byaldi
byaldi copied to clipboard
Use late-interaction multi-modal models such as ColPali in just a few lines of code.
We have infra to host the model and I’m looking to just host an “indexing service” that calls the hosted model instead of running inference “locally”. This decouples the “stateless”...
Hi @bclavie & team, I currently don't see support for searching through an index with a query image instead of a text query. I understand that there is an encode_image...
can we load the colpali model in parallel gpu?
Hi, the error "Document ID 0 with page ID 1 already exists in the index" happens when I create an index with the same files as a previous one, even...
This PR includes the following changes 1. If we pass multiple metadata for each document in a folder, the `add_to_index` will error out because in the below code, it tries...
`for i, item in enumerate(list(input_path.iterdir())): ` can return the files in all sorts of ordering styles. I'm not even sure what it is on my local, but it isn't lexical....
When trying to add metadata to an index, either using a list of metadata dicts or a mapping of uid to metadata dict (shown below), it always produces a key...
In this PR, I’ve added support for [ColSmolVLM](https://huggingface.co/vidore/colsmolvlm-alpha). The code is fully functional, with the only pending issue stemming from the [colpali-engine](https://github.com/illuin-tech/colpali) package, as the latest package version has yet...
Hi, Is it necessary for byaldi to always create a new .byaldi folder and store the embeddings in a folder? Can we store the embeddings in a traditional vector database...
Hi, thank you for this awesome repository. It works really well. However, I’m encountering an issue when sending two base64-encoded images to the Qwen2-VL-7B-Instruct model (served via VLLM with --limit-mm-per-prompt...