from chromadb import Search, K, Knn, Rrf

# Dense semantic embeddings

dense_rank = Knn(

query="machine learning research", # Text query for dense embeddings

return_rank=True,

limit=200 # Consider top 200 candidates

)

# Sparse keyword embeddings

sparse_rank = Knn(

query="machine learning research", # Text query for sparse embeddings

key="sparse_vector_key", # Metadata field for sparse vectors

return_rank=True,

limit=200

)

# Combine with RRF

hybrid_rank = Rrf(

ranks=[dense_rank, sparse_rank],

weights=[0.7, 0.3], # 70% semantic, 30% keyword

k=60

)

# Use in search

search = (Search()

.where(K("status") == "published") # Optional filtering

.rank(hybrid_rank)

.limit(20)

.select(K.DOCUMENT, K.SCORE, "title")

)

results = collection.search(search)