AnswerDotAI / AnswerDotAI/RAGatouille
Is the RAGatouille supports multimodal document retrival like Colpali?
Open
- Dominant language
- Python
- Stars
- 4k
- Forks
- 276
- PR merge metrics
- No merged PRs in 30d
Description
Hi, I'm just curious if is there any smooth way to only use the indexing/searching component for a customized embedding model to support the ColBERT style multi-modal rag pipeline (like Colpali)
Contributor guide
No contributing guide indexed for this repository
Research direction
Review the indexing and searching components and how they accept customized embedding models. Compare those interfaces with the Colpali multimodal RAG pipeline. Done means establishing whether the existing components can support this workflow and documenting the required scope or limitations.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, search
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100