Hybrid Search — Pipeline Code by Framework

# Imports (2 lines)
from synapsekit.retrieval import HybridSearchRetriever, Retriever, InMemoryVectorStore
from synapsekit.embeddings import SynapsekitEmbeddings

# Functional (6 lines)
emb    = SynapsekitEmbeddings(model="all-MiniLM-L6-v2", use_gpu=False)
r      = Retriever(InMemoryVectorStore(emb))
hybrid = HybridSearchRetriever(r, bm25_weight=0.5, vector_weight=0.5, rrf_k=60)
hybrid.add_documents(DOCS)
await r.add(DOCS)
results = await hybrid.retrieve(QUERY, top_k=3)

# Imports (4 lines)
from langchain_classic.retrievers.ensemble import EnsembleRetriever
from langchain_community.retrievers import BM25Retriever
from langchain_core.vectorstores import InMemoryVectorStore
from langchain_community.embeddings import HuggingFaceEmbeddings

# Functional (7 lines)
emb    = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
vs     = InMemoryVectorStore(emb)
vs.add_texts(DOCS)
bm25   = BM25Retriever.from_texts(DOCS, k=3)
vec_r  = vs.as_retriever(search_kwargs={"k": 3})
hybrid = EnsembleRetriever(retrievers=[bm25, vec_r], weights=[0.5, 0.5])
results = [doc.page_content for doc in hybrid.invoke(QUERY)]

# Imports (4 lines)
from llama_index.core.retrievers import QueryFusionRetriever, VectorIndexRetriever
from llama_index.core import Document, VectorStoreIndex, Settings
from llama_index.core.node_parser import SentenceSplitter
from llama_index.retrievers.bm25 import BM25Retriever

# Functional (8 lines)
Settings.llm = None
nodes  = SentenceSplitter(chunk_size=512).get_nodes_from_documents(
             [Document(text=d) for d in DOCS])
bm25_r = BM25Retriever.from_defaults(nodes=nodes, similarity_top_k=3)
vec_r  = VectorIndexRetriever(index=VectorStoreIndex(nodes), similarity_top_k=3)
fused  = QueryFusionRetriever([bm25_r, vec_r], similarity_top_k=3,
                              num_queries=1, use_async=False)
results = [n.text for n in fused.retrieve(QUERY)]