[BUG] Invalid buffer size

[fred-gb]

Pre-check

• I have searched the existing issues and none cover this bug.

Description

Bonjour 👋🏻

When I try to ingest folder, I have this error:

RuntimeError: Invalid buffer size: 12.17 GB
Generating embeddings:  96%|███████████▌              | 49/51 [00:05<00:00,  8.67it/s]
make: *** [ingest] Error 1

Folder can have 2 documents or many, same error.

I tried with mock for llm in settings, not working.

Where come from this error?
Thanks

Steps to Reproduce

Install:

git clone https://github.com/zylon-ai/private-gpt.git
cd private-gpt

brew install make peotry

poetry install --extras "ui llms-ollama embeddings-ollama vector-stores-qdrant llms-llama-cpp embeddings-huggingface"

poetry run python scripts/setup

CMAKE_ARGS="-DLLAMA_METAL=on" pip install --force-reinstall --no-cache-dir llama-cpp-python numpy==1.26.0

And ingest:

make ingest /Users/fred/privategpt -- --watch --log-file privategpt.log

14:57:06.984 [INFO    ] private_gpt.components.embedding.embedding_component - Initializing the embedding model in mode=huggingface
14:57:07.330 [INFO    ] sentence_transformers.SentenceTransformer - Load pretrained SentenceTransformer: nomic-ai/nomic-embed-text-v1.5
14:57:12.632 [WARNING ] transformers_modules.nomic-ai.nomic-bert-2048.4bb68f63016e88e53e48df904c6ab4e6f718e198.modeling_hf_nomic_bert - <All keys matched successfully>
14:57:13.945 [INFO    ] sentence_transformers.SentenceTransformer - 2 prompts are loaded, with the keys: ['query', 'text']
14:57:14.060 [INFO    ] llama_index.core.indices.loading - Loading all indices.
[...]
RuntimeError: Invalid buffer size: 12.17 GB
Generating embeddings:  96%|███████████▌              | 49/51 [00:05<00:00,  8.67it/s]
make: *** [ingest] Error 1

Expected Behavior

Ingest my folder

Actual Behavior

Not ingest all files and get error code 1

Environment

macOS 14.6.1, MacBook M1 16Go

Additional Information

No response

Version

main branch (v0.6.2)

Setup Checklist

• Confirm that you have followed the installation instructions in the project’s documentation.
• Check that you are using the latest version of the project.
• Verify disk space availability for model storage and data processing.
• Ensure that you have the necessary permissions to run the project.

NVIDIA GPU Setup Checklist

• Check that the all CUDA dependencies are installed and are compatible with your GPU (refer to CUDA's documentation)
• Ensure an NVIDIA GPU is installed and recognized by the system (run nvidia-smi to verify).
• Ensure proper permissions are set for accessing GPU resources.
• Docker users - Verify that the NVIDIA Container Toolkit is configured correctly (e.g. run sudo docker run --rm --gpus all nvidia/cuda:11.0.3-base-ubuntu20.04 nvidia-smi)