Production hybrid retrieval using bgem3
#115
by swapashtekar - opened
Hi,
What are the model inferencing options to use BGE-M3 model in production scenario? I am using model to obtain hybrid retrieval (both dense and sparse embeddings) as mentioned in milvus documentation.
Are there any ways where i can run bge-m3 model to get hybrid retrieval as mentioned in https://github.com/huggingface/text-embeddings-inference
Thank you.
Hi, I'm also curious about this as I have created a setup which works locally, but I'm struggling to get it working in production. What did you find?
If you're still looking for a production-level inference engine for BGE-M3 for hybrid retrieval, I've built this!
https://github.com/MauroCE/m3serve