The vector_store API only offers 2 chunking strategies. I have written a library (still evolving) that discusses a lot of chunking strategies one can leverage for effective RAG. I am looking for contributors who can help evolving this open source project. The GitHub project name is chunking4rag (GitHub - harpreetset1/chunking4rag: This repo will have various chunking strategies one can build in order to get best performance out of RAG framework)
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| How do i chunk PDFs with complex layout in RAG application? | 1 | 474 | December 4, 2024 | |
| Need advice on chunking strategy for RAG based OpenAI chatbot | 0 | 172 | October 1, 2024 | |
| What is the best way to chunk a PDF file for RAG in a smart way that preserves the meaning during retrieval? | 5 | 14263 | October 28, 2024 | |
| Strategy for chunking rag input | 0 | 246 | May 27, 2024 | |
| Source document chunk identification and highlighting for RAG usecase | 1 | 2567 | August 13, 2024 |