# Chunking strategy for governments and internal org docs

> Source: <https://discuss.huggingface.co/t/chunking-strategy-for-governments-and-internal-org-docs/178454#post_1>
> Published: 2026-08-04 10:35:47+00:00

while creating rag for chunking strategy (using BM25+Semantic search-cosine similarity for retrieval) - the data it has governments documents like rules and laws and internal org docs, what would chunk size can be preferred, what are data best to store in relation db(postgres) and vector db(Opensearch,/milvus) separately, what each db should store to retrieve easily, fast and efficient

Suggest any good research paper or any codebase i can look