2.2.2
huggingface-hub 0.22.2

Files

LLM.ipynb: The main Jupyter notebook to run the code.

model.py: Defines the model and other functionality.

packages.py: Contains the necessary libraries and modules.