Pulp

The problem of requirements in visual studio seems related to your setup/configuration of visual studio itself. The script works so you clearly have them. The `unknown token` is unrelated, see...

> Can a GPU be integrated into the processing? See https://github.com/imartinez/privateGPT/discussions/350 for example, lot of discussion about that.

You are using an old version of this repo, update to the latest version, re install the requirements and recreate your `.env`. It should look like this: ``` PERSIST_DIRECTORY=db MODEL_TYPE=GPT4All...

> Model llama not supported! This is because of a small bug there's in the code. We don't correctly terminate when an invalid `model_type` is found. Check your `.env` config...

See https://github.com/imartinez/privateGPT/pull/327#issuecomment-1556010352. We are already filtering the `file_path` to only the one with a known extension, so the `ValueError` is never reached, and same thing for your `print()`. You can...

`LOADER_MAPPING` is hardcoded as a global dictionary. I think what you are adding would be more useful as a unit test. Inside a function doesn't seem great.

It's not currently in the code, but if you search for this line in `ingest.py`: ```python3 embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name) ``` and you turn it into: ```python3 embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name, encode_kwargs={'show_progress_bar':...

Oh wait, are you using an old version of this software (if you don't have `EMBEDDINGS_MODEL_NAME` in your `.env` it's the old version)? You should update to the latest version...

> Maybe this could be in the env file, I feel it would be useful to many beginners. I think it will be added shortly. > Does anyone have a...

Yeah, without more information it's hard to help you, the more details you can give the better (think about your privacy when posting logs or any other material). I'd recommend...