DuckDB
本笔记展示了如何将 DuckDB
用作向量存储。
! pip install duckdb langchain langchain-community langchain-openai
我们想使用OpenAI嵌入模型,因此我们必须获取OpenAI API密钥。
import getpass
import os
if "OPENAI_API_KEY" not in os.environ:
os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")
<!--IMPORTS:[{"imported": "DuckDB", "source": "langchain_community.vectorstores", "docs": "https://python.langchain.com/api_reference/community/vectorstores/langchain_community.vectorstores.duckdb.DuckDB.html", "title": "DuckDB"}, {"imported": "OpenAIEmbeddings", "source": "langchain_openai", "docs": "https://python.langchain.com/api_reference/openai/embeddings/langchain_openai.embeddings.base.OpenAIEmbeddings.html", "title": "DuckDB"}]-->
from langchain_community.vectorstores import DuckDB
from langchain_openai import OpenAIEmbeddings
<!--IMPORTS:[{"imported": "TextLoader", "source": "langchain_community.document_loaders", "docs": "https://python.langchain.com/api_reference/community/document_loaders/langchain_community.document_loaders.text.TextLoader.html", "title": "DuckDB"}, {"imported": "CharacterTextSplitter", "source": "langchain_text_splitters", "docs": "https://python.langchain.com/api_reference/text_splitters/character/langchain_text_splitters.character.CharacterTextSplitter.html", "title": "DuckDB"}]-->
from langchain_community.document_loaders import TextLoader
from langchain_text_splitters import CharacterTextSplitter
loader = TextLoader("../../how_to/state_of_the_union.txt")
documents = loader.load()
documents = CharacterTextSplitter().split_documents(documents)
embeddings = OpenAIEmbeddings()
docsearch = DuckDB.from_documents(documents, embeddings)
query = "What did the president say about Ketanji Brown Jackson"
docs = docsearch.similarity_search(query)
print(docs[0].page_content)