# Advanced RAG Architecture: Using GLiNER for Hybrid Search Boosting & Query Expansion (Beyond Metadata Filtering)

**URL:** <https://community.deeplearning.ai/t/advanced-rag-architecture-using-gliner-for-hybrid-search-boosting-query-expansion-beyond-metadata-filtering/885825>\
**Category:** Retrieval Augmented Generation\
**Tags:** week-module-3, coursera-platform\
**Created:** [December 28, 2025, 7:38pm UTC](https://community.deeplearning.ai/t/advanced-rag-architecture-using-gliner-for-hybrid-search-boosting-query-expansion-beyond-metadata-filtering/885825 "2025-12-28T19:38:49Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![ulyaaliyeva206](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/ulyaaliyeva206/32/134264_2.png) [@ulyaaliyeva206](https://community.deeplearning.ai/u/ulyaaliyeva206)\
**Post date:** [December 28, 2025, 7:38pm UTC](https://community.deeplearning.ai/t/advanced-rag-architecture-using-gliner-for-hybrid-search-boosting-query-expansion-beyond-metadata-filtering/885825/1 "2025-12-28T19:38:49Z")

</div>

Hi everyone,

I am currently working on optimizing a RAG pipeline and researching **GLiNER** (Generalist and Lightweight Named Entity Recognition) integration.

I already understand the standard use case where we extract entities (like `dates`, `locations`, `product_names`) to create **hard metadata filters** (SQL-style filtering) before the vector search. This works well for narrowing the search space.

However, I am looking for architectural patterns and Python examples for more advanced implementations to improve retrieval accuracy. Specifically, I am interested in how to use extracted entities to **influence the vector search directly** , rather than just filtering it.