NucliaDB
您可以使用本地的 NucliaDB 实例或使用 Nuclia Cloud。
使用本地实例时,您需要一个 Nuclia Understanding API 密钥,以便您的文本能够正确地向量化和索引。您可以通过在 https://nuclia.cloud 创建一个免费账户来获取密钥,然后 创建一个 NUA 密钥。
%pip install --upgrade --quiet langchain langchain-community nuclia
在 nuclia.cloud 上的使用
<!--IMPORTS:[{"imported": "NucliaDB", "source": "langchain_community.vectorstores.nucliadb", "docs": "https://python.langchain.com/api_reference/community/vectorstores/langchain_community.vectorstores.nucliadb.NucliaDB.html", "title": "NucliaDB"}]-->
from langchain_community.vectorstores.nucliadb import NucliaDB
API_KEY = "YOUR_API_KEY"
ndb = NucliaDB(knowledge_box="YOUR_KB_ID", local=False, api_key=API_KEY)
在本地实例上的使用
注意:默认情况下 backend
设置为 http://localhost:8080
。
<!--IMPORTS:[{"imported": "NucliaDB", "source": "langchain_community.vectorstores.nucliadb", "docs": "https://python.langchain.com/api_reference/community/vectorstores/langchain_community.vectorstores.nucliadb.NucliaDB.html", "title": "NucliaDB"}]-->
from langchain_community.vectorstores.nucliadb import NucliaDB
ndb = NucliaDB(knowledge_box="YOUR_KB_ID", local=True, backend="http://my-local-server")
添加和删 除知识库中的文本
ids = ndb.add_texts(["This is a new test", "This is a second test"])
ndb.delete(ids=ids)
在知识库中搜索
results = ndb.similarity_search("Who was inspired by Ada Lovelace?")
print(results[0].page_content)