George

I use `bcrypt` with `passlib` I updated `bcrypt` to `4.1.0` today and it has broken my service I run my service in a docker container from docker image `python:3.11-slim` With...

@alex > https://github.com/pyca/bcrypt/blob/4.0.1/src/bcrypt/__init__.py#L72-L74 I send strings to `passlib context object`, not directly to `bcrypt`. I haven't dug deep into the codebase, but I found this https://foss.heptapod.net/python-libs/passlib/-/blob/branch/stable/passlib/handlers/bcrypt.py#L646 , so encoding happens...

Hi @giacomobartoli there is no FastEmbed class in fastembed, could you point us to the resource where you found it? The correct import is `from fastembed import TextEmbedding`

#743

Unfortunately, it is broken: ``` Traceback (most recent call last): File ".../qdrant/qdrant_client/checks.py", line 3, in cl = QdrantClient(local_files_only=True) File ".../qdrant/qdrant_client/qdrant_client/qdrant_client.py", line 134, in __init__ self._client = QdrantRemote( File ".../qdrant/qdrant_client/qdrant_client/qdrant_remote.py", line...

already supported via `set_model` and `set_sparse_model`

hi @abdelkareemkobo, parallel=4 does not span all the data across all available gpu by default, you need to initialize your model with `cuda` and `device_ids` params, like ```python LateInteractionTextEmbedding( model_name=model_name,...

Hi @shern2 Thanks for pointing it out, it's indeed looks like a mistake from our side, the model is english only We'll update the description

Hey @BezBartek Sorry for the waiting time Could you provide a code snippet, so we could try to debug it? Also, could you provide information about qdrant-client version you're using,...

Hey @microcoder-py @NirantK is no longer a maintainer of fastembed We'll look into your problem asap