百度向量数据库

!pip3 install pymochow

from langchain_community.document_loaders import TextLoader
from langchain_community.embeddings.fake import FakeEmbeddings
from langchain_community.vectorstores import BaiduVectorDB
from langchain_community.vectorstores.baiduvectordb import ConnectionParams
from langchain_text_splitters import CharacterTextSplitter

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)

conn_params = ConnectionParams(
    endpoint="http://192.168.xx.xx:xxxx", account="root", api_key="****"
)

vector_db = BaiduVectorDB.from_documents(
    docs, embeddings, connection_params=conn_params, drop_old=True
)

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

vector_db = BaiduVectorDB(embeddings, conn_params)
vector_db.add_texts(["Ankush went to Princeton"])
query = "Where did Ankush go to college?"
docs = vector_db.max_marginal_relevance_search(query)
docs[0].page_content