Tair

from langchain_community.embeddings.fake import FakeEmbeddings
from langchain_community.vectorstores import Tair
from langchain_text_splitters import CharacterTextSplitter

from langchain_community.document_loaders import TextLoader

loader = TextLoader("../../how_to/state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

embeddings = FakeEmbeddings(size=128)

export TAIR_URL="redis://{username}:{password}@{tair_address}:{tair_port}"

tair_url = "redis://localhost:6379"

# drop first if index already exists
Tair.drop_index(tair_url=tair_url)

vector_store = Tair.from_documents(docs, embeddings, tair_url=tair_url)

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

# drop first if index already exists
Tair.drop_index(tair_url=tair_url)

vector_store = Tair.from_documents(
    docs, embeddings, tair_url=tair_url, index_params={"lexical_algorithm": "bm25"}
)

query = "What did the president say about Ketanji Brown Jackson"
# hybrid_ratio: 0.5 hybrid search, 0.9999 vector search, 0.0001 text search
kwargs = {"TEXT": query, "hybrid_ratio": 0.5}
docs = vector_store.similarity_search(query, **kwargs)
docs[0]