arxiv-dataset.zip: Contains the entire arXiv dataset from Kaggle.
astro-ph-arXiv-abstracts.pkl: Pickled file that can be loaded into pandas dataframe. Contains all the abstracts with categories containing astro-ph
astropy-github.jsonl: Jsonlines file that contains parsed Astropy GitHub documentation as LangChain Documents
scipy_qdrant.zip: Zipped qdrant database that contains astro-ph abstracts and Astropy GitHub documentation with collection name as arxiv_astro-ph_abstracts_astropy_github_documentation
The current qdrant database contains the abstracts. Add Astropy's GitHub documentation and update the asset.
https://github.com/uw-ssec/tutorials-data