# Distinct RAG tools need different embedding models (Hugginface ST)

**URL:** <https://community.crewai.com/t/distinct-rag-tools-need-different-embedding-models-hugginface-st/1280>\
**Category:** CrewAI Community Support\
**Created:** [November 8, 2024, 8:33am UTC](https://community.crewai.com/t/distinct-rag-tools-need-different-embedding-models-hugginface-st/1280 "2024-11-08T08:33:38Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Clinbay\_Ltd](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/clinbay_ltd/32/917_2.png) [@Clinbay\_Ltd](https://community.crewai.com/u/Clinbay_Ltd)\
**Post date:** [November 8, 2024, 8:33am UTC](https://community.crewai.com/t/distinct-rag-tools-need-different-embedding-models-hugginface-st/1280/1 "2024-11-08T08:33:38Z")

</div>

I’m building a sequential crew with distinct tasks/tools : [DIR and FILE search about topic 1, then PDFsearch topic 2].  
I’m using sentence transformer models for embedding, such as :  
emb\_conf=dict(  
embedder=dict(  
provider=“huggingface”,  
config=dict(model=EMBEDDING\_MODEL\_NAME)  
)  
)  
and GPT4o for LLM.  
I noticed issues when the same embedding model is used for the PDF and for the DIR/FILE search tools. Task does not complete, or RAG mixes up PDF and folder info,…

Things get resolved when using distinct embedding models for the 2 tool sets.

Any one has a similar issue? Is it specific to ST model? Did I miss something?  
Thanks in advance for your response.