byaldi

byaldi copied to clipboard

how to load existing index from persistant directory

1

hy can anyone know how to load the existing index from persitant directory means my indexses are stored in .byadli with index name subfolder so how i can load the...

HafizNouman666

Hi all - I've gotten this code to work in a RAG, but it is prohibitively slow even for a small number of documents (I have access to multiple A100s)....

JonathanFolstein

Getting "Torch not compiled with CUDA enabled error"

4

I have CPU based windows system and while running the below code I get the "Torch not compiled with CUDA enabled error". Code:- RAG = RAGMultiModalModel.from_pretrained("vidore/colpali") Error:- --------------------------------------------------------------------------- AssertionError Traceback...

dhirajkumarsinha27091982

Adding ColQwen2.5 support

1

Dammerzone

Is there a way to access similarity maps?

3

Hey, Thank you so much for your library! I’m nearly done preparing a practical session for my master's students using it. I was wondering if there's an easy way to...

FlorianSaby

## Description Add support for the ColSmol model family. Reference thread: https://x.com/tonywu_71/status/1882434084657590522. ## Changes ### Added - Add support for ColSmol model ### Tests - Add test for ColSmol model

tonywu71

qwen2 models causing indexerror

1

I'm trying to run the example quick_overview.ipynb on m1 mbp. ```import os from dotenv import load_dotenv from pathlib import Path from byaldi import RAGMultiModalModel load_dotenv() # print(os.environ["HF_TOKEN"]) # Initialize RAGMultiModalModel...

ml2s

Multimodal way to retrieve documents

1

Hello, Thank you for the amazing library. I referred the RAG implementation notebooks from hugging face using this library and loved it. I am just wondering if there is a...

AmazingK2k3

Need to be able to set mmap=true for torch.load() for us humble people without very good computers. That is all. For those that need a Fix now just make your...

celtiberi

**Description:** When running the colqwen2 model on an MPS device (Apple Silicon), the default attention implementation causes compatibility issues. The fix ensures that attn_implementation="eager" is used when the device is...

murshidm