curate-gpt
curate-gpt copied to clipboard
monarch-initiative
LLM-driven curation assist tool (pre-alpha)
See https://github.com/linkml/linkml-store This would swap out the abstraction layer here https://github.com/monarch-initiative/curate-gpt/tree/main/src/curate_gpt/store Note that no chromadb adapter is required - it's sufficient to use the default duckdb adapter (fast) and the...
In discussion with RNA-KG group (Marco Mesiti, Elena Casiraghi, Emanuele Cavalleri) and @justaddcoffee - we would like to be able to extract triples (s, p, o) from a provided text,...
groq has jawdroppingly fast access to mixtral. Currently you can use the UI and API for no cost. There is throttling but it seems quite generous it's easy to use...
Add command group embeddings and add index command to put embeddings into a collection
See https://github.com/monarch-initiative/curate-gpt/pull/35 So for example you can do this: `curategpt embeddings index /path/to/local/embeddings.parquet` or this: `curategpt embeddings index https://huggingface.co/datasets/biomedical-translator/monarch_kg_embeddings/resolve/main/deepwalk_embedding.parquet?download=true -f parquet`
This project implements its own abstraction layer over vector dbs and its own logic for RAG Consider using a standard framework * langchain * llamaindex * dspy dspy is very...
This PR adds support for using Azure OpenAI Services deployments instead of directly calling OpenAI. I was testing out this tool, and figured I would push the change upstream in...
At present, 89 unit tests are [failing](https://github.com/monarch-initiative/curate-gpt/actions/runs/7252156141/job/19756025224)
Metadata
Owner
Metadata
LLM-driven curation assist tool (pre-alpha)