DuckDB 数据库

此笔记本演示如何使用DuckDB作为 vector store 进行。

! pip install duckdb langchain langchain-community langchain-openai

我们想要使用 OpenAIEmbeddings，所以我们必须获取 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:")

from langchain_community.vectorstores import DuckDB
from langchain_openai import OpenAIEmbeddings

API 参考：DuckDB | OpenAI 嵌入

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()

API 参考：TextLoader | CharacterTextSplitter（字符文本拆分器）

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)

矢量存储概念指南
Vector store 操作指南

相关