Find answers from the community

Updated 4 months ago

https://docs.llamaindex.ai/en/stable/

https://docs.llamaindex.ai/en/stable/examples/vector_stores/qdrant_hybrid/ in this,

Plain Text

query_engine = index.as_query_engine(
    similarity_top_k=2, sparse_top_k=12, vector_store_query_mode="hybrid"
)

what kind of hybrid retrieval is being used ?

6 comments

LLogan M

Depends on the vector store

LLogan M

And if the vector store you are using supports hybrid

ppayload

i am using qdrant currently https://docs.llamaindex.ai/en/stable/examples/vector_stores/qdrant_hybrid/#indexing-data for this I am guessing they will be using this https://qdrant.tech/documentation/tutorials/hybrid-search-fastembed/ as mentioned in docs aslo

ppayload

This will run sparse vector generation locally using the "prithvida/Splade_PP_en_v1" using fastembed, in addition to generating dense vectors with OpenAI.

ppayload

one more question will i require GPU also for sparse vector generation locally

LLogan M

You don't need a gpu, but it will go faster if you do have one

Add a reply