TileDB

pip install -qU  tiledb-vector-search langchain-community

from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import TileDB
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_text_splitters import CharacterTextSplitter

raw_documents = TextLoader("../../how_to/state_of_the_union.txt").load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
documents = text_splitter.split_documents(raw_documents)
model_name = "sentence-transformers/all-mpnet-base-v2"
embeddings = HuggingFaceEmbeddings(model_name=model_name)
db = TileDB.from_documents(
    documents, embeddings, index_uri="/tmp/tiledb_index", index_type="FLAT"
)

query = "What did the president say about Ketanji Brown Jackson"
docs = db.similarity_search(query)
docs[0].page_content

embedding_vector = embeddings.embed_query(query)
docs = db.similarity_search_by_vector(embedding_vector)
docs[0].page_content

docs_and_scores = db.similarity_search_with_score(query)
docs_and_scores[0]

retriever = db.as_retriever(search_type="mmr")
retriever.invoke(query)

db.max_marginal_relevance_search(query, k=2, fetch_k=10)