Qdrant intergration and Rerank intergration #359
Replies: 1 comment
-
|
Thanks for your suggestions. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Feature Request: Custom OCR, Reranker, and Qdrant Integration
Summary: I would like to propose enhancing OpenNotebook's modularity by allowing users to customize the OCR engine, Reranker, and Vector Database.
Key Proposals:
Custom OCR: Enable support for specialized OCR engines (e.g., PaddleOCR, Google Vision) to better handle complex document layouts and specific languages.
Reranking Layer: Add a configurable Rerank step (e.g., BGE-Reranker, Cohere) after retrieval to improve the precision of the context provided to the LLM.
Qdrant Integration: Allow connection to external Qdrant instances for better scalability, metadata filtering, and performance in large-scale RAG workflows.
Impact: These updates would make OpenNotebook significantly more flexible for production-grade environments and specialized use cases.
Beta Was this translation helpful? Give feedback.
All reactions