Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
import streamlit as st | |
st.set_page_config( | |
page_title="Pathfinder", | |
page_icon="π", | |
) | |
# st.write("# Welcome to Pathfinder! π") | |
st.image('local_files/pathfinder_logo.png',caption="Pathfinder: LLM enabled literature search") | |
st.sidebar.success("Select a function above.") | |
st.sidebar.markdown("Current functions include visualizing papers in the arxiv embedding, searching for similar papers to an input paper or prompt phrase, or answering quick questions.") | |
st.markdown( | |
""" | |
Pathfinder (formerly called arXiv+GPT) is a framework for searching and | |
visualizing papers on the [arXiv](https://arxiv.org/) using the context | |
sensitivity from modern large language models (LLMs) to better link paper contexts. | |
**π Select a tool from the sidebar** to see some examples | |
of what this framework can do! | |
### Tool summary: | |
- `Paper search` looks for relevant papers given an arxiv id or a question. | |
- `Arxiv embedding` shows the landscape of current galaxy evolution papers (astro-ph.GA) | |
- `Answering questions` brings it all together using RAG to give concise answers to questions with primary sources and relevant papers. | |
- `Author search` uses a list of authors for the papers to visualize trajectories of individual researchers or groups over time. | |
- `Research hotspots` uses paper ages to visualize excess research at a particular time in the past in different parts of the embedding space. | |
This is not meant to be a replacement to existing tools like the | |
[ADS](https://ui.adsabs.harvard.edu/), | |
[arxivsorter](https://www.arxivsorter.org/), but rather a supplement to find papers | |
that otherwise might be missed during a literature survey. | |
It is also only trained on astro-ph.GA (astrophysics of galaxies) papers currently, | |
if you are interested in extending it please reach out! | |
The image below shows a representation of all the astro-ph.GA papers that can be explored in more detail | |
using the `Arxiv embedding` page. The papers tend to cluster together by similarity, and result in an | |
atlas that shows well studied (forests) and currently uncharted areas (water). | |
""" | |
) | |
# st.image('https://drive.google.com/uc?id=1yQQCdlgnFzi-_yOMplGIqEyPKJhIsZpO&export=download') | |
st.image('local_files/galaxy_worldmap_kiyer-min.png') | |
st.markdown( | |
""" | |
### Coming soon: | |
- [AstroLLaMA](https://huggingface.co/spaces/universeTBD/astrollama) embeddings! | |
- export results | |
- daily updates to repo | |
- other fields apart from `astro-ph.GA` | |
### Want to learn more? | |
- Check out `AstroLLaMA` [paper](https://huggingface.co/papers/2309.06126) | |
- Check out `chaotic_neural` [(link)](http://chaotic-neural.readthedocs.io/) | |
- Jump into our [documentation](https://docs.streamlit.io) | |
- Contribute! | |
Pathfinder is developed and maintained by [UniverseTBD](https://universetbd.org/). Updates on [huggingface](https://huggingface.co/universeTBD) or [twitter](https://twitter.com/universe_tbd). | |
""" | |
) | |