Skip to content

This project is a Streamlit-based research assistant that uses LangGraph to build a multi-step workflow for searching academic papers on arXiv, selecting one, and performing question answering directly on its content.

Notifications You must be signed in to change notification settings

aditya20t/ResearchAssistant

Repository files navigation

Arxiv Research Assistant

Try it out here

  • You need a HuggingFace inference token to access the project.
  • Create a conda environment and install pip, use python version 3.10.
  • Clone the repository and install all the pip dependencies mentioned in requirements.txt and conda dependencies mentioned in conda_requirements.txt
  • In the backend we have used Llama models which is gated so make sure to take the permission before trying out the app.

The flow of the project is shown below

Alt Text

Alt Text

Alt Text

Alt Text

Alt Text

About

This project is a Streamlit-based research assistant that uses LangGraph to build a multi-step workflow for searching academic papers on arXiv, selecting one, and performing question answering directly on its content.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages