hsm207

already run ingest.py and same issue too 😀

@pseudotensor is it also possible to set up h2ogpt the same as privateGPT i.e. do document QnA locally without having any data leave the local machine?

In case anyone is blocked by this, I made a [fork](https://github.com/hsm207/privateGPT/tree/weaviate) to add support for weavite as the vector store. Configuring the project to use weaviate works! Instructions to do...

@Suniron @ado5 there is already an issue for this. See [here](https://github.com/imartinez/privateGPT/issues/132#issuecomment-1551288459)

@pseudotensor great! any pointers to get started e.g. some docs to read on how to add a new db, interfaces to implement, etc?

@pseudotensor I see in the test_langchain_units.py file that there are only 2 tests with chroma or faiss in the name: 1. test_qa_daidocs_db_chunk_hf_faiss 2. test_qa_daidocs_db_chunk_hf_chroma so, is creating test_qa_daidocs_db_chunk_hf_weaviate really enough...

@pseudotensor are the tests in `tests/test_langchain_units.py` meant to be run on a machine with a GPU? I ran `pytest tests/test_langchain_units.py` and all the test_qa tests e.g. `test_qa_daidocs_db_chunk_hf_chroma` failed with this...

@pseudotensor thanks for the draft PR. The test can be run on a CPU too, right? If not, let me know what kind of GPU you develop this project on.

@pseudotensor why is the db_type in [make_db_main](https://github.com/hsm207/h2ogpt/blob/cb51472a52540418bf0fd2786c887534288c7ddd/make_db.py#L91)() hardcoded with chroma? it is also hardcoded [here](https://github.com/hsm207/h2ogpt/blob/cb51472a52540418bf0fd2786c887534288c7ddd/make_db.py#L160-L164) what do you think of making it a parameter of the make_db_main function instead with...

Has this been assigned to anyone? I would like to help implement this integration.