jacobmarks/fiftyone-multimodal-rag-plugin

Testbed for multimodal retrieval augmented generation techniques with FiftyOne, LlamaIndex, and Milvus

25
/ 100
Experimental

This project helps AI developers and researchers experiment with and refine multimodal Retrieval Augmented Generation (RAG) techniques. It takes directories containing various multimodal data (images, text, PDFs) as input and allows users to index this data using different strategies. The output is a highly configurable system for querying your data and generating improved responses from advanced AI models, offering insights into what works best for specific use cases.

No commits in the last 6 months.

Use this if you are an AI developer or researcher working with multimodal data and need a flexible testbed to explore and optimize RAG workflows for large language models.

Not ideal if you are looking for a plug-and-play solution for general content creation or do not have experience working with AI models and data pipelines.

Multimodal AI RAG LLM development Data indexing AI experimentation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

21

Forks

3

Language

Python

License

Category

local-rag-stacks

Last pushed

Aug 09, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/jacobmarks/fiftyone-multimodal-rag-plugin"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.