Search CellxGene metadata to get single cell gene expression data

[dmccloskey]

As a user, I would like to be able to semantically search the CellxGene metadata to identify the single cell gene expression dataset that I would like to analyze. An example use case from the hackathon utilized a RAG setup to chunk, vectorize, and search the CellxGene metadata

Potential solution

• Textual RAG over a local cache of the CellxGene metadata
• CI to update the local cache on an e.g., weekly basis to stay up to date

[JaydeepBhat]

Would one potential solution be the use of API? For example, Python API from CellxGene