Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Multi modal rag demo #698

Open
wants to merge 56 commits into
base: main
Choose a base branch
from
Open

Multi modal rag demo #698

wants to merge 56 commits into from

Conversation

init27
Copy link
Contributor

@init27 init27 commented Oct 1, 2024

MM RAG Demo:

3 Part Series:

  • Notebook 1: Data Prep and Synethetic Labelling using 11B model
  • WIP: Notebook 2: Cleaning up Synthetic Labels using 1B or 3B model and creating DB with
  • WIP: Notebook 3: MM-RAG using lance-db

Scripts:

  • Script 1: Annotating Dataset with multi-GPUs
  • Script 2: Cleaning up Descriptions and making the db
  • Script 3: Llama 3.2 + lance db gradio demo

Not working-Validating idea for MM RAG
Notebook 1: I will add MD details later (as usual)
@init27 init27 marked this pull request as ready for review October 17, 2024 20:01
Copy link
Contributor

@HamidShojanazeri HamidShojanazeri left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @init27 for the PR! left some comments inline.

recipes/quickstart/Multi-Modal-RAG/README.md Outdated Show resolved Hide resolved
1. Please grab your HF CLI Token from [here](https://huggingface.co/settings/tokens)
2. git clone [this dataset](https://huggingface.co/datasets/Sanyam/MM-Demo) inside the Multi-Modal-RAG folder: `git clone https://huggingface.co/datasets/Sanyam/MM-Demo`
3. Launch jupyter notebook inside this folder
4. We will also run two scripts after the notebooks
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this seems unnecessary to be part of the requirements?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@HamidShojanazeri actually we need to clone the dataset from Huggingface, so im pointing that out.

Do you think I should move it inside a notebook?

recipes/quickstart/Multi-Modal-RAG/README.md Outdated Show resolved Hide resolved
recipes/quickstart/Multi-Modal-RAG/README.md Outdated Show resolved Hide resolved
recipes/quickstart/Multi-Modal-RAG/README.md Outdated Show resolved Hide resolved
recipes/quickstart/Multi-Modal-RAG/README.md Outdated Show resolved Hide resolved
recipes/quickstart/Multi-Modal-RAG/README.md Outdated Show resolved Hide resolved
recipes/quickstart/Multi-Modal-RAG/README.md Outdated Show resolved Hide resolved
recipes/quickstart/Multi-Modal-RAG/README.md Outdated Show resolved Hide resolved
recipes/quickstart/Multi-Modal-RAG/README.md Outdated Show resolved Hide resolved
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants