# Where to save BM25Encoder?

**URL:** <https://community.pinecone.io/t/where-to-save-bm25encoder/8396>\
**Category:** General\
**Created:** [September 22, 2025, 2:25pm UTC](https://community.pinecone.io/t/where-to-save-bm25encoder/8396 "2025-09-22T14:25:08Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![ftihsrglu](https://sea2.discourse-cdn.com/flex020/user_avatar/community.pinecone.io/ftihsrglu/32/4115_2.png) [@ftihsrglu](https://community.pinecone.io/u/ftihsrglu)\
**Post date:** [September 22, 2025, 2:25pm UTC](https://community.pinecone.io/t/where-to-save-bm25encoder/8396/1 "2025-09-22T14:25:08Z")

</div>

Hello everyone,

I am trying to build a RAG system with hybrid search for my application. In the applciation users will upload their documents and later on they will be able to chat with their documents. I can store the dense and sparse vectors to a Pinecone instance, so far so good. But I have BM25 encoder to encode the queries to make hybrid search, where should i save this encoder? I am aware that there is a model in Pinecone called **pinecone-sparse-english-v0** for sparse vectors but I think this model is only for English language, as the name suggests.

I can save the encoder to an AWS S3 bucket but I feel like it’s overkill

So, if anyone knows what to do, please let me know.

bm25\_encoder = BM25Encoder() ## where to save this encoder after creating it?  
bm25\_encoder.fit([chunk.page\_content for chunk in all\_chunks])

---

<div class="post-metadata">

**Author:** ![perry](https://sea2.discourse-cdn.com/flex020/user_avatar/community.pinecone.io/perry/32/1729_2.png) [@perry](https://community.pinecone.io/u/perry)\
**Post date:** [September 22, 2025, 2:26pm UTC](https://community.pinecone.io/t/where-to-save-bm25encoder/8396/2 "2025-09-22T14:26:20Z")

</div>

Why not use our hosted sparse model? [pinecone-sparse-english-v0 - Pinecone Docs](https://docs.pinecone.io/models/pinecone-sparse-english-v0)

---

<div class="post-metadata">

**Author:** ![ftihsrglu](https://sea2.discourse-cdn.com/flex020/user_avatar/community.pinecone.io/ftihsrglu/32/4115_2.png) [@ftihsrglu](https://community.pinecone.io/u/ftihsrglu)\
**Post date:** [September 22, 2025, 2:27pm UTC](https://community.pinecone.io/t/where-to-save-bm25encoder/8396/3 "2025-09-22T14:27:21Z")

</div>

As I have written, I think it’s only for English. But I want my app to be multilingual.