mirror of
https://github.com/langchain-ai/langchain.git
synced 2026-10-10 11:55:11 +03:00
[Epsilla](https://github.com/epsilla-cloud/vectordb) vectordb is an open-source vector database that leverages the advanced academic parallel graph traversal techniques for vector indexing. This PR adds basic integration with [pyepsilla](https://github.com/epsilla-cloud/epsilla-python-client)(Epsilla vectordb python client) as a vectorstore. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>
4.6 KiB
4.6 KiB
In [ ]:
!pip/pip3 install pyepsillaIn [ ]:
import os
import getpass
os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")In [ ]:
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import EpsillaIn [ ]:
from langchain.document_loaders import TextLoader
from langchain.text_splitter import CharacterTextSplitter
loader = TextLoader("../../modules/state_of_the_union.txt")
documents = loader.load()
documents = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0).split_documents(documents)
embeddings = OpenAIEmbeddings()In [ ]:
from pyepsilla import vectordb
client = vectordb.Client()
vector_store = Epsilla.from_documents(
documents,
embeddings,
client,
db_path="/tmp/mypath",
db_name="MyDB",
collection_name="MyCollection"
)In [ ]:
query = "What did the president say about Ketanji Brown Jackson"
docs = vector_store.similarity_search(query)
print(docs[0].page_content)